bagging_RF_models.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a538e823",
   "metadata": {
    "tags": []
   },
   "source": [
    "## MODELING"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e4185b6f",
   "metadata": {},
   "source": [
    "Queremos predecir el precio de venta de la vivienda en base al dataset de venta."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6dd0a6f",
   "metadata": {},
   "source": [
    "En primer lugar generamos un DataFrame para almacenar los resultados obtenidos de todos los modelos que generemos:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 640,
   "id": "023ac8a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "models_results_df = pd.DataFrame(columns=['regressor', 'train_r2_score', 'test_r2_score'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55848c26",
   "metadata": {},
   "source": [
    "- Almacenaremos los resultados para los distintos modelos en model_results_df. \n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1344904",
   "metadata": {},
   "source": [
    "### Bagging & Random Forest Models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "393737b0",
   "metadata": {},
   "source": [
    "Haremos 3 aproximaciones: \n",
    "\n",
    "- Modelo 1:  BaggingRegressor y RandomForestRegressor con todas las variables del dataset sin seleccionar variables importantes, sin tratar outliers y sin escalar las variables numéricas.\n",
    "\n",
    "- Modelo 2: BaggingRegressor y RandomForestRegressor con todas las variables del dataset sin seleccionar variables importantes, tratando outliers (método IQR) y escalando las variables numéricas (MinMaxScaler).\n",
    "\n",
    "- Modelo 3: BaggingRegressor y RandomForestRegressor seleccionando las variables más importantes (mediante técnicas como PCA, Análisis de Correlación, Información Mutua, ANOVA y ExtraTreesRegressor), tratando outliers (método IQR) y escalando las variables numéricas (MinMaxScaler).\n",
    "\n",
    "    - Modelo 3.1: BaggingRegressor y RandomForestRegressor seleccionando las variables más importantes (mediante técnicas como PCA, Análisis de Correlación, Información Mutua, ANOVA y ExtraTreesRegressor), tratando outliers (método IQR) pero NO escalando las variables numéricas."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c1fbb36",
   "metadata": {},
   "source": [
    "#### Models Pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abda1d17",
   "metadata": {},
   "source": [
    "Creamos la Pipeline con los modelos de Bagging y RF:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 614,
   "id": "01424ee6",
   "metadata": {},
   "outputs": [],
   "source": [
    "class PipelineRunner:\n",
    "    \"\"\"A class that runs multiple regression models on given train and test dataframes\"\"\"\n",
    "\n",
    "    def __init__(self, cv_folds: int = CROSS_VALIDATION_FOLDS):\n",
    "        \"\"\"\n",
    "        Args:\n",
    "            cv_folds: Number of cross validation folds to be used in grid search\n",
    "        \"\"\"\n",
    "        self.cv_folds = cv_folds\n",
    "        \n",
    "    def generate_train_test_sets(self, \n",
    "                                 df_train: pd.DataFrame, \n",
    "                                 df_test: pd.DataFrame, \n",
    "                                 target: str) -> Tuple[pd.DataFrame, pd.Series, pd.DataFrame, pd.Series]:\n",
    "        \"\"\"\n",
    "            Generate training and test sets.\n",
    "\n",
    "            Args:\n",
    "                df_train (pd.DataFrame): Training dataset.\n",
    "                df_test (pd.DataFrame): Test dataset.\n",
    "                target (str): Target variable name.\n",
    "\n",
    "            Returns:\n",
    "                X_train (pd.DataFrame): Training features.\n",
    "                y_train (pd.Series): Training target variable.\n",
    "                X_test (pd.DataFrame): Test features.\n",
    "                y_test (pd.Series): Test target variable.\n",
    "        \"\"\"\n",
    "        X_train = df_train.drop(columns=[target])\n",
    "        y_train = df_train[target]\n",
    "\n",
    "        X_test = df_test.drop(columns=[target])\n",
    "        y_test = df_test[target]\n",
    "\n",
    "        return X_train, y_train, X_test, y_test\n",
    "        \n",
    "    def run_pipeline(self, \n",
    "                     df_train: pd.DataFrame, \n",
    "                     df_test: pd.DataFrame, \n",
    "                     target: str) -> GridSearchCV:\n",
    "        \"\"\"\n",
    "        Run multiple regression models on given train and test dataframes.\n",
    "\n",
    "        Args:\n",
    "            df_train (pd.DataFrame): Training dataset.\n",
    "            df_test (pd.DataFrame): Test dataset.\n",
    "            target (str): Target variable name.\n",
    "\n",
    "        Returns:\n",
    "            A GridSearchCV object containing the fitted regression model with the best hyperparameters.\n",
    "        \"\"\"\n",
    "        X_train, y_train, X_test, y_test = self.generate_train_test_sets(df_train, df_test, target)\n",
    "\n",
    "        models = [\n",
    "            {\n",
    "                'name': 'BaggingRegressor',\n",
    "                'model': BaggingRegressor(DecisionTreeRegressor()),\n",
    "                'params': {\n",
    "                    'model__n_estimators': [10, 20, 50, 100, 200]\n",
    "                }\n",
    "            },\n",
    "            {\n",
    "                'name': 'RandomForestRegressor',\n",
    "                'model': RandomForestRegressor(),\n",
    "                'params': {\n",
    "                    'model__n_estimators': [10, 20, 50, 100, 200],\n",
    "                    'model__max_depth': [2, 3, 4, 5, 6, 7, 9],\n",
    "                    'model__min_samples_split': [2, 5, 10]\n",
    "                }\n",
    "            }\n",
    "        ]\n",
    "\n",
    "        results = []\n",
    "        for model_info in models:\n",
    "            model = model_info['model']\n",
    "            params = model_info['params']\n",
    "\n",
    "            pipeline = Pipeline(steps=[\n",
    "                ('model', model)\n",
    "            ])\n",
    "\n",
    "            grid_search = GridSearchCV(pipeline, params, cv=self.cv_folds, scoring='r2')\n",
    "            grid_search.fit(X_train, y_train)\n",
    "\n",
    "            y_train_pred = grid_search.predict(X_train)\n",
    "            train_r2_score = r2_score(y_train, y_train_pred)\n",
    "\n",
    "            y_test_pred = grid_search.predict(X_test)\n",
    "            test_r2_score = r2_score(y_test, y_test_pred)\n",
    "            \n",
    "            results.append({\n",
    "                'name': model_info['name'],\n",
    "                'best_params': grid_search.best_params_,\n",
    "                'best_score': grid_search.best_score_,\n",
    "                'train_r2_score': train_r2_score,\n",
    "                'test_r2_score': test_r2_score\n",
    "            })\n",
    "            print(f\"Model: {model_info['name']}\")\n",
    "            print(f\"Best model parameters: {grid_search.best_params_}\")\n",
    "            \n",
    "            # median R^2 score for the training set across all folds in the cross-validation process.\n",
    "            print(f\"Best cross-validation R^2 score: {grid_search.best_score_:.4f}\") \n",
    "            \n",
    "            print(f\"Train R^2 score: {train_r2_score:.4f}\") \n",
    "            print(f\"Test R^2 score: {test_r2_score:.4f}\")\n",
    "            print()\n",
    "    \n",
    "        best_model = max(results, key=lambda x: x['best_score'])\n",
    "        print(f\"Best model: {best_model['name']}\")\n",
    "        print(f\"Best model parameters: {best_model['best_params']}\")\n",
    "        # median R^2 score for the training set across all folds in the cross-validation process.\n",
    "        print(f\"Best cross-validation R^2 score: {best_model['best_score']:.4f}\")\n",
    "        print(f\"Train R^2 score: {best_model['train_r2_score']:.4f}\") \n",
    "        print(f\"Test R^2 score: {best_model['test_r2_score']:.4f}\")\n",
    "\n",
    "        return results #grid_search\n",
    "\n",
    "    def predict(self, df: pd.DataFrame, model: GridSearchCV) -> np.ndarray:\n",
    "        \"\"\"\n",
    "        Make predictions using a fitted regression model.\n",
    "\n",
    "        Args:\n",
    "            df (pd.DataFrame): Preprocessed dataset to be used for prediction.\n",
    "            model (GridSearchCV): Fitted regression model.\n",
    "\n",
    "        Returns:\n",
    "            Predictions of the target variable.\n",
    "        \"\"\"\n",
    "        X = df.drop(columns=[model.best_params_['model']])\n",
    "        return model.predict(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6372cc6f",
   "metadata": {},
   "source": [
    "#### Modelo 1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a97b3aa8",
   "metadata": {},
   "source": [
    "Modelo sin escalar los atributos ni hacer una selección de las variables predictoras más relevantes.\n",
    "\n",
    "- Train dataset: bagging_df1\n",
    "- Test dataset: bagging_df1_test\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bb165ca",
   "metadata": {
    "tags": []
   },
   "source": [
    "##### Train dataset (bagging_df1) y Test dataset (bagging_df1_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf2587d3",
   "metadata": {},
   "source": [
    "Debemos codificar las variables categóricas para realizar los modelos de bagging (modelos de bagging solo aceptan variables numéricas).\n",
    "\n",
    "Para ello utilizaremos:\n",
    "- one-hot encoding: para las variables que no siguen un orden o jerarquía\n",
    "- ordinal encoder: para las que hay un order o jerarquía, como floor_cat, property_age_cat y neighborhood_rent_index_cluster. Esto garantiza que los valores codificados reflejen el orden inherente de las categorías y puedan utilizarse para el análisis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 615,
   "id": "404a2635",
   "metadata": {},
   "outputs": [],
   "source": [
    "# creamos los datasets para el primer modelo de Bagging Y RF\n",
    "bagging_df1 = sales_simplified_df.copy(deep=True)\n",
    "bagging_df1_test = test_data_preprocessed.copy(deep=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "235784f9",
   "metadata": {},
   "source": [
    "**Ordinal Encoding**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "028fe1e2",
   "metadata": {},
   "source": [
    "Codificamos las variables floor_cat, property_age_cat y neighborhood_rent_index_cluster utilizando ordinal encoding. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50838d4c",
   "metadata": {},
   "source": [
    "Codificaremos la categoría \"Unknown\" como una etiqueta separada: la sustituimis por -1. Esta es una práctica común cuando se trata de datos desconocidos o faltantes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 788,
   "id": "56a7f7c4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0 - 4      2359\n",
       "Unknown    1680\n",
       "5 - 11      623\n",
       "+11          15\n",
       "Name: floor_cat, dtype: int64"
      ]
     },
     "execution_count": 788,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bagging_df1.floor_cat.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 789,
   "id": "1722957e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "40 - 70      1933\n",
       "Unknown      1415\n",
       "70 - 120      500\n",
       "0 - 40        389\n",
       "120 - 150     300\n",
       "+150          140\n",
       "Name: property_age_cat, dtype: int64"
      ]
     },
     "execution_count": 789,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bagging_df1.property_age_cat.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 790,
   "id": "9bd6301e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0 - 2337       1571\n",
       "3371 - 5042    1403\n",
       "2337 - 3371    1060\n",
       "+5042           643\n",
       "Name: neighborhood_rent_index_cluster, dtype: int64"
      ]
     },
     "execution_count": 790,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bagging_df1.neighborhood_rent_index_cluster.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 616,
   "id": "754811ed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>floor_cat</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0 - 4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0 - 40</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Unknown</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0 - 2337</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0 - 4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0 - 2337</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Unknown</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5 - 11</td>\n",
       "      <td>2.0</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  floor_cat  floor_cat_encoded property_age_cat  property_age_cat_encoded  \\\n",
       "0     0 - 4                1.0           0 - 40                       1.0   \n",
       "1   Unknown               -1.0          40 - 70                       2.0   \n",
       "2     0 - 4                1.0          Unknown                      -1.0   \n",
       "3   Unknown               -1.0          40 - 70                       2.0   \n",
       "4    5 - 11                2.0         70 - 120                       3.0   \n",
       "\n",
       "  neighborhood_rent_index_cluster  neighborhood_rent_index_cluster_encoded  \n",
       "0                     3371 - 5042                                      3.0  \n",
       "1                        0 - 2337                                      1.0  \n",
       "2                        0 - 2337                                      1.0  \n",
       "3                     3371 - 5042                                      3.0  \n",
       "4                     3371 - 5042                                      3.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>floor_cat</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0 - 4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2337 - 3371</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Unknown</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5 - 11</td>\n",
       "      <td>2.0</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0 - 4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2337 - 3371</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0 - 4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>3.0</td>\n",
       "      <td>+5042</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  floor_cat  floor_cat_encoded property_age_cat  property_age_cat_encoded  \\\n",
       "0     0 - 4                1.0          40 - 70                       2.0   \n",
       "1   Unknown               -1.0         70 - 120                       3.0   \n",
       "2    5 - 11                2.0          40 - 70                       2.0   \n",
       "3     0 - 4                1.0          40 - 70                       2.0   \n",
       "4     0 - 4                1.0         70 - 120                       3.0   \n",
       "\n",
       "  neighborhood_rent_index_cluster  neighborhood_rent_index_cluster_encoded  \n",
       "0                     2337 - 3371                                      2.0  \n",
       "1                     3371 - 5042                                      3.0  \n",
       "2                     3371 - 5042                                      3.0  \n",
       "3                     2337 - 3371                                      2.0  \n",
       "4                           +5042                                      4.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# variables que queremos codificar usando ordinal encoder\n",
    "oe_cols = oe_cols = ['floor_cat', # unknown\n",
    "                     'property_age_cat', # unknown\n",
    "                     'neighborhood_rent_index_cluster' \n",
    "                    ]\n",
    "# Define the order of the categories for each column\n",
    "floor_cat_order = ['Unknown', '0 - 4', '5 - 11', '+11']\n",
    "property_age_cat_order = ['Unknown', '0 - 40', '40 - 70', '70 - 120', '120 - 150', '+150']\n",
    "neighborhood_rent_index_cluster_order = ['Unknown', '0 - 2337', '2337 - 3371', '3371 - 5042', '+5042']\n",
    "\n",
    "# Create an instance of the ordinal encoder\n",
    "encoder = OrdinalEncoder(categories=[floor_cat_order, \n",
    "                                     property_age_cat_order, \n",
    "                                     neighborhood_rent_index_cluster_order])\n",
    "\n",
    "for col in oe_cols:\n",
    "    # Create a new column name for the encoded data\n",
    "    new_col = col + '_encoded'\n",
    "    # Create an instance of the ordinal encoder\n",
    "    encoder = OrdinalEncoder(categories=[eval(col+'_order')])\n",
    "    # Fit and transform the selected columns\n",
    "    bagging_df1[new_col] = encoder.fit_transform(bagging_df1[[col]])\n",
    "    bagging_df1_test[new_col] = encoder.fit_transform(bagging_df1_test[[col]])\n",
    "    # replace 0 by -1 ('Unknown' by -1)\n",
    "    bagging_df1[new_col] = bagging_df1[new_col].replace(0, -1)\n",
    "    bagging_df1_test[new_col] = bagging_df1_test[new_col].replace(0, -1)\n",
    "\n",
    "\n",
    "# Print the encoded data\n",
    "display(bagging_df1[['floor_cat','floor_cat_encoded','property_age_cat','property_age_cat_encoded','neighborhood_rent_index_cluster','neighborhood_rent_index_cluster_encoded']].head())\n",
    "display(bagging_df1_test[['floor_cat','floor_cat_encoded','property_age_cat','property_age_cat_encoded','neighborhood_rent_index_cluster','neighborhood_rent_index_cluster_encoded']].head())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b3db99f",
   "metadata": {},
   "source": [
    "- Ya tenemos las variables codificadas usando ordinal encoding. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4f3bfa2",
   "metadata": {},
   "source": [
    "**One-hot Encoding**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f5228ed6",
   "metadata": {},
   "source": [
    "Codificamos las variables binarias junto con orientation, heating y property_type utilizando OHE."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 617,
   "id": "8c11ee6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "def one_hot_encode(df: pd.DataFrame, cat_features: List[str]) -> pd.DataFrame:\n",
    "    \"\"\"\n",
    "    Encodes categorical features in a dataframe using scikit-learn's OneHotEncoder.\n",
    "\n",
    "    Args:\n",
    "    df (pandas.DataFrame): input dataframe\n",
    "    cat_features (list): list of categorical feature column names\n",
    "\n",
    "    Returns:\n",
    "    pandas.DataFrame: dataframe with categorical features one-hot encoded\n",
    "    \"\"\"\n",
    "    # create OneHotEncoder object and fit on categorical features\n",
    "    encoder = OneHotEncoder(handle_unknown='ignore', sparse=False)\n",
    "    encoder.fit(df[cat_features])\n",
    "\n",
    "    # get category names from encoder\n",
    "    cat_names = encoder.get_feature_names_out(cat_features)\n",
    "\n",
    "    # transform categorical features to one-hot encoded features and create new dataframe\n",
    "    encoded_cat_features = encoder.transform(df[cat_features])\n",
    "    df_encoded = pd.DataFrame(encoded_cat_features, columns=cat_names)\n",
    "\n",
    "    # add original numerical features to encoded features dataframe\n",
    "    num_features = df.drop(cat_features, axis=1)\n",
    "    df_encoded = pd.concat([num_features.reset_index(drop=True), df_encoded], axis=1)\n",
    "\n",
    "    return df_encoded\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 618,
   "id": "61db0676",
   "metadata": {},
   "outputs": [],
   "source": [
    "# variables que queremos codificar usando OHE\n",
    "ohe_cols = get_binary_cols(sales_simplified_df) + ['orientation', 'heating', 'property_type']\n",
    "# binary variables:\n",
    "    # ['balcony',\n",
    "    #  'terrace',\n",
    "    #  'exterior',\n",
    "    #  'rooftop',\n",
    "    #  'elevator',\n",
    "    #  'pool',\n",
    "    #  'ac',\n",
    "    #  'garage',\n",
    "    #  'garden']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 619,
   "id": "f3f77b81",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>neighborhood</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>property_age_cat</th>\n",
       "      <th>floor_cat</th>\n",
       "      <th>neighborhood_rent_index_cluster</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2290000</td>\n",
       "      <td>41.409071</td>\n",
       "      <td>2.099850</td>\n",
       "      <td>532</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>Vallvidrera - El Tibidabo i les Planes</td>\n",
       "      <td>6.302847</td>\n",
       "      <td>2.949904</td>\n",
       "      <td>0 - 40</td>\n",
       "      <td>0 - 4</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>0.939850</td>\n",
       "      <td>1.127820</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>90000</td>\n",
       "      <td>41.434545</td>\n",
       "      <td>2.171110</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Can Peguera - El Turó de la Peira</td>\n",
       "      <td>5.189265</td>\n",
       "      <td>0.329115</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0 - 2337</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>145000</td>\n",
       "      <td>41.444518</td>\n",
       "      <td>2.175309</td>\n",
       "      <td>53</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Verdun</td>\n",
       "      <td>6.313668</td>\n",
       "      <td>0.284071</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0 - 4</td>\n",
       "      <td>0 - 2337</td>\n",
       "      <td>5.660377</td>\n",
       "      <td>1.886792</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>675000</td>\n",
       "      <td>41.392209</td>\n",
       "      <td>2.153368</td>\n",
       "      <td>120</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>L'Antiga Esquerra de l'Eixample</td>\n",
       "      <td>1.462060</td>\n",
       "      <td>0.443717</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.333333</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>319000</td>\n",
       "      <td>41.413385</td>\n",
       "      <td>2.162246</td>\n",
       "      <td>69</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>El Baix Guinardó</td>\n",
       "      <td>2.906147</td>\n",
       "      <td>0.371854</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>5 - 11</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>1.449275</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0  2290000  41.409071   2.099850              532      5          6   \n",
       "1    90000  41.434545   2.171110               50      1          1   \n",
       "2   145000  41.444518   2.175309               53      3          1   \n",
       "3   675000  41.392209   2.153368              120      4          2   \n",
       "4   319000  41.413385   2.162246               69      3          1   \n",
       "\n",
       "                             neighborhood  dist_city_center  \\\n",
       "0  Vallvidrera - El Tibidabo i les Planes          6.302847   \n",
       "1       Can Peguera - El Turó de la Peira          5.189265   \n",
       "2                                  Verdun          6.313668   \n",
       "3         L'Antiga Esquerra de l'Eixample          1.462060   \n",
       "4                        El Baix Guinardó          2.906147   \n",
       "\n",
       "   dist_closest_station property_age_cat floor_cat  \\\n",
       "0              2.949904           0 - 40     0 - 4   \n",
       "1              0.329115          40 - 70   Unknown   \n",
       "2              0.284071          Unknown     0 - 4   \n",
       "3              0.443717          40 - 70   Unknown   \n",
       "4              0.371854         70 - 120    5 - 11   \n",
       "\n",
       "  neighborhood_rent_index_cluster  rooms_per_100_sqm  bathrooms_per_100_sqm  \\\n",
       "0                     3371 - 5042           0.939850               1.127820   \n",
       "1                        0 - 2337           2.000000               2.000000   \n",
       "2                        0 - 2337           5.660377               1.886792   \n",
       "3                     3371 - 5042           3.333333               1.666667   \n",
       "4                     3371 - 5042           4.347826               1.449275   \n",
       "\n",
       "   floor_cat_encoded  property_age_cat_encoded  \\\n",
       "0                1.0                       1.0   \n",
       "1               -1.0                       2.0   \n",
       "2                1.0                      -1.0   \n",
       "3               -1.0                       2.0   \n",
       "4                2.0                       3.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  balcony_0  balcony_1  terrace_0  \\\n",
       "0                                      3.0        0.0        1.0        0.0   \n",
       "1                                      1.0        1.0        0.0        1.0   \n",
       "2                                      1.0        0.0        1.0        1.0   \n",
       "3                                      3.0        1.0        0.0        0.0   \n",
       "4                                      3.0        1.0        0.0        1.0   \n",
       "\n",
       "   terrace_1  exterior_0  exterior_1  rooftop_0  rooftop_1  elevator_0  \\\n",
       "0        1.0         1.0         0.0        1.0        0.0         1.0   \n",
       "1        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "2        0.0         0.0         1.0        1.0        0.0         1.0   \n",
       "3        1.0         1.0         0.0        0.0        1.0         0.0   \n",
       "4        0.0         0.0         1.0        0.0        1.0         0.0   \n",
       "\n",
       "   elevator_1  pool_0  pool_1  ac_0  ac_1  garage_0  garage_1  garden_0  \\\n",
       "0         0.0     0.0     1.0   0.0   1.0       0.0       1.0       0.0   \n",
       "1         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "2         0.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "3         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "4         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "0       1.0                0.0                 0.0                 0.0   \n",
       "1       0.0                0.0                 1.0                 0.0   \n",
       "2       0.0                0.0                 0.0                 0.0   \n",
       "3       0.0                0.0                 1.0                 0.0   \n",
       "4       0.0                0.0                 0.0                 0.0   \n",
       "\n",
       "   orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "0               1.0                  0.0              0.0            0.0   \n",
       "1               0.0                  0.0              0.0            1.0   \n",
       "2               0.0                  1.0              1.0            0.0   \n",
       "3               0.0                  0.0              0.0            0.0   \n",
       "4               0.0                  1.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "0               0.0          0.0                 1.0                  0.0   \n",
       "1               0.0          0.0                 0.0                  0.0   \n",
       "2               0.0          0.0                 0.0                  0.0   \n",
       "3               0.0          0.0                 1.0                  1.0   \n",
       "4               0.0          0.0                 0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 1.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \n",
       "0                   0.0                    0.0                 0.0  \n",
       "1                   0.0                    0.0                 1.0  \n",
       "2                   0.0                    0.0                 1.0  \n",
       "3                   0.0                    0.0                 0.0  \n",
       "4                   0.0                    0.0                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(4675, 53)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>neighborhood</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>property_age_cat</th>\n",
       "      <th>floor_cat</th>\n",
       "      <th>neighborhood_rent_index_cluster</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>133000</td>\n",
       "      <td>41.421077</td>\n",
       "      <td>2.213120</td>\n",
       "      <td>76</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Sant Martí</td>\n",
       "      <td>5.158288</td>\n",
       "      <td>0.272653</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>0 - 4</td>\n",
       "      <td>2337 - 3371</td>\n",
       "      <td>3.947368</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>485000</td>\n",
       "      <td>41.380788</td>\n",
       "      <td>2.152472</td>\n",
       "      <td>130</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>La Nova Esquerra de l'Eixample</td>\n",
       "      <td>1.657143</td>\n",
       "      <td>0.245719</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.076923</td>\n",
       "      <td>1.538462</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>265000</td>\n",
       "      <td>41.406803</td>\n",
       "      <td>2.183533</td>\n",
       "      <td>77</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>El Camp de l'Arpa del Clot</td>\n",
       "      <td>2.389801</td>\n",
       "      <td>0.084520</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>5 - 11</td>\n",
       "      <td>3371 - 5042</td>\n",
       "      <td>3.896104</td>\n",
       "      <td>1.298701</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>154500</td>\n",
       "      <td>41.433890</td>\n",
       "      <td>2.172277</td>\n",
       "      <td>61</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Porta</td>\n",
       "      <td>5.119194</td>\n",
       "      <td>0.355555</td>\n",
       "      <td>40 - 70</td>\n",
       "      <td>0 - 4</td>\n",
       "      <td>2337 - 3371</td>\n",
       "      <td>3.278689</td>\n",
       "      <td>1.639344</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1200000</td>\n",
       "      <td>41.393411</td>\n",
       "      <td>2.145017</td>\n",
       "      <td>120</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>Sant Gervasi - Galvany</td>\n",
       "      <td>2.166588</td>\n",
       "      <td>0.735841</td>\n",
       "      <td>70 - 120</td>\n",
       "      <td>0 - 4</td>\n",
       "      <td>+5042</td>\n",
       "      <td>2.500000</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0   133000  41.421077   2.213120               76      3          1   \n",
       "1   485000  41.380788   2.152472              130      4          2   \n",
       "2   265000  41.406803   2.183533               77      3          1   \n",
       "3   154500  41.433890   2.172277               61      2          1   \n",
       "4  1200000  41.393411   2.145017              120      3          2   \n",
       "\n",
       "                     neighborhood  dist_city_center  dist_closest_station  \\\n",
       "0                      Sant Martí          5.158288              0.272653   \n",
       "1  La Nova Esquerra de l'Eixample          1.657143              0.245719   \n",
       "2      El Camp de l'Arpa del Clot          2.389801              0.084520   \n",
       "3                           Porta          5.119194              0.355555   \n",
       "4          Sant Gervasi - Galvany          2.166588              0.735841   \n",
       "\n",
       "  property_age_cat floor_cat neighborhood_rent_index_cluster  \\\n",
       "0          40 - 70     0 - 4                     2337 - 3371   \n",
       "1         70 - 120   Unknown                     3371 - 5042   \n",
       "2          40 - 70    5 - 11                     3371 - 5042   \n",
       "3          40 - 70     0 - 4                     2337 - 3371   \n",
       "4         70 - 120     0 - 4                           +5042   \n",
       "\n",
       "   rooms_per_100_sqm  bathrooms_per_100_sqm  floor_cat_encoded  \\\n",
       "0           3.947368               1.315789                1.0   \n",
       "1           3.076923               1.538462               -1.0   \n",
       "2           3.896104               1.298701                2.0   \n",
       "3           3.278689               1.639344                1.0   \n",
       "4           2.500000               1.666667                1.0   \n",
       "\n",
       "   property_age_cat_encoded  neighborhood_rent_index_cluster_encoded  \\\n",
       "0                       2.0                                      2.0   \n",
       "1                       3.0                                      3.0   \n",
       "2                       2.0                                      3.0   \n",
       "3                       2.0                                      2.0   \n",
       "4                       3.0                                      4.0   \n",
       "\n",
       "   balcony_0  balcony_1  terrace_0  terrace_1  exterior_0  exterior_1  \\\n",
       "0        1.0        0.0        1.0        0.0         0.0         1.0   \n",
       "1        1.0        0.0        1.0        0.0         1.0         0.0   \n",
       "2        1.0        0.0        1.0        0.0         0.0         1.0   \n",
       "3        0.0        1.0        1.0        0.0         0.0         1.0   \n",
       "4        1.0        0.0        1.0        0.0         0.0         1.0   \n",
       "\n",
       "   rooftop_0  rooftop_1  elevator_0  elevator_1  pool_0  pool_1  ac_0  ac_1  \\\n",
       "0        1.0        0.0         0.0         1.0     1.0     0.0   1.0   0.0   \n",
       "1        1.0        0.0         0.0         1.0     1.0     0.0   1.0   0.0   \n",
       "2        1.0        0.0         0.0         1.0     1.0     0.0   0.0   1.0   \n",
       "3        1.0        0.0         0.0         1.0     1.0     0.0   1.0   0.0   \n",
       "4        1.0        0.0         0.0         1.0     1.0     0.0   0.0   1.0   \n",
       "\n",
       "   garage_0  garage_1  garden_0  garden_1  orientation_ este  \\\n",
       "0       1.0       0.0       1.0       0.0                0.0   \n",
       "1       1.0       0.0       1.0       0.0                0.0   \n",
       "2       1.0       0.0       1.0       0.0                0.0   \n",
       "3       1.0       0.0       1.0       0.0                0.0   \n",
       "4       1.0       0.0       1.0       0.0                0.0   \n",
       "\n",
       "   orientation_ norte  orientation_ oeste  orientation_ sur  \\\n",
       "0                 0.0                 0.0               0.0   \n",
       "1                 0.0                 0.0               0.0   \n",
       "2                 1.0                 0.0               0.0   \n",
       "3                 0.0                 0.0               0.0   \n",
       "4                 0.0                 0.0               1.0   \n",
       "\n",
       "   orientation_Unknown  heating_Unknown  heating_bomba  heating_electric  \\\n",
       "0                  1.0              0.0            0.0               0.0   \n",
       "1                  1.0              1.0            0.0               0.0   \n",
       "2                  0.0              1.0            0.0               0.0   \n",
       "3                  1.0              0.0            0.0               0.0   \n",
       "4                  0.0              0.0            0.0               0.0   \n",
       "\n",
       "   heating_gas  heating_individual  property_type_atico  property_type_chalet  \\\n",
       "0          1.0                 0.0                  0.0                   0.0   \n",
       "1          0.0                 0.0                  0.0                   0.0   \n",
       "2          0.0                 0.0                  0.0                   0.0   \n",
       "3          1.0                 0.0                  0.0                   0.0   \n",
       "4          1.0                 0.0                  0.0                   0.0   \n",
       "\n",
       "   property_type_chalet_adosado  property_type_chalet_independiente  \\\n",
       "0                           0.0                                 0.0   \n",
       "1                           0.0                                 0.0   \n",
       "2                           0.0                                 0.0   \n",
       "3                           0.0                                 0.0   \n",
       "4                           0.0                                 0.0   \n",
       "\n",
       "   property_type_chalet_pareado  property_type_duplex  property_type_estudio  \\\n",
       "0                           0.0                   0.0                    0.0   \n",
       "1                           0.0                   0.0                    0.0   \n",
       "2                           0.0                   0.0                    0.0   \n",
       "3                           0.0                   0.0                    0.0   \n",
       "4                           0.0                   0.0                    0.0   \n",
       "\n",
       "   property_type_piso  \n",
       "0                 1.0  \n",
       "1                 1.0  \n",
       "2                 1.0  \n",
       "3                 1.0  \n",
       "4                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(1170, 53)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# aplicamos one - hot encoding al dataset\n",
    "bagging_df1 = one_hot_encode(bagging_df1, ohe_cols)\n",
    "bagging_df1_test = one_hot_encode(bagging_df1_test, ohe_cols)\n",
    "\n",
    "\n",
    "display(bagging_df1.head())\n",
    "display(bagging_df1.shape)\n",
    "\n",
    "display(bagging_df1_test.head())\n",
    "display(bagging_df1_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f5481e0a",
   "metadata": {},
   "source": [
    "Eliminamos las variables categóricas no codificadas: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 620,
   "id": "b657264e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['neighborhood',\n",
       " 'property_age_cat',\n",
       " 'floor_cat',\n",
       " 'neighborhood_rent_index_cluster']"
      ]
     },
     "execution_count": 620,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "no_encoded_cat_vars = bagging_df1.select_dtypes(include=['category']).columns.tolist()\n",
    "no_encoded_cat_vars"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 621,
   "id": "399c8153",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['neighborhood',\n",
       " 'property_age_cat',\n",
       " 'floor_cat',\n",
       " 'neighborhood_rent_index_cluster']"
      ]
     },
     "execution_count": 621,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "no_encoded_cat_vars_test = bagging_df1_test.select_dtypes(include=['category']).columns.tolist()\n",
    "no_encoded_cat_vars_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 622,
   "id": "a7609691",
   "metadata": {},
   "outputs": [],
   "source": [
    "bagging_df1.drop(no_encoded_cat_vars, axis=1, inplace=True)\n",
    "bagging_df1_test.drop(no_encoded_cat_vars_test, axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 623,
   "id": "13e2a04e",
   "metadata": {
    "jupyter": {
     "outputs_hidden": true
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAIN: \n",
      "The dataset includes 4675 instances (rows) and 49 variables (columns).\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2290000</td>\n",
       "      <td>41.409071</td>\n",
       "      <td>2.099850</td>\n",
       "      <td>532</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>6.302847</td>\n",
       "      <td>2.949904</td>\n",
       "      <td>0.939850</td>\n",
       "      <td>1.127820</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>90000</td>\n",
       "      <td>41.434545</td>\n",
       "      <td>2.171110</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5.189265</td>\n",
       "      <td>0.329115</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>145000</td>\n",
       "      <td>41.444518</td>\n",
       "      <td>2.175309</td>\n",
       "      <td>53</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>6.313668</td>\n",
       "      <td>0.284071</td>\n",
       "      <td>5.660377</td>\n",
       "      <td>1.886792</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>675000</td>\n",
       "      <td>41.392209</td>\n",
       "      <td>2.153368</td>\n",
       "      <td>120</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1.462060</td>\n",
       "      <td>0.443717</td>\n",
       "      <td>3.333333</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>319000</td>\n",
       "      <td>41.413385</td>\n",
       "      <td>2.162246</td>\n",
       "      <td>69</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.906147</td>\n",
       "      <td>0.371854</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>1.449275</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0  2290000  41.409071   2.099850              532      5          6   \n",
       "1    90000  41.434545   2.171110               50      1          1   \n",
       "2   145000  41.444518   2.175309               53      3          1   \n",
       "3   675000  41.392209   2.153368              120      4          2   \n",
       "4   319000  41.413385   2.162246               69      3          1   \n",
       "\n",
       "   dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "0          6.302847              2.949904           0.939850   \n",
       "1          5.189265              0.329115           2.000000   \n",
       "2          6.313668              0.284071           5.660377   \n",
       "3          1.462060              0.443717           3.333333   \n",
       "4          2.906147              0.371854           4.347826   \n",
       "\n",
       "   bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "0               1.127820                1.0                       1.0   \n",
       "1               2.000000               -1.0                       2.0   \n",
       "2               1.886792                1.0                      -1.0   \n",
       "3               1.666667               -1.0                       2.0   \n",
       "4               1.449275                2.0                       3.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  balcony_0  balcony_1  terrace_0  \\\n",
       "0                                      3.0        0.0        1.0        0.0   \n",
       "1                                      1.0        1.0        0.0        1.0   \n",
       "2                                      1.0        0.0        1.0        1.0   \n",
       "3                                      3.0        1.0        0.0        0.0   \n",
       "4                                      3.0        1.0        0.0        1.0   \n",
       "\n",
       "   terrace_1  exterior_0  exterior_1  rooftop_0  rooftop_1  elevator_0  \\\n",
       "0        1.0         1.0         0.0        1.0        0.0         1.0   \n",
       "1        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "2        0.0         0.0         1.0        1.0        0.0         1.0   \n",
       "3        1.0         1.0         0.0        0.0        1.0         0.0   \n",
       "4        0.0         0.0         1.0        0.0        1.0         0.0   \n",
       "\n",
       "   elevator_1  pool_0  pool_1  ac_0  ac_1  garage_0  garage_1  garden_0  \\\n",
       "0         0.0     0.0     1.0   0.0   1.0       0.0       1.0       0.0   \n",
       "1         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "2         0.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "3         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "4         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "0       1.0                0.0                 0.0                 0.0   \n",
       "1       0.0                0.0                 1.0                 0.0   \n",
       "2       0.0                0.0                 0.0                 0.0   \n",
       "3       0.0                0.0                 1.0                 0.0   \n",
       "4       0.0                0.0                 0.0                 0.0   \n",
       "\n",
       "   orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "0               1.0                  0.0              0.0            0.0   \n",
       "1               0.0                  0.0              0.0            1.0   \n",
       "2               0.0                  1.0              1.0            0.0   \n",
       "3               0.0                  0.0              0.0            0.0   \n",
       "4               0.0                  1.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "0               0.0          0.0                 1.0                  0.0   \n",
       "1               0.0          0.0                 0.0                  0.0   \n",
       "2               0.0          0.0                 0.0                  0.0   \n",
       "3               0.0          0.0                 1.0                  1.0   \n",
       "4               0.0          0.0                 0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 1.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \n",
       "0                   0.0                    0.0                 0.0  \n",
       "1                   0.0                    0.0                 1.0  \n",
       "2                   0.0                    0.0                 1.0  \n",
       "3                   0.0                    0.0                 0.0  \n",
       "4                   0.0                    0.0                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4675 entries, 0 to 4674\n",
      "Data columns (total 49 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    4675 non-null   int64  \n",
      " 1   latitude                                 4675 non-null   float64\n",
      " 2   longitude                                4675 non-null   float64\n",
      " 3   sq_meters_built                          4675 non-null   int64  \n",
      " 4   rooms                                    4675 non-null   int64  \n",
      " 5   bathrooms                                4675 non-null   int64  \n",
      " 6   dist_city_center                         4675 non-null   float64\n",
      " 7   dist_closest_station                     4675 non-null   float64\n",
      " 8   rooms_per_100_sqm                        4675 non-null   float64\n",
      " 9   bathrooms_per_100_sqm                    4675 non-null   float64\n",
      " 10  floor_cat_encoded                        4675 non-null   float64\n",
      " 11  property_age_cat_encoded                 4675 non-null   float64\n",
      " 12  neighborhood_rent_index_cluster_encoded  4675 non-null   float64\n",
      " 13  balcony_0                                4675 non-null   float64\n",
      " 14  balcony_1                                4675 non-null   float64\n",
      " 15  terrace_0                                4675 non-null   float64\n",
      " 16  terrace_1                                4675 non-null   float64\n",
      " 17  exterior_0                               4675 non-null   float64\n",
      " 18  exterior_1                               4675 non-null   float64\n",
      " 19  rooftop_0                                4675 non-null   float64\n",
      " 20  rooftop_1                                4675 non-null   float64\n",
      " 21  elevator_0                               4675 non-null   float64\n",
      " 22  elevator_1                               4675 non-null   float64\n",
      " 23  pool_0                                   4675 non-null   float64\n",
      " 24  pool_1                                   4675 non-null   float64\n",
      " 25  ac_0                                     4675 non-null   float64\n",
      " 26  ac_1                                     4675 non-null   float64\n",
      " 27  garage_0                                 4675 non-null   float64\n",
      " 28  garage_1                                 4675 non-null   float64\n",
      " 29  garden_0                                 4675 non-null   float64\n",
      " 30  garden_1                                 4675 non-null   float64\n",
      " 31  orientation_ este                        4675 non-null   float64\n",
      " 32  orientation_ norte                       4675 non-null   float64\n",
      " 33  orientation_ oeste                       4675 non-null   float64\n",
      " 34  orientation_ sur                         4675 non-null   float64\n",
      " 35  orientation_Unknown                      4675 non-null   float64\n",
      " 36  heating_Unknown                          4675 non-null   float64\n",
      " 37  heating_bomba                            4675 non-null   float64\n",
      " 38  heating_electric                         4675 non-null   float64\n",
      " 39  heating_gas                              4675 non-null   float64\n",
      " 40  heating_individual                       4675 non-null   float64\n",
      " 41  property_type_atico                      4675 non-null   float64\n",
      " 42  property_type_chalet                     4675 non-null   float64\n",
      " 43  property_type_chalet_adosado             4675 non-null   float64\n",
      " 44  property_type_chalet_independiente       4675 non-null   float64\n",
      " 45  property_type_chalet_pareado             4675 non-null   float64\n",
      " 46  property_type_duplex                     4675 non-null   float64\n",
      " 47  property_type_estudio                    4675 non-null   float64\n",
      " 48  property_type_piso                       4675 non-null   float64\n",
      "dtypes: float64(45), int64(4)\n",
      "memory usage: 1.7 MB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "latitude                                   0\n",
      "longitude                                  0\n",
      "sq_meters_built                            0\n",
      "rooms                                      0\n",
      "bathrooms                                  0\n",
      "dist_city_center                           0\n",
      "dist_closest_station                       0\n",
      "rooms_per_100_sqm                          0\n",
      "bathrooms_per_100_sqm                      0\n",
      "floor_cat_encoded                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "balcony_0                                  0\n",
      "balcony_1                                  0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "exterior_0                                 0\n",
      "exterior_1                                 0\n",
      "rooftop_0                                  0\n",
      "rooftop_1                                  0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "orientation_ este                          0\n",
      "orientation_ norte                         0\n",
      "orientation_ oeste                         0\n",
      "orientation_ sur                           0\n",
      "orientation_Unknown                        0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4.675000e+03</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.567950e+05</td>\n",
       "      <td>41.406603</td>\n",
       "      <td>2.168282</td>\n",
       "      <td>85.819465</td>\n",
       "      <td>2.580749</td>\n",
       "      <td>1.410481</td>\n",
       "      <td>3.501909</td>\n",
       "      <td>0.359388</td>\n",
       "      <td>3.379902</td>\n",
       "      <td>1.844308</td>\n",
       "      <td>0.421390</td>\n",
       "      <td>1.333904</td>\n",
       "      <td>2.238717</td>\n",
       "      <td>0.623957</td>\n",
       "      <td>0.376043</td>\n",
       "      <td>0.760428</td>\n",
       "      <td>0.239572</td>\n",
       "      <td>0.293262</td>\n",
       "      <td>0.706738</td>\n",
       "      <td>0.930695</td>\n",
       "      <td>0.069305</td>\n",
       "      <td>0.436791</td>\n",
       "      <td>0.563209</td>\n",
       "      <td>0.973690</td>\n",
       "      <td>0.026310</td>\n",
       "      <td>0.549091</td>\n",
       "      <td>0.450909</td>\n",
       "      <td>0.931551</td>\n",
       "      <td>0.068449</td>\n",
       "      <td>0.989733</td>\n",
       "      <td>0.010267</td>\n",
       "      <td>0.118289</td>\n",
       "      <td>0.125775</td>\n",
       "      <td>0.050053</td>\n",
       "      <td>0.245775</td>\n",
       "      <td>0.460107</td>\n",
       "      <td>0.589733</td>\n",
       "      <td>0.056898</td>\n",
       "      <td>0.042567</td>\n",
       "      <td>0.235936</td>\n",
       "      <td>0.074866</td>\n",
       "      <td>0.050267</td>\n",
       "      <td>0.007701</td>\n",
       "      <td>0.005989</td>\n",
       "      <td>0.005561</td>\n",
       "      <td>0.002567</td>\n",
       "      <td>0.016043</td>\n",
       "      <td>0.037861</td>\n",
       "      <td>0.874011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>4.910966e+05</td>\n",
       "      <td>0.026137</td>\n",
       "      <td>0.022753</td>\n",
       "      <td>66.934320</td>\n",
       "      <td>1.160086</td>\n",
       "      <td>0.793276</td>\n",
       "      <td>2.034103</td>\n",
       "      <td>0.280663</td>\n",
       "      <td>1.693352</td>\n",
       "      <td>1.088397</td>\n",
       "      <td>1.117207</td>\n",
       "      <td>1.731172</td>\n",
       "      <td>1.062609</td>\n",
       "      <td>0.484443</td>\n",
       "      <td>0.484443</td>\n",
       "      <td>0.426868</td>\n",
       "      <td>0.426868</td>\n",
       "      <td>0.455306</td>\n",
       "      <td>0.455306</td>\n",
       "      <td>0.253999</td>\n",
       "      <td>0.253999</td>\n",
       "      <td>0.496042</td>\n",
       "      <td>0.496042</td>\n",
       "      <td>0.160073</td>\n",
       "      <td>0.160073</td>\n",
       "      <td>0.497637</td>\n",
       "      <td>0.497637</td>\n",
       "      <td>0.252542</td>\n",
       "      <td>0.252542</td>\n",
       "      <td>0.100817</td>\n",
       "      <td>0.100817</td>\n",
       "      <td>0.322984</td>\n",
       "      <td>0.331632</td>\n",
       "      <td>0.218079</td>\n",
       "      <td>0.430592</td>\n",
       "      <td>0.498459</td>\n",
       "      <td>0.491935</td>\n",
       "      <td>0.231673</td>\n",
       "      <td>0.201900</td>\n",
       "      <td>0.424628</td>\n",
       "      <td>0.263204</td>\n",
       "      <td>0.218520</td>\n",
       "      <td>0.087424</td>\n",
       "      <td>0.077167</td>\n",
       "      <td>0.074376</td>\n",
       "      <td>0.050604</td>\n",
       "      <td>0.125653</td>\n",
       "      <td>0.190880</td>\n",
       "      <td>0.331873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.800000e+04</td>\n",
       "      <td>41.355002</td>\n",
       "      <td>2.092727</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.075001</td>\n",
       "      <td>0.003595</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.227273</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.350000e+05</td>\n",
       "      <td>41.382507</td>\n",
       "      <td>2.153545</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.748592</td>\n",
       "      <td>0.212796</td>\n",
       "      <td>2.439024</td>\n",
       "      <td>1.428571</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.870000e+05</td>\n",
       "      <td>41.404373</td>\n",
       "      <td>2.170370</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.361583</td>\n",
       "      <td>0.311358</td>\n",
       "      <td>3.448276</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.900000e+05</td>\n",
       "      <td>41.424739</td>\n",
       "      <td>2.180816</td>\n",
       "      <td>92.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.914956</td>\n",
       "      <td>0.420666</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>2.083333</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.500000e+06</td>\n",
       "      <td>41.465303</td>\n",
       "      <td>2.220785</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>8.627149</td>\n",
       "      <td>4.203571</td>\n",
       "      <td>55.555556</td>\n",
       "      <td>52.941176</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price     latitude    longitude  sq_meters_built        rooms  \\\n",
       "count  4.675000e+03  4675.000000  4675.000000      4675.000000  4675.000000   \n",
       "mean   3.567950e+05    41.406603     2.168282        85.819465     2.580749   \n",
       "std    4.910966e+05     0.026137     0.022753        66.934320     1.160086   \n",
       "min    2.800000e+04    41.355002     2.092727        13.000000     0.000000   \n",
       "25%    1.350000e+05    41.382507     2.153545        55.000000     2.000000   \n",
       "50%    1.870000e+05    41.404373     2.170370        68.000000     3.000000   \n",
       "75%    3.900000e+05    41.424739     2.180816        92.000000     3.000000   \n",
       "max    9.500000e+06    41.465303     2.220785       970.000000    11.000000   \n",
       "\n",
       "         bathrooms  dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "count  4675.000000       4675.000000           4675.000000        4675.000000   \n",
       "mean      1.410481          3.501909              0.359388           3.379902   \n",
       "std       0.793276          2.034103              0.280663           1.693352   \n",
       "min       1.000000          0.075001              0.003595           0.000000   \n",
       "25%       1.000000          1.748592              0.212796           2.439024   \n",
       "50%       1.000000          3.361583              0.311358           3.448276   \n",
       "75%       2.000000          4.914956              0.420666           4.347826   \n",
       "max       9.000000          8.627149              4.203571          55.555556   \n",
       "\n",
       "       bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "count            4675.000000        4675.000000               4675.000000   \n",
       "mean                1.844308           0.421390                  1.333904   \n",
       "std                 1.088397           1.117207                  1.731172   \n",
       "min                 0.227273          -1.000000                 -1.000000   \n",
       "25%                 1.428571          -1.000000                 -1.000000   \n",
       "50%                 1.666667           1.000000                  2.000000   \n",
       "75%                 2.083333           1.000000                  2.000000   \n",
       "max                52.941176           3.000000                  5.000000   \n",
       "\n",
       "       neighborhood_rent_index_cluster_encoded    balcony_0    balcony_1  \\\n",
       "count                              4675.000000  4675.000000  4675.000000   \n",
       "mean                                  2.238717     0.623957     0.376043   \n",
       "std                                   1.062609     0.484443     0.484443   \n",
       "min                                   1.000000     0.000000     0.000000   \n",
       "25%                                   1.000000     0.000000     0.000000   \n",
       "50%                                   2.000000     1.000000     0.000000   \n",
       "75%                                   3.000000     1.000000     1.000000   \n",
       "max                                   4.000000     1.000000     1.000000   \n",
       "\n",
       "         terrace_0    terrace_1   exterior_0   exterior_1    rooftop_0  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.760428     0.239572     0.293262     0.706738     0.930695   \n",
       "std       0.426868     0.426868     0.455306     0.455306     0.253999   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       1.000000     0.000000     0.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     0.000000     1.000000     1.000000   \n",
       "75%       1.000000     0.000000     1.000000     1.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "         rooftop_1   elevator_0   elevator_1       pool_0       pool_1  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.069305     0.436791     0.563209     0.973690     0.026310   \n",
       "std       0.253999     0.496042     0.496042     0.160073     0.160073   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     1.000000     0.000000   \n",
       "50%       0.000000     0.000000     1.000000     1.000000     0.000000   \n",
       "75%       0.000000     1.000000     1.000000     1.000000     0.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "              ac_0         ac_1     garage_0     garage_1     garden_0  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.549091     0.450909     0.931551     0.068449     0.989733   \n",
       "std       0.497637     0.497637     0.252542     0.252542     0.100817   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "          garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "count  4675.000000        4675.000000         4675.000000         4675.000000   \n",
       "mean      0.010267           0.118289            0.125775            0.050053   \n",
       "std       0.100817           0.322984            0.331632            0.218079   \n",
       "min       0.000000           0.000000            0.000000            0.000000   \n",
       "25%       0.000000           0.000000            0.000000            0.000000   \n",
       "50%       0.000000           0.000000            0.000000            0.000000   \n",
       "75%       0.000000           0.000000            0.000000            0.000000   \n",
       "max       1.000000           1.000000            1.000000            1.000000   \n",
       "\n",
       "       orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "count       4675.000000          4675.000000      4675.000000    4675.000000   \n",
       "mean           0.245775             0.460107         0.589733       0.056898   \n",
       "std            0.430592             0.498459         0.491935       0.231673   \n",
       "min            0.000000             0.000000         0.000000       0.000000   \n",
       "25%            0.000000             0.000000         0.000000       0.000000   \n",
       "50%            0.000000             0.000000         1.000000       0.000000   \n",
       "75%            0.000000             1.000000         1.000000       0.000000   \n",
       "max            1.000000             1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "count       4675.000000  4675.000000         4675.000000          4675.000000   \n",
       "mean           0.042567     0.235936            0.074866             0.050267   \n",
       "std            0.201900     0.424628            0.263204             0.218520   \n",
       "min            0.000000     0.000000            0.000000             0.000000   \n",
       "25%            0.000000     0.000000            0.000000             0.000000   \n",
       "50%            0.000000     0.000000            0.000000             0.000000   \n",
       "75%            0.000000     0.000000            0.000000             0.000000   \n",
       "max            1.000000     1.000000            1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           4675.000000                   4675.000000   \n",
       "mean               0.007701                      0.005989   \n",
       "std                0.087424                      0.077167   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         4675.000000                   4675.000000   \n",
       "mean                             0.005561                      0.002567   \n",
       "std                              0.074376                      0.050604   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \n",
       "count           4675.000000            4675.000000         4675.000000  \n",
       "mean               0.016043               0.037861            0.874011  \n",
       "std                0.125653               0.190880            0.331873  \n",
       "min                0.000000               0.000000            0.000000  \n",
       "25%                0.000000               0.000000            1.000000  \n",
       "50%                0.000000               0.000000            1.000000  \n",
       "75%                0.000000               0.000000            1.000000  \n",
       "max                1.000000               1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 4\n",
      "\n",
      "\n",
      "\n",
      "TEST: \n",
      "The dataset includes 1170 instances (rows) and 49 variables (columns).\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>133000</td>\n",
       "      <td>41.421077</td>\n",
       "      <td>2.213120</td>\n",
       "      <td>76</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.158288</td>\n",
       "      <td>0.272653</td>\n",
       "      <td>3.947368</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>485000</td>\n",
       "      <td>41.380788</td>\n",
       "      <td>2.152472</td>\n",
       "      <td>130</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1.657143</td>\n",
       "      <td>0.245719</td>\n",
       "      <td>3.076923</td>\n",
       "      <td>1.538462</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>265000</td>\n",
       "      <td>41.406803</td>\n",
       "      <td>2.183533</td>\n",
       "      <td>77</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.389801</td>\n",
       "      <td>0.084520</td>\n",
       "      <td>3.896104</td>\n",
       "      <td>1.298701</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>154500</td>\n",
       "      <td>41.433890</td>\n",
       "      <td>2.172277</td>\n",
       "      <td>61</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>5.119194</td>\n",
       "      <td>0.355555</td>\n",
       "      <td>3.278689</td>\n",
       "      <td>1.639344</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1200000</td>\n",
       "      <td>41.393411</td>\n",
       "      <td>2.145017</td>\n",
       "      <td>120</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2.166588</td>\n",
       "      <td>0.735841</td>\n",
       "      <td>2.500000</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0   133000  41.421077   2.213120               76      3          1   \n",
       "1   485000  41.380788   2.152472              130      4          2   \n",
       "2   265000  41.406803   2.183533               77      3          1   \n",
       "3   154500  41.433890   2.172277               61      2          1   \n",
       "4  1200000  41.393411   2.145017              120      3          2   \n",
       "\n",
       "   dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "0          5.158288              0.272653           3.947368   \n",
       "1          1.657143              0.245719           3.076923   \n",
       "2          2.389801              0.084520           3.896104   \n",
       "3          5.119194              0.355555           3.278689   \n",
       "4          2.166588              0.735841           2.500000   \n",
       "\n",
       "   bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "0               1.315789                1.0                       2.0   \n",
       "1               1.538462               -1.0                       3.0   \n",
       "2               1.298701                2.0                       2.0   \n",
       "3               1.639344                1.0                       2.0   \n",
       "4               1.666667                1.0                       3.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  balcony_0  balcony_1  terrace_0  \\\n",
       "0                                      2.0        1.0        0.0        1.0   \n",
       "1                                      3.0        1.0        0.0        1.0   \n",
       "2                                      3.0        1.0        0.0        1.0   \n",
       "3                                      2.0        0.0        1.0        1.0   \n",
       "4                                      4.0        1.0        0.0        1.0   \n",
       "\n",
       "   terrace_1  exterior_0  exterior_1  rooftop_0  rooftop_1  elevator_0  \\\n",
       "0        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "1        0.0         1.0         0.0        1.0        0.0         0.0   \n",
       "2        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "3        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "4        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "\n",
       "   elevator_1  pool_0  pool_1  ac_0  ac_1  garage_0  garage_1  garden_0  \\\n",
       "0         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "1         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "2         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "3         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "4         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "0       0.0                0.0                 0.0                 0.0   \n",
       "1       0.0                0.0                 0.0                 0.0   \n",
       "2       0.0                0.0                 1.0                 0.0   \n",
       "3       0.0                0.0                 0.0                 0.0   \n",
       "4       0.0                0.0                 0.0                 0.0   \n",
       "\n",
       "   orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "0               0.0                  1.0              0.0            0.0   \n",
       "1               0.0                  1.0              1.0            0.0   \n",
       "2               0.0                  0.0              1.0            0.0   \n",
       "3               0.0                  1.0              0.0            0.0   \n",
       "4               1.0                  0.0              0.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "0               0.0          1.0                 0.0                  0.0   \n",
       "1               0.0          0.0                 0.0                  0.0   \n",
       "2               0.0          0.0                 0.0                  0.0   \n",
       "3               0.0          1.0                 0.0                  0.0   \n",
       "4               0.0          1.0                 0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 0.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \n",
       "0                   0.0                    0.0                 1.0  \n",
       "1                   0.0                    0.0                 1.0  \n",
       "2                   0.0                    0.0                 1.0  \n",
       "3                   0.0                    0.0                 1.0  \n",
       "4                   0.0                    0.0                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1170 entries, 0 to 1169\n",
      "Data columns (total 49 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    1170 non-null   int64  \n",
      " 1   latitude                                 1170 non-null   float64\n",
      " 2   longitude                                1170 non-null   float64\n",
      " 3   sq_meters_built                          1170 non-null   int64  \n",
      " 4   rooms                                    1170 non-null   int64  \n",
      " 5   bathrooms                                1170 non-null   int64  \n",
      " 6   dist_city_center                         1170 non-null   float64\n",
      " 7   dist_closest_station                     1170 non-null   float64\n",
      " 8   rooms_per_100_sqm                        1170 non-null   float64\n",
      " 9   bathrooms_per_100_sqm                    1170 non-null   float64\n",
      " 10  floor_cat_encoded                        1170 non-null   float64\n",
      " 11  property_age_cat_encoded                 1170 non-null   float64\n",
      " 12  neighborhood_rent_index_cluster_encoded  1170 non-null   float64\n",
      " 13  balcony_0                                1170 non-null   float64\n",
      " 14  balcony_1                                1170 non-null   float64\n",
      " 15  terrace_0                                1170 non-null   float64\n",
      " 16  terrace_1                                1170 non-null   float64\n",
      " 17  exterior_0                               1170 non-null   float64\n",
      " 18  exterior_1                               1170 non-null   float64\n",
      " 19  rooftop_0                                1170 non-null   float64\n",
      " 20  rooftop_1                                1170 non-null   float64\n",
      " 21  elevator_0                               1170 non-null   float64\n",
      " 22  elevator_1                               1170 non-null   float64\n",
      " 23  pool_0                                   1170 non-null   float64\n",
      " 24  pool_1                                   1170 non-null   float64\n",
      " 25  ac_0                                     1170 non-null   float64\n",
      " 26  ac_1                                     1170 non-null   float64\n",
      " 27  garage_0                                 1170 non-null   float64\n",
      " 28  garage_1                                 1170 non-null   float64\n",
      " 29  garden_0                                 1170 non-null   float64\n",
      " 30  garden_1                                 1170 non-null   float64\n",
      " 31  orientation_ este                        1170 non-null   float64\n",
      " 32  orientation_ norte                       1170 non-null   float64\n",
      " 33  orientation_ oeste                       1170 non-null   float64\n",
      " 34  orientation_ sur                         1170 non-null   float64\n",
      " 35  orientation_Unknown                      1170 non-null   float64\n",
      " 36  heating_Unknown                          1170 non-null   float64\n",
      " 37  heating_bomba                            1170 non-null   float64\n",
      " 38  heating_electric                         1170 non-null   float64\n",
      " 39  heating_gas                              1170 non-null   float64\n",
      " 40  heating_individual                       1170 non-null   float64\n",
      " 41  property_type_atico                      1170 non-null   float64\n",
      " 42  property_type_chalet                     1170 non-null   float64\n",
      " 43  property_type_chalet_adosado             1170 non-null   float64\n",
      " 44  property_type_chalet_independiente       1170 non-null   float64\n",
      " 45  property_type_chalet_pareado             1170 non-null   float64\n",
      " 46  property_type_duplex                     1170 non-null   float64\n",
      " 47  property_type_estudio                    1170 non-null   float64\n",
      " 48  property_type_piso                       1170 non-null   float64\n",
      "dtypes: float64(45), int64(4)\n",
      "memory usage: 448.0 KB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "latitude                                   0\n",
      "longitude                                  0\n",
      "sq_meters_built                            0\n",
      "rooms                                      0\n",
      "bathrooms                                  0\n",
      "dist_city_center                           0\n",
      "dist_closest_station                       0\n",
      "rooms_per_100_sqm                          0\n",
      "bathrooms_per_100_sqm                      0\n",
      "floor_cat_encoded                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "balcony_0                                  0\n",
      "balcony_1                                  0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "exterior_0                                 0\n",
      "exterior_1                                 0\n",
      "rooftop_0                                  0\n",
      "rooftop_1                                  0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "orientation_ este                          0\n",
      "orientation_ norte                         0\n",
      "orientation_ oeste                         0\n",
      "orientation_ sur                           0\n",
      "orientation_Unknown                        0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1.170000e+03</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.050583e+05</td>\n",
       "      <td>41.406164</td>\n",
       "      <td>2.167129</td>\n",
       "      <td>89.911966</td>\n",
       "      <td>2.647863</td>\n",
       "      <td>1.453846</td>\n",
       "      <td>3.494901</td>\n",
       "      <td>0.367251</td>\n",
       "      <td>3.403759</td>\n",
       "      <td>1.847461</td>\n",
       "      <td>0.452137</td>\n",
       "      <td>1.335897</td>\n",
       "      <td>2.361538</td>\n",
       "      <td>0.614530</td>\n",
       "      <td>0.385470</td>\n",
       "      <td>0.737607</td>\n",
       "      <td>0.262393</td>\n",
       "      <td>0.264103</td>\n",
       "      <td>0.735897</td>\n",
       "      <td>0.929060</td>\n",
       "      <td>0.070940</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.960684</td>\n",
       "      <td>0.039316</td>\n",
       "      <td>0.537607</td>\n",
       "      <td>0.462393</td>\n",
       "      <td>0.929060</td>\n",
       "      <td>0.070940</td>\n",
       "      <td>0.990598</td>\n",
       "      <td>0.009402</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.136752</td>\n",
       "      <td>0.050427</td>\n",
       "      <td>0.234188</td>\n",
       "      <td>0.478632</td>\n",
       "      <td>0.610256</td>\n",
       "      <td>0.052137</td>\n",
       "      <td>0.048718</td>\n",
       "      <td>0.210256</td>\n",
       "      <td>0.078632</td>\n",
       "      <td>0.053846</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.007692</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.011966</td>\n",
       "      <td>0.037607</td>\n",
       "      <td>0.876068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.442154e+05</td>\n",
       "      <td>0.025809</td>\n",
       "      <td>0.023118</td>\n",
       "      <td>67.150712</td>\n",
       "      <td>1.130085</td>\n",
       "      <td>0.844652</td>\n",
       "      <td>1.980491</td>\n",
       "      <td>0.295759</td>\n",
       "      <td>2.202354</td>\n",
       "      <td>1.893766</td>\n",
       "      <td>1.109805</td>\n",
       "      <td>1.722640</td>\n",
       "      <td>1.077839</td>\n",
       "      <td>0.486914</td>\n",
       "      <td>0.486914</td>\n",
       "      <td>0.440123</td>\n",
       "      <td>0.440123</td>\n",
       "      <td>0.441043</td>\n",
       "      <td>0.441043</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.490107</td>\n",
       "      <td>0.490107</td>\n",
       "      <td>0.194429</td>\n",
       "      <td>0.194429</td>\n",
       "      <td>0.498797</td>\n",
       "      <td>0.498797</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.096547</td>\n",
       "      <td>0.096547</td>\n",
       "      <td>0.300128</td>\n",
       "      <td>0.343732</td>\n",
       "      <td>0.218919</td>\n",
       "      <td>0.423671</td>\n",
       "      <td>0.499757</td>\n",
       "      <td>0.487901</td>\n",
       "      <td>0.222398</td>\n",
       "      <td>0.215370</td>\n",
       "      <td>0.407665</td>\n",
       "      <td>0.269279</td>\n",
       "      <td>0.225810</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.087405</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.108778</td>\n",
       "      <td>0.190325</td>\n",
       "      <td>0.329644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.900000e+04</td>\n",
       "      <td>41.355143</td>\n",
       "      <td>2.099004</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.074264</td>\n",
       "      <td>0.014215</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.558659</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.396000e+05</td>\n",
       "      <td>41.383035</td>\n",
       "      <td>2.152141</td>\n",
       "      <td>57.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.782861</td>\n",
       "      <td>0.217491</td>\n",
       "      <td>2.439024</td>\n",
       "      <td>1.388889</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.025000e+05</td>\n",
       "      <td>41.403535</td>\n",
       "      <td>2.169455</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.415416</td>\n",
       "      <td>0.315010</td>\n",
       "      <td>3.380309</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.147500e+05</td>\n",
       "      <td>41.424744</td>\n",
       "      <td>2.180327</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.787665</td>\n",
       "      <td>0.429002</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.500000e+06</td>\n",
       "      <td>41.464340</td>\n",
       "      <td>2.220334</td>\n",
       "      <td>807.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>8.522102</td>\n",
       "      <td>3.549846</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price     latitude    longitude  sq_meters_built        rooms  \\\n",
       "count  1.170000e+03  1170.000000  1170.000000      1170.000000  1170.000000   \n",
       "mean   4.050583e+05    41.406164     2.167129        89.911966     2.647863   \n",
       "std    6.442154e+05     0.025809     0.023118        67.150712     1.130085   \n",
       "min    2.900000e+04    41.355143     2.099004        10.000000     0.000000   \n",
       "25%    1.396000e+05    41.383035     2.152141        57.000000     2.000000   \n",
       "50%    2.025000e+05    41.403535     2.169455        70.000000     3.000000   \n",
       "75%    4.147500e+05    41.424744     2.180327       100.000000     3.000000   \n",
       "max    9.500000e+06    41.464340     2.220334       807.000000     8.000000   \n",
       "\n",
       "         bathrooms  dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "count  1170.000000       1170.000000           1170.000000        1170.000000   \n",
       "mean      1.453846          3.494901              0.367251           3.403759   \n",
       "std       0.844652          1.980491              0.295759           2.202354   \n",
       "min       1.000000          0.074264              0.014215           0.000000   \n",
       "25%       1.000000          1.782861              0.217491           2.439024   \n",
       "50%       1.000000          3.415416              0.315010           3.380309   \n",
       "75%       2.000000          4.787665              0.429002           4.347826   \n",
       "max       7.000000          8.522102              3.549846          50.000000   \n",
       "\n",
       "       bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "count            1170.000000        1170.000000               1170.000000   \n",
       "mean                1.847461           0.452137                  1.335897   \n",
       "std                 1.893766           1.109805                  1.722640   \n",
       "min                 0.558659          -1.000000                 -1.000000   \n",
       "25%                 1.388889          -1.000000                 -1.000000   \n",
       "50%                 1.666667           1.000000                  2.000000   \n",
       "75%                 2.000000           1.000000                  2.000000   \n",
       "max                50.000000           3.000000                  5.000000   \n",
       "\n",
       "       neighborhood_rent_index_cluster_encoded    balcony_0    balcony_1  \\\n",
       "count                              1170.000000  1170.000000  1170.000000   \n",
       "mean                                  2.361538     0.614530     0.385470   \n",
       "std                                   1.077839     0.486914     0.486914   \n",
       "min                                   1.000000     0.000000     0.000000   \n",
       "25%                                   1.000000     0.000000     0.000000   \n",
       "50%                                   2.000000     1.000000     0.000000   \n",
       "75%                                   3.000000     1.000000     1.000000   \n",
       "max                                   4.000000     1.000000     1.000000   \n",
       "\n",
       "         terrace_0    terrace_1   exterior_0   exterior_1    rooftop_0  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.737607     0.262393     0.264103     0.735897     0.929060   \n",
       "std       0.440123     0.440123     0.441043     0.441043     0.256835   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     0.000000     1.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "         rooftop_1   elevator_0   elevator_1       pool_0       pool_1  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.070940     0.400000     0.600000     0.960684     0.039316   \n",
       "std       0.256835     0.490107     0.490107     0.194429     0.194429   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     1.000000     0.000000   \n",
       "50%       0.000000     0.000000     1.000000     1.000000     0.000000   \n",
       "75%       0.000000     1.000000     1.000000     1.000000     0.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "              ac_0         ac_1     garage_0     garage_1     garden_0  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.537607     0.462393     0.929060     0.070940     0.990598   \n",
       "std       0.498797     0.498797     0.256835     0.256835     0.096547   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "          garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "count  1170.000000        1170.000000         1170.000000         1170.000000   \n",
       "mean      0.009402           0.100000            0.136752            0.050427   \n",
       "std       0.096547           0.300128            0.343732            0.218919   \n",
       "min       0.000000           0.000000            0.000000            0.000000   \n",
       "25%       0.000000           0.000000            0.000000            0.000000   \n",
       "50%       0.000000           0.000000            0.000000            0.000000   \n",
       "75%       0.000000           0.000000            0.000000            0.000000   \n",
       "max       1.000000           1.000000            1.000000            1.000000   \n",
       "\n",
       "       orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "count       1170.000000          1170.000000      1170.000000    1170.000000   \n",
       "mean           0.234188             0.478632         0.610256       0.052137   \n",
       "std            0.423671             0.499757         0.487901       0.222398   \n",
       "min            0.000000             0.000000         0.000000       0.000000   \n",
       "25%            0.000000             0.000000         0.000000       0.000000   \n",
       "50%            0.000000             0.000000         1.000000       0.000000   \n",
       "75%            0.000000             1.000000         1.000000       0.000000   \n",
       "max            1.000000             1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "count       1170.000000  1170.000000         1170.000000          1170.000000   \n",
       "mean           0.048718     0.210256            0.078632             0.053846   \n",
       "std            0.215370     0.407665            0.269279             0.225810   \n",
       "min            0.000000     0.000000            0.000000             0.000000   \n",
       "25%            0.000000     0.000000            0.000000             0.000000   \n",
       "50%            0.000000     0.000000            0.000000             0.000000   \n",
       "75%            0.000000     0.000000            0.000000             0.000000   \n",
       "max            1.000000     1.000000            1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           1170.000000                   1170.000000   \n",
       "mean               0.004274                      0.004274   \n",
       "std                0.065260                      0.065260   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         1170.000000                   1170.000000   \n",
       "mean                             0.007692                      0.004274   \n",
       "std                              0.087405                      0.065260   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \n",
       "count           1170.000000            1170.000000         1170.000000  \n",
       "mean               0.011966               0.037607            0.876068  \n",
       "std                0.108778               0.190325            0.329644  \n",
       "min                0.000000               0.000000            0.000000  \n",
       "25%                0.000000               0.000000            1.000000  \n",
       "50%                0.000000               0.000000            1.000000  \n",
       "75%                0.000000               0.000000            1.000000  \n",
       "max                1.000000               1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 0\n"
     ]
    }
   ],
   "source": [
    "# exploración rápida del df\n",
    "print(\"TRAIN: \")\n",
    "explore_data(bagging_df1)\n",
    "print(\"\\n\\n\")\n",
    "print(\"TEST: \")\n",
    "explore_data(bagging_df1_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b3429bb",
   "metadata": {},
   "source": [
    "- No tenemos valores nulos y todas las variables son numéricas. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "767f293d",
   "metadata": {},
   "source": [
    "##### Model 1: Bagging & RF "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 624,
   "id": "b84497ef",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 100}\n",
      "Best cross-validation R^2 score: 0.8413\n",
      "Train R^2 score: 0.9767\n",
      "Test R^2 score: 0.7393\n",
      "\n",
      "Model: RandomForestRegressor\n",
      "Best model parameters: {'model__max_depth': 9, 'model__min_samples_split': 10, 'model__n_estimators': 20}\n",
      "Best cross-validation R^2 score: 0.8376\n",
      "Train R^2 score: 0.9392\n",
      "Test R^2 score: 0.7231\n",
      "\n",
      "Best model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 100}\n",
      "Best cross-validation R^2 score: 0.8413\n",
      "Train R^2 score: 0.9767\n",
      "Test R^2 score: 0.7393\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'name': 'BaggingRegressor',\n",
       "  'best_params': {'model__n_estimators': 100},\n",
       "  'best_score': 0.8413459550193905,\n",
       "  'train_r2_score': 0.9766845778640442,\n",
       "  'test_r2_score': 0.739290218306422},\n",
       " {'name': 'RandomForestRegressor',\n",
       "  'best_params': {'model__max_depth': 9,\n",
       "   'model__min_samples_split': 10,\n",
       "   'model__n_estimators': 20},\n",
       "  'best_score': 0.8376489876860275,\n",
       "  'train_r2_score': 0.9392475407127426,\n",
       "  'test_r2_score': 0.7231028416313489}]"
      ]
     },
     "execution_count": 624,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create an instance of PipelineRunner\n",
    "pipeline_runner = PipelineRunner()\n",
    "# call the run_pipeline() method, passing in the dataframes and target variable name\n",
    "results = pipeline_runner.run_pipeline(df_train=bagging_df1, \n",
    "                                       df_test=bagging_df1_test, \n",
    "                                       target=TARGET_VARIABLE)\n",
    "# examine the results for each model\n",
    "results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 655,
   "id": "4011c224",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regressor</th>\n",
       "      <th>train_r2_score</th>\n",
       "      <th>test_r2_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BaggingRegressor_1</td>\n",
       "      <td>0.976685</td>\n",
       "      <td>0.739290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>RandomForestRegressor_1</td>\n",
       "      <td>0.939248</td>\n",
       "      <td>0.723103</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 regressor  train_r2_score  test_r2_score\n",
       "0       BaggingRegressor_1        0.976685       0.739290\n",
       "1  RandomForestRegressor_1        0.939248       0.723103"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Loop through each model in results\n",
    "for model in results:\n",
    "    model_name = model['name']+'_1'\n",
    "    train_r2_score = model['train_r2_score']\n",
    "    test_r2_score = model['test_r2_score']\n",
    "    \n",
    "    # Append the results to the DataFrame\n",
    "    models_results_df = pd.concat([models_results_df, pd.DataFrame({'regressor': model_name, \n",
    "                                                                   'train_r2_score': train_r2_score,\n",
    "                                                                   'test_r2_score': test_r2_score},\n",
    "                                                                   index=[0])], ignore_index=True)\n",
    "# Display the DataFrame\n",
    "display(models_results_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43ba4b34",
   "metadata": {},
   "source": [
    "#### Modelo 2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e4db5a2",
   "metadata": {},
   "source": [
    "En los modelos anteriores (BaggingRegressor y RandomForestRegressor) nos se han escalado las variables, no se han quitado los outliers y no se ha hecho una selección de variables.\n",
    "\n",
    "Por tanto, ahora escalaremos las variables numéricas y trataremos los outliers. La selección de variables predictoras más importantes la realizaremos en el tercer modelo. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7901de38",
   "metadata": {},
   "source": [
    "#####  Train dataset (bagging_df2) y Test dataset (bagging_df2_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6157ae86",
   "metadata": {},
   "source": [
    "Primero, realizamos el mismo preprocesamiento que en el primer modelo: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 626,
   "id": "b1149487",
   "metadata": {
    "jupyter": {
     "outputs_hidden": true
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAIN: \n",
      "The dataset includes 4675 instances (rows) and 49 variables (columns).\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2290000</td>\n",
       "      <td>41.409071</td>\n",
       "      <td>2.099850</td>\n",
       "      <td>532</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>6.302847</td>\n",
       "      <td>2.949904</td>\n",
       "      <td>0.939850</td>\n",
       "      <td>1.127820</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>90000</td>\n",
       "      <td>41.434545</td>\n",
       "      <td>2.171110</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>5.189265</td>\n",
       "      <td>0.329115</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>145000</td>\n",
       "      <td>41.444518</td>\n",
       "      <td>2.175309</td>\n",
       "      <td>53</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>6.313668</td>\n",
       "      <td>0.284071</td>\n",
       "      <td>5.660377</td>\n",
       "      <td>1.886792</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>675000</td>\n",
       "      <td>41.392209</td>\n",
       "      <td>2.153368</td>\n",
       "      <td>120</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1.462060</td>\n",
       "      <td>0.443717</td>\n",
       "      <td>3.333333</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>319000</td>\n",
       "      <td>41.413385</td>\n",
       "      <td>2.162246</td>\n",
       "      <td>69</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.906147</td>\n",
       "      <td>0.371854</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>1.449275</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0  2290000  41.409071   2.099850              532      5          6   \n",
       "1    90000  41.434545   2.171110               50      1          1   \n",
       "2   145000  41.444518   2.175309               53      3          1   \n",
       "3   675000  41.392209   2.153368              120      4          2   \n",
       "4   319000  41.413385   2.162246               69      3          1   \n",
       "\n",
       "   dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "0          6.302847              2.949904           0.939850   \n",
       "1          5.189265              0.329115           2.000000   \n",
       "2          6.313668              0.284071           5.660377   \n",
       "3          1.462060              0.443717           3.333333   \n",
       "4          2.906147              0.371854           4.347826   \n",
       "\n",
       "   bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "0               1.127820                1.0                       1.0   \n",
       "1               2.000000               -1.0                       2.0   \n",
       "2               1.886792                1.0                      -1.0   \n",
       "3               1.666667               -1.0                       2.0   \n",
       "4               1.449275                2.0                       3.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  balcony_0  balcony_1  terrace_0  \\\n",
       "0                                      3.0        0.0        1.0        0.0   \n",
       "1                                      1.0        1.0        0.0        1.0   \n",
       "2                                      1.0        0.0        1.0        1.0   \n",
       "3                                      3.0        1.0        0.0        0.0   \n",
       "4                                      3.0        1.0        0.0        1.0   \n",
       "\n",
       "   terrace_1  exterior_0  exterior_1  rooftop_0  rooftop_1  elevator_0  \\\n",
       "0        1.0         1.0         0.0        1.0        0.0         1.0   \n",
       "1        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "2        0.0         0.0         1.0        1.0        0.0         1.0   \n",
       "3        1.0         1.0         0.0        0.0        1.0         0.0   \n",
       "4        0.0         0.0         1.0        0.0        1.0         0.0   \n",
       "\n",
       "   elevator_1  pool_0  pool_1  ac_0  ac_1  garage_0  garage_1  garden_0  \\\n",
       "0         0.0     0.0     1.0   0.0   1.0       0.0       1.0       0.0   \n",
       "1         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "2         0.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "3         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "4         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "0       1.0                0.0                 0.0                 0.0   \n",
       "1       0.0                0.0                 1.0                 0.0   \n",
       "2       0.0                0.0                 0.0                 0.0   \n",
       "3       0.0                0.0                 1.0                 0.0   \n",
       "4       0.0                0.0                 0.0                 0.0   \n",
       "\n",
       "   orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "0               1.0                  0.0              0.0            0.0   \n",
       "1               0.0                  0.0              0.0            1.0   \n",
       "2               0.0                  1.0              1.0            0.0   \n",
       "3               0.0                  0.0              0.0            0.0   \n",
       "4               0.0                  1.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "0               0.0          0.0                 1.0                  0.0   \n",
       "1               0.0          0.0                 0.0                  0.0   \n",
       "2               0.0          0.0                 0.0                  0.0   \n",
       "3               0.0          0.0                 1.0                  1.0   \n",
       "4               0.0          0.0                 0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 1.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \n",
       "0                   0.0                    0.0                 0.0  \n",
       "1                   0.0                    0.0                 1.0  \n",
       "2                   0.0                    0.0                 1.0  \n",
       "3                   0.0                    0.0                 0.0  \n",
       "4                   0.0                    0.0                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 4675 entries, 0 to 4674\n",
      "Data columns (total 49 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    4675 non-null   int64  \n",
      " 1   latitude                                 4675 non-null   float64\n",
      " 2   longitude                                4675 non-null   float64\n",
      " 3   sq_meters_built                          4675 non-null   int64  \n",
      " 4   rooms                                    4675 non-null   int64  \n",
      " 5   bathrooms                                4675 non-null   int64  \n",
      " 6   dist_city_center                         4675 non-null   float64\n",
      " 7   dist_closest_station                     4675 non-null   float64\n",
      " 8   rooms_per_100_sqm                        4675 non-null   float64\n",
      " 9   bathrooms_per_100_sqm                    4675 non-null   float64\n",
      " 10  floor_cat_encoded                        4675 non-null   float64\n",
      " 11  property_age_cat_encoded                 4675 non-null   float64\n",
      " 12  neighborhood_rent_index_cluster_encoded  4675 non-null   float64\n",
      " 13  balcony_0                                4675 non-null   float64\n",
      " 14  balcony_1                                4675 non-null   float64\n",
      " 15  terrace_0                                4675 non-null   float64\n",
      " 16  terrace_1                                4675 non-null   float64\n",
      " 17  exterior_0                               4675 non-null   float64\n",
      " 18  exterior_1                               4675 non-null   float64\n",
      " 19  rooftop_0                                4675 non-null   float64\n",
      " 20  rooftop_1                                4675 non-null   float64\n",
      " 21  elevator_0                               4675 non-null   float64\n",
      " 22  elevator_1                               4675 non-null   float64\n",
      " 23  pool_0                                   4675 non-null   float64\n",
      " 24  pool_1                                   4675 non-null   float64\n",
      " 25  ac_0                                     4675 non-null   float64\n",
      " 26  ac_1                                     4675 non-null   float64\n",
      " 27  garage_0                                 4675 non-null   float64\n",
      " 28  garage_1                                 4675 non-null   float64\n",
      " 29  garden_0                                 4675 non-null   float64\n",
      " 30  garden_1                                 4675 non-null   float64\n",
      " 31  orientation_ este                        4675 non-null   float64\n",
      " 32  orientation_ norte                       4675 non-null   float64\n",
      " 33  orientation_ oeste                       4675 non-null   float64\n",
      " 34  orientation_ sur                         4675 non-null   float64\n",
      " 35  orientation_Unknown                      4675 non-null   float64\n",
      " 36  heating_Unknown                          4675 non-null   float64\n",
      " 37  heating_bomba                            4675 non-null   float64\n",
      " 38  heating_electric                         4675 non-null   float64\n",
      " 39  heating_gas                              4675 non-null   float64\n",
      " 40  heating_individual                       4675 non-null   float64\n",
      " 41  property_type_atico                      4675 non-null   float64\n",
      " 42  property_type_chalet                     4675 non-null   float64\n",
      " 43  property_type_chalet_adosado             4675 non-null   float64\n",
      " 44  property_type_chalet_independiente       4675 non-null   float64\n",
      " 45  property_type_chalet_pareado             4675 non-null   float64\n",
      " 46  property_type_duplex                     4675 non-null   float64\n",
      " 47  property_type_estudio                    4675 non-null   float64\n",
      " 48  property_type_piso                       4675 non-null   float64\n",
      "dtypes: float64(45), int64(4)\n",
      "memory usage: 1.7 MB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "latitude                                   0\n",
      "longitude                                  0\n",
      "sq_meters_built                            0\n",
      "rooms                                      0\n",
      "bathrooms                                  0\n",
      "dist_city_center                           0\n",
      "dist_closest_station                       0\n",
      "rooms_per_100_sqm                          0\n",
      "bathrooms_per_100_sqm                      0\n",
      "floor_cat_encoded                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "balcony_0                                  0\n",
      "balcony_1                                  0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "exterior_0                                 0\n",
      "exterior_1                                 0\n",
      "rooftop_0                                  0\n",
      "rooftop_1                                  0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "orientation_ este                          0\n",
      "orientation_ norte                         0\n",
      "orientation_ oeste                         0\n",
      "orientation_ sur                           0\n",
      "orientation_Unknown                        0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4.675000e+03</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "      <td>4675.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.567950e+05</td>\n",
       "      <td>41.406603</td>\n",
       "      <td>2.168282</td>\n",
       "      <td>85.819465</td>\n",
       "      <td>2.580749</td>\n",
       "      <td>1.410481</td>\n",
       "      <td>3.501909</td>\n",
       "      <td>0.359388</td>\n",
       "      <td>3.379902</td>\n",
       "      <td>1.844308</td>\n",
       "      <td>0.421390</td>\n",
       "      <td>1.333904</td>\n",
       "      <td>2.238717</td>\n",
       "      <td>0.623957</td>\n",
       "      <td>0.376043</td>\n",
       "      <td>0.760428</td>\n",
       "      <td>0.239572</td>\n",
       "      <td>0.293262</td>\n",
       "      <td>0.706738</td>\n",
       "      <td>0.930695</td>\n",
       "      <td>0.069305</td>\n",
       "      <td>0.436791</td>\n",
       "      <td>0.563209</td>\n",
       "      <td>0.973690</td>\n",
       "      <td>0.026310</td>\n",
       "      <td>0.549091</td>\n",
       "      <td>0.450909</td>\n",
       "      <td>0.931551</td>\n",
       "      <td>0.068449</td>\n",
       "      <td>0.989733</td>\n",
       "      <td>0.010267</td>\n",
       "      <td>0.118289</td>\n",
       "      <td>0.125775</td>\n",
       "      <td>0.050053</td>\n",
       "      <td>0.245775</td>\n",
       "      <td>0.460107</td>\n",
       "      <td>0.589733</td>\n",
       "      <td>0.056898</td>\n",
       "      <td>0.042567</td>\n",
       "      <td>0.235936</td>\n",
       "      <td>0.074866</td>\n",
       "      <td>0.050267</td>\n",
       "      <td>0.007701</td>\n",
       "      <td>0.005989</td>\n",
       "      <td>0.005561</td>\n",
       "      <td>0.002567</td>\n",
       "      <td>0.016043</td>\n",
       "      <td>0.037861</td>\n",
       "      <td>0.874011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>4.910966e+05</td>\n",
       "      <td>0.026137</td>\n",
       "      <td>0.022753</td>\n",
       "      <td>66.934320</td>\n",
       "      <td>1.160086</td>\n",
       "      <td>0.793276</td>\n",
       "      <td>2.034103</td>\n",
       "      <td>0.280663</td>\n",
       "      <td>1.693352</td>\n",
       "      <td>1.088397</td>\n",
       "      <td>1.117207</td>\n",
       "      <td>1.731172</td>\n",
       "      <td>1.062609</td>\n",
       "      <td>0.484443</td>\n",
       "      <td>0.484443</td>\n",
       "      <td>0.426868</td>\n",
       "      <td>0.426868</td>\n",
       "      <td>0.455306</td>\n",
       "      <td>0.455306</td>\n",
       "      <td>0.253999</td>\n",
       "      <td>0.253999</td>\n",
       "      <td>0.496042</td>\n",
       "      <td>0.496042</td>\n",
       "      <td>0.160073</td>\n",
       "      <td>0.160073</td>\n",
       "      <td>0.497637</td>\n",
       "      <td>0.497637</td>\n",
       "      <td>0.252542</td>\n",
       "      <td>0.252542</td>\n",
       "      <td>0.100817</td>\n",
       "      <td>0.100817</td>\n",
       "      <td>0.322984</td>\n",
       "      <td>0.331632</td>\n",
       "      <td>0.218079</td>\n",
       "      <td>0.430592</td>\n",
       "      <td>0.498459</td>\n",
       "      <td>0.491935</td>\n",
       "      <td>0.231673</td>\n",
       "      <td>0.201900</td>\n",
       "      <td>0.424628</td>\n",
       "      <td>0.263204</td>\n",
       "      <td>0.218520</td>\n",
       "      <td>0.087424</td>\n",
       "      <td>0.077167</td>\n",
       "      <td>0.074376</td>\n",
       "      <td>0.050604</td>\n",
       "      <td>0.125653</td>\n",
       "      <td>0.190880</td>\n",
       "      <td>0.331873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.800000e+04</td>\n",
       "      <td>41.355002</td>\n",
       "      <td>2.092727</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.075001</td>\n",
       "      <td>0.003595</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.227273</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.350000e+05</td>\n",
       "      <td>41.382507</td>\n",
       "      <td>2.153545</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.748592</td>\n",
       "      <td>0.212796</td>\n",
       "      <td>2.439024</td>\n",
       "      <td>1.428571</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.870000e+05</td>\n",
       "      <td>41.404373</td>\n",
       "      <td>2.170370</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.361583</td>\n",
       "      <td>0.311358</td>\n",
       "      <td>3.448276</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.900000e+05</td>\n",
       "      <td>41.424739</td>\n",
       "      <td>2.180816</td>\n",
       "      <td>92.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.914956</td>\n",
       "      <td>0.420666</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>2.083333</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.500000e+06</td>\n",
       "      <td>41.465303</td>\n",
       "      <td>2.220785</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>8.627149</td>\n",
       "      <td>4.203571</td>\n",
       "      <td>55.555556</td>\n",
       "      <td>52.941176</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price     latitude    longitude  sq_meters_built        rooms  \\\n",
       "count  4.675000e+03  4675.000000  4675.000000      4675.000000  4675.000000   \n",
       "mean   3.567950e+05    41.406603     2.168282        85.819465     2.580749   \n",
       "std    4.910966e+05     0.026137     0.022753        66.934320     1.160086   \n",
       "min    2.800000e+04    41.355002     2.092727        13.000000     0.000000   \n",
       "25%    1.350000e+05    41.382507     2.153545        55.000000     2.000000   \n",
       "50%    1.870000e+05    41.404373     2.170370        68.000000     3.000000   \n",
       "75%    3.900000e+05    41.424739     2.180816        92.000000     3.000000   \n",
       "max    9.500000e+06    41.465303     2.220785       970.000000    11.000000   \n",
       "\n",
       "         bathrooms  dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "count  4675.000000       4675.000000           4675.000000        4675.000000   \n",
       "mean      1.410481          3.501909              0.359388           3.379902   \n",
       "std       0.793276          2.034103              0.280663           1.693352   \n",
       "min       1.000000          0.075001              0.003595           0.000000   \n",
       "25%       1.000000          1.748592              0.212796           2.439024   \n",
       "50%       1.000000          3.361583              0.311358           3.448276   \n",
       "75%       2.000000          4.914956              0.420666           4.347826   \n",
       "max       9.000000          8.627149              4.203571          55.555556   \n",
       "\n",
       "       bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "count            4675.000000        4675.000000               4675.000000   \n",
       "mean                1.844308           0.421390                  1.333904   \n",
       "std                 1.088397           1.117207                  1.731172   \n",
       "min                 0.227273          -1.000000                 -1.000000   \n",
       "25%                 1.428571          -1.000000                 -1.000000   \n",
       "50%                 1.666667           1.000000                  2.000000   \n",
       "75%                 2.083333           1.000000                  2.000000   \n",
       "max                52.941176           3.000000                  5.000000   \n",
       "\n",
       "       neighborhood_rent_index_cluster_encoded    balcony_0    balcony_1  \\\n",
       "count                              4675.000000  4675.000000  4675.000000   \n",
       "mean                                  2.238717     0.623957     0.376043   \n",
       "std                                   1.062609     0.484443     0.484443   \n",
       "min                                   1.000000     0.000000     0.000000   \n",
       "25%                                   1.000000     0.000000     0.000000   \n",
       "50%                                   2.000000     1.000000     0.000000   \n",
       "75%                                   3.000000     1.000000     1.000000   \n",
       "max                                   4.000000     1.000000     1.000000   \n",
       "\n",
       "         terrace_0    terrace_1   exterior_0   exterior_1    rooftop_0  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.760428     0.239572     0.293262     0.706738     0.930695   \n",
       "std       0.426868     0.426868     0.455306     0.455306     0.253999   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       1.000000     0.000000     0.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     0.000000     1.000000     1.000000   \n",
       "75%       1.000000     0.000000     1.000000     1.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "         rooftop_1   elevator_0   elevator_1       pool_0       pool_1  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.069305     0.436791     0.563209     0.973690     0.026310   \n",
       "std       0.253999     0.496042     0.496042     0.160073     0.160073   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     1.000000     0.000000   \n",
       "50%       0.000000     0.000000     1.000000     1.000000     0.000000   \n",
       "75%       0.000000     1.000000     1.000000     1.000000     0.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "              ac_0         ac_1     garage_0     garage_1     garden_0  \\\n",
       "count  4675.000000  4675.000000  4675.000000  4675.000000  4675.000000   \n",
       "mean      0.549091     0.450909     0.931551     0.068449     0.989733   \n",
       "std       0.497637     0.497637     0.252542     0.252542     0.100817   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "          garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "count  4675.000000        4675.000000         4675.000000         4675.000000   \n",
       "mean      0.010267           0.118289            0.125775            0.050053   \n",
       "std       0.100817           0.322984            0.331632            0.218079   \n",
       "min       0.000000           0.000000            0.000000            0.000000   \n",
       "25%       0.000000           0.000000            0.000000            0.000000   \n",
       "50%       0.000000           0.000000            0.000000            0.000000   \n",
       "75%       0.000000           0.000000            0.000000            0.000000   \n",
       "max       1.000000           1.000000            1.000000            1.000000   \n",
       "\n",
       "       orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "count       4675.000000          4675.000000      4675.000000    4675.000000   \n",
       "mean           0.245775             0.460107         0.589733       0.056898   \n",
       "std            0.430592             0.498459         0.491935       0.231673   \n",
       "min            0.000000             0.000000         0.000000       0.000000   \n",
       "25%            0.000000             0.000000         0.000000       0.000000   \n",
       "50%            0.000000             0.000000         1.000000       0.000000   \n",
       "75%            0.000000             1.000000         1.000000       0.000000   \n",
       "max            1.000000             1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "count       4675.000000  4675.000000         4675.000000          4675.000000   \n",
       "mean           0.042567     0.235936            0.074866             0.050267   \n",
       "std            0.201900     0.424628            0.263204             0.218520   \n",
       "min            0.000000     0.000000            0.000000             0.000000   \n",
       "25%            0.000000     0.000000            0.000000             0.000000   \n",
       "50%            0.000000     0.000000            0.000000             0.000000   \n",
       "75%            0.000000     0.000000            0.000000             0.000000   \n",
       "max            1.000000     1.000000            1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           4675.000000                   4675.000000   \n",
       "mean               0.007701                      0.005989   \n",
       "std                0.087424                      0.077167   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         4675.000000                   4675.000000   \n",
       "mean                             0.005561                      0.002567   \n",
       "std                              0.074376                      0.050604   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \n",
       "count           4675.000000            4675.000000         4675.000000  \n",
       "mean               0.016043               0.037861            0.874011  \n",
       "std                0.125653               0.190880            0.331873  \n",
       "min                0.000000               0.000000            0.000000  \n",
       "25%                0.000000               0.000000            1.000000  \n",
       "50%                0.000000               0.000000            1.000000  \n",
       "75%                0.000000               0.000000            1.000000  \n",
       "max                1.000000               1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 4\n",
      "\n",
      "\n",
      "\n",
      "TEST: \n",
      "The dataset includes 1170 instances (rows) and 49 variables (columns).\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>133000</td>\n",
       "      <td>41.421077</td>\n",
       "      <td>2.213120</td>\n",
       "      <td>76</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.158288</td>\n",
       "      <td>0.272653</td>\n",
       "      <td>3.947368</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>485000</td>\n",
       "      <td>41.380788</td>\n",
       "      <td>2.152472</td>\n",
       "      <td>130</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>1.657143</td>\n",
       "      <td>0.245719</td>\n",
       "      <td>3.076923</td>\n",
       "      <td>1.538462</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>265000</td>\n",
       "      <td>41.406803</td>\n",
       "      <td>2.183533</td>\n",
       "      <td>77</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.389801</td>\n",
       "      <td>0.084520</td>\n",
       "      <td>3.896104</td>\n",
       "      <td>1.298701</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>154500</td>\n",
       "      <td>41.433890</td>\n",
       "      <td>2.172277</td>\n",
       "      <td>61</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>5.119194</td>\n",
       "      <td>0.355555</td>\n",
       "      <td>3.278689</td>\n",
       "      <td>1.639344</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1200000</td>\n",
       "      <td>41.393411</td>\n",
       "      <td>2.145017</td>\n",
       "      <td>120</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2.166588</td>\n",
       "      <td>0.735841</td>\n",
       "      <td>2.500000</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     price   latitude  longitude  sq_meters_built  rooms  bathrooms  \\\n",
       "0   133000  41.421077   2.213120               76      3          1   \n",
       "1   485000  41.380788   2.152472              130      4          2   \n",
       "2   265000  41.406803   2.183533               77      3          1   \n",
       "3   154500  41.433890   2.172277               61      2          1   \n",
       "4  1200000  41.393411   2.145017              120      3          2   \n",
       "\n",
       "   dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "0          5.158288              0.272653           3.947368   \n",
       "1          1.657143              0.245719           3.076923   \n",
       "2          2.389801              0.084520           3.896104   \n",
       "3          5.119194              0.355555           3.278689   \n",
       "4          2.166588              0.735841           2.500000   \n",
       "\n",
       "   bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "0               1.315789                1.0                       2.0   \n",
       "1               1.538462               -1.0                       3.0   \n",
       "2               1.298701                2.0                       2.0   \n",
       "3               1.639344                1.0                       2.0   \n",
       "4               1.666667                1.0                       3.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  balcony_0  balcony_1  terrace_0  \\\n",
       "0                                      2.0        1.0        0.0        1.0   \n",
       "1                                      3.0        1.0        0.0        1.0   \n",
       "2                                      3.0        1.0        0.0        1.0   \n",
       "3                                      2.0        0.0        1.0        1.0   \n",
       "4                                      4.0        1.0        0.0        1.0   \n",
       "\n",
       "   terrace_1  exterior_0  exterior_1  rooftop_0  rooftop_1  elevator_0  \\\n",
       "0        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "1        0.0         1.0         0.0        1.0        0.0         0.0   \n",
       "2        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "3        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "4        0.0         0.0         1.0        1.0        0.0         0.0   \n",
       "\n",
       "   elevator_1  pool_0  pool_1  ac_0  ac_1  garage_0  garage_1  garden_0  \\\n",
       "0         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "1         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "2         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "3         1.0     1.0     0.0   1.0   0.0       1.0       0.0       1.0   \n",
       "4         1.0     1.0     0.0   0.0   1.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "0       0.0                0.0                 0.0                 0.0   \n",
       "1       0.0                0.0                 0.0                 0.0   \n",
       "2       0.0                0.0                 1.0                 0.0   \n",
       "3       0.0                0.0                 0.0                 0.0   \n",
       "4       0.0                0.0                 0.0                 0.0   \n",
       "\n",
       "   orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "0               0.0                  1.0              0.0            0.0   \n",
       "1               0.0                  1.0              1.0            0.0   \n",
       "2               0.0                  0.0              1.0            0.0   \n",
       "3               0.0                  1.0              0.0            0.0   \n",
       "4               1.0                  0.0              0.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "0               0.0          1.0                 0.0                  0.0   \n",
       "1               0.0          0.0                 0.0                  0.0   \n",
       "2               0.0          0.0                 0.0                  0.0   \n",
       "3               0.0          1.0                 0.0                  0.0   \n",
       "4               0.0          1.0                 0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 0.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \n",
       "0                   0.0                    0.0                 1.0  \n",
       "1                   0.0                    0.0                 1.0  \n",
       "2                   0.0                    0.0                 1.0  \n",
       "3                   0.0                    0.0                 1.0  \n",
       "4                   0.0                    0.0                 1.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1170 entries, 0 to 1169\n",
      "Data columns (total 49 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    1170 non-null   int64  \n",
      " 1   latitude                                 1170 non-null   float64\n",
      " 2   longitude                                1170 non-null   float64\n",
      " 3   sq_meters_built                          1170 non-null   int64  \n",
      " 4   rooms                                    1170 non-null   int64  \n",
      " 5   bathrooms                                1170 non-null   int64  \n",
      " 6   dist_city_center                         1170 non-null   float64\n",
      " 7   dist_closest_station                     1170 non-null   float64\n",
      " 8   rooms_per_100_sqm                        1170 non-null   float64\n",
      " 9   bathrooms_per_100_sqm                    1170 non-null   float64\n",
      " 10  floor_cat_encoded                        1170 non-null   float64\n",
      " 11  property_age_cat_encoded                 1170 non-null   float64\n",
      " 12  neighborhood_rent_index_cluster_encoded  1170 non-null   float64\n",
      " 13  balcony_0                                1170 non-null   float64\n",
      " 14  balcony_1                                1170 non-null   float64\n",
      " 15  terrace_0                                1170 non-null   float64\n",
      " 16  terrace_1                                1170 non-null   float64\n",
      " 17  exterior_0                               1170 non-null   float64\n",
      " 18  exterior_1                               1170 non-null   float64\n",
      " 19  rooftop_0                                1170 non-null   float64\n",
      " 20  rooftop_1                                1170 non-null   float64\n",
      " 21  elevator_0                               1170 non-null   float64\n",
      " 22  elevator_1                               1170 non-null   float64\n",
      " 23  pool_0                                   1170 non-null   float64\n",
      " 24  pool_1                                   1170 non-null   float64\n",
      " 25  ac_0                                     1170 non-null   float64\n",
      " 26  ac_1                                     1170 non-null   float64\n",
      " 27  garage_0                                 1170 non-null   float64\n",
      " 28  garage_1                                 1170 non-null   float64\n",
      " 29  garden_0                                 1170 non-null   float64\n",
      " 30  garden_1                                 1170 non-null   float64\n",
      " 31  orientation_ este                        1170 non-null   float64\n",
      " 32  orientation_ norte                       1170 non-null   float64\n",
      " 33  orientation_ oeste                       1170 non-null   float64\n",
      " 34  orientation_ sur                         1170 non-null   float64\n",
      " 35  orientation_Unknown                      1170 non-null   float64\n",
      " 36  heating_Unknown                          1170 non-null   float64\n",
      " 37  heating_bomba                            1170 non-null   float64\n",
      " 38  heating_electric                         1170 non-null   float64\n",
      " 39  heating_gas                              1170 non-null   float64\n",
      " 40  heating_individual                       1170 non-null   float64\n",
      " 41  property_type_atico                      1170 non-null   float64\n",
      " 42  property_type_chalet                     1170 non-null   float64\n",
      " 43  property_type_chalet_adosado             1170 non-null   float64\n",
      " 44  property_type_chalet_independiente       1170 non-null   float64\n",
      " 45  property_type_chalet_pareado             1170 non-null   float64\n",
      " 46  property_type_duplex                     1170 non-null   float64\n",
      " 47  property_type_estudio                    1170 non-null   float64\n",
      " 48  property_type_piso                       1170 non-null   float64\n",
      "dtypes: float64(45), int64(4)\n",
      "memory usage: 448.0 KB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "latitude                                   0\n",
      "longitude                                  0\n",
      "sq_meters_built                            0\n",
      "rooms                                      0\n",
      "bathrooms                                  0\n",
      "dist_city_center                           0\n",
      "dist_closest_station                       0\n",
      "rooms_per_100_sqm                          0\n",
      "bathrooms_per_100_sqm                      0\n",
      "floor_cat_encoded                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "balcony_0                                  0\n",
      "balcony_1                                  0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "exterior_0                                 0\n",
      "exterior_1                                 0\n",
      "rooftop_0                                  0\n",
      "rooftop_1                                  0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "orientation_ este                          0\n",
      "orientation_ norte                         0\n",
      "orientation_ oeste                         0\n",
      "orientation_ sur                           0\n",
      "orientation_Unknown                        0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>latitude</th>\n",
       "      <th>longitude</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>rooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>dist_closest_station</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>floor_cat_encoded</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>balcony_0</th>\n",
       "      <th>balcony_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>exterior_0</th>\n",
       "      <th>exterior_1</th>\n",
       "      <th>rooftop_0</th>\n",
       "      <th>rooftop_1</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>orientation_ este</th>\n",
       "      <th>orientation_ norte</th>\n",
       "      <th>orientation_ oeste</th>\n",
       "      <th>orientation_ sur</th>\n",
       "      <th>orientation_Unknown</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1.170000e+03</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "      <td>1170.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.050583e+05</td>\n",
       "      <td>41.406164</td>\n",
       "      <td>2.167129</td>\n",
       "      <td>89.911966</td>\n",
       "      <td>2.647863</td>\n",
       "      <td>1.453846</td>\n",
       "      <td>3.494901</td>\n",
       "      <td>0.367251</td>\n",
       "      <td>3.403759</td>\n",
       "      <td>1.847461</td>\n",
       "      <td>0.452137</td>\n",
       "      <td>1.335897</td>\n",
       "      <td>2.361538</td>\n",
       "      <td>0.614530</td>\n",
       "      <td>0.385470</td>\n",
       "      <td>0.737607</td>\n",
       "      <td>0.262393</td>\n",
       "      <td>0.264103</td>\n",
       "      <td>0.735897</td>\n",
       "      <td>0.929060</td>\n",
       "      <td>0.070940</td>\n",
       "      <td>0.400000</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>0.960684</td>\n",
       "      <td>0.039316</td>\n",
       "      <td>0.537607</td>\n",
       "      <td>0.462393</td>\n",
       "      <td>0.929060</td>\n",
       "      <td>0.070940</td>\n",
       "      <td>0.990598</td>\n",
       "      <td>0.009402</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.136752</td>\n",
       "      <td>0.050427</td>\n",
       "      <td>0.234188</td>\n",
       "      <td>0.478632</td>\n",
       "      <td>0.610256</td>\n",
       "      <td>0.052137</td>\n",
       "      <td>0.048718</td>\n",
       "      <td>0.210256</td>\n",
       "      <td>0.078632</td>\n",
       "      <td>0.053846</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.007692</td>\n",
       "      <td>0.004274</td>\n",
       "      <td>0.011966</td>\n",
       "      <td>0.037607</td>\n",
       "      <td>0.876068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.442154e+05</td>\n",
       "      <td>0.025809</td>\n",
       "      <td>0.023118</td>\n",
       "      <td>67.150712</td>\n",
       "      <td>1.130085</td>\n",
       "      <td>0.844652</td>\n",
       "      <td>1.980491</td>\n",
       "      <td>0.295759</td>\n",
       "      <td>2.202354</td>\n",
       "      <td>1.893766</td>\n",
       "      <td>1.109805</td>\n",
       "      <td>1.722640</td>\n",
       "      <td>1.077839</td>\n",
       "      <td>0.486914</td>\n",
       "      <td>0.486914</td>\n",
       "      <td>0.440123</td>\n",
       "      <td>0.440123</td>\n",
       "      <td>0.441043</td>\n",
       "      <td>0.441043</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.490107</td>\n",
       "      <td>0.490107</td>\n",
       "      <td>0.194429</td>\n",
       "      <td>0.194429</td>\n",
       "      <td>0.498797</td>\n",
       "      <td>0.498797</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.256835</td>\n",
       "      <td>0.096547</td>\n",
       "      <td>0.096547</td>\n",
       "      <td>0.300128</td>\n",
       "      <td>0.343732</td>\n",
       "      <td>0.218919</td>\n",
       "      <td>0.423671</td>\n",
       "      <td>0.499757</td>\n",
       "      <td>0.487901</td>\n",
       "      <td>0.222398</td>\n",
       "      <td>0.215370</td>\n",
       "      <td>0.407665</td>\n",
       "      <td>0.269279</td>\n",
       "      <td>0.225810</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.087405</td>\n",
       "      <td>0.065260</td>\n",
       "      <td>0.108778</td>\n",
       "      <td>0.190325</td>\n",
       "      <td>0.329644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.900000e+04</td>\n",
       "      <td>41.355143</td>\n",
       "      <td>2.099004</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.074264</td>\n",
       "      <td>0.014215</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.558659</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.396000e+05</td>\n",
       "      <td>41.383035</td>\n",
       "      <td>2.152141</td>\n",
       "      <td>57.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.782861</td>\n",
       "      <td>0.217491</td>\n",
       "      <td>2.439024</td>\n",
       "      <td>1.388889</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.025000e+05</td>\n",
       "      <td>41.403535</td>\n",
       "      <td>2.169455</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.415416</td>\n",
       "      <td>0.315010</td>\n",
       "      <td>3.380309</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.147500e+05</td>\n",
       "      <td>41.424744</td>\n",
       "      <td>2.180327</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.787665</td>\n",
       "      <td>0.429002</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.500000e+06</td>\n",
       "      <td>41.464340</td>\n",
       "      <td>2.220334</td>\n",
       "      <td>807.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>8.522102</td>\n",
       "      <td>3.549846</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              price     latitude    longitude  sq_meters_built        rooms  \\\n",
       "count  1.170000e+03  1170.000000  1170.000000      1170.000000  1170.000000   \n",
       "mean   4.050583e+05    41.406164     2.167129        89.911966     2.647863   \n",
       "std    6.442154e+05     0.025809     0.023118        67.150712     1.130085   \n",
       "min    2.900000e+04    41.355143     2.099004        10.000000     0.000000   \n",
       "25%    1.396000e+05    41.383035     2.152141        57.000000     2.000000   \n",
       "50%    2.025000e+05    41.403535     2.169455        70.000000     3.000000   \n",
       "75%    4.147500e+05    41.424744     2.180327       100.000000     3.000000   \n",
       "max    9.500000e+06    41.464340     2.220334       807.000000     8.000000   \n",
       "\n",
       "         bathrooms  dist_city_center  dist_closest_station  rooms_per_100_sqm  \\\n",
       "count  1170.000000       1170.000000           1170.000000        1170.000000   \n",
       "mean      1.453846          3.494901              0.367251           3.403759   \n",
       "std       0.844652          1.980491              0.295759           2.202354   \n",
       "min       1.000000          0.074264              0.014215           0.000000   \n",
       "25%       1.000000          1.782861              0.217491           2.439024   \n",
       "50%       1.000000          3.415416              0.315010           3.380309   \n",
       "75%       2.000000          4.787665              0.429002           4.347826   \n",
       "max       7.000000          8.522102              3.549846          50.000000   \n",
       "\n",
       "       bathrooms_per_100_sqm  floor_cat_encoded  property_age_cat_encoded  \\\n",
       "count            1170.000000        1170.000000               1170.000000   \n",
       "mean                1.847461           0.452137                  1.335897   \n",
       "std                 1.893766           1.109805                  1.722640   \n",
       "min                 0.558659          -1.000000                 -1.000000   \n",
       "25%                 1.388889          -1.000000                 -1.000000   \n",
       "50%                 1.666667           1.000000                  2.000000   \n",
       "75%                 2.000000           1.000000                  2.000000   \n",
       "max                50.000000           3.000000                  5.000000   \n",
       "\n",
       "       neighborhood_rent_index_cluster_encoded    balcony_0    balcony_1  \\\n",
       "count                              1170.000000  1170.000000  1170.000000   \n",
       "mean                                  2.361538     0.614530     0.385470   \n",
       "std                                   1.077839     0.486914     0.486914   \n",
       "min                                   1.000000     0.000000     0.000000   \n",
       "25%                                   1.000000     0.000000     0.000000   \n",
       "50%                                   2.000000     1.000000     0.000000   \n",
       "75%                                   3.000000     1.000000     1.000000   \n",
       "max                                   4.000000     1.000000     1.000000   \n",
       "\n",
       "         terrace_0    terrace_1   exterior_0   exterior_1    rooftop_0  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.737607     0.262393     0.264103     0.735897     0.929060   \n",
       "std       0.440123     0.440123     0.441043     0.441043     0.256835   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     0.000000     1.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "         rooftop_1   elevator_0   elevator_1       pool_0       pool_1  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.070940     0.400000     0.600000     0.960684     0.039316   \n",
       "std       0.256835     0.490107     0.490107     0.194429     0.194429   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     0.000000     1.000000     0.000000   \n",
       "50%       0.000000     0.000000     1.000000     1.000000     0.000000   \n",
       "75%       0.000000     1.000000     1.000000     1.000000     0.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "              ac_0         ac_1     garage_0     garage_1     garden_0  \\\n",
       "count  1170.000000  1170.000000  1170.000000  1170.000000  1170.000000   \n",
       "mean      0.537607     0.462393     0.929060     0.070940     0.990598   \n",
       "std       0.498797     0.498797     0.256835     0.256835     0.096547   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     1.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "          garden_1  orientation_ este  orientation_ norte  orientation_ oeste  \\\n",
       "count  1170.000000        1170.000000         1170.000000         1170.000000   \n",
       "mean      0.009402           0.100000            0.136752            0.050427   \n",
       "std       0.096547           0.300128            0.343732            0.218919   \n",
       "min       0.000000           0.000000            0.000000            0.000000   \n",
       "25%       0.000000           0.000000            0.000000            0.000000   \n",
       "50%       0.000000           0.000000            0.000000            0.000000   \n",
       "75%       0.000000           0.000000            0.000000            0.000000   \n",
       "max       1.000000           1.000000            1.000000            1.000000   \n",
       "\n",
       "       orientation_ sur  orientation_Unknown  heating_Unknown  heating_bomba  \\\n",
       "count       1170.000000          1170.000000      1170.000000    1170.000000   \n",
       "mean           0.234188             0.478632         0.610256       0.052137   \n",
       "std            0.423671             0.499757         0.487901       0.222398   \n",
       "min            0.000000             0.000000         0.000000       0.000000   \n",
       "25%            0.000000             0.000000         0.000000       0.000000   \n",
       "50%            0.000000             0.000000         1.000000       0.000000   \n",
       "75%            0.000000             1.000000         1.000000       0.000000   \n",
       "max            1.000000             1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  property_type_atico  \\\n",
       "count       1170.000000  1170.000000         1170.000000          1170.000000   \n",
       "mean           0.048718     0.210256            0.078632             0.053846   \n",
       "std            0.215370     0.407665            0.269279             0.225810   \n",
       "min            0.000000     0.000000            0.000000             0.000000   \n",
       "25%            0.000000     0.000000            0.000000             0.000000   \n",
       "50%            0.000000     0.000000            0.000000             0.000000   \n",
       "75%            0.000000     0.000000            0.000000             0.000000   \n",
       "max            1.000000     1.000000            1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           1170.000000                   1170.000000   \n",
       "mean               0.004274                      0.004274   \n",
       "std                0.065260                      0.065260   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         1170.000000                   1170.000000   \n",
       "mean                             0.007692                      0.004274   \n",
       "std                              0.087405                      0.065260   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \n",
       "count           1170.000000            1170.000000         1170.000000  \n",
       "mean               0.011966               0.037607            0.876068  \n",
       "std                0.108778               0.190325            0.329644  \n",
       "min                0.000000               0.000000            0.000000  \n",
       "25%                0.000000               0.000000            1.000000  \n",
       "50%                0.000000               0.000000            1.000000  \n",
       "75%                0.000000               0.000000            1.000000  \n",
       "max                1.000000               1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 0\n"
     ]
    }
   ],
   "source": [
    "# creamos los datasets para el primer modelo de Bagging\n",
    "bagging_df2 = sales_simplified_df.copy(deep=True)\n",
    "bagging_df2_test = test_data_preprocessed.copy(deep=True)\n",
    "\n",
    "\n",
    "# variables que queremos codificar usando ordinal encoder\n",
    "oe_cols = oe_cols = ['floor_cat', # unknown\n",
    "                     'property_age_cat', # unknown\n",
    "                     'neighborhood_rent_index_cluster' \n",
    "                    ]\n",
    "# Define the order of the categories for each column\n",
    "floor_cat_order = ['Unknown', '0 - 4', '5 - 11', '+11']\n",
    "property_age_cat_order = ['Unknown', '0 - 40', '40 - 70', '70 - 120', '120 - 150', '+150']\n",
    "neighborhood_rent_index_cluster_order = ['Unknown', '0 - 2337', '2337 - 3371', '3371 - 5042', '+5042']\n",
    "\n",
    "# Create an instance of the ordinal encoder\n",
    "encoder = OrdinalEncoder(categories=[floor_cat_order, \n",
    "                                     property_age_cat_order, \n",
    "                                     neighborhood_rent_index_cluster_order])\n",
    "\n",
    "for col in oe_cols:\n",
    "    # Create a new column name for the encoded data\n",
    "    new_col = col + '_encoded'\n",
    "    # Create an instance of the ordinal encoder\n",
    "    encoder = OrdinalEncoder(categories=[eval(col+'_order')])\n",
    "    # Fit and transform the selected columns\n",
    "    bagging_df2[new_col] = encoder.fit_transform(bagging_df2[[col]])\n",
    "    bagging_df2_test[new_col] = encoder.fit_transform(bagging_df2_test[[col]])\n",
    "    # replace 0 by -1 ('Unknown' by -1)\n",
    "    bagging_df2[new_col] = bagging_df2[new_col].replace(0, -1)\n",
    "    bagging_df2_test[new_col] = bagging_df2_test[new_col].replace(0, -1)\n",
    "\n",
    "# variables que queremos codificar usando OHE\n",
    "ohe_cols = get_binary_cols(sales_simplified_df) + ['orientation', 'heating', 'property_type']\n",
    "# binary variables:\n",
    "    # ['balcony',\n",
    "    #  'terrace',\n",
    "    #  'exterior',\n",
    "    #  'rooftop',\n",
    "    #  'elevator',\n",
    "    #  'pool',\n",
    "    #  'ac',\n",
    "    #  'garage',\n",
    "    #  'garden']\n",
    "\n",
    "# aplicamos one - hot encoding al dataset\n",
    "bagging_df2 = one_hot_encode(bagging_df2, ohe_cols)\n",
    "bagging_df2_test = one_hot_encode(bagging_df2_test, ohe_cols)\n",
    "\n",
    "# eliminamos variables categóricas no codificadas\n",
    "no_encoded_cat_vars = bagging_df2.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df2.drop(no_encoded_cat_vars, axis=1, inplace=True)\n",
    "\n",
    "no_encoded_cat_vars_test = bagging_df2_test.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df2_test.drop(no_encoded_cat_vars_test, axis=1, inplace=True)\n",
    "\n",
    "# exploración rápida del df\n",
    "print(\"TRAIN: \")\n",
    "explore_data(bagging_df2)\n",
    "print(\"\\n\\n\")\n",
    "print(\"TEST: \")\n",
    "explore_data(bagging_df2_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4bbf95f",
   "metadata": {
    "tags": []
   },
   "source": [
    "**Tratamiento de Outliers**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6dff6483",
   "metadata": {},
   "source": [
    "Empezaremos por la eliminación de outliers antes de escalar las variables, ya que los outliers pueden afectar la distribución de los datos y hacer que los resultados del escalado no sean los esperados.\n",
    "\n",
    "\n",
    "Dado que la mayoría de las variables numéricas tienen muchos valores atípicos, usaremos el método IQR para tratar los outliers.\n",
    "\n",
    "El método IQR es un método robusto para la detección y eliminación de valores atípicos (puede tratar un gran número de valores atípicos en los datos). Además, es menos sensible a los valores extremos que el método Z-score, lo que lo hace más adecuado para un dataset con muchos outliers."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "397040e0",
   "metadata": {},
   "source": [
    "Para utilizar el método IQR, primero calcularemos el IQR para cada variable numérica. A continuación, identificaremos cualquier data point que caiga por debajo de Q1 - 1.5 * IQR o por encima de Q3 + 1.5 * IQR como un valor atípico y lo eliminaremos del conjunto de datos.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 627,
   "id": "9644b7aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "def remove_outliers_iqr(df: pd.DataFrame, cols: List[str], threshold: float = 1.5) -> pd.DataFrame:\n",
    "    \"\"\"\n",
    "    Remove outliers from a pandas DataFrame using the interquartile range (IQR) method.\n",
    "    \n",
    "    Args:\n",
    "        df: A pandas DataFrame containing the data.\n",
    "        cols: A list of columns to remove outliers from.\n",
    "        threshold: The number of IQRs beyond which a data point is considered an outlier.\n",
    "                   Defaults to 1.5.\n",
    "                   \n",
    "    Returns:\n",
    "        A pandas DataFrame with the outliers removed.\n",
    "    \"\"\"\n",
    "    # Calculate the IQR for each specified column\n",
    "    Q1 = df[cols].quantile(0.25)\n",
    "    Q3 = df[cols].quantile(0.75)\n",
    "    IQR = Q3 - Q1\n",
    "    \n",
    "    # Determine the threshold values for each specified column\n",
    "    thresholds = (Q1 - threshold * IQR, Q3 + threshold * IQR)\n",
    "    \n",
    "    # Identify and remove the outliers\n",
    "    is_outlier = ((df[cols] < thresholds[0]) | (df[cols] > thresholds[1])).any(axis=1)\n",
    "    df_clean = df.loc[~is_outlier, :]\n",
    "    \n",
    "    return df_clean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 628,
   "id": "32aac069",
   "metadata": {},
   "outputs": [],
   "source": [
    "# variables numéricas\n",
    "num_vars = ['price', 'latitude', 'longitude', \n",
    "            'sq_meters_built', 'rooms', 'bathrooms', \n",
    "            'dist_city_center', 'dist_closest_station',\n",
    "            'rooms_per_100_sqm', 'bathrooms_per_100_sqm']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 629,
   "id": "45973c6e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove outliers using the IQR method\n",
    "bagging_df2 = remove_outliers_iqr(bagging_df2, num_vars)\n",
    "bagging_df2_test = remove_outliers_iqr(bagging_df2_test, num_vars)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 630,
   "id": "683790ec",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAIN: \n",
      "(3669, 49)\n",
      "TEST: \n",
      "(898, 49)\n"
     ]
    }
   ],
   "source": [
    "# exploración rápida del df\n",
    "print(\"TRAIN: \")\n",
    "print(bagging_df2.shape)\n",
    "print(\"TEST: \")\n",
    "print(bagging_df2_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a2a2f5c",
   "metadata": {},
   "source": [
    "**Escalar los atributos**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "569c0277",
   "metadata": {},
   "source": [
    "Escalamos los atributos ya que, por ejemplo, los metros cuadrados o el número de habitaciones, están en una escala diferente a otras características, como la ubicación (longitud y latitud) o el año de construcción. Escalar las características de entrada a una escala común puede ayudar a garantizar que todas estas características reciben el mismo tratamiento en el modelo."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7be6eb0e",
   "metadata": {},
   "source": [
    "Como los datos no siguen una distribución normal y ya hemos tratado los valores atípicos utilizando la técnica IQR, entonces utilizar el MinMaxScaler puede ser una buena opción para escalar las variables numéricas.\n",
    "\n",
    "El MinMaxScaler escala los atributos a un rango fijo entre 0 y 1, por lo que es apropiado cuando los atributos no tienen una distribución normal o tienen un rango limitado."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 631,
   "id": "6cecc4e3",
   "metadata": {},
   "outputs": [],
   "source": [
    "def scale_columns(df: pd.DataFrame, columns: List[str]) -> pd.DataFrame:\n",
    "    \"\"\"\n",
    "    Applies MinMaxScaler to the specified columns of a pandas DataFrame.\n",
    "\n",
    "    Parameters:\n",
    "    -----------\n",
    "    df : pd.DataFrame\n",
    "        The pandas DataFrame to scale.\n",
    "    columns : List[str]\n",
    "        The list of column names to scale.\n",
    "\n",
    "    Returns:\n",
    "    --------\n",
    "    pd.DataFrame\n",
    "        The scaled pandas DataFrame.\n",
    "    \"\"\"\n",
    "\n",
    "    # Create a copy of the DataFrame\n",
    "    df_scaled = df.copy()\n",
    "\n",
    "    # Create a MinMaxScaler object\n",
    "    scaler = MinMaxScaler()\n",
    "\n",
    "    # Scale the specified columns\n",
    "    df_scaled[columns] = scaler.fit_transform(df_scaled[columns])\n",
    "\n",
    "    return df_scaled\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 632,
   "id": "1c630801",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Scale the columns\n",
    "bagging_df2 = scale_columns(bagging_df2, num_vars)\n",
    "bagging_df2_test = scale_columns(bagging_df2_test, num_vars)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4893142",
   "metadata": {},
   "source": [
    "El siguiente código hace lo mismo pero usando un Pipeline: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 633,
   "id": "6c813692",
   "metadata": {},
   "outputs": [],
   "source": [
    "class OutlierRemover(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self, cols=None, threshold=1.5):\n",
    "        self.cols = cols\n",
    "        self.threshold = threshold\n",
    "\n",
    "    def fit(self, X, y=None):\n",
    "        return self\n",
    "\n",
    "    def transform(self, X, y=None):\n",
    "        X_clean = X.copy()\n",
    "        # Calculate the IQR for each specified column\n",
    "        Q1 = X_clean[self.cols].quantile(0.25)\n",
    "        Q3 = X_clean[self.cols].quantile(0.75)\n",
    "        IQR = Q3 - Q1\n",
    "\n",
    "        # Determine the threshold values for each specified column\n",
    "        thresholds = (Q1 - self.threshold * IQR, Q3 + self.threshold * IQR)\n",
    "\n",
    "        # Identify and remove the outliers\n",
    "        is_outlier = ((X_clean[self.cols] < thresholds[0]) | (X_clean[self.cols] > thresholds[1])).any(axis=1)\n",
    "        X_clean = X_clean.loc[~is_outlier, :]\n",
    "\n",
    "        return X_clean\n",
    "\n",
    "\n",
    "class MinMaxScalerTransformer(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self):\n",
    "        self.scaler = MinMaxScaler()\n",
    "\n",
    "    def fit(self, X, y=None):\n",
    "        self.scaler.fit(X)\n",
    "        return self\n",
    "\n",
    "    def transform(self, X):\n",
    "        X_scaled = self.scaler.transform(X)\n",
    "        feature_names = [f'{col}' for col in X.columns]\n",
    "        return pd.DataFrame(X_scaled, columns=feature_names)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1248,
   "id": "b767ba85",
   "metadata": {},
   "outputs": [],
   "source": [
    "# define the preprocessing pipeline\n",
    "preprocessing_pipeline = Pipeline([\n",
    "    ('outlier_removal', OutlierRemover(cols=num_vars)),\n",
    "    ('scaler', ColumnTransformer([('num_scaler', MinMaxScaler(), num_vars)], \n",
    "                                 remainder='passthrough'))\n",
    "])\n",
    "\n",
    "\n",
    "# Apply the preprocessing pipeline to the training and testing data\n",
    "    # Fit and transform the training data\n",
    "bagging_df2 = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df2), columns=num_vars + list(bagging_df2.columns[len(num_vars):]))\n",
    "bagging_df2_test = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df2_test), columns=num_vars + list(bagging_df2_test.columns[len(num_vars):]))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8df137a3",
   "metadata": {},
   "source": [
    "##### Model 2: Bagging & RF "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4264adb",
   "metadata": {},
   "source": [
    "Una vez hemos tratado los outliers y hemos escalado los atributos numéricos, vemos cómo se comportan los modelos:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 635,
   "id": "505b549e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.7708\n",
      "Train R^2 score: 0.9701\n",
      "Test R^2 score: 0.6908\n",
      "\n",
      "Model: RandomForestRegressor\n",
      "Best model parameters: {'model__max_depth': 9, 'model__min_samples_split': 2, 'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.7601\n",
      "Train R^2 score: 0.9245\n",
      "Test R^2 score: 0.6744\n",
      "\n",
      "Best model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.7708\n",
      "Train R^2 score: 0.9701\n",
      "Test R^2 score: 0.6908\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'name': 'BaggingRegressor',\n",
       "  'best_params': {'model__n_estimators': 200},\n",
       "  'best_score': 0.7707652188812547,\n",
       "  'train_r2_score': 0.97011092170689,\n",
       "  'test_r2_score': 0.6907957655585963},\n",
       " {'name': 'RandomForestRegressor',\n",
       "  'best_params': {'model__max_depth': 9,\n",
       "   'model__min_samples_split': 2,\n",
       "   'model__n_estimators': 200},\n",
       "  'best_score': 0.7600922045988325,\n",
       "  'train_r2_score': 0.9245244491203484,\n",
       "  'test_r2_score': 0.6744430145609775}]"
      ]
     },
     "execution_count": 635,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create an instance of PipelineRunner\n",
    "pipeline_runner = PipelineRunner()\n",
    "# call the run_pipeline() method, passing in the dataframes and target variable name\n",
    "results_2 = pipeline_runner.run_pipeline(df_train=bagging_df2, \n",
    "                                         df_test=bagging_df2_test, \n",
    "                                         target=TARGET_VARIABLE)\n",
    "# examine the results for each model\n",
    "results_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 656,
   "id": "5cd41672",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regressor</th>\n",
       "      <th>train_r2_score</th>\n",
       "      <th>test_r2_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BaggingRegressor_1</td>\n",
       "      <td>0.976685</td>\n",
       "      <td>0.739290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>RandomForestRegressor_1</td>\n",
       "      <td>0.939248</td>\n",
       "      <td>0.723103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>BaggingRegressor_2</td>\n",
       "      <td>0.970111</td>\n",
       "      <td>0.690796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>RandomForestRegressor_2</td>\n",
       "      <td>0.924524</td>\n",
       "      <td>0.674443</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 regressor  train_r2_score  test_r2_score\n",
       "0       BaggingRegressor_1        0.976685       0.739290\n",
       "1  RandomForestRegressor_1        0.939248       0.723103\n",
       "2       BaggingRegressor_2        0.970111       0.690796\n",
       "3  RandomForestRegressor_2        0.924524       0.674443"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Loop through each model in results\n",
    "for model in results_2:\n",
    "    model_name = model['name']+'_2'\n",
    "    train_r2_score = model['train_r2_score']\n",
    "    test_r2_score = model['test_r2_score']\n",
    "    \n",
    "    # Append the results to the DataFrame\n",
    "    models_results_df = pd.concat([models_results_df, pd.DataFrame({'regressor': model_name, \n",
    "                                                                   'train_r2_score': train_r2_score,\n",
    "                                                                   'test_r2_score': test_r2_score},\n",
    "                                                                   index=[0])], ignore_index=True)\n",
    "# Display the DataFrame\n",
    "display(models_results_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6fa23a9",
   "metadata": {},
   "source": [
    "- Parece que de momento, el tratamiento de outliers y el escalado de las variables numéricas no han mejorado el rendimiento de los modelos, sino todo lo contrario. \n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46c9652e",
   "metadata": {},
   "source": [
    "#### Modelo 3"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7bc70c4c",
   "metadata": {},
   "source": [
    "Recordemos lo que obtuvimos de cada técnica (para seleccionar las mejores variables predictoras del precio de la vivienda): \n",
    "\n",
    "- Del análisis de componentes principales (PCA), observamos que las variables sq_meters_built, bathrooms, longitude, dist_city_center, latitude, bathrooms_per_100_sqm y rooms_per_100_sqm tenían los mayores pesos en los primeros 3 componentes principales, lo que indica que estas variables contribuyen significativamente a la variación total de los datos. Sin embargo, se requiere un análisis adicional para determinar si estas variables tienen una relación significativa con el precio de la vivienda y cómo se relacionan con él.\n",
    "\n",
    "- Del análisis de información mutua (recordemos que una puntuación más alta significa que la característica es más informativa para predecir la variable objetivo) vimos que \"sq_meters_built\" tenía la puntuación de información mutua más alta, lo que significa que puede ser el atributo más informativo para predecir el precio de la vivienda. Del mismo modo, \"rooms_per_100_sqm\" y \"bathrooms_per_100_sqm\" también tenían puntuaciones de información mutua relativamente altas, lo que indica que también son atributos informativos. Otros atributos que tienen puntuaciones de información mutua relativamente altas eran \" latitude\", \"bathrooms\" y \"neighborhood_rent_index_cluster \", mientras que atributos como \"property_type_duplex\", \"property_type_chalet_adosado\" y \"heating_electric\" tenían puntuaciones muy bajas, lo que indica que son menos informativos a la hora predecir el precio de la vivienda.\n",
    "\n",
    "- Del análisis ANOVA (y Kruskall-Wallis) vimos que las variables con mayor efecto sobre el precio de venta de la vivienda eran neighborhood_rent_index_cluster, garage, garden, pool, terrace, property_type, property_age_cat, elevator, ac, heating y property_age_cat.\n",
    "\n",
    "- Al realizar el método ExtraTreesRegressor vimos que que según el modelo, sq_meters_built es el atributo más importante para predecir el precio de la vivienda, seguida de bathrooms y neighborhood_rent_index_cluster_encoded. Otras características como rooms_per_100_sqm, garden y bathrooms_per_100_sqm también tenían puntuaciones de importancia relativamente altas.\n",
    "\n",
    "\n",
    "Al considerar los resultados de los diferentes métodos, parece que \"sq_meters_built\", \"bathrooms\", \"longitude\", \"dist_city_center\", \"latitude\", \"bathrooms_per_100_sqm\", \"rooms_per_100_sqm\", \"neighborhood_rent_index_cluster\", \"garage\", \"garden\", \"pool\", \"terrace\", \"property_type\", \"property_age_cat\", \"elevator\", \"ac\", \"heating\" y \"property_age_cat\" son las variables más importantes o informativas para predecir el precio de la vivienda en Barcelona. Recordemos que \"bathrooms\" estaba fuertemente correlacionado con \"sq_meters_built\" y por eso creamos \"bathrooms_per_100_sqm\". Por tanto, nos quedamos con \"bathrooms_per_100_sqm\". \n",
    "\n",
    "Por tanto, realizaremos los modelos de Bagging y Random Forest con estas variables. \n",
    "Como los resultados han mejorado después de tratar los outliers y escalar los atributos numéricos, relizaremos el mismo proceso con las variables seleccionadas. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ef90ac80",
   "metadata": {},
   "source": [
    "#####  Train dataset (bagging_df3) y Test dataset (bagging_df3_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 636,
   "id": "e813bff4",
   "metadata": {
    "jupyter": {
     "outputs_hidden": true
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAIN: \n",
      "The dataset includes 3914 instances (rows) and 34 variables (columns).\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.083558</td>\n",
       "      <td>0.149123</td>\n",
       "      <td>0.539966</td>\n",
       "      <td>0.598009</td>\n",
       "      <td>0.721144</td>\n",
       "      <td>0.555140</td>\n",
       "      <td>0.280000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.157682</td>\n",
       "      <td>0.175439</td>\n",
       "      <td>0.578853</td>\n",
       "      <td>0.729485</td>\n",
       "      <td>0.811563</td>\n",
       "      <td>0.506260</td>\n",
       "      <td>0.792453</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.871968</td>\n",
       "      <td>0.763158</td>\n",
       "      <td>0.375652</td>\n",
       "      <td>0.162188</td>\n",
       "      <td>0.337326</td>\n",
       "      <td>0.411215</td>\n",
       "      <td>0.466667</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.392183</td>\n",
       "      <td>0.315789</td>\n",
       "      <td>0.457874</td>\n",
       "      <td>0.331045</td>\n",
       "      <td>0.529310</td>\n",
       "      <td>0.317351</td>\n",
       "      <td>0.608696</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.080863</td>\n",
       "      <td>0.271930</td>\n",
       "      <td>0.391947</td>\n",
       "      <td>0.470643</td>\n",
       "      <td>0.616941</td>\n",
       "      <td>0.366238</td>\n",
       "      <td>0.437500</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price  sq_meters_built  longitude  dist_city_center  latitude  \\\n",
       "0  0.083558         0.149123   0.539966          0.598009  0.721144   \n",
       "1  0.157682         0.175439   0.578853          0.729485  0.811563   \n",
       "2  0.871968         0.763158   0.375652          0.162188  0.337326   \n",
       "3  0.392183         0.315789   0.457874          0.331045  0.529310   \n",
       "4  0.080863         0.271930   0.391947          0.470643  0.616941   \n",
       "\n",
       "   bathrooms_per_100_sqm  rooms_per_100_sqm  property_age_cat_encoded  \\\n",
       "0               0.555140           0.280000                       2.0   \n",
       "1               0.506260           0.792453                      -1.0   \n",
       "2               0.411215           0.466667                       2.0   \n",
       "3               0.317351           0.608696                       3.0   \n",
       "4               0.366238           0.437500                       2.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  garage_0  garage_1  garden_0  \\\n",
       "0                                      1.0       1.0       0.0       1.0   \n",
       "1                                      1.0       1.0       0.0       1.0   \n",
       "2                                      3.0       1.0       0.0       1.0   \n",
       "3                                      3.0       1.0       0.0       1.0   \n",
       "4                                      1.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  pool_0  pool_1  terrace_0  terrace_1  property_type_atico  \\\n",
       "0       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "1       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "2       0.0     1.0     0.0        0.0        1.0                  1.0   \n",
       "3       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "4       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 0.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "0                   0.0                    0.0                 1.0   \n",
       "1                   0.0                    0.0                 1.0   \n",
       "2                   0.0                    0.0                 0.0   \n",
       "3                   0.0                    0.0                 1.0   \n",
       "4                   0.0                    0.0                 1.0   \n",
       "\n",
       "   elevator_0  elevator_1  ac_0  ac_1  heating_Unknown  heating_bomba  \\\n",
       "0         0.0         1.0   0.0   1.0              0.0            1.0   \n",
       "1         1.0         0.0   1.0   0.0              1.0            0.0   \n",
       "2         0.0         1.0   0.0   1.0              0.0            0.0   \n",
       "3         0.0         1.0   1.0   0.0              1.0            0.0   \n",
       "4         1.0         0.0   1.0   0.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  \n",
       "0               0.0          0.0                 0.0  \n",
       "1               0.0          0.0                 0.0  \n",
       "2               0.0          0.0                 1.0  \n",
       "3               0.0          0.0                 0.0  \n",
       "4               0.0          0.0                 0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 3914 entries, 0 to 3913\n",
      "Data columns (total 34 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    3914 non-null   float64\n",
      " 1   sq_meters_built                          3914 non-null   float64\n",
      " 2   longitude                                3914 non-null   float64\n",
      " 3   dist_city_center                         3914 non-null   float64\n",
      " 4   latitude                                 3914 non-null   float64\n",
      " 5   bathrooms_per_100_sqm                    3914 non-null   float64\n",
      " 6   rooms_per_100_sqm                        3914 non-null   float64\n",
      " 7   property_age_cat_encoded                 3914 non-null   float64\n",
      " 8   neighborhood_rent_index_cluster_encoded  3914 non-null   float64\n",
      " 9   garage_0                                 3914 non-null   float64\n",
      " 10  garage_1                                 3914 non-null   float64\n",
      " 11  garden_0                                 3914 non-null   float64\n",
      " 12  garden_1                                 3914 non-null   float64\n",
      " 13  pool_0                                   3914 non-null   float64\n",
      " 14  pool_1                                   3914 non-null   float64\n",
      " 15  terrace_0                                3914 non-null   float64\n",
      " 16  terrace_1                                3914 non-null   float64\n",
      " 17  property_type_atico                      3914 non-null   float64\n",
      " 18  property_type_chalet                     3914 non-null   float64\n",
      " 19  property_type_chalet_adosado             3914 non-null   float64\n",
      " 20  property_type_chalet_independiente       3914 non-null   float64\n",
      " 21  property_type_chalet_pareado             3914 non-null   float64\n",
      " 22  property_type_duplex                     3914 non-null   float64\n",
      " 23  property_type_estudio                    3914 non-null   float64\n",
      " 24  property_type_piso                       3914 non-null   float64\n",
      " 25  elevator_0                               3914 non-null   float64\n",
      " 26  elevator_1                               3914 non-null   float64\n",
      " 27  ac_0                                     3914 non-null   float64\n",
      " 28  ac_1                                     3914 non-null   float64\n",
      " 29  heating_Unknown                          3914 non-null   float64\n",
      " 30  heating_bomba                            3914 non-null   float64\n",
      " 31  heating_electric                         3914 non-null   float64\n",
      " 32  heating_gas                              3914 non-null   float64\n",
      " 33  heating_individual                       3914 non-null   float64\n",
      "dtypes: float64(34)\n",
      "memory usage: 1.0 MB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "sq_meters_built                            0\n",
      "longitude                                  0\n",
      "dist_city_center                           0\n",
      "latitude                                   0\n",
      "bathrooms_per_100_sqm                      0\n",
      "rooms_per_100_sqm                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.278795</td>\n",
       "      <td>0.327542</td>\n",
       "      <td>0.534793</td>\n",
       "      <td>0.424337</td>\n",
       "      <td>0.488343</td>\n",
       "      <td>0.460803</td>\n",
       "      <td>0.501716</td>\n",
       "      <td>1.296883</td>\n",
       "      <td>2.045989</td>\n",
       "      <td>0.970363</td>\n",
       "      <td>0.029637</td>\n",
       "      <td>0.999234</td>\n",
       "      <td>0.000766</td>\n",
       "      <td>0.991824</td>\n",
       "      <td>0.008176</td>\n",
       "      <td>0.811957</td>\n",
       "      <td>0.188043</td>\n",
       "      <td>0.041901</td>\n",
       "      <td>0.001022</td>\n",
       "      <td>0.002044</td>\n",
       "      <td>0.001022</td>\n",
       "      <td>0.002044</td>\n",
       "      <td>0.013797</td>\n",
       "      <td>0.028871</td>\n",
       "      <td>0.909300</td>\n",
       "      <td>0.457333</td>\n",
       "      <td>0.542667</td>\n",
       "      <td>0.591722</td>\n",
       "      <td>0.408278</td>\n",
       "      <td>0.616505</td>\n",
       "      <td>0.059019</td>\n",
       "      <td>0.040112</td>\n",
       "      <td>0.213337</td>\n",
       "      <td>0.071027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.195855</td>\n",
       "      <td>0.197310</td>\n",
       "      <td>0.200325</td>\n",
       "      <td>0.240007</td>\n",
       "      <td>0.247701</td>\n",
       "      <td>0.200167</td>\n",
       "      <td>0.174327</td>\n",
       "      <td>1.716043</td>\n",
       "      <td>0.983602</td>\n",
       "      <td>0.169606</td>\n",
       "      <td>0.169606</td>\n",
       "      <td>0.027678</td>\n",
       "      <td>0.027678</td>\n",
       "      <td>0.090061</td>\n",
       "      <td>0.090061</td>\n",
       "      <td>0.390796</td>\n",
       "      <td>0.390796</td>\n",
       "      <td>0.200388</td>\n",
       "      <td>0.031956</td>\n",
       "      <td>0.045170</td>\n",
       "      <td>0.031956</td>\n",
       "      <td>0.045170</td>\n",
       "      <td>0.116661</td>\n",
       "      <td>0.167465</td>\n",
       "      <td>0.287219</td>\n",
       "      <td>0.498240</td>\n",
       "      <td>0.498240</td>\n",
       "      <td>0.491578</td>\n",
       "      <td>0.491578</td>\n",
       "      <td>0.486299</td>\n",
       "      <td>0.235690</td>\n",
       "      <td>0.196248</td>\n",
       "      <td>0.409716</td>\n",
       "      <td>0.256903</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.143026</td>\n",
       "      <td>0.192982</td>\n",
       "      <td>0.401951</td>\n",
       "      <td>0.212459</td>\n",
       "      <td>0.245523</td>\n",
       "      <td>0.317351</td>\n",
       "      <td>0.394366</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.176550</td>\n",
       "      <td>0.289474</td>\n",
       "      <td>0.550578</td>\n",
       "      <td>0.418645</td>\n",
       "      <td>0.495922</td>\n",
       "      <td>0.411215</td>\n",
       "      <td>0.525000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.386456</td>\n",
       "      <td>0.421053</td>\n",
       "      <td>0.642030</td>\n",
       "      <td>0.585306</td>\n",
       "      <td>0.684464</td>\n",
       "      <td>0.572764</td>\n",
       "      <td>0.622222</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             price  sq_meters_built    longitude  dist_city_center  \\\n",
       "count  3914.000000      3914.000000  3914.000000       3914.000000   \n",
       "mean      0.278795         0.327542     0.534793          0.424337   \n",
       "std       0.195855         0.197310     0.200325          0.240007   \n",
       "min       0.000000         0.000000     0.000000          0.000000   \n",
       "25%       0.143026         0.192982     0.401951          0.212459   \n",
       "50%       0.176550         0.289474     0.550578          0.418645   \n",
       "75%       0.386456         0.421053     0.642030          0.585306   \n",
       "max       1.000000         1.000000     1.000000          1.000000   \n",
       "\n",
       "          latitude  bathrooms_per_100_sqm  rooms_per_100_sqm  \\\n",
       "count  3914.000000            3914.000000        3914.000000   \n",
       "mean      0.488343               0.460803           0.501716   \n",
       "std       0.247701               0.200167           0.174327   \n",
       "min       0.000000               0.000000           0.000000   \n",
       "25%       0.245523               0.317351           0.394366   \n",
       "50%       0.495922               0.411215           0.525000   \n",
       "75%       0.684464               0.572764           0.622222   \n",
       "max       1.000000               1.000000           1.000000   \n",
       "\n",
       "       property_age_cat_encoded  neighborhood_rent_index_cluster_encoded  \\\n",
       "count               3914.000000                              3914.000000   \n",
       "mean                   1.296883                                 2.045989   \n",
       "std                    1.716043                                 0.983602   \n",
       "min                   -1.000000                                 1.000000   \n",
       "25%                   -1.000000                                 1.000000   \n",
       "50%                    2.000000                                 2.000000   \n",
       "75%                    2.000000                                 3.000000   \n",
       "max                    5.000000                                 4.000000   \n",
       "\n",
       "          garage_0     garage_1     garden_0     garden_1       pool_0  \\\n",
       "count  3914.000000  3914.000000  3914.000000  3914.000000  3914.000000   \n",
       "mean      0.970363     0.029637     0.999234     0.000766     0.991824   \n",
       "std       0.169606     0.169606     0.027678     0.027678     0.090061   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "            pool_1    terrace_0    terrace_1  property_type_atico  \\\n",
       "count  3914.000000  3914.000000  3914.000000          3914.000000   \n",
       "mean      0.008176     0.811957     0.188043             0.041901   \n",
       "std       0.090061     0.390796     0.390796             0.200388   \n",
       "min       0.000000     0.000000     0.000000             0.000000   \n",
       "25%       0.000000     1.000000     0.000000             0.000000   \n",
       "50%       0.000000     1.000000     0.000000             0.000000   \n",
       "75%       0.000000     1.000000     0.000000             0.000000   \n",
       "max       1.000000     1.000000     1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           3914.000000                   3914.000000   \n",
       "mean               0.001022                      0.002044   \n",
       "std                0.031956                      0.045170   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         3914.000000                   3914.000000   \n",
       "mean                             0.001022                      0.002044   \n",
       "std                              0.031956                      0.045170   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "count           3914.000000            3914.000000         3914.000000   \n",
       "mean               0.013797               0.028871            0.909300   \n",
       "std                0.116661               0.167465            0.287219   \n",
       "min                0.000000               0.000000            0.000000   \n",
       "25%                0.000000               0.000000            1.000000   \n",
       "50%                0.000000               0.000000            1.000000   \n",
       "75%                0.000000               0.000000            1.000000   \n",
       "max                1.000000               1.000000            1.000000   \n",
       "\n",
       "        elevator_0   elevator_1         ac_0         ac_1  heating_Unknown  \\\n",
       "count  3914.000000  3914.000000  3914.000000  3914.000000      3914.000000   \n",
       "mean      0.457333     0.542667     0.591722     0.408278         0.616505   \n",
       "std       0.498240     0.498240     0.491578     0.491578         0.486299   \n",
       "min       0.000000     0.000000     0.000000     0.000000         0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000         0.000000   \n",
       "50%       0.000000     1.000000     1.000000     0.000000         1.000000   \n",
       "75%       1.000000     1.000000     1.000000     1.000000         1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000         1.000000   \n",
       "\n",
       "       heating_bomba  heating_electric  heating_gas  heating_individual  \n",
       "count    3914.000000       3914.000000  3914.000000         3914.000000  \n",
       "mean        0.059019          0.040112     0.213337            0.071027  \n",
       "std         0.235690          0.196248     0.409716            0.256903  \n",
       "min         0.000000          0.000000     0.000000            0.000000  \n",
       "25%         0.000000          0.000000     0.000000            0.000000  \n",
       "50%         0.000000          0.000000     0.000000            0.000000  \n",
       "75%         0.000000          0.000000     0.000000            0.000000  \n",
       "max         1.000000          1.000000     1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 3\n",
      "\n",
      "\n",
      "\n",
      "TEST: \n",
      "The dataset includes 970 instances (rows) and 34 variables (columns).\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.130653</td>\n",
       "      <td>0.320312</td>\n",
       "      <td>0.934009</td>\n",
       "      <td>0.601814</td>\n",
       "      <td>0.603811</td>\n",
       "      <td>0.292241</td>\n",
       "      <td>0.552632</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.572864</td>\n",
       "      <td>0.742188</td>\n",
       "      <td>0.379277</td>\n",
       "      <td>0.187371</td>\n",
       "      <td>0.234849</td>\n",
       "      <td>0.391812</td>\n",
       "      <td>0.430769</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.296482</td>\n",
       "      <td>0.328125</td>\n",
       "      <td>0.663388</td>\n",
       "      <td>0.274098</td>\n",
       "      <td>0.473093</td>\n",
       "      <td>0.284600</td>\n",
       "      <td>0.545455</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.157663</td>\n",
       "      <td>0.203125</td>\n",
       "      <td>0.560432</td>\n",
       "      <td>0.597186</td>\n",
       "      <td>0.721143</td>\n",
       "      <td>0.436924</td>\n",
       "      <td>0.459016</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.134422</td>\n",
       "      <td>0.257812</td>\n",
       "      <td>0.561850</td>\n",
       "      <td>0.200849</td>\n",
       "      <td>0.155197</td>\n",
       "      <td>0.361462</td>\n",
       "      <td>0.617647</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      price  sq_meters_built  longitude  dist_city_center  latitude  \\\n",
       "0  0.130653         0.320312   0.934009          0.601814  0.603811   \n",
       "1  0.572864         0.742188   0.379277          0.187371  0.234849   \n",
       "2  0.296482         0.328125   0.663388          0.274098  0.473093   \n",
       "3  0.157663         0.203125   0.560432          0.597186  0.721143   \n",
       "4  0.134422         0.257812   0.561850          0.200849  0.155197   \n",
       "\n",
       "   bathrooms_per_100_sqm  rooms_per_100_sqm  property_age_cat_encoded  \\\n",
       "0               0.292241           0.552632                       2.0   \n",
       "1               0.391812           0.430769                       3.0   \n",
       "2               0.284600           0.545455                       2.0   \n",
       "3               0.436924           0.459016                       2.0   \n",
       "4               0.361462           0.617647                       2.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  garage_0  garage_1  garden_0  \\\n",
       "0                                      2.0       1.0       0.0       1.0   \n",
       "1                                      3.0       1.0       0.0       1.0   \n",
       "2                                      3.0       1.0       0.0       1.0   \n",
       "3                                      2.0       1.0       0.0       1.0   \n",
       "4                                      1.0       0.0       1.0       1.0   \n",
       "\n",
       "   garden_1  pool_0  pool_1  terrace_0  terrace_1  property_type_atico  \\\n",
       "0       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "1       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "2       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "3       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "4       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 0.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "0                   0.0                    0.0                 1.0   \n",
       "1                   0.0                    0.0                 1.0   \n",
       "2                   0.0                    0.0                 1.0   \n",
       "3                   0.0                    0.0                 1.0   \n",
       "4                   0.0                    0.0                 1.0   \n",
       "\n",
       "   elevator_0  elevator_1  ac_0  ac_1  heating_Unknown  heating_bomba  \\\n",
       "0         0.0         1.0   1.0   0.0              0.0            0.0   \n",
       "1         0.0         1.0   1.0   0.0              1.0            0.0   \n",
       "2         0.0         1.0   0.0   1.0              1.0            0.0   \n",
       "3         0.0         1.0   1.0   0.0              0.0            0.0   \n",
       "4         1.0         0.0   0.0   1.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  \n",
       "0               0.0          1.0                 0.0  \n",
       "1               0.0          0.0                 0.0  \n",
       "2               0.0          0.0                 0.0  \n",
       "3               0.0          1.0                 0.0  \n",
       "4               0.0          0.0                 0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 970 entries, 0 to 969\n",
      "Data columns (total 34 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    970 non-null    float64\n",
      " 1   sq_meters_built                          970 non-null    float64\n",
      " 2   longitude                                970 non-null    float64\n",
      " 3   dist_city_center                         970 non-null    float64\n",
      " 4   latitude                                 970 non-null    float64\n",
      " 5   bathrooms_per_100_sqm                    970 non-null    float64\n",
      " 6   rooms_per_100_sqm                        970 non-null    float64\n",
      " 7   property_age_cat_encoded                 970 non-null    float64\n",
      " 8   neighborhood_rent_index_cluster_encoded  970 non-null    float64\n",
      " 9   garage_0                                 970 non-null    float64\n",
      " 10  garage_1                                 970 non-null    float64\n",
      " 11  garden_0                                 970 non-null    float64\n",
      " 12  garden_1                                 970 non-null    float64\n",
      " 13  pool_0                                   970 non-null    float64\n",
      " 14  pool_1                                   970 non-null    float64\n",
      " 15  terrace_0                                970 non-null    float64\n",
      " 16  terrace_1                                970 non-null    float64\n",
      " 17  property_type_atico                      970 non-null    float64\n",
      " 18  property_type_chalet                     970 non-null    float64\n",
      " 19  property_type_chalet_adosado             970 non-null    float64\n",
      " 20  property_type_chalet_independiente       970 non-null    float64\n",
      " 21  property_type_chalet_pareado             970 non-null    float64\n",
      " 22  property_type_duplex                     970 non-null    float64\n",
      " 23  property_type_estudio                    970 non-null    float64\n",
      " 24  property_type_piso                       970 non-null    float64\n",
      " 25  elevator_0                               970 non-null    float64\n",
      " 26  elevator_1                               970 non-null    float64\n",
      " 27  ac_0                                     970 non-null    float64\n",
      " 28  ac_1                                     970 non-null    float64\n",
      " 29  heating_Unknown                          970 non-null    float64\n",
      " 30  heating_bomba                            970 non-null    float64\n",
      " 31  heating_electric                         970 non-null    float64\n",
      " 32  heating_gas                              970 non-null    float64\n",
      " 33  heating_individual                       970 non-null    float64\n",
      "dtypes: float64(34)\n",
      "memory usage: 257.8 KB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "sq_meters_built                            0\n",
      "longitude                                  0\n",
      "dist_city_center                           0\n",
      "latitude                                   0\n",
      "bathrooms_per_100_sqm                      0\n",
      "rooms_per_100_sqm                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.278775</td>\n",
       "      <td>0.306258</td>\n",
       "      <td>0.530647</td>\n",
       "      <td>0.429441</td>\n",
       "      <td>0.488279</td>\n",
       "      <td>0.476849</td>\n",
       "      <td>0.498464</td>\n",
       "      <td>1.288660</td>\n",
       "      <td>2.182474</td>\n",
       "      <td>0.968041</td>\n",
       "      <td>0.031959</td>\n",
       "      <td>0.997938</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.986598</td>\n",
       "      <td>0.013402</td>\n",
       "      <td>0.790722</td>\n",
       "      <td>0.209278</td>\n",
       "      <td>0.041237</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.001031</td>\n",
       "      <td>0.001031</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.010309</td>\n",
       "      <td>0.030928</td>\n",
       "      <td>0.911340</td>\n",
       "      <td>0.415464</td>\n",
       "      <td>0.584536</td>\n",
       "      <td>0.573196</td>\n",
       "      <td>0.426804</td>\n",
       "      <td>0.637113</td>\n",
       "      <td>0.054639</td>\n",
       "      <td>0.046392</td>\n",
       "      <td>0.194845</td>\n",
       "      <td>0.067010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.204398</td>\n",
       "      <td>0.199326</td>\n",
       "      <td>0.200919</td>\n",
       "      <td>0.234314</td>\n",
       "      <td>0.247501</td>\n",
       "      <td>0.194325</td>\n",
       "      <td>0.174288</td>\n",
       "      <td>1.694152</td>\n",
       "      <td>1.017241</td>\n",
       "      <td>0.175981</td>\n",
       "      <td>0.175981</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.115048</td>\n",
       "      <td>0.115048</td>\n",
       "      <td>0.407003</td>\n",
       "      <td>0.407003</td>\n",
       "      <td>0.198941</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.032108</td>\n",
       "      <td>0.032108</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.101062</td>\n",
       "      <td>0.173212</td>\n",
       "      <td>0.284399</td>\n",
       "      <td>0.493056</td>\n",
       "      <td>0.493056</td>\n",
       "      <td>0.494869</td>\n",
       "      <td>0.494869</td>\n",
       "      <td>0.481081</td>\n",
       "      <td>0.227392</td>\n",
       "      <td>0.210441</td>\n",
       "      <td>0.396286</td>\n",
       "      <td>0.250169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.137563</td>\n",
       "      <td>0.171875</td>\n",
       "      <td>0.404450</td>\n",
       "      <td>0.228346</td>\n",
       "      <td>0.250443</td>\n",
       "      <td>0.342673</td>\n",
       "      <td>0.388889</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.184673</td>\n",
       "      <td>0.257812</td>\n",
       "      <td>0.550297</td>\n",
       "      <td>0.422272</td>\n",
       "      <td>0.496598</td>\n",
       "      <td>0.449142</td>\n",
       "      <td>0.512195</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.376884</td>\n",
       "      <td>0.398438</td>\n",
       "      <td>0.643505</td>\n",
       "      <td>0.583830</td>\n",
       "      <td>0.675860</td>\n",
       "      <td>0.598197</td>\n",
       "      <td>0.617647</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            price  sq_meters_built   longitude  dist_city_center    latitude  \\\n",
       "count  970.000000       970.000000  970.000000        970.000000  970.000000   \n",
       "mean     0.278775         0.306258    0.530647          0.429441    0.488279   \n",
       "std      0.204398         0.199326    0.200919          0.234314    0.247501   \n",
       "min      0.000000         0.000000    0.000000          0.000000    0.000000   \n",
       "25%      0.137563         0.171875    0.404450          0.228346    0.250443   \n",
       "50%      0.184673         0.257812    0.550297          0.422272    0.496598   \n",
       "75%      0.376884         0.398438    0.643505          0.583830    0.675860   \n",
       "max      1.000000         1.000000    1.000000          1.000000    1.000000   \n",
       "\n",
       "       bathrooms_per_100_sqm  rooms_per_100_sqm  property_age_cat_encoded  \\\n",
       "count             970.000000         970.000000                970.000000   \n",
       "mean                0.476849           0.498464                  1.288660   \n",
       "std                 0.194325           0.174288                  1.694152   \n",
       "min                 0.000000           0.000000                 -1.000000   \n",
       "25%                 0.342673           0.388889                 -1.000000   \n",
       "50%                 0.449142           0.512195                  2.000000   \n",
       "75%                 0.598197           0.617647                  2.000000   \n",
       "max                 1.000000           1.000000                  5.000000   \n",
       "\n",
       "       neighborhood_rent_index_cluster_encoded    garage_0    garage_1  \\\n",
       "count                               970.000000  970.000000  970.000000   \n",
       "mean                                  2.182474    0.968041    0.031959   \n",
       "std                                   1.017241    0.175981    0.175981   \n",
       "min                                   1.000000    0.000000    0.000000   \n",
       "25%                                   1.000000    1.000000    0.000000   \n",
       "50%                                   2.000000    1.000000    0.000000   \n",
       "75%                                   3.000000    1.000000    0.000000   \n",
       "max                                   4.000000    1.000000    1.000000   \n",
       "\n",
       "         garden_0    garden_1      pool_0      pool_1   terrace_0   terrace_1  \\\n",
       "count  970.000000  970.000000  970.000000  970.000000  970.000000  970.000000   \n",
       "mean     0.997938    0.002062    0.986598    0.013402    0.790722    0.209278   \n",
       "std      0.045384    0.045384    0.115048    0.115048    0.407003    0.407003   \n",
       "min      0.000000    0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "50%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "75%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "max      1.000000    1.000000    1.000000    1.000000    1.000000    1.000000   \n",
       "\n",
       "       property_type_atico  property_type_chalet  \\\n",
       "count           970.000000            970.000000   \n",
       "mean              0.041237              0.002062   \n",
       "std               0.198941              0.045384   \n",
       "min               0.000000              0.000000   \n",
       "25%               0.000000              0.000000   \n",
       "50%               0.000000              0.000000   \n",
       "75%               0.000000              0.000000   \n",
       "max               1.000000              1.000000   \n",
       "\n",
       "       property_type_chalet_adosado  property_type_chalet_independiente  \\\n",
       "count                    970.000000                          970.000000   \n",
       "mean                       0.001031                            0.001031   \n",
       "std                        0.032108                            0.032108   \n",
       "min                        0.000000                            0.000000   \n",
       "25%                        0.000000                            0.000000   \n",
       "50%                        0.000000                            0.000000   \n",
       "75%                        0.000000                            0.000000   \n",
       "max                        1.000000                            1.000000   \n",
       "\n",
       "       property_type_chalet_pareado  property_type_duplex  \\\n",
       "count                    970.000000            970.000000   \n",
       "mean                       0.002062              0.010309   \n",
       "std                        0.045384              0.101062   \n",
       "min                        0.000000              0.000000   \n",
       "25%                        0.000000              0.000000   \n",
       "50%                        0.000000              0.000000   \n",
       "75%                        0.000000              0.000000   \n",
       "max                        1.000000              1.000000   \n",
       "\n",
       "       property_type_estudio  property_type_piso  elevator_0  elevator_1  \\\n",
       "count             970.000000          970.000000  970.000000  970.000000   \n",
       "mean                0.030928            0.911340    0.415464    0.584536   \n",
       "std                 0.173212            0.284399    0.493056    0.493056   \n",
       "min                 0.000000            0.000000    0.000000    0.000000   \n",
       "25%                 0.000000            1.000000    0.000000    0.000000   \n",
       "50%                 0.000000            1.000000    0.000000    1.000000   \n",
       "75%                 0.000000            1.000000    1.000000    1.000000   \n",
       "max                 1.000000            1.000000    1.000000    1.000000   \n",
       "\n",
       "             ac_0        ac_1  heating_Unknown  heating_bomba  \\\n",
       "count  970.000000  970.000000       970.000000     970.000000   \n",
       "mean     0.573196    0.426804         0.637113       0.054639   \n",
       "std      0.494869    0.494869         0.481081       0.227392   \n",
       "min      0.000000    0.000000         0.000000       0.000000   \n",
       "25%      0.000000    0.000000         0.000000       0.000000   \n",
       "50%      1.000000    0.000000         1.000000       0.000000   \n",
       "75%      1.000000    1.000000         1.000000       0.000000   \n",
       "max      1.000000    1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  \n",
       "count        970.000000   970.000000          970.000000  \n",
       "mean           0.046392     0.194845            0.067010  \n",
       "std            0.210441     0.396286            0.250169  \n",
       "min            0.000000     0.000000            0.000000  \n",
       "25%            0.000000     0.000000            0.000000  \n",
       "50%            0.000000     0.000000            0.000000  \n",
       "75%            0.000000     0.000000            0.000000  \n",
       "max            1.000000     1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 0\n"
     ]
    }
   ],
   "source": [
    "# creamos los datasets para el tercer modelo de Bagging y RF\n",
    "bagging_df3 = sales_simplified_df.copy(deep=True)\n",
    "bagging_df3_test = test_data_preprocessed.copy(deep=True)\n",
    "\n",
    "# lista contiene las variables que se consideran más importantes o informativas \n",
    "# para predecir el precio de la vivienda en Barcelona, según los diferentes métodos de análisis utilizados.\n",
    "good_predictors = [\"price\", # target variable\n",
    "                   \"sq_meters_built\", \"longitude\", \n",
    "                   \"dist_city_center\", \"latitude\", \"bathrooms_per_100_sqm\", \n",
    "                   \"rooms_per_100_sqm\", \"neighborhood_rent_index_cluster\",                    \n",
    "                   \"garage\", \"garden\", \"pool\", \"terrace\", \"property_type\", \n",
    "                   \"property_age_cat\", \"elevator\", \"ac\", \"heating\"]\n",
    "# nos quedamos sólo con las columnas indicadas en la lista good_predictors\n",
    "bagging_df3 = bagging_df3[good_predictors]\n",
    "bagging_df3_test = bagging_df3_test[good_predictors]\n",
    "\n",
    "# variables que queremos codificar usando ordinal encoder\n",
    "oe_cols = oe_cols = ['property_age_cat', 'neighborhood_rent_index_cluster']\n",
    "# Define the order of the categories for each column\n",
    "property_age_cat_order = ['Unknown', '0 - 40', '40 - 70', '70 - 120', '120 - 150', '+150']\n",
    "neighborhood_rent_index_cluster_order = ['Unknown', '0 - 2337', '2337 - 3371', '3371 - 5042', '+5042']\n",
    "# Create an instance of the ordinal encoder\n",
    "encoder = OrdinalEncoder(categories=[property_age_cat_order, \n",
    "                                     neighborhood_rent_index_cluster_order])\n",
    "\n",
    "for col in oe_cols:\n",
    "    # Create a new column name for the encoded data\n",
    "    new_col = col + '_encoded'\n",
    "    # Create an instance of the ordinal encoder\n",
    "    encoder = OrdinalEncoder(categories=[eval(col+'_order')])\n",
    "    # Fit and transform the selected columns\n",
    "    bagging_df3[new_col] = encoder.fit_transform(bagging_df3[[col]])\n",
    "    bagging_df3_test[new_col] = encoder.fit_transform(bagging_df3_test[[col]])\n",
    "    # replace 0 by -1 ('Unknown' by -1)\n",
    "    bagging_df3[new_col] = bagging_df3[new_col].replace(0, -1)\n",
    "    bagging_df3_test[new_col] = bagging_df3_test[new_col].replace(0, -1)\n",
    "\n",
    "# variables que queremos codificar usando OHE\n",
    "ohe_cols = [\"garage\", \"garden\", \"pool\", \n",
    "            \"terrace\", \"property_type\", \n",
    "            \"elevator\", \"ac\", \"heating\"]\n",
    "\n",
    "# aplicamos one - hot encoding al dataset\n",
    "bagging_df3 = one_hot_encode(bagging_df3, ohe_cols)\n",
    "bagging_df3_test = one_hot_encode(bagging_df3_test, ohe_cols)\n",
    "\n",
    "# eliminamos variables categóricas no codificadas\n",
    "no_encoded_cat_vars = bagging_df3.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df3.drop(no_encoded_cat_vars, axis=1, inplace=True)\n",
    "no_encoded_cat_vars_test = bagging_df3_test.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df3_test.drop(no_encoded_cat_vars_test, axis=1, inplace=True)\n",
    "\n",
    "\n",
    "############# Tratamos los outliers y escalamos los atributos numéricos: ###############\n",
    "num_vars = [\"price\", \"sq_meters_built\", \"longitude\", \"dist_city_center\", \"latitude\", \"bathrooms_per_100_sqm\", \"rooms_per_100_sqm\"]\n",
    "\n",
    "# define the preprocessing pipeline\n",
    "preprocessing_pipeline = Pipeline([\n",
    "    ('outlier_removal', OutlierRemover(cols=num_vars)),\n",
    "    ('scaler', ColumnTransformer([('num_scaler', MinMaxScaler(), num_vars)], \n",
    "                                 remainder='passthrough'))\n",
    "])\n",
    "\n",
    "# Apply the preprocessing pipeline to the training and testing data\n",
    "    # Fit and transform the training data\n",
    "bagging_df3 = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df3), columns=num_vars + list(bagging_df3.columns[len(num_vars):]))\n",
    "bagging_df3_test = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df3_test), columns=num_vars + list(bagging_df3_test.columns[len(num_vars):]))\n",
    "\n",
    "# exploración rápida del df\n",
    "print(\"TRAIN: \")\n",
    "explore_data(bagging_df3)\n",
    "print(\"\\n\\n\")\n",
    "print(\"TEST: \")\n",
    "explore_data(bagging_df3_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c242c67b",
   "metadata": {},
   "source": [
    "##### Model 3: Bagging & RF "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b3c843b",
   "metadata": {},
   "source": [
    "Una vez hemos hemos seleccionado las variables predictoras más importantes, hemos tratado los outliers y hemos escalado los atributos numéricos, vemos cómo se comportan los modelos:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1294,
   "id": "939f16b7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'model_name': 'BaggingRegressor',\n",
       "  'best_params': {'model__n_estimators': 200},\n",
       "  'train_r2_score': 0.982214048578808,\n",
       "  'test_r2_score': 0.8512093886379279},\n",
       " {'model_name': 'RandomForestRegressor',\n",
       "  'best_params': {'model__max_depth': 9,\n",
       "   'model__min_samples_split': 2,\n",
       "   'model__n_estimators': 200},\n",
       "  'train_r2_score': 0.9479322101359778,\n",
       "  'test_r2_score': 0.8462529129408495}]"
      ]
     },
     "execution_count": 1294,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create an instance of PipelineRunner\n",
    "pipeline_runner = PipelineRunner()\n",
    "# call the run_pipeline() method, passing in the dataframes and target variable name\n",
    "results_3 = pipeline_runner.run_pipeline(df_train=bagging_df3, \n",
    "                                         df_test=bagging_df3_test, \n",
    "                                         target=TARGET_VARIABLE)\n",
    "# examine the results for each model\n",
    "results_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 637,
   "id": "f4991d15",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.8708\n",
      "Train R^2 score: 0.9823\n",
      "Test R^2 score: 0.8525\n",
      "\n",
      "Model: RandomForestRegressor\n",
      "Best model parameters: {'model__max_depth': 9, 'model__min_samples_split': 2, 'model__n_estimators': 100}\n",
      "Best cross-validation R^2 score: 0.8618\n",
      "Train R^2 score: 0.9469\n",
      "Test R^2 score: 0.8451\n",
      "\n",
      "Best model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.8708\n",
      "Train R^2 score: 0.9823\n",
      "Test R^2 score: 0.8525\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'name': 'BaggingRegressor',\n",
       "  'best_params': {'model__n_estimators': 200},\n",
       "  'best_score': 0.8707953896715244,\n",
       "  'train_r2_score': 0.9822737024925415,\n",
       "  'test_r2_score': 0.8525076454575563},\n",
       " {'name': 'RandomForestRegressor',\n",
       "  'best_params': {'model__max_depth': 9,\n",
       "   'model__min_samples_split': 2,\n",
       "   'model__n_estimators': 100},\n",
       "  'best_score': 0.8618490056134946,\n",
       "  'train_r2_score': 0.9469431030838147,\n",
       "  'test_r2_score': 0.8451119639621244}]"
      ]
     },
     "execution_count": 637,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create an instance of PipelineRunner\n",
    "pipeline_runner = PipelineRunner()\n",
    "# call the run_pipeline() method, passing in the dataframes and target variable name\n",
    "results_3 = pipeline_runner.run_pipeline(df_train=bagging_df3, \n",
    "                                         df_test=bagging_df3_test, \n",
    "                                         target=TARGET_VARIABLE)\n",
    "# examine the results for each model\n",
    "results_3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 657,
   "id": "e32de696",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regressor</th>\n",
       "      <th>train_r2_score</th>\n",
       "      <th>test_r2_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BaggingRegressor_1</td>\n",
       "      <td>0.976685</td>\n",
       "      <td>0.739290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>RandomForestRegressor_1</td>\n",
       "      <td>0.939248</td>\n",
       "      <td>0.723103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>BaggingRegressor_2</td>\n",
       "      <td>0.970111</td>\n",
       "      <td>0.690796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>RandomForestRegressor_2</td>\n",
       "      <td>0.924524</td>\n",
       "      <td>0.674443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BaggingRegressor_3</td>\n",
       "      <td>0.982274</td>\n",
       "      <td>0.852508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>RandomForestRegressor_3</td>\n",
       "      <td>0.946943</td>\n",
       "      <td>0.845112</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 regressor  train_r2_score  test_r2_score\n",
       "0       BaggingRegressor_1        0.976685       0.739290\n",
       "1  RandomForestRegressor_1        0.939248       0.723103\n",
       "2       BaggingRegressor_2        0.970111       0.690796\n",
       "3  RandomForestRegressor_2        0.924524       0.674443\n",
       "4       BaggingRegressor_3        0.982274       0.852508\n",
       "5  RandomForestRegressor_3        0.946943       0.845112"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Loop through each model in results\n",
    "for model in results_3:\n",
    "    model_name = model['name']+'_3'\n",
    "    train_r2_score = model['train_r2_score']\n",
    "    test_r2_score = model['test_r2_score']\n",
    "    \n",
    "    # Append the results to the DataFrame\n",
    "    models_results_df = pd.concat([models_results_df, pd.DataFrame({'regressor': model_name, \n",
    "                                                                   'train_r2_score': train_r2_score,\n",
    "                                                                   'test_r2_score': test_r2_score},\n",
    "                                                                   index=[0])], ignore_index=True)\n",
    "# Display the DataFrame\n",
    "display(models_results_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "561ccad2",
   "metadata": {},
   "source": [
    "- Seleccionando las variables predictoras más importantes los modelos han funcionado mucho mejor."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d3dc5b2",
   "metadata": {},
   "source": [
    "##### Model 3.1: Bagging & RF (NO SCALING)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b108878",
   "metadata": {},
   "source": [
    "Escalar los atributos numéricos puede dificultar la interpretación de los resultados. Por tanto, probaremos el modelo anterior (Modelo 3) sin escalar los atributos numéricos. Si nos dá un resultado parecido en validación (o la diferencia no es significativa), nos quedaremos con el modelo sin estandarizar las variables, ya que será más fácil de interpertar. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 428,
   "id": "c5e420a7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAIN: \n",
      "The dataset includes 3914 instances (rows) and 34 variables (columns).\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n",
      "`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>90000</td>\n",
       "      <td>50</td>\n",
       "      <td>2.171110</td>\n",
       "      <td>5.189265</td>\n",
       "      <td>41.434545</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>145000</td>\n",
       "      <td>53</td>\n",
       "      <td>2.175309</td>\n",
       "      <td>6.313668</td>\n",
       "      <td>41.444518</td>\n",
       "      <td>1.886792</td>\n",
       "      <td>5.660377</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>675000</td>\n",
       "      <td>120</td>\n",
       "      <td>2.153368</td>\n",
       "      <td>1.462060</td>\n",
       "      <td>41.392209</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>3.333333</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>319000</td>\n",
       "      <td>69</td>\n",
       "      <td>2.162246</td>\n",
       "      <td>2.906147</td>\n",
       "      <td>41.413385</td>\n",
       "      <td>1.449275</td>\n",
       "      <td>4.347826</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>88000</td>\n",
       "      <td>64</td>\n",
       "      <td>2.155127</td>\n",
       "      <td>4.100012</td>\n",
       "      <td>41.423051</td>\n",
       "      <td>1.562500</td>\n",
       "      <td>3.125000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    price  sq_meters_built  longitude  dist_city_center   latitude  \\\n",
       "1   90000               50   2.171110          5.189265  41.434545   \n",
       "2  145000               53   2.175309          6.313668  41.444518   \n",
       "3  675000              120   2.153368          1.462060  41.392209   \n",
       "4  319000               69   2.162246          2.906147  41.413385   \n",
       "5   88000               64   2.155127          4.100012  41.423051   \n",
       "\n",
       "   bathrooms_per_100_sqm  rooms_per_100_sqm  property_age_cat_encoded  \\\n",
       "1               2.000000           2.000000                       2.0   \n",
       "2               1.886792           5.660377                      -1.0   \n",
       "3               1.666667           3.333333                       2.0   \n",
       "4               1.449275           4.347826                       3.0   \n",
       "5               1.562500           3.125000                       2.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  garage_0  garage_1  garden_0  \\\n",
       "1                                      1.0       1.0       0.0       1.0   \n",
       "2                                      1.0       1.0       0.0       1.0   \n",
       "3                                      3.0       1.0       0.0       1.0   \n",
       "4                                      3.0       1.0       0.0       1.0   \n",
       "5                                      1.0       1.0       0.0       1.0   \n",
       "\n",
       "   garden_1  pool_0  pool_1  terrace_0  terrace_1  property_type_atico  \\\n",
       "1       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "2       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "3       0.0     1.0     0.0        0.0        1.0                  1.0   \n",
       "4       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "5       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "4                   0.0                           0.0   \n",
       "5                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "4                                 0.0                           0.0   \n",
       "5                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "1                   0.0                    0.0                 1.0   \n",
       "2                   0.0                    0.0                 1.0   \n",
       "3                   0.0                    0.0                 0.0   \n",
       "4                   0.0                    0.0                 1.0   \n",
       "5                   0.0                    0.0                 1.0   \n",
       "\n",
       "   elevator_0  elevator_1  ac_0  ac_1  heating_Unknown  heating_bomba  \\\n",
       "1         0.0         1.0   0.0   1.0              0.0            1.0   \n",
       "2         1.0         0.0   1.0   0.0              1.0            0.0   \n",
       "3         0.0         1.0   0.0   1.0              0.0            0.0   \n",
       "4         0.0         1.0   1.0   0.0              1.0            0.0   \n",
       "5         1.0         0.0   1.0   0.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  \n",
       "1               0.0          0.0                 0.0  \n",
       "2               0.0          0.0                 0.0  \n",
       "3               0.0          0.0                 1.0  \n",
       "4               0.0          0.0                 0.0  \n",
       "5               0.0          0.0                 0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 3914 entries, 1 to 4673\n",
      "Data columns (total 34 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    3914 non-null   int64  \n",
      " 1   sq_meters_built                          3914 non-null   int64  \n",
      " 2   longitude                                3914 non-null   float64\n",
      " 3   dist_city_center                         3914 non-null   float64\n",
      " 4   latitude                                 3914 non-null   float64\n",
      " 5   bathrooms_per_100_sqm                    3914 non-null   float64\n",
      " 6   rooms_per_100_sqm                        3914 non-null   float64\n",
      " 7   property_age_cat_encoded                 3914 non-null   float64\n",
      " 8   neighborhood_rent_index_cluster_encoded  3914 non-null   float64\n",
      " 9   garage_0                                 3914 non-null   float64\n",
      " 10  garage_1                                 3914 non-null   float64\n",
      " 11  garden_0                                 3914 non-null   float64\n",
      " 12  garden_1                                 3914 non-null   float64\n",
      " 13  pool_0                                   3914 non-null   float64\n",
      " 14  pool_1                                   3914 non-null   float64\n",
      " 15  terrace_0                                3914 non-null   float64\n",
      " 16  terrace_1                                3914 non-null   float64\n",
      " 17  property_type_atico                      3914 non-null   float64\n",
      " 18  property_type_chalet                     3914 non-null   float64\n",
      " 19  property_type_chalet_adosado             3914 non-null   float64\n",
      " 20  property_type_chalet_independiente       3914 non-null   float64\n",
      " 21  property_type_chalet_pareado             3914 non-null   float64\n",
      " 22  property_type_duplex                     3914 non-null   float64\n",
      " 23  property_type_estudio                    3914 non-null   float64\n",
      " 24  property_type_piso                       3914 non-null   float64\n",
      " 25  elevator_0                               3914 non-null   float64\n",
      " 26  elevator_1                               3914 non-null   float64\n",
      " 27  ac_0                                     3914 non-null   float64\n",
      " 28  ac_1                                     3914 non-null   float64\n",
      " 29  heating_Unknown                          3914 non-null   float64\n",
      " 30  heating_bomba                            3914 non-null   float64\n",
      " 31  heating_electric                         3914 non-null   float64\n",
      " 32  heating_gas                              3914 non-null   float64\n",
      " 33  heating_individual                       3914 non-null   float64\n",
      "dtypes: float64(32), int64(2)\n",
      "memory usage: 1.0 MB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "sq_meters_built                            0\n",
      "longitude                                  0\n",
      "dist_city_center                           0\n",
      "latitude                                   0\n",
      "bathrooms_per_100_sqm                      0\n",
      "rooms_per_100_sqm                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "      <td>3914.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>234866.117016</td>\n",
       "      <td>70.339806</td>\n",
       "      <td>2.170552</td>\n",
       "      <td>3.703994</td>\n",
       "      <td>41.408867</td>\n",
       "      <td>1.781512</td>\n",
       "      <td>3.583683</td>\n",
       "      <td>1.296883</td>\n",
       "      <td>2.045989</td>\n",
       "      <td>0.970363</td>\n",
       "      <td>0.029637</td>\n",
       "      <td>0.999234</td>\n",
       "      <td>0.000766</td>\n",
       "      <td>0.991824</td>\n",
       "      <td>0.008176</td>\n",
       "      <td>0.811957</td>\n",
       "      <td>0.188043</td>\n",
       "      <td>0.041901</td>\n",
       "      <td>0.001022</td>\n",
       "      <td>0.002044</td>\n",
       "      <td>0.001022</td>\n",
       "      <td>0.002044</td>\n",
       "      <td>0.013797</td>\n",
       "      <td>0.028871</td>\n",
       "      <td>0.909300</td>\n",
       "      <td>0.457333</td>\n",
       "      <td>0.542667</td>\n",
       "      <td>0.591722</td>\n",
       "      <td>0.408278</td>\n",
       "      <td>0.616505</td>\n",
       "      <td>0.059019</td>\n",
       "      <td>0.040112</td>\n",
       "      <td>0.213337</td>\n",
       "      <td>0.071027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>145324.083035</td>\n",
       "      <td>22.493365</td>\n",
       "      <td>0.021631</td>\n",
       "      <td>2.052572</td>\n",
       "      <td>0.027322</td>\n",
       "      <td>0.463591</td>\n",
       "      <td>1.245189</td>\n",
       "      <td>1.716043</td>\n",
       "      <td>0.983602</td>\n",
       "      <td>0.169606</td>\n",
       "      <td>0.169606</td>\n",
       "      <td>0.027678</td>\n",
       "      <td>0.027678</td>\n",
       "      <td>0.090061</td>\n",
       "      <td>0.090061</td>\n",
       "      <td>0.390796</td>\n",
       "      <td>0.390796</td>\n",
       "      <td>0.200388</td>\n",
       "      <td>0.031956</td>\n",
       "      <td>0.045170</td>\n",
       "      <td>0.031956</td>\n",
       "      <td>0.045170</td>\n",
       "      <td>0.116661</td>\n",
       "      <td>0.167465</td>\n",
       "      <td>0.287219</td>\n",
       "      <td>0.498240</td>\n",
       "      <td>0.498240</td>\n",
       "      <td>0.491578</td>\n",
       "      <td>0.491578</td>\n",
       "      <td>0.486299</td>\n",
       "      <td>0.235690</td>\n",
       "      <td>0.196248</td>\n",
       "      <td>0.409716</td>\n",
       "      <td>0.256903</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>28000.000000</td>\n",
       "      <td>33.000000</td>\n",
       "      <td>2.112805</td>\n",
       "      <td>0.075001</td>\n",
       "      <td>41.355002</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>134125.000000</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>2.156207</td>\n",
       "      <td>1.891978</td>\n",
       "      <td>41.382083</td>\n",
       "      <td>1.449275</td>\n",
       "      <td>2.816901</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>159000.000000</td>\n",
       "      <td>66.000000</td>\n",
       "      <td>2.172256</td>\n",
       "      <td>3.655316</td>\n",
       "      <td>41.409703</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>3.750000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>314750.000000</td>\n",
       "      <td>81.000000</td>\n",
       "      <td>2.182131</td>\n",
       "      <td>5.080628</td>\n",
       "      <td>41.430499</td>\n",
       "      <td>2.040816</td>\n",
       "      <td>4.444444</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>770000.000000</td>\n",
       "      <td>147.000000</td>\n",
       "      <td>2.220785</td>\n",
       "      <td>8.627149</td>\n",
       "      <td>41.465303</td>\n",
       "      <td>3.030303</td>\n",
       "      <td>7.142857</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               price  sq_meters_built    longitude  dist_city_center  \\\n",
       "count    3914.000000      3914.000000  3914.000000       3914.000000   \n",
       "mean   234866.117016        70.339806     2.170552          3.703994   \n",
       "std    145324.083035        22.493365     0.021631          2.052572   \n",
       "min     28000.000000        33.000000     2.112805          0.075001   \n",
       "25%    134125.000000        55.000000     2.156207          1.891978   \n",
       "50%    159000.000000        66.000000     2.172256          3.655316   \n",
       "75%    314750.000000        81.000000     2.182131          5.080628   \n",
       "max    770000.000000       147.000000     2.220785          8.627149   \n",
       "\n",
       "          latitude  bathrooms_per_100_sqm  rooms_per_100_sqm  \\\n",
       "count  3914.000000            3914.000000        3914.000000   \n",
       "mean     41.408867               1.781512           3.583683   \n",
       "std       0.027322               0.463591           1.245189   \n",
       "min      41.355002               0.714286           0.000000   \n",
       "25%      41.382083               1.449275           2.816901   \n",
       "50%      41.409703               1.666667           3.750000   \n",
       "75%      41.430499               2.040816           4.444444   \n",
       "max      41.465303               3.030303           7.142857   \n",
       "\n",
       "       property_age_cat_encoded  neighborhood_rent_index_cluster_encoded  \\\n",
       "count               3914.000000                              3914.000000   \n",
       "mean                   1.296883                                 2.045989   \n",
       "std                    1.716043                                 0.983602   \n",
       "min                   -1.000000                                 1.000000   \n",
       "25%                   -1.000000                                 1.000000   \n",
       "50%                    2.000000                                 2.000000   \n",
       "75%                    2.000000                                 3.000000   \n",
       "max                    5.000000                                 4.000000   \n",
       "\n",
       "          garage_0     garage_1     garden_0     garden_1       pool_0  \\\n",
       "count  3914.000000  3914.000000  3914.000000  3914.000000  3914.000000   \n",
       "mean      0.970363     0.029637     0.999234     0.000766     0.991824   \n",
       "std       0.169606     0.169606     0.027678     0.027678     0.090061   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "25%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "50%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "75%       1.000000     0.000000     1.000000     0.000000     1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000     1.000000   \n",
       "\n",
       "            pool_1    terrace_0    terrace_1  property_type_atico  \\\n",
       "count  3914.000000  3914.000000  3914.000000          3914.000000   \n",
       "mean      0.008176     0.811957     0.188043             0.041901   \n",
       "std       0.090061     0.390796     0.390796             0.200388   \n",
       "min       0.000000     0.000000     0.000000             0.000000   \n",
       "25%       0.000000     1.000000     0.000000             0.000000   \n",
       "50%       0.000000     1.000000     0.000000             0.000000   \n",
       "75%       0.000000     1.000000     0.000000             0.000000   \n",
       "max       1.000000     1.000000     1.000000             1.000000   \n",
       "\n",
       "       property_type_chalet  property_type_chalet_adosado  \\\n",
       "count           3914.000000                   3914.000000   \n",
       "mean               0.001022                      0.002044   \n",
       "std                0.031956                      0.045170   \n",
       "min                0.000000                      0.000000   \n",
       "25%                0.000000                      0.000000   \n",
       "50%                0.000000                      0.000000   \n",
       "75%                0.000000                      0.000000   \n",
       "max                1.000000                      1.000000   \n",
       "\n",
       "       property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "count                         3914.000000                   3914.000000   \n",
       "mean                             0.001022                      0.002044   \n",
       "std                              0.031956                      0.045170   \n",
       "min                              0.000000                      0.000000   \n",
       "25%                              0.000000                      0.000000   \n",
       "50%                              0.000000                      0.000000   \n",
       "75%                              0.000000                      0.000000   \n",
       "max                              1.000000                      1.000000   \n",
       "\n",
       "       property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "count           3914.000000            3914.000000         3914.000000   \n",
       "mean               0.013797               0.028871            0.909300   \n",
       "std                0.116661               0.167465            0.287219   \n",
       "min                0.000000               0.000000            0.000000   \n",
       "25%                0.000000               0.000000            1.000000   \n",
       "50%                0.000000               0.000000            1.000000   \n",
       "75%                0.000000               0.000000            1.000000   \n",
       "max                1.000000               1.000000            1.000000   \n",
       "\n",
       "        elevator_0   elevator_1         ac_0         ac_1  heating_Unknown  \\\n",
       "count  3914.000000  3914.000000  3914.000000  3914.000000      3914.000000   \n",
       "mean      0.457333     0.542667     0.591722     0.408278         0.616505   \n",
       "std       0.498240     0.498240     0.491578     0.491578         0.486299   \n",
       "min       0.000000     0.000000     0.000000     0.000000         0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000         0.000000   \n",
       "50%       0.000000     1.000000     1.000000     0.000000         1.000000   \n",
       "75%       1.000000     1.000000     1.000000     1.000000         1.000000   \n",
       "max       1.000000     1.000000     1.000000     1.000000         1.000000   \n",
       "\n",
       "       heating_bomba  heating_electric  heating_gas  heating_individual  \n",
       "count    3914.000000       3914.000000  3914.000000         3914.000000  \n",
       "mean        0.059019          0.040112     0.213337            0.071027  \n",
       "std         0.235690          0.196248     0.409716            0.256903  \n",
       "min         0.000000          0.000000     0.000000            0.000000  \n",
       "25%         0.000000          0.000000     0.000000            0.000000  \n",
       "50%         0.000000          0.000000     0.000000            0.000000  \n",
       "75%         0.000000          0.000000     0.000000            0.000000  \n",
       "max         1.000000          1.000000     1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 3\n",
      "\n",
      "\n",
      "\n",
      "TEST: \n",
      "The dataset includes 970 instances (rows) and 34 variables (columns).\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>133000</td>\n",
       "      <td>76</td>\n",
       "      <td>2.213120</td>\n",
       "      <td>5.158288</td>\n",
       "      <td>41.421077</td>\n",
       "      <td>1.315789</td>\n",
       "      <td>3.947368</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>485000</td>\n",
       "      <td>130</td>\n",
       "      <td>2.152472</td>\n",
       "      <td>1.657143</td>\n",
       "      <td>41.380788</td>\n",
       "      <td>1.538462</td>\n",
       "      <td>3.076923</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>265000</td>\n",
       "      <td>77</td>\n",
       "      <td>2.183533</td>\n",
       "      <td>2.389801</td>\n",
       "      <td>41.406803</td>\n",
       "      <td>1.298701</td>\n",
       "      <td>3.896104</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>154500</td>\n",
       "      <td>61</td>\n",
       "      <td>2.172277</td>\n",
       "      <td>5.119194</td>\n",
       "      <td>41.433890</td>\n",
       "      <td>1.639344</td>\n",
       "      <td>3.278689</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>136000</td>\n",
       "      <td>68</td>\n",
       "      <td>2.172432</td>\n",
       "      <td>1.771000</td>\n",
       "      <td>41.372090</td>\n",
       "      <td>1.470588</td>\n",
       "      <td>4.411765</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    price  sq_meters_built  longitude  dist_city_center   latitude  \\\n",
       "0  133000               76   2.213120          5.158288  41.421077   \n",
       "1  485000              130   2.152472          1.657143  41.380788   \n",
       "2  265000               77   2.183533          2.389801  41.406803   \n",
       "3  154500               61   2.172277          5.119194  41.433890   \n",
       "6  136000               68   2.172432          1.771000  41.372090   \n",
       "\n",
       "   bathrooms_per_100_sqm  rooms_per_100_sqm  property_age_cat_encoded  \\\n",
       "0               1.315789           3.947368                       2.0   \n",
       "1               1.538462           3.076923                       3.0   \n",
       "2               1.298701           3.896104                       2.0   \n",
       "3               1.639344           3.278689                       2.0   \n",
       "6               1.470588           4.411765                       2.0   \n",
       "\n",
       "   neighborhood_rent_index_cluster_encoded  garage_0  garage_1  garden_0  \\\n",
       "0                                      2.0       1.0       0.0       1.0   \n",
       "1                                      3.0       1.0       0.0       1.0   \n",
       "2                                      3.0       1.0       0.0       1.0   \n",
       "3                                      2.0       1.0       0.0       1.0   \n",
       "6                                      1.0       0.0       1.0       1.0   \n",
       "\n",
       "   garden_1  pool_0  pool_1  terrace_0  terrace_1  property_type_atico  \\\n",
       "0       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "1       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "2       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "3       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "6       0.0     1.0     0.0        1.0        0.0                  0.0   \n",
       "\n",
       "   property_type_chalet  property_type_chalet_adosado  \\\n",
       "0                   0.0                           0.0   \n",
       "1                   0.0                           0.0   \n",
       "2                   0.0                           0.0   \n",
       "3                   0.0                           0.0   \n",
       "6                   0.0                           0.0   \n",
       "\n",
       "   property_type_chalet_independiente  property_type_chalet_pareado  \\\n",
       "0                                 0.0                           0.0   \n",
       "1                                 0.0                           0.0   \n",
       "2                                 0.0                           0.0   \n",
       "3                                 0.0                           0.0   \n",
       "6                                 0.0                           0.0   \n",
       "\n",
       "   property_type_duplex  property_type_estudio  property_type_piso  \\\n",
       "0                   0.0                    0.0                 1.0   \n",
       "1                   0.0                    0.0                 1.0   \n",
       "2                   0.0                    0.0                 1.0   \n",
       "3                   0.0                    0.0                 1.0   \n",
       "6                   0.0                    0.0                 1.0   \n",
       "\n",
       "   elevator_0  elevator_1  ac_0  ac_1  heating_Unknown  heating_bomba  \\\n",
       "0         0.0         1.0   1.0   0.0              0.0            0.0   \n",
       "1         0.0         1.0   1.0   0.0              1.0            0.0   \n",
       "2         0.0         1.0   0.0   1.0              1.0            0.0   \n",
       "3         0.0         1.0   1.0   0.0              0.0            0.0   \n",
       "6         1.0         0.0   0.0   1.0              1.0            0.0   \n",
       "\n",
       "   heating_electric  heating_gas  heating_individual  \n",
       "0               0.0          1.0                 0.0  \n",
       "1               0.0          0.0                 0.0  \n",
       "2               0.0          0.0                 0.0  \n",
       "3               0.0          1.0                 0.0  \n",
       "6               0.0          0.0                 0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 970 entries, 0 to 1169\n",
      "Data columns (total 34 columns):\n",
      " #   Column                                   Non-Null Count  Dtype  \n",
      "---  ------                                   --------------  -----  \n",
      " 0   price                                    970 non-null    int64  \n",
      " 1   sq_meters_built                          970 non-null    int64  \n",
      " 2   longitude                                970 non-null    float64\n",
      " 3   dist_city_center                         970 non-null    float64\n",
      " 4   latitude                                 970 non-null    float64\n",
      " 5   bathrooms_per_100_sqm                    970 non-null    float64\n",
      " 6   rooms_per_100_sqm                        970 non-null    float64\n",
      " 7   property_age_cat_encoded                 970 non-null    float64\n",
      " 8   neighborhood_rent_index_cluster_encoded  970 non-null    float64\n",
      " 9   garage_0                                 970 non-null    float64\n",
      " 10  garage_1                                 970 non-null    float64\n",
      " 11  garden_0                                 970 non-null    float64\n",
      " 12  garden_1                                 970 non-null    float64\n",
      " 13  pool_0                                   970 non-null    float64\n",
      " 14  pool_1                                   970 non-null    float64\n",
      " 15  terrace_0                                970 non-null    float64\n",
      " 16  terrace_1                                970 non-null    float64\n",
      " 17  property_type_atico                      970 non-null    float64\n",
      " 18  property_type_chalet                     970 non-null    float64\n",
      " 19  property_type_chalet_adosado             970 non-null    float64\n",
      " 20  property_type_chalet_independiente       970 non-null    float64\n",
      " 21  property_type_chalet_pareado             970 non-null    float64\n",
      " 22  property_type_duplex                     970 non-null    float64\n",
      " 23  property_type_estudio                    970 non-null    float64\n",
      " 24  property_type_piso                       970 non-null    float64\n",
      " 25  elevator_0                               970 non-null    float64\n",
      " 26  elevator_1                               970 non-null    float64\n",
      " 27  ac_0                                     970 non-null    float64\n",
      " 28  ac_1                                     970 non-null    float64\n",
      " 29  heating_Unknown                          970 non-null    float64\n",
      " 30  heating_bomba                            970 non-null    float64\n",
      " 31  heating_electric                         970 non-null    float64\n",
      " 32  heating_gas                              970 non-null    float64\n",
      " 33  heating_individual                       970 non-null    float64\n",
      "dtypes: float64(32), int64(2)\n",
      "memory usage: 265.2 KB\n",
      "None\n",
      "\n",
      "\n",
      "Missing values: \n",
      "price                                      0\n",
      "sq_meters_built                            0\n",
      "longitude                                  0\n",
      "dist_city_center                           0\n",
      "latitude                                   0\n",
      "bathrooms_per_100_sqm                      0\n",
      "rooms_per_100_sqm                          0\n",
      "property_age_cat_encoded                   0\n",
      "neighborhood_rent_index_cluster_encoded    0\n",
      "garage_0                                   0\n",
      "garage_1                                   0\n",
      "garden_0                                   0\n",
      "garden_1                                   0\n",
      "pool_0                                     0\n",
      "pool_1                                     0\n",
      "terrace_0                                  0\n",
      "terrace_1                                  0\n",
      "property_type_atico                        0\n",
      "property_type_chalet                       0\n",
      "property_type_chalet_adosado               0\n",
      "property_type_chalet_independiente         0\n",
      "property_type_chalet_pareado               0\n",
      "property_type_duplex                       0\n",
      "property_type_estudio                      0\n",
      "property_type_piso                         0\n",
      "elevator_0                                 0\n",
      "elevator_1                                 0\n",
      "ac_0                                       0\n",
      "ac_1                                       0\n",
      "heating_Unknown                            0\n",
      "heating_bomba                              0\n",
      "heating_electric                           0\n",
      "heating_gas                                0\n",
      "heating_individual                         0\n",
      "dtype: int64\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>price</th>\n",
       "      <th>sq_meters_built</th>\n",
       "      <th>longitude</th>\n",
       "      <th>dist_city_center</th>\n",
       "      <th>latitude</th>\n",
       "      <th>bathrooms_per_100_sqm</th>\n",
       "      <th>rooms_per_100_sqm</th>\n",
       "      <th>property_age_cat_encoded</th>\n",
       "      <th>neighborhood_rent_index_cluster_encoded</th>\n",
       "      <th>garage_0</th>\n",
       "      <th>garage_1</th>\n",
       "      <th>garden_0</th>\n",
       "      <th>garden_1</th>\n",
       "      <th>pool_0</th>\n",
       "      <th>pool_1</th>\n",
       "      <th>terrace_0</th>\n",
       "      <th>terrace_1</th>\n",
       "      <th>property_type_atico</th>\n",
       "      <th>property_type_chalet</th>\n",
       "      <th>property_type_chalet_adosado</th>\n",
       "      <th>property_type_chalet_independiente</th>\n",
       "      <th>property_type_chalet_pareado</th>\n",
       "      <th>property_type_duplex</th>\n",
       "      <th>property_type_estudio</th>\n",
       "      <th>property_type_piso</th>\n",
       "      <th>elevator_0</th>\n",
       "      <th>elevator_1</th>\n",
       "      <th>ac_0</th>\n",
       "      <th>ac_1</th>\n",
       "      <th>heating_Unknown</th>\n",
       "      <th>heating_bomba</th>\n",
       "      <th>heating_electric</th>\n",
       "      <th>heating_gas</th>\n",
       "      <th>heating_individual</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "      <td>970.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>250904.920619</td>\n",
       "      <td>74.201031</td>\n",
       "      <td>2.169021</td>\n",
       "      <td>3.702115</td>\n",
       "      <td>41.408462</td>\n",
       "      <td>1.728628</td>\n",
       "      <td>3.560459</td>\n",
       "      <td>1.288660</td>\n",
       "      <td>2.182474</td>\n",
       "      <td>0.968041</td>\n",
       "      <td>0.031959</td>\n",
       "      <td>0.997938</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.986598</td>\n",
       "      <td>0.013402</td>\n",
       "      <td>0.790722</td>\n",
       "      <td>0.209278</td>\n",
       "      <td>0.041237</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.001031</td>\n",
       "      <td>0.001031</td>\n",
       "      <td>0.002062</td>\n",
       "      <td>0.010309</td>\n",
       "      <td>0.030928</td>\n",
       "      <td>0.911340</td>\n",
       "      <td>0.415464</td>\n",
       "      <td>0.584536</td>\n",
       "      <td>0.573196</td>\n",
       "      <td>0.426804</td>\n",
       "      <td>0.637113</td>\n",
       "      <td>0.054639</td>\n",
       "      <td>0.046392</td>\n",
       "      <td>0.194845</td>\n",
       "      <td>0.067010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>162700.963515</td>\n",
       "      <td>25.513666</td>\n",
       "      <td>0.021966</td>\n",
       "      <td>1.979443</td>\n",
       "      <td>0.027026</td>\n",
       "      <td>0.434568</td>\n",
       "      <td>1.244912</td>\n",
       "      <td>1.694152</td>\n",
       "      <td>1.017241</td>\n",
       "      <td>0.175981</td>\n",
       "      <td>0.175981</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.115048</td>\n",
       "      <td>0.115048</td>\n",
       "      <td>0.407003</td>\n",
       "      <td>0.407003</td>\n",
       "      <td>0.198941</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.032108</td>\n",
       "      <td>0.032108</td>\n",
       "      <td>0.045384</td>\n",
       "      <td>0.101062</td>\n",
       "      <td>0.173212</td>\n",
       "      <td>0.284399</td>\n",
       "      <td>0.493056</td>\n",
       "      <td>0.493056</td>\n",
       "      <td>0.494869</td>\n",
       "      <td>0.494869</td>\n",
       "      <td>0.481081</td>\n",
       "      <td>0.227392</td>\n",
       "      <td>0.210441</td>\n",
       "      <td>0.396286</td>\n",
       "      <td>0.250169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>29000.000000</td>\n",
       "      <td>35.000000</td>\n",
       "      <td>2.111006</td>\n",
       "      <td>0.074264</td>\n",
       "      <td>41.355143</td>\n",
       "      <td>0.662252</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>138500.000000</td>\n",
       "      <td>57.000000</td>\n",
       "      <td>2.155224</td>\n",
       "      <td>2.003293</td>\n",
       "      <td>41.382491</td>\n",
       "      <td>1.428571</td>\n",
       "      <td>2.777778</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>176000.000000</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>2.171169</td>\n",
       "      <td>3.641553</td>\n",
       "      <td>41.409370</td>\n",
       "      <td>1.666667</td>\n",
       "      <td>3.658537</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>329000.000000</td>\n",
       "      <td>86.000000</td>\n",
       "      <td>2.181359</td>\n",
       "      <td>5.006365</td>\n",
       "      <td>41.428945</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.411765</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>825000.000000</td>\n",
       "      <td>163.000000</td>\n",
       "      <td>2.220334</td>\n",
       "      <td>8.522102</td>\n",
       "      <td>41.464340</td>\n",
       "      <td>2.898551</td>\n",
       "      <td>7.142857</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               price  sq_meters_built   longitude  dist_city_center  \\\n",
       "count     970.000000       970.000000  970.000000        970.000000   \n",
       "mean   250904.920619        74.201031    2.169021          3.702115   \n",
       "std    162700.963515        25.513666    0.021966          1.979443   \n",
       "min     29000.000000        35.000000    2.111006          0.074264   \n",
       "25%    138500.000000        57.000000    2.155224          2.003293   \n",
       "50%    176000.000000        68.000000    2.171169          3.641553   \n",
       "75%    329000.000000        86.000000    2.181359          5.006365   \n",
       "max    825000.000000       163.000000    2.220334          8.522102   \n",
       "\n",
       "         latitude  bathrooms_per_100_sqm  rooms_per_100_sqm  \\\n",
       "count  970.000000             970.000000         970.000000   \n",
       "mean    41.408462               1.728628           3.560459   \n",
       "std      0.027026               0.434568           1.244912   \n",
       "min     41.355143               0.662252           0.000000   \n",
       "25%     41.382491               1.428571           2.777778   \n",
       "50%     41.409370               1.666667           3.658537   \n",
       "75%     41.428945               2.000000           4.411765   \n",
       "max     41.464340               2.898551           7.142857   \n",
       "\n",
       "       property_age_cat_encoded  neighborhood_rent_index_cluster_encoded  \\\n",
       "count                970.000000                               970.000000   \n",
       "mean                   1.288660                                 2.182474   \n",
       "std                    1.694152                                 1.017241   \n",
       "min                   -1.000000                                 1.000000   \n",
       "25%                   -1.000000                                 1.000000   \n",
       "50%                    2.000000                                 2.000000   \n",
       "75%                    2.000000                                 3.000000   \n",
       "max                    5.000000                                 4.000000   \n",
       "\n",
       "         garage_0    garage_1    garden_0    garden_1      pool_0      pool_1  \\\n",
       "count  970.000000  970.000000  970.000000  970.000000  970.000000  970.000000   \n",
       "mean     0.968041    0.031959    0.997938    0.002062    0.986598    0.013402   \n",
       "std      0.175981    0.175981    0.045384    0.045384    0.115048    0.115048   \n",
       "min      0.000000    0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "50%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "75%      1.000000    0.000000    1.000000    0.000000    1.000000    0.000000   \n",
       "max      1.000000    1.000000    1.000000    1.000000    1.000000    1.000000   \n",
       "\n",
       "        terrace_0   terrace_1  property_type_atico  property_type_chalet  \\\n",
       "count  970.000000  970.000000           970.000000            970.000000   \n",
       "mean     0.790722    0.209278             0.041237              0.002062   \n",
       "std      0.407003    0.407003             0.198941              0.045384   \n",
       "min      0.000000    0.000000             0.000000              0.000000   \n",
       "25%      1.000000    0.000000             0.000000              0.000000   \n",
       "50%      1.000000    0.000000             0.000000              0.000000   \n",
       "75%      1.000000    0.000000             0.000000              0.000000   \n",
       "max      1.000000    1.000000             1.000000              1.000000   \n",
       "\n",
       "       property_type_chalet_adosado  property_type_chalet_independiente  \\\n",
       "count                    970.000000                          970.000000   \n",
       "mean                       0.001031                            0.001031   \n",
       "std                        0.032108                            0.032108   \n",
       "min                        0.000000                            0.000000   \n",
       "25%                        0.000000                            0.000000   \n",
       "50%                        0.000000                            0.000000   \n",
       "75%                        0.000000                            0.000000   \n",
       "max                        1.000000                            1.000000   \n",
       "\n",
       "       property_type_chalet_pareado  property_type_duplex  \\\n",
       "count                    970.000000            970.000000   \n",
       "mean                       0.002062              0.010309   \n",
       "std                        0.045384              0.101062   \n",
       "min                        0.000000              0.000000   \n",
       "25%                        0.000000              0.000000   \n",
       "50%                        0.000000              0.000000   \n",
       "75%                        0.000000              0.000000   \n",
       "max                        1.000000              1.000000   \n",
       "\n",
       "       property_type_estudio  property_type_piso  elevator_0  elevator_1  \\\n",
       "count             970.000000          970.000000  970.000000  970.000000   \n",
       "mean                0.030928            0.911340    0.415464    0.584536   \n",
       "std                 0.173212            0.284399    0.493056    0.493056   \n",
       "min                 0.000000            0.000000    0.000000    0.000000   \n",
       "25%                 0.000000            1.000000    0.000000    0.000000   \n",
       "50%                 0.000000            1.000000    0.000000    1.000000   \n",
       "75%                 0.000000            1.000000    1.000000    1.000000   \n",
       "max                 1.000000            1.000000    1.000000    1.000000   \n",
       "\n",
       "             ac_0        ac_1  heating_Unknown  heating_bomba  \\\n",
       "count  970.000000  970.000000       970.000000     970.000000   \n",
       "mean     0.573196    0.426804         0.637113       0.054639   \n",
       "std      0.494869    0.494869         0.481081       0.227392   \n",
       "min      0.000000    0.000000         0.000000       0.000000   \n",
       "25%      0.000000    0.000000         0.000000       0.000000   \n",
       "50%      1.000000    0.000000         1.000000       0.000000   \n",
       "75%      1.000000    1.000000         1.000000       0.000000   \n",
       "max      1.000000    1.000000         1.000000       1.000000   \n",
       "\n",
       "       heating_electric  heating_gas  heating_individual  \n",
       "count        970.000000   970.000000          970.000000  \n",
       "mean           0.046392     0.194845            0.067010  \n",
       "std            0.210441     0.396286            0.250169  \n",
       "min            0.000000     0.000000            0.000000  \n",
       "25%            0.000000     0.000000            0.000000  \n",
       "50%            0.000000     0.000000            0.000000  \n",
       "75%            0.000000     0.000000            0.000000  \n",
       "max            1.000000     1.000000            1.000000  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Number of duplicates: 0\n"
     ]
    }
   ],
   "source": [
    "# creamos los datasets para el tercer modelo de Bagging y RF\n",
    "bagging_df3 = sales_simplified_df.copy(deep=True)\n",
    "bagging_df3_test = test_data_preprocessed.copy(deep=True)\n",
    "\n",
    "# lista contiene las variables que se consideran más importantes o informativas \n",
    "# para predecir el precio de la vivienda en Barcelona, según los diferentes métodos de análisis utilizados.\n",
    "good_predictors = [\"price\", # target variable\n",
    "                   \"sq_meters_built\", \"longitude\", \n",
    "                   \"dist_city_center\", \"latitude\", \"bathrooms_per_100_sqm\", \n",
    "                   \"rooms_per_100_sqm\", \"neighborhood_rent_index_cluster\",                    \n",
    "                   \"garage\", \"garden\", \"pool\", \"terrace\", \"property_type\", \n",
    "                   \"property_age_cat\", \"elevator\", \"ac\", \"heating\"]\n",
    "# nos quedamos sólo con las columnas indicadas en la lista good_predictors\n",
    "bagging_df3 = bagging_df3[good_predictors]\n",
    "bagging_df3_test = bagging_df3_test[good_predictors]\n",
    "\n",
    "# variables que queremos codificar usando ordinal encoder\n",
    "oe_cols = oe_cols = ['property_age_cat', 'neighborhood_rent_index_cluster']\n",
    "# Define the order of the categories for each column\n",
    "property_age_cat_order = ['Unknown', '0 - 40', '40 - 70', '70 - 120', '120 - 150', '+150']\n",
    "neighborhood_rent_index_cluster_order = ['Unknown', '0 - 2337', '2337 - 3371', '3371 - 5042', '+5042']\n",
    "# Create an instance of the ordinal encoder\n",
    "encoder = OrdinalEncoder(categories=[property_age_cat_order, \n",
    "                                     neighborhood_rent_index_cluster_order])\n",
    "\n",
    "for col in oe_cols:\n",
    "    # Create a new column name for the encoded data\n",
    "    new_col = col + '_encoded'\n",
    "    # Create an instance of the ordinal encoder\n",
    "    encoder = OrdinalEncoder(categories=[eval(col+'_order')])\n",
    "    # Fit and transform the selected columns\n",
    "    bagging_df3[new_col] = encoder.fit_transform(bagging_df3[[col]])\n",
    "    bagging_df3_test[new_col] = encoder.fit_transform(bagging_df3_test[[col]])\n",
    "    # replace 0 by -1 ('Unknown' by -1)\n",
    "    bagging_df3[new_col] = bagging_df3[new_col].replace(0, -1)\n",
    "    bagging_df3_test[new_col] = bagging_df3_test[new_col].replace(0, -1)\n",
    "\n",
    "# variables que queremos codificar usando OHE\n",
    "ohe_cols = [\"garage\", \"garden\", \"pool\", \n",
    "            \"terrace\", \"property_type\", \n",
    "            \"elevator\", \"ac\", \"heating\"]\n",
    "\n",
    "# aplicamos one - hot encoding al dataset\n",
    "bagging_df3 = one_hot_encode(bagging_df3, ohe_cols)\n",
    "bagging_df3_test = one_hot_encode(bagging_df3_test, ohe_cols)\n",
    "\n",
    "# eliminamos variables categóricas no codificadas\n",
    "no_encoded_cat_vars = bagging_df3.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df3.drop(no_encoded_cat_vars, axis=1, inplace=True)\n",
    "no_encoded_cat_vars_test = bagging_df3_test.select_dtypes(include=['category']).columns.tolist()\n",
    "bagging_df3_test.drop(no_encoded_cat_vars_test, axis=1, inplace=True)\n",
    "\n",
    "\n",
    "############# Tratamos los outliers per NO escalamos los atributos numéricos: ###############\n",
    "num_vars = [\"price\", \"sq_meters_built\", \"longitude\", \"dist_city_center\", \"latitude\", \"bathrooms_per_100_sqm\", \"rooms_per_100_sqm\"]\n",
    "\n",
    "# define the preprocessing pipeline\n",
    "preprocessing_pipeline = Pipeline([\n",
    "    ('outlier_removal', OutlierRemover(cols=num_vars)),\n",
    "    #('scaler', ColumnTransformer([('num_scaler', MinMaxScaler(), num_vars)], \n",
    "                                # remainder='passthrough'))\n",
    "])\n",
    "\n",
    "# Apply the preprocessing pipeline to the training and testing data\n",
    "    # Fit and transform the training data\n",
    "bagging_df3 = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df3), columns=num_vars + list(bagging_df3.columns[len(num_vars):]))\n",
    "bagging_df3_test = pd.DataFrame(preprocessing_pipeline.fit_transform(bagging_df3_test), columns=num_vars + list(bagging_df3_test.columns[len(num_vars):]))\n",
    "\n",
    "# exploración rápida del df\n",
    "print(\"TRAIN: \")\n",
    "explore_data(bagging_df3)\n",
    "print(\"\\n\\n\")\n",
    "print(\"TEST: \")\n",
    "explore_data(bagging_df3_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 512,
   "id": "76683ea4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.8699\n",
      "Train R^2 score: 0.9826\n",
      "Test R^2 score: 0.8562\n",
      "\n",
      "Model: RandomForestRegressor\n",
      "Best model parameters: {'model__max_depth': 9, 'model__min_samples_split': 2, 'model__n_estimators': 100}\n",
      "Best cross-validation R^2 score: 0.8615\n",
      "Train R^2 score: 0.9473\n",
      "Test R^2 score: 0.8466\n",
      "\n",
      "Best model: BaggingRegressor\n",
      "Best model parameters: {'model__n_estimators': 200}\n",
      "Best cross-validation R^2 score: 0.8699\n",
      "Train R^2 score: 0.9826\n",
      "Test R^2 score: 0.8562\n"
     ]
    }
   ],
   "source": [
    "# create an instance of PipelineRunner\n",
    "pipeline_runner = PipelineRunner()  \n",
    "# call the run_pipeline() method, passing in the dataframes and target variable name\n",
    "results_4 = pipeline_runner.run_pipeline(df_train=bagging_df3, \n",
    "                                         df_test=bagging_df3_test, \n",
    "                                         target=TARGET_VARIABLE)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 513,
   "id": "4b2b89ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'name': 'BaggingRegressor',\n",
       "  'best_params': {'model__n_estimators': 200},\n",
       "  'best_score': 0.8699084485798494,\n",
       "  'train_r2_score': 0.9826165282700704,\n",
       "  'test_r2_score': 0.8562174003334514},\n",
       " {'name': 'RandomForestRegressor',\n",
       "  'best_params': {'model__max_depth': 9,\n",
       "   'model__min_samples_split': 2,\n",
       "   'model__n_estimators': 100},\n",
       "  'best_score': 0.8614809042234631,\n",
       "  'train_r2_score': 0.9472748317785578,\n",
       "  'test_r2_score': 0.8466012770286642}]"
      ]
     },
     "execution_count": 513,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results_4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 658,
   "id": "ddcc6751",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>regressor</th>\n",
       "      <th>train_r2_score</th>\n",
       "      <th>test_r2_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BaggingRegressor_1</td>\n",
       "      <td>0.976685</td>\n",
       "      <td>0.739290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>RandomForestRegressor_1</td>\n",
       "      <td>0.939248</td>\n",
       "      <td>0.723103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>BaggingRegressor_2</td>\n",
       "      <td>0.970111</td>\n",
       "      <td>0.690796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>RandomForestRegressor_2</td>\n",
       "      <td>0.924524</td>\n",
       "      <td>0.674443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BaggingRegressor_3</td>\n",
       "      <td>0.982274</td>\n",
       "      <td>0.852508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>RandomForestRegressor_3</td>\n",
       "      <td>0.946943</td>\n",
       "      <td>0.845112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>BaggingRegressor_4</td>\n",
       "      <td>0.982617</td>\n",
       "      <td>0.856217</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>RandomForestRegressor_4</td>\n",
       "      <td>0.947275</td>\n",
       "      <td>0.846601</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 regressor  train_r2_score  test_r2_score\n",
       "0       BaggingRegressor_1        0.976685       0.739290\n",
       "1  RandomForestRegressor_1        0.939248       0.723103\n",
       "2       BaggingRegressor_2        0.970111       0.690796\n",
       "3  RandomForestRegressor_2        0.924524       0.674443\n",
       "4       BaggingRegressor_3        0.982274       0.852508\n",
       "5  RandomForestRegressor_3        0.946943       0.845112\n",
       "6       BaggingRegressor_4        0.982617       0.856217\n",
       "7  RandomForestRegressor_4        0.947275       0.846601"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Loop through each model in results\n",
    "for model in results_4:\n",
    "    model_name = model['name']+'_4'\n",
    "    train_r2_score = model['train_r2_score']\n",
    "    test_r2_score = model['test_r2_score']\n",
    "    \n",
    "    # Append the results to the DataFrame\n",
    "    models_results_df = pd.concat([models_results_df, pd.DataFrame({'regressor': model_name, \n",
    "                                                                   'train_r2_score': train_r2_score,\n",
    "                                                                   'test_r2_score': test_r2_score},\n",
    "                                                                   index=[0])], ignore_index=True)\n",
    "# Display the DataFrame\n",
    "display(models_results_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b66e26f6",
   "metadata": {},
   "source": [
    "- Observamos que sin escalar los atributos numéricos, los resultados son muy similares a cuando los hemos escalado (entre 0 y 1), incluso ligeramente superiores en validación para los dos modelos. \n",
    "- Por tanto, de momento, este ha sido nuestro mejor modelo: BaggingRegressor con test_r2_score = 0.856."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9977429",
   "metadata": {},
   "source": [
    "\n",
    "Podemos concluir que el modelo 3.1, que utilizó la selección de variables más importantes y también incluyó el tratamiento de outliers, pero no el escalado de variables numéricas, tuvo el mejor rendimiento en términos de R2, tanto en training como en test. En este caso, la selección de variables importantes y el tratamiento de outliers han sido factores importantes para mejorar la capacidad predictiva de los modelos de BaggingRegressor y RandomForestRegressor para predecir el precio de las viviendas en Barcelona.\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.16"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "343.3px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}