water_quality_prediction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## O Dataset Water Metrics "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Importa bibliotecas necessárias"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np \n",
    "import sklearn\n",
    "import random\n",
    "\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.metrics import mean_absolute_percentage_error\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn.metrics import mean_absolute_error"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Define o seed para o gerador de números aleatórios"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "random.seed(42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Importa o dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "original_dataset = pd.read_csv('water_metrics_embrapa.csv', delimiter=',')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Exibe as 5 primeiras amostras do dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>Data Coleta</th>\n",
       "      <th>Amostra</th>\n",
       "      <th>Produtor</th>\n",
       "      <th>Viveiro</th>\n",
       "      <th>T(ºC)</th>\n",
       "      <th>pH</th>\n",
       "      <th>ORP (mv)</th>\n",
       "      <th>Condutividade (mS/cm)</th>\n",
       "      <th>Turbidez (ntu)</th>\n",
       "      <th>OD (mg/L)</th>\n",
       "      <th>OD %</th>\n",
       "      <th>TDS</th>\n",
       "      <th>Salinidade %</th>\n",
       "      <th>Cidade</th>\n",
       "      <th>Estado</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>B1E</td>\n",
       "      <td>B</td>\n",
       "      <td>Viveiro 1</td>\n",
       "      <td>19.10</td>\n",
       "      <td>7.44</td>\n",
       "      <td>355.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>18.3</td>\n",
       "      <td>7.90</td>\n",
       "      <td>87.8</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>MOGI MIRIM</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>B1M</td>\n",
       "      <td>B</td>\n",
       "      <td>Viveiro 1</td>\n",
       "      <td>19.37</td>\n",
       "      <td>7.42</td>\n",
       "      <td>355.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>19.5</td>\n",
       "      <td>7.75</td>\n",
       "      <td>86.6</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>MOGI MIRIM</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>B1S</td>\n",
       "      <td>B</td>\n",
       "      <td>Viveiro 1</td>\n",
       "      <td>19.98</td>\n",
       "      <td>7.43</td>\n",
       "      <td>351.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>13.1</td>\n",
       "      <td>6.52</td>\n",
       "      <td>73.7</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>MOGI MIRIM</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>B2E</td>\n",
       "      <td>B</td>\n",
       "      <td>Viveiro 2</td>\n",
       "      <td>18.97</td>\n",
       "      <td>7.20</td>\n",
       "      <td>325.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>38.0</td>\n",
       "      <td>7.56</td>\n",
       "      <td>83.8</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>MOGI MIRIM</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>B2M</td>\n",
       "      <td>B</td>\n",
       "      <td>Viveiro 2</td>\n",
       "      <td>19.38</td>\n",
       "      <td>7.35</td>\n",
       "      <td>342.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>32.5</td>\n",
       "      <td>7.33</td>\n",
       "      <td>81.9</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "      <td>MOGI MIRIM</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Data Coleta Amostra Produtor    Viveiro  T(ºC)    pH  ORP (mv)  \\\n",
       "0  03-05-2016     B1E        B  Viveiro 1  19.10  7.44     355.0   \n",
       "1  03-05-2016     B1M        B  Viveiro 1  19.37  7.42     355.0   \n",
       "2  03-05-2016     B1S        B  Viveiro 1  19.98  7.43     351.0   \n",
       "3  03-05-2016     B2E        B  Viveiro 2  18.97  7.20     325.0   \n",
       "4  03-05-2016     B2M        B  Viveiro 2  19.38  7.35     342.0   \n",
       "\n",
       "   Condutividade (mS/cm)  Turbidez (ntu)  OD (mg/L)  OD %   TDS  Salinidade %  \\\n",
       "0                   0.05            18.3       7.90  87.8  0.03           0.0   \n",
       "1                   0.05            19.5       7.75  86.6  0.03           0.0   \n",
       "2                   0.05            13.1       6.52  73.7  0.03           0.0   \n",
       "3                   0.05            38.0       7.56  83.8  0.03           0.0   \n",
       "4                   0.05            32.5       7.33  81.9  0.03           0.0   \n",
       "\n",
       "       Cidade     Estado  \n",
       "0  MOGI MIRIM  SÃO PAULO  \n",
       "1  MOGI MIRIM  SÃO PAULO  \n",
       "2  MOGI MIRIM  SÃO PAULO  \n",
       "3  MOGI MIRIM  SÃO PAULO  \n",
       "4  MOGI MIRIM  SÃO PAULO  "
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "original_dataset.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Informa o tipo de variável de cada coluna do dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 169 entries, 0 to 168\n",
      "Data columns (total 15 columns):\n",
      " #   Column                 Non-Null Count  Dtype  \n",
      "---  ------                 --------------  -----  \n",
      " 0   Data Coleta            169 non-null    object \n",
      " 1   Amostra                169 non-null    object \n",
      " 2   Produtor               169 non-null    object \n",
      " 3   Viveiro                169 non-null    object \n",
      " 4   T(ºC)                  169 non-null    float64\n",
      " 5   pH                     169 non-null    float64\n",
      " 6   ORP (mv)               169 non-null    float64\n",
      " 7   Condutividade (mS/cm)  169 non-null    float64\n",
      " 8   Turbidez (ntu)         169 non-null    float64\n",
      " 9   OD (mg/L)              169 non-null    float64\n",
      " 10  OD %                   169 non-null    float64\n",
      " 11  TDS                    169 non-null    float64\n",
      " 12  Salinidade %           169 non-null    float64\n",
      " 13  Cidade                 169 non-null    object \n",
      " 14  Estado                 169 non-null    object \n",
      "dtypes: float64(9), object(6)\n",
      "memory usage: 19.9+ KB\n"
     ]
    }
   ],
   "source": [
    "original_dataset.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Obtem medidas das features numéricas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "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>Data Coleta</th>\n",
       "      <th>Amostra</th>\n",
       "      <th>Produtor</th>\n",
       "      <th>Viveiro</th>\n",
       "      <th>T(ºC)</th>\n",
       "      <th>pH</th>\n",
       "      <th>ORP (mv)</th>\n",
       "      <th>Condutividade (mS/cm)</th>\n",
       "      <th>Turbidez (ntu)</th>\n",
       "      <th>OD (mg/L)</th>\n",
       "      <th>OD %</th>\n",
       "      <th>TDS</th>\n",
       "      <th>Salinidade %</th>\n",
       "      <th>Cidade</th>\n",
       "      <th>Estado</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>169</td>\n",
       "      <td>169</td>\n",
       "      <td>169</td>\n",
       "      <td>169</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169.000000</td>\n",
       "      <td>169</td>\n",
       "      <td>169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>13</td>\n",
       "      <td>24</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>03-05-2016</td>\n",
       "      <td>C2M</td>\n",
       "      <td>C</td>\n",
       "      <td>Viveiro 2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ITAPIRA</td>\n",
       "      <td>SÃO PAULO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>24</td>\n",
       "      <td>8</td>\n",
       "      <td>43</td>\n",
       "      <td>85</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>85</td>\n",
       "      <td>169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>26.805858</td>\n",
       "      <td>6.985976</td>\n",
       "      <td>312.177515</td>\n",
       "      <td>0.060947</td>\n",
       "      <td>46.542012</td>\n",
       "      <td>5.685503</td>\n",
       "      <td>71.662130</td>\n",
       "      <td>0.039467</td>\n",
       "      <td>0.002485</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.410101</td>\n",
       "      <td>0.713310</td>\n",
       "      <td>47.628690</td>\n",
       "      <td>0.043497</td>\n",
       "      <td>34.457705</td>\n",
       "      <td>1.683798</td>\n",
       "      <td>20.457499</td>\n",
       "      <td>0.029078</td>\n",
       "      <td>0.004334</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>18.970000</td>\n",
       "      <td>5.710000</td>\n",
       "      <td>210.000000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>6.300000</td>\n",
       "      <td>2.410000</td>\n",
       "      <td>31.900000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>25.630000</td>\n",
       "      <td>6.380000</td>\n",
       "      <td>276.000000</td>\n",
       "      <td>0.020000</td>\n",
       "      <td>17.400000</td>\n",
       "      <td>4.330000</td>\n",
       "      <td>54.500000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>27.350000</td>\n",
       "      <td>7.050000</td>\n",
       "      <td>312.000000</td>\n",
       "      <td>0.050000</td>\n",
       "      <td>40.700000</td>\n",
       "      <td>5.790000</td>\n",
       "      <td>74.800000</td>\n",
       "      <td>0.030000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>28.510000</td>\n",
       "      <td>7.420000</td>\n",
       "      <td>348.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>61.600000</td>\n",
       "      <td>7.240000</td>\n",
       "      <td>88.300000</td>\n",
       "      <td>0.070000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>34.690000</td>\n",
       "      <td>9.180000</td>\n",
       "      <td>429.000000</td>\n",
       "      <td>0.160000</td>\n",
       "      <td>213.000000</td>\n",
       "      <td>9.170000</td>\n",
       "      <td>116.800000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Data Coleta Amostra Produtor    Viveiro       T(ºC)          pH  \\\n",
       "count          169     169      169        169  169.000000  169.000000   \n",
       "unique          13      24        4          2         NaN         NaN   \n",
       "top     03-05-2016     C2M        C  Viveiro 2         NaN         NaN   \n",
       "freq            24       8       43         85         NaN         NaN   \n",
       "mean           NaN     NaN      NaN        NaN   26.805858    6.985976   \n",
       "std            NaN     NaN      NaN        NaN    3.410101    0.713310   \n",
       "min            NaN     NaN      NaN        NaN   18.970000    5.710000   \n",
       "25%            NaN     NaN      NaN        NaN   25.630000    6.380000   \n",
       "50%            NaN     NaN      NaN        NaN   27.350000    7.050000   \n",
       "75%            NaN     NaN      NaN        NaN   28.510000    7.420000   \n",
       "max            NaN     NaN      NaN        NaN   34.690000    9.180000   \n",
       "\n",
       "          ORP (mv)  Condutividade (mS/cm)  Turbidez (ntu)   OD (mg/L)  \\\n",
       "count   169.000000             169.000000      169.000000  169.000000   \n",
       "unique         NaN                    NaN             NaN         NaN   \n",
       "top            NaN                    NaN             NaN         NaN   \n",
       "freq           NaN                    NaN             NaN         NaN   \n",
       "mean    312.177515               0.060947       46.542012    5.685503   \n",
       "std      47.628690               0.043497       34.457705    1.683798   \n",
       "min     210.000000               0.010000        6.300000    2.410000   \n",
       "25%     276.000000               0.020000       17.400000    4.330000   \n",
       "50%     312.000000               0.050000       40.700000    5.790000   \n",
       "75%     348.000000               0.100000       61.600000    7.240000   \n",
       "max     429.000000               0.160000      213.000000    9.170000   \n",
       "\n",
       "              OD %         TDS  Salinidade %   Cidade     Estado  \n",
       "count   169.000000  169.000000    169.000000      169        169  \n",
       "unique         NaN         NaN           NaN        3          1  \n",
       "top            NaN         NaN           NaN  ITAPIRA  SÃO PAULO  \n",
       "freq           NaN         NaN           NaN       85        169  \n",
       "mean     71.662130    0.039467      0.002485      NaN        NaN  \n",
       "std      20.457499    0.029078      0.004334      NaN        NaN  \n",
       "min      31.900000    0.000000      0.000000      NaN        NaN  \n",
       "25%      54.500000    0.010000      0.000000      NaN        NaN  \n",
       "50%      74.800000    0.030000      0.000000      NaN        NaN  \n",
       "75%      88.300000    0.070000      0.000000      NaN        NaN  \n",
       "max     116.800000    0.100000      0.010000      NaN        NaN  "
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "original_dataset.describe(include='all')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Conta os valores faltantes em cada coluna"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data Coleta              0\n",
      "Amostra                  0\n",
      "Produtor                 0\n",
      "Viveiro                  0\n",
      "T(ºC)                    0\n",
      "pH                       0\n",
      "ORP (mv)                 0\n",
      "Condutividade (mS/cm)    0\n",
      "Turbidez (ntu)           0\n",
      "OD (mg/L)                0\n",
      "OD %                     0\n",
      "TDS                      0\n",
      "Salinidade %             0\n",
      "Cidade                   0\n",
      "Estado                   0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(original_dataset.isna().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Exibe as dimensões do dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(169, 15)"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "original_dataset.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Remove colunas que não serão utlizadas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = original_dataset.drop(['Data Coleta', 'Amostra', 'Produtor', 'Viveiro', 'Estado', 'Cidade'], axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Exibe as 5 primeiras amostras do dataset após a remoção das colunas que não serão utlizadas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "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>T(ºC)</th>\n",
       "      <th>pH</th>\n",
       "      <th>ORP (mv)</th>\n",
       "      <th>Condutividade (mS/cm)</th>\n",
       "      <th>Turbidez (ntu)</th>\n",
       "      <th>OD (mg/L)</th>\n",
       "      <th>OD %</th>\n",
       "      <th>TDS</th>\n",
       "      <th>Salinidade %</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19.10</td>\n",
       "      <td>7.44</td>\n",
       "      <td>355.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>18.3</td>\n",
       "      <td>7.90</td>\n",
       "      <td>87.8</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>19.37</td>\n",
       "      <td>7.42</td>\n",
       "      <td>355.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>19.5</td>\n",
       "      <td>7.75</td>\n",
       "      <td>86.6</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.98</td>\n",
       "      <td>7.43</td>\n",
       "      <td>351.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>13.1</td>\n",
       "      <td>6.52</td>\n",
       "      <td>73.7</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>18.97</td>\n",
       "      <td>7.20</td>\n",
       "      <td>325.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>38.0</td>\n",
       "      <td>7.56</td>\n",
       "      <td>83.8</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19.38</td>\n",
       "      <td>7.35</td>\n",
       "      <td>342.0</td>\n",
       "      <td>0.05</td>\n",
       "      <td>32.5</td>\n",
       "      <td>7.33</td>\n",
       "      <td>81.9</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   T(ºC)    pH  ORP (mv)  Condutividade (mS/cm)  Turbidez (ntu)  OD (mg/L)  \\\n",
       "0  19.10  7.44     355.0                   0.05            18.3       7.90   \n",
       "1  19.37  7.42     355.0                   0.05            19.5       7.75   \n",
       "2  19.98  7.43     351.0                   0.05            13.1       6.52   \n",
       "3  18.97  7.20     325.0                   0.05            38.0       7.56   \n",
       "4  19.38  7.35     342.0                   0.05            32.5       7.33   \n",
       "\n",
       "   OD %   TDS  Salinidade %  \n",
       "0  87.8  0.03           0.0  \n",
       "1  86.6  0.03           0.0  \n",
       "2  73.7  0.03           0.0  \n",
       "3  83.8  0.03           0.0  \n",
       "4  81.9  0.03           0.0  "
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Separa features e labels\n",
    "    * pH é a coluna alvo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "features = dataset.drop(['pH'], axis=1)\n",
    "features = features.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "labels = dataset['pH']\n",
    "labels = labels.to_numpy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Divide o dataset em treino e teste na proporção 75% / 25%"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.25, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(126, 8)"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(43, 8)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Normalização dos dados"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Utiliza a normalização com valores centrados na média e desvio padrão igual a 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "scaler = StandardScaler()\n",
    "X_train = scaler.fit_transform(X_train)\n",
    "X_test = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-2.47333018e-15,  2.33499287e-16,  2.13585763e-15, -3.57297965e-16,\n",
       "       -1.17718886e-15,  3.48927236e-16,  1.86446978e-15, -2.99583991e-16])"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Média de cada coluna do conjunto de treino após a normalização\n",
    "np.mean(X_train, axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1., 1., 1., 1., 1., 1., 1., 1.])"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Desvio padrão de cada coluna do conjunto de treino após a normalização\n",
    "np.std(X_train, axis=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modelos de Machine Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Dicionários para armazenar a performace dos modelos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [],
   "source": [
    "MAE_dict = dict()\n",
    "MAPE_dict = dict()\n",
    "RMSE_dict = dict()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## MLP Regressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Importa o modelo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neural_network import MLPRegressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Utiliza o grid search para encontrar os melhores parâmetros para o modelo\n",
    "* A métrica para definir os melhores parâmetros é a MAPE (Mean Absolute Percentage Error)\n",
    "* Utiliza k-fold cross validation com k=3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {color: black;background-color: white;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3, estimator=MLPRegressor(),\n",
       "             param_grid={&#x27;hidden_layer_sizes&#x27;: [8, 10, 15, 20, 25, 30, 35, 40,\n",
       "                                                45, 50, 60, 70, 80, 90, 100],\n",
       "                         &#x27;max_iter&#x27;: [10000], &#x27;random_state&#x27;: [42],\n",
       "                         &#x27;solver&#x27;: [&#x27;lbfgs&#x27;, &#x27;sgd&#x27;, &#x27;adam&#x27;]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3, estimator=MLPRegressor(),\n",
       "             param_grid={&#x27;hidden_layer_sizes&#x27;: [8, 10, 15, 20, 25, 30, 35, 40,\n",
       "                                                45, 50, 60, 70, 80, 90, 100],\n",
       "                         &#x27;max_iter&#x27;: [10000], &#x27;random_state&#x27;: [42],\n",
       "                         &#x27;solver&#x27;: [&#x27;lbfgs&#x27;, &#x27;sgd&#x27;, &#x27;adam&#x27;]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: MLPRegressor</label><div class=\"sk-toggleable__content\"><pre>MLPRegressor()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-21\" type=\"checkbox\" ><label for=\"sk-estimator-id-21\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPRegressor</label><div class=\"sk-toggleable__content\"><pre>MLPRegressor()</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3, estimator=MLPRegressor(),\n",
       "             param_grid={'hidden_layer_sizes': [8, 10, 15, 20, 25, 30, 35, 40,\n",
       "                                                45, 50, 60, 70, 80, 90, 100],\n",
       "                         'max_iter': [10000], 'random_state': [42],\n",
       "                         'solver': ['lbfgs', 'sgd', 'adam']},\n",
       "             scoring='neg_mean_absolute_percentage_error')"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mlp = MLPRegressor()\n",
    "parameters = {'hidden_layer_sizes': [8, 10, 15, 20, 25, 30, 35, 40, 45, 50, 60, 70, 80, 90, 100], 'solver': ['lbfgs', 'sgd', 'adam'], 'random_state': [42], 'max_iter':[10000]}\n",
    "mlp_regressor = GridSearchCV(mlp, parameters, scoring = 'neg_mean_absolute_percentage_error', cv = 3)\n",
    "mlp_regressor.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Exibe os melhores parâmetros"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'hidden_layer_sizes': 10, 'max_iter': 10000, 'random_state': 42, 'solver': 'lbfgs'}\n",
      "-0.03189832051674752\n"
     ]
    }
   ],
   "source": [
    "print(mlp_regressor.best_params_)\n",
    "print(mlp_regressor.best_score_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Utliza o modelo já treinado para prever os valores de pH no conjunto de teste"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict = mlp_regressor.predict(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Calcula e exibe as principais métricas em relação aos valores previstos no conjunto de teste"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.20191903590938926\n",
      "MAPE: 0.028745637269660503\n",
      "MSE: 0.27881272290564507\n",
      "RMSE: 0.07773653445406002\n"
     ]
    }
   ],
   "source": [
    "MAE = mean_absolute_error(y_test, predict)\n",
    "MAPE = mean_absolute_percentage_error(y_test, predict)\n",
    "MSE = mean_squared_error(y_test, predict, squared=False)\n",
    "RMSE = mean_squared_error(y_test, predict)\n",
    "\n",
    "print(f'MAE: {MAE}')\n",
    "print(f'MAPE: {MAPE}')\n",
    "print(f'MSE: {MSE}')\n",
    "print(f'RMSE: {RMSE}')\n",
    "\n",
    "MAE_dict['MLPRegressor'] = MAE\n",
    "MAPE_dict['MLPRegressor'] = MAPE\n",
    "RMSE_dict['MLPRegressor'] = RMSE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## SVR (Support Vector Regression)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-8 {color: black;background-color: white;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3, estimator=SVR(),\n",
       "             param_grid={&#x27;C&#x27;: [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0,\n",
       "                               50.0, 100.0],\n",
       "                         &#x27;kernel&#x27;: [&#x27;linear&#x27;, &#x27;poly&#x27;, &#x27;rbf&#x27;, &#x27;sigmoid&#x27;]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" ><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3, estimator=SVR(),\n",
       "             param_grid={&#x27;C&#x27;: [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0,\n",
       "                               50.0, 100.0],\n",
       "                         &#x27;kernel&#x27;: [&#x27;linear&#x27;, &#x27;poly&#x27;, &#x27;rbf&#x27;, &#x27;sigmoid&#x27;]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" ><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: SVR</label><div class=\"sk-toggleable__content\"><pre>SVR()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" ><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVR</label><div class=\"sk-toggleable__content\"><pre>SVR()</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3, estimator=SVR(),\n",
       "             param_grid={'C': [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0,\n",
       "                               50.0, 100.0],\n",
       "                         'kernel': ['linear', 'poly', 'rbf', 'sigmoid']},\n",
       "             scoring='neg_mean_absolute_percentage_error')"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "support_vector = SVR()\n",
    "parameters = {'C': [1.0,2.0,3.0,4.0,5.0,10.0,20.0,30.0,40.0,50.0,100.0], 'kernel': ['linear', 'poly', 'rbf', 'sigmoid']}\n",
    "support_vector_regressor = GridSearchCV(support_vector, parameters, scoring = 'neg_mean_absolute_percentage_error', cv = 3)\n",
    "support_vector_regressor.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'C': 3.0, 'kernel': 'rbf'}\n",
      "-0.02882310384538937\n"
     ]
    }
   ],
   "source": [
    "print(support_vector_regressor.best_params_)\n",
    "print(support_vector_regressor.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict = support_vector_regressor.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.20678650088452666\n",
      "MAPE: 0.029490535666033706\n",
      "MSE: 0.28182201183891314\n",
      "RMSE: 0.07942364635693251\n"
     ]
    }
   ],
   "source": [
    "MAE = mean_absolute_error(y_test, predict)\n",
    "MAPE = mean_absolute_percentage_error(y_test, predict)\n",
    "MSE = mean_squared_error(y_test, predict, squared=False)\n",
    "RMSE = mean_squared_error(y_test, predict)\n",
    "\n",
    "print(f'MAE: {MAE}')\n",
    "print(f'MAPE: {MAPE}')\n",
    "print(f'MSE: {MSE}')\n",
    "print(f'RMSE: {RMSE}')\n",
    "\n",
    "MAE_dict['SVR'] = MAE\n",
    "MAPE_dict['SVR'] = MAPE\n",
    "RMSE_dict['SVR'] = RMSE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Decisionn Tree Regressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-9 {color: black;background-color: white;}#sk-container-id-9 pre{padding: 0;}#sk-container-id-9 div.sk-toggleable {background-color: white;}#sk-container-id-9 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-9 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-9 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-9 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-9 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-9 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-9 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-9 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-9 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-9 div.sk-item {position: relative;z-index: 1;}#sk-container-id-9 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-9 div.sk-item::before, #sk-container-id-9 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-9 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-9 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-9 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-9 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-9 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-9 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-9 div.sk-label-container {text-align: center;}#sk-container-id-9 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-9 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3, estimator=DecisionTreeRegressor(),\n",
       "             param_grid={&#x27;criterion&#x27;: [&#x27;squared_error&#x27;, &#x27;absolute_error&#x27;,\n",
       "                                       &#x27;poisson&#x27;],\n",
       "                         &#x27;random_state&#x27;: [42]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-25\" type=\"checkbox\" ><label for=\"sk-estimator-id-25\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3, estimator=DecisionTreeRegressor(),\n",
       "             param_grid={&#x27;criterion&#x27;: [&#x27;squared_error&#x27;, &#x27;absolute_error&#x27;,\n",
       "                                       &#x27;poisson&#x27;],\n",
       "                         &#x27;random_state&#x27;: [42]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-26\" type=\"checkbox\" ><label for=\"sk-estimator-id-26\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-27\" type=\"checkbox\" ><label for=\"sk-estimator-id-27\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor()</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3, estimator=DecisionTreeRegressor(),\n",
       "             param_grid={'criterion': ['squared_error', 'absolute_error',\n",
       "                                       'poisson'],\n",
       "                         'random_state': [42]},\n",
       "             scoring='neg_mean_absolute_percentage_error')"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "decision_tree = DecisionTreeRegressor()\n",
    "parameters = {'criterion': ['squared_error', 'absolute_error', 'poisson'], 'random_state':[42]}\n",
    "decision_tree_regressor = GridSearchCV(decision_tree, parameters, scoring = 'neg_mean_absolute_percentage_error', cv = 3)\n",
    "decision_tree_regressor.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'criterion': 'absolute_error', 'random_state': 42}\n",
      "-0.036987357256841547\n"
     ]
    }
   ],
   "source": [
    "print(decision_tree_regressor.best_params_)\n",
    "print(decision_tree_regressor.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict = decision_tree_regressor.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.20046511627906982\n",
      "MAPE: 0.028481238653962335\n",
      "MSE: 0.2744042172026601\n",
      "RMSE: 0.07529767441860467\n"
     ]
    }
   ],
   "source": [
    "MAE = mean_absolute_error(y_test, predict)\n",
    "MAPE = mean_absolute_percentage_error(y_test, predict)\n",
    "MSE = mean_squared_error(y_test, predict, squared=False)\n",
    "RMSE = mean_squared_error(y_test, predict)\n",
    "\n",
    "print(f'MAE: {MAE}')\n",
    "print(f'MAPE: {MAPE}')\n",
    "print(f'MSE: {MSE}')\n",
    "print(f'RMSE: {RMSE}')\n",
    "\n",
    "MAE_dict['DecisionTreeRegressor'] = MAE\n",
    "MAPE_dict['DecisionTreeRegressor'] = MAPE\n",
    "RMSE_dict['DecisionTreeRegressor'] = RMSE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RF Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-10 {color: black;background-color: white;}#sk-container-id-10 pre{padding: 0;}#sk-container-id-10 div.sk-toggleable {background-color: white;}#sk-container-id-10 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-10 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-10 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-10 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-10 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-10 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-10 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-10 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-10 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-10 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-10 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-10 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-10 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-10 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-10 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-10 div.sk-item {position: relative;z-index: 1;}#sk-container-id-10 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-10 div.sk-item::before, #sk-container-id-10 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-10 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-10 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-10 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-10 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-10 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-10 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-10 div.sk-label-container {text-align: center;}#sk-container-id-10 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-10 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-10\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3, estimator=RandomForestRegressor(),\n",
       "             param_grid={&#x27;criterion&#x27;: [&#x27;squared_error&#x27;, &#x27;absolute_error&#x27;,\n",
       "                                       &#x27;poisson&#x27;],\n",
       "                         &#x27;n_estimators&#x27;: [1, 5, 10, 20, 30, 35, 40, 45, 50, 55,\n",
       "                                          100],\n",
       "                         &#x27;random_state&#x27;: [42]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-28\" type=\"checkbox\" ><label for=\"sk-estimator-id-28\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3, estimator=RandomForestRegressor(),\n",
       "             param_grid={&#x27;criterion&#x27;: [&#x27;squared_error&#x27;, &#x27;absolute_error&#x27;,\n",
       "                                       &#x27;poisson&#x27;],\n",
       "                         &#x27;n_estimators&#x27;: [1, 5, 10, 20, 30, 35, 40, 45, 50, 55,\n",
       "                                          100],\n",
       "                         &#x27;random_state&#x27;: [42]},\n",
       "             scoring=&#x27;neg_mean_absolute_percentage_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-29\" type=\"checkbox\" ><label for=\"sk-estimator-id-29\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-30\" type=\"checkbox\" ><label for=\"sk-estimator-id-30\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor()</pre></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3, estimator=RandomForestRegressor(),\n",
       "             param_grid={'criterion': ['squared_error', 'absolute_error',\n",
       "                                       'poisson'],\n",
       "                         'n_estimators': [1, 5, 10, 20, 30, 35, 40, 45, 50, 55,\n",
       "                                          100],\n",
       "                         'random_state': [42]},\n",
       "             scoring='neg_mean_absolute_percentage_error')"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random_forest = RandomForestRegressor()\n",
    "parameters = {'n_estimators': [1, 5, 10, 20, 30, 35, 40, 45, 50, 55, 100], 'random_state':[42], 'criterion': ['squared_error', 'absolute_error', 'poisson']}\n",
    "random_forest_regressor = GridSearchCV(random_forest, parameters, scoring = 'neg_mean_absolute_percentage_error', cv = 3)\n",
    "random_forest_regressor.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'criterion': 'poisson', 'n_estimators': 10, 'random_state': 42}\n",
      "-0.029213141627099676\n"
     ]
    }
   ],
   "source": [
    "print(random_forest_regressor.best_params_)\n",
    "print(random_forest_regressor.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "rf_predict = random_forest_regressor.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MAE: 0.17211627906976726\n",
      "MAPE: 0.024454393391468605\n",
      "MSE: 0.24125847376370144\n",
      "RMSE: 0.05820565116279061\n"
     ]
    }
   ],
   "source": [
    "MAE = mean_absolute_error(y_test, rf_predict)\n",
    "MAPE = mean_absolute_percentage_error(y_test, rf_predict)\n",
    "MSE = mean_squared_error(y_test, rf_predict, squared=False)\n",
    "RMSE = mean_squared_error(y_test, rf_predict)\n",
    "\n",
    "print(f'MAE: {MAE}')\n",
    "print(f'MAPE: {MAPE}')\n",
    "print(f'MSE: {MSE}')\n",
    "print(f'RMSE: {RMSE}')\n",
    "\n",
    "MAE_dict['RandomForestRegressor'] = MAE\n",
    "MAPE_dict['RandomForestRegressor'] = MAPE\n",
    "RMSE_dict['RandomForestRegressor'] = RMSE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RESULTADOS\n",
    "* Avaliando as métricas de MAE, MAPE e RMSE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RandomForestRegressor: 0.17211627906976726\n",
      "DecisionTreeRegressor: 0.20046511627906982\n",
      "MLPRegressor: 0.20191903590938926\n",
      "SVR: 0.20678650088452666\n"
     ]
    }
   ],
   "source": [
    "# Modelos em ordem crescente em relação ao valor de MAE\n",
    "for i in sorted(MAE_dict, key = MAE_dict.get):\n",
    "    print(f'{i}: {MAE_dict[i]}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RandomForestRegressor: 0.024454393391468605\n",
      "DecisionTreeRegressor: 0.028481238653962335\n",
      "MLPRegressor: 0.028745637269660503\n",
      "SVR: 0.029490535666033706\n"
     ]
    }
   ],
   "source": [
    "# Modelos em ordem crescente em relação ao valor de MAPE\n",
    "for i in sorted(MAPE_dict, key = MAPE_dict.get):\n",
    "    print(f'{i}: {MAPE_dict[i]}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RandomForestRegressor: 0.05820565116279061\n",
      "DecisionTreeRegressor: 0.07529767441860467\n",
      "MLPRegressor: 0.07773653445406002\n",
      "SVR: 0.07942364635693251\n"
     ]
    }
   ],
   "source": [
    "# Modelos em ordem crescente em relação ao valor de RMSE\n",
    "for i in sorted(RMSE_dict, key = RMSE_dict.get):\n",
    "    print(f'{i}: {RMSE_dict[i]}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Cria um dataframe para armazenar os resultados obtidos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [],
   "source": [
    "columns = ['Modelo', 'MAE', 'MAPE', 'RMSE']\n",
    "results = pd.DataFrame(columns=columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "modelos = ['MLPRegressor', 'SVR', 'DecisionTreeRegressor', 'RandomForestRegressor']\n",
    "results['Modelo'] = modelos"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Armazena as métricas obtidas em listas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "MAE_list = []\n",
    "MAPE_list = []\n",
    "RMSE_list = []\n",
    "\n",
    "for i in range(0,len(modelos)):\n",
    "    modelo = modelos[i]\n",
    "\n",
    "    MAE_list.append(MAE_dict[modelo])\n",
    "    MAPE_list.append(MAPE_dict[modelo])\n",
    "    RMSE_list.append(RMSE_dict[modelo])    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [],
   "source": [
    "results['MAE'] = MAE_list\n",
    "results['MAPE'] = MAPE_list\n",
    "results['RMSE'] = RMSE_list "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Exibe o dataframe criado"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "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>Modelo</th>\n",
       "      <th>MAE</th>\n",
       "      <th>MAPE</th>\n",
       "      <th>RMSE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>MLPRegressor</td>\n",
       "      <td>0.201919</td>\n",
       "      <td>0.028746</td>\n",
       "      <td>0.077737</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>SVR</td>\n",
       "      <td>0.206787</td>\n",
       "      <td>0.029491</td>\n",
       "      <td>0.079424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>DecisionTreeRegressor</td>\n",
       "      <td>0.200465</td>\n",
       "      <td>0.028481</td>\n",
       "      <td>0.075298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>RandomForestRegressor</td>\n",
       "      <td>0.172116</td>\n",
       "      <td>0.024454</td>\n",
       "      <td>0.058206</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  Modelo       MAE      MAPE      RMSE\n",
       "0           MLPRegressor  0.201919  0.028746  0.077737\n",
       "1                    SVR  0.206787  0.029491  0.079424\n",
       "2  DecisionTreeRegressor  0.200465  0.028481  0.075298\n",
       "3  RandomForestRegressor  0.172116  0.024454  0.058206"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Salva os resultados em uma planilha excel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Necessário instalar openpyxl ( pip install openpyxl )\n",
    "results.to_excel('Results.xlsx')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Plota gráfico da comparação dos valores de pH reais do conjunto de teste com as previsões feitas pelo melhor modelo (RF Regressor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pyplot import figure\n",
    "\n",
    "number_of_samples = range(1, len(X_test) + 1)\n",
    "figure(figsize=(10,6))\n",
    "plt.plot(number_of_samples, y_test,'b', marker = 's', markerfacecolor='none', linewidth = 1, label='pH Real')\n",
    "plt.plot(number_of_samples, rf_predict, 'r', marker = 'o', markerfacecolor='none', linestyle = 'dashed', linewidth = 1, label='pH Previsto')\n",
    "plt.xticks(np.arange(min(number_of_samples), max(number_of_samples), 2))\n",
    "plt.xlabel('Amostras', fontsize= 12)\n",
    "plt.ylabel('pH', fontsize= 12)\n",
    "\n",
    "plt.legend()\n",
    "\n",
    "plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.13 ('dl2')",
   "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": "3.9.13"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "eccc23d48a62043bd00c052d05deb9fa45ff1b47490812ca50f062e0ca50dba0"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}