thyroid_prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9319e34e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'C:/Users/santh/Downloads/knn_trained1.csv'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.impute import KNNImputer\n",
    "\n",
    "# Load the dataset\n",
    "file_path = \"C:/Users/santh/Downloads/hypothyroid_1.csv\"\n",
    "data = pd.read_csv(file_path)\n",
    "\n",
    "# Replace '?' with NaN\n",
    "data.replace('?', np.nan, inplace=True)\n",
    "\n",
    "# Identify numerical and categorical columns\n",
    "numerical_cols = ['age', 'tsh', 't3', 'tt4', 't4u', 'fti']  # Assuming these are the numerical columns\n",
    "\n",
    "# Convert numerical columns to numeric type\n",
    "for col in numerical_cols:\n",
    "    data[col] = pd.to_numeric(data[col], errors='coerce')\n",
    "\n",
    "# Impute missing values in numerical columns using KNN\n",
    "imputer = KNNImputer(n_neighbors=5)\n",
    "numerical_data_imputed = pd.DataFrame(imputer.fit_transform(data[numerical_cols]), columns=numerical_cols)\n",
    "\n",
    "# List of columns to convert 'f'/'t' to 0/1\n",
    "binary_cols = [\n",
    "    'on_thyroxine', 'query_on_thyroxine', 'on_antithyroid_medication', 'sick', 'pregnant',\n",
    "    'thyroid_surgery', 'i131_treatment', 'query_hypothyroid', 'query_hyperthyroid', 'lithium',\n",
    "    'goitre', 'tumor', 'hypopituitary', 'psych', 'tsh_measured', 't3_measured', 'tt4_measured',\n",
    "    't4u_measured', 'fti_measured', 'tbg_measured'\n",
    "]\n",
    "\n",
    "# Impute missing values in categorical columns with the mode\n",
    "def impute_mode(series):\n",
    "    mode = series.mode()\n",
    "    if mode.empty:\n",
    "        return series\n",
    "    return series.fillna(mode[0])\n",
    "\n",
    "for col in binary_cols:\n",
    "    data[col] = impute_mode(data[col])\n",
    "    data[col] = data[col].replace({'f': 0, 't': 1})\n",
    "\n",
    "# Handle the 'sex' column\n",
    "data['sex'] = impute_mode(data['sex'])\n",
    "data['sex'] = data['sex'].replace({'F': 0, 'M': 1})\n",
    "\n",
    "# Convert 'binaryclass' column to 0 and 1\n",
    "data['binaryclass'] = data['binaryclass'].replace({'P': 1, 'N': 0})\n",
    "\n",
    "# Combine imputed numerical and categorical data\n",
    "categorical_cols = [col for col in data.columns if col not in numerical_cols]\n",
    "categorical_data_imputed = data[categorical_cols]\n",
    "data_imputed = pd.concat([numerical_data_imputed, categorical_data_imputed], axis=1)\n",
    "\n",
    "# Save the cleaned data\n",
    "cleaned_file_path = \"C:/Users/santh/Downloads/knn_trained1.csv\"\n",
    "data_imputed.to_csv(cleaned_file_path, index=False)\n",
    "\n",
    "cleaned_file_path\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "81e233d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\sklearn\\feature_selection\\_univariate_selection.py:112: UserWarning: Features [26] are constant.\n",
      "  warnings.warn(\"Features %s are constant.\" % constant_features_idx, UserWarning)\n",
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\sklearn\\feature_selection\\_univariate_selection.py:113: RuntimeWarning: invalid value encountered in divide\n",
      "  f = msb / msw\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reduced features: Index(['tsh', 't3', 'tt4', 't4u', 'fti', 'sex', 'on_thyroxine',\n",
      "       'query_on_thyroxine', 'on_antithyroid_medication', 'pregnant',\n",
      "       'thyroid_surgery', 'query_hypothyroid', 'query_hyperthyroid', 'lithium',\n",
      "       'goitre', 'tumor', 'hypopituitary', 'psych', 'tsh_measured',\n",
      "       't3_measured', 'tt4_measured', 't4u_measured', 'fti_measured',\n",
      "       'referral_source_SVHC', 'referral_source_SVI', 'referral_source_other'],\n",
      "      dtype='object')\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>tsh</th>\n",
       "      <th>t3</th>\n",
       "      <th>tt4</th>\n",
       "      <th>t4u</th>\n",
       "      <th>fti</th>\n",
       "      <th>sex</th>\n",
       "      <th>on_thyroxine</th>\n",
       "      <th>query_on_thyroxine</th>\n",
       "      <th>on_antithyroid_medication</th>\n",
       "      <th>pregnant</th>\n",
       "      <th>...</th>\n",
       "      <th>psych</th>\n",
       "      <th>tsh_measured</th>\n",
       "      <th>t3_measured</th>\n",
       "      <th>tt4_measured</th>\n",
       "      <th>t4u_measured</th>\n",
       "      <th>fti_measured</th>\n",
       "      <th>referral_source_SVHC</th>\n",
       "      <th>referral_source_SVI</th>\n",
       "      <th>referral_source_other</th>\n",
       "      <th>binaryclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.30</td>\n",
       "      <td>2.50</td>\n",
       "      <td>125.0</td>\n",
       "      <td>1.140</td>\n",
       "      <td>109.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.10</td>\n",
       "      <td>2.00</td>\n",
       "      <td>102.0</td>\n",
       "      <td>1.014</td>\n",
       "      <td>102.2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.98</td>\n",
       "      <td>1.62</td>\n",
       "      <td>109.0</td>\n",
       "      <td>0.910</td>\n",
       "      <td>120.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.16</td>\n",
       "      <td>1.90</td>\n",
       "      <td>175.0</td>\n",
       "      <td>0.988</td>\n",
       "      <td>163.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.72</td>\n",
       "      <td>1.20</td>\n",
       "      <td>61.0</td>\n",
       "      <td>0.870</td>\n",
       "      <td>70.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    tsh    t3    tt4    t4u    fti  sex  on_thyroxine  query_on_thyroxine  \\\n",
       "0  1.30  2.50  125.0  1.140  109.0    0             0                   0   \n",
       "1  4.10  2.00  102.0  1.014  102.2    0             0                   0   \n",
       "2  0.98  1.62  109.0  0.910  120.0    1             0                   0   \n",
       "3  0.16  1.90  175.0  0.988  163.0    0             1                   0   \n",
       "4  0.72  1.20   61.0  0.870   70.0    0             0                   0   \n",
       "\n",
       "   on_antithyroid_medication  pregnant  ...  psych  tsh_measured  t3_measured  \\\n",
       "0                          0         0  ...      0             1            1   \n",
       "1                          0         0  ...      0             1            1   \n",
       "2                          0         0  ...      0             1            0   \n",
       "3                          0         0  ...      0             1            1   \n",
       "4                          0         0  ...      0             1            1   \n",
       "\n",
       "   tt4_measured  t4u_measured  fti_measured  referral_source_SVHC  \\\n",
       "0             1             1             1                     1   \n",
       "1             1             0             0                     0   \n",
       "2             1             1             1                     0   \n",
       "3             1             0             0                     0   \n",
       "4             1             1             1                     0   \n",
       "\n",
       "   referral_source_SVI  referral_source_other  binaryclass  \n",
       "0                    0                      0            1  \n",
       "1                    0                      1            1  \n",
       "2                    0                      1            1  \n",
       "3                    0                      1            1  \n",
       "4                    1                      0            1  \n",
       "\n",
       "[5 rows x 27 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.feature_selection import SelectKBest, f_classif\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Load the dataset\n",
    "data = pd.read_csv(\"C:/Users/santh/Downloads/knn_trained.csv\")\n",
    "\n",
    "# Drop columns with any NaN values\n",
    "data = data.dropna(axis=1)\n",
    "\n",
    "# Separate features and target variable\n",
    "X = data.drop('binaryclass', axis=1)\n",
    "y = data['binaryclass']\n",
    "\n",
    "# One-hot encode categorical variables (like 'sex' and 'referral_source')\n",
    "X = pd.get_dummies(X, drop_first=True)\n",
    "\n",
    "# Feature selection using SelectKBest\n",
    "selector = SelectKBest(f_classif, k='all')  # k='all' to get scores for all features\n",
    "X_selected = selector.fit_transform(X, y)\n",
    "\n",
    "# Get selected feature names and their scores\n",
    "selected_features = X.columns[selector.get_support()]\n",
    "feature_scores = selector.scores_[selector.get_support()]\n",
    "\n",
    "# Create a DataFrame to store the feature names and their scores\n",
    "feature_scores_data_set = pd.DataFrame({'Features': selected_features, 'Scores': feature_scores})\n",
    "\n",
    "# Sort the DataFrame by score in descending order\n",
    "feature_scores_data_set = feature_scores_data_set.sort_values(by='Scores', ascending=False)\n",
    "\n",
    "# Plot the feature scores\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.barplot(x='Scores', y='Features', data=feature_scores_data_set, palette='viridis')\n",
    "plt.title('Feature Scores')\n",
    "plt.xlabel('Scores')\n",
    "plt.ylabel('Features')\n",
    "plt.show()\n",
    "\n",
    "# Identify and remove the least important features\n",
    "# For this example, let's remove the bottom 5 features\n",
    "least_important_features = feature_scores_data_set.tail(5)['Features'].tolist()\n",
    "X_reduced = X.drop(columns=least_important_features)\n",
    "\n",
    "# Display the columns of X_reduced\n",
    "reduced_features = X_reduced.columns\n",
    "print(\"Reduced features:\", reduced_features)\n",
    "\n",
    "# Combine reduced features with the target variable\n",
    "data_reduced = pd.concat([X_reduced, y], axis=1)\n",
    "\n",
    "# Display the reduced dataset\n",
    "data_reduced.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "adfb0fc5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\sklearn\\feature_selection\\_univariate_selection.py:112: UserWarning: Features [26] are constant.\n",
      "  warnings.warn(\"Features %s are constant.\" % constant_features_idx, UserWarning)\n",
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\sklearn\\feature_selection\\_univariate_selection.py:113: RuntimeWarning: invalid value encountered in divide\n",
      "  f = msb / msw\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reduced features: Index(['tsh', 't3', 'tt4', 't4u', 'fti', 'sex', 'on_thyroxine',\n",
      "       'query_on_thyroxine', 'on_antithyroid_medication', 'pregnant',\n",
      "       'thyroid_surgery', 'query_hypothyroid', 'query_hyperthyroid', 'lithium',\n",
      "       'goitre', 'tumor', 'hypopituitary', 'psych', 'tsh_measured',\n",
      "       't3_measured', 'tt4_measured', 't4u_measured', 'fti_measured',\n",
      "       'referral_source_SVHC', 'referral_source_SVI', 'referral_source_other'],\n",
      "      dtype='object')\n",
      "Accuracy: 0.9960\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.98      0.97      0.97        58\n",
      "           1       1.00      1.00      1.00       697\n",
      "\n",
      "    accuracy                           1.00       755\n",
      "   macro avg       0.99      0.98      0.99       755\n",
      "weighted avg       1.00      1.00      1.00       755\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross-Validation Accuracy: 0.9944 ± 0.0021\n",
      "Fitting 5 folds for each of 108 candidates, totalling 540 fits\n",
      "Best Parameters: {'max_depth': None, 'min_samples_leaf': 1, 'min_samples_split': 10, 'n_estimators': 200}\n",
      "Best Model Accuracy: 0.9947\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.98      0.95      0.96        58\n",
      "           1       1.00      1.00      1.00       697\n",
      "\n",
      "    accuracy                           0.99       755\n",
      "   macro avg       0.99      0.97      0.98       755\n",
      "weighted avg       0.99      0.99      0.99       755\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn.feature_selection import SelectKBest, f_classif\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Load the dataset\n",
    "data = pd.read_csv(\"C:/Users/santh/Downloads/knn_trained.csv\")\n",
    "\n",
    "# Drop columns with any NaN values\n",
    "data = data.dropna(axis=1)\n",
    "\n",
    "# Separate features and target variable\n",
    "X = data.drop('binaryclass', axis=1)\n",
    "y = data['binaryclass']\n",
    "\n",
    "# One-hot encode categorical variables (like 'sex' and 'referral_source')\n",
    "X = pd.get_dummies(X, drop_first=True)\n",
    "\n",
    "# Feature selection using SelectKBest\n",
    "selector = SelectKBest(f_classif, k='all')  # k='all' to get scores for all features\n",
    "X_selected = selector.fit_transform(X, y)\n",
    "\n",
    "# Get selected feature names and their scores\n",
    "selected_features = X.columns[selector.get_support()]\n",
    "feature_scores = selector.scores_[selector.get_support()]\n",
    "\n",
    "# Create a DataFrame to store the feature names and their scores\n",
    "feature_scores_data_set = pd.DataFrame({'Features': selected_features, 'Scores': feature_scores})\n",
    "\n",
    "# Sort the DataFrame by score in descending order\n",
    "feature_scores_data_set = feature_scores_data_set.sort_values(by='Scores', ascending=False)\n",
    "\n",
    "# Plot the feature scores\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.barplot(x='Scores', y='Features', data=feature_scores_data_set, palette='viridis')\n",
    "plt.title('Feature Scores')\n",
    "plt.xlabel('Scores')\n",
    "plt.ylabel('Features')\n",
    "plt.show()\n",
    "\n",
    "# Identify and remove the least important features\n",
    "# For this example, let's remove the bottom 5 features\n",
    "least_important_features = feature_scores_data_set.tail(5)['Features'].tolist()\n",
    "X_reduced = X.drop(columns=least_important_features)\n",
    "# Display the columns of X_reduced\n",
    "reduced_features = X_reduced.columns\n",
    "print(\"Reduced features:\", reduced_features)\n",
    "\n",
    "\n",
    "# Combine reduced features with the target variable\n",
    "data_reduced = pd.concat([X_reduced, y], axis=1)\n",
    "\n",
    "\n",
    "# Display the reduced dataset\n",
    "data_reduced.head()\n",
    "from sklearn.model_selection import train_test_split\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.feature_selection import SelectKBest, f_classif\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import cross_val_score, GridSearchCV\n",
    "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_reduced, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Train a Random Forest model\n",
    "rf_model = RandomForestClassifier(random_state=42)\n",
    "rf_model.fit(X_train, y_train)\n",
    "\n",
    "# Predict on the test set\n",
    "y_pred = rf_model.predict(X_test)\n",
    "\n",
    "# Evaluate the model\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(f'Accuracy: {accuracy:.4f}')\n",
    "\n",
    "# Print classification report\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "# Plot confusion matrix\n",
    "conf_matrix = confusion_matrix(y_test, y_pred)\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "plt.show()\n",
    "\n",
    "# Perform cross-validation\n",
    "cv_scores = cross_val_score(rf_model, X_reduced, y, cv=5)\n",
    "print(f'Cross-Validation Accuracy: {np.mean(cv_scores):.4f} ± {np.std(cv_scores):.4f}')\n",
    "\n",
    "# Hyperparameter tuning using GridSearchCV\n",
    "param_grid = {\n",
    "    'n_estimators': [100, 200, 300],\n",
    "    'max_depth': [None, 10, 20, 30],\n",
    "    'min_samples_split': [2, 5, 10],\n",
    "    'min_samples_leaf': [1, 2, 4]\n",
    "}\n",
    "\n",
    "grid_search = GridSearchCV(estimator=rf_model, param_grid=param_grid, cv=5, n_jobs=-1, verbose=2)\n",
    "grid_search.fit(X_train, y_train)\n",
    "\n",
    "# Best parameters from GridSearchCV\n",
    "print(f'Best Parameters: {grid_search.best_params_}')\n",
    "\n",
    "# Predict on the test set with the best model\n",
    "best_model = grid_search.best_estimator_\n",
    "y_pred_best = best_model.predict(X_test)\n",
    "\n",
    "# Evaluate the best model\n",
    "best_accuracy = accuracy_score(y_test, y_pred_best)\n",
    "print(f'Best Model Accuracy: {best_accuracy:.4f}')\n",
    "print(classification_report(y_test, y_pred_best))\n",
    "\n",
    "# Plot confusion matrix for the best model\n",
    "conf_matrix_best = confusion_matrix(y_test, y_pred_best)\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.heatmap(conf_matrix_best, annot=True, fmt='d', cmap='Blues')\n",
    "plt.title('Confusion Matrix for Best Model')\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bd1fffee",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Assuming you have a trained model named 'best_model'\n",
    "model_path = 'model.pkl'\n",
    "with open(model_path, 'wb') as f:\n",
    "    pickle.dump(best_model, f)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d80ff69a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * Serving Flask app '__main__'\n",
      " * Debug mode: on\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.\n",
      " * Running on http://127.0.0.1:5000\n",
      "Press CTRL+C to quit\n",
      " * Restarting with watchdog (windowsapi)\n"
     ]
    },
    {
     "ename": "SystemExit",
     "evalue": "1",
     "output_type": "error",
     "traceback": [
      "An exception has occurred, use %tb to see the full traceback.\n",
      "\u001b[1;31mSystemExit\u001b[0m\u001b[1;31m:\u001b[0m 1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\IPython\\core\\interactiveshell.py:3513: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.\n",
      "  warn(\"To exit: use 'exit', 'quit', or Ctrl-D.\", stacklevel=1)\n"
     ]
    }
   ],
   "source": [
    "from flask import Flask, render_template, request, jsonify\n",
    "import pickle\n",
    "import numpy as np\n",
    "import threading\n",
    "import webbrowser\n",
    "import time\n",
    "\n",
    "# Load the trained model\n",
    "with open('model.pkl', 'rb') as file:\n",
    "    model = pickle.load(file)\n",
    "\n",
    "app = Flask(__name__)\n",
    "\n",
    "@app.route('/')\n",
    "def home():\n",
    "    return render_template('index.html')\n",
    "\n",
    "@app.route('/predict', methods=['POST'])\n",
    "def predict():\n",
    "    # Collect form data\n",
    "    form_data = request.form\n",
    "    features = [\n",
    "        float(form_data['tsh']),\n",
    "        float(form_data['t3']),\n",
    "        float(form_data['tt4']),\n",
    "        float(form_data['t4u']),\n",
    "        float(form_data['fti'])\n",
    "    ]\n",
    "    \n",
    "    # Collect binary features\n",
    "    binary_features = [\n",
    "        form_data.get('sex'),\n",
    "        form_data.get('on_thyroxine'),\n",
    "        form_data.get('query_on_thyroxine'),\n",
    "        form_data.get('on_antithyroid_medication'),\n",
    "        form_data.get('pregnant'),\n",
    "        form_data.get('thyroid_surgery'),\n",
    "        form_data.get('query_hypothyroid'),\n",
    "        form_data.get('query_hyperthyroid'),\n",
    "        form_data.get('lithium'),\n",
    "        form_data.get('goitre'),\n",
    "        form_data.get('tumor'),\n",
    "        form_data.get('hypopituitary'),\n",
    "        form_data.get('psych'),\n",
    "        form_data.get('tsh_measured'),\n",
    "        form_data.get('t3_measured'),\n",
    "        form_data.get('tt4_measured'),\n",
    "        form_data.get('t4u_measured'),\n",
    "        form_data.get('fti_measured'),\n",
    "        form_data.get('referral_source_SVHC'),\n",
    "        form_data.get('referral_source_SVI'),\n",
    "        form_data.get('referral_source_other')\n",
    "    ]\n",
    "    \n",
    "    # Convert binary features to 1 or 0\n",
    "    binary_values = [1 if value else 0 for value in binary_features]\n",
    "    input_features = features + binary_values\n",
    "    \n",
    "    # Convert input to numpy array\n",
    "    input_array = np.array([input_features])\n",
    "    \n",
    "    # Make prediction\n",
    "    prediction = model.predict(input_array)[0]\n",
    "    \n",
    "    # Map prediction to positive/negative\n",
    "    prediction_label = 'Positive' if prediction == 1 else 'Negative'\n",
    "    \n",
    "    return jsonify({'prediction': prediction_label})\n",
    "\n",
    "def open_browser():\n",
    "    time.sleep(1)\n",
    "    webbrowser.open(\"http://127.0.0.1:5000/\")\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    threading.Thread(target=open_browser).start()\n",
    "    app.run(debug=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0160ca76",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " * Serving Flask app '__main__'\n",
      " * Debug mode: off\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.\n",
      " * Running on http://127.0.0.1:8000\n",
      "Press CTRL+C to quit\n",
      "127.0.0.1 - - [09/Jul/2024 20:03:32] \"GET / HTTP/1.1\" 200 -\n",
      "127.0.0.1 - - [09/Jul/2024 20:03:32] \"GET /static/styles.css HTTP/1.1\" 200 -\n",
      "127.0.0.1 - - [09/Jul/2024 20:03:32] \"GET /favicon.ico HTTP/1.1\" 404 -\n",
      "C:\\Users\\santh\\anaconda3\\Lib\\site-packages\\sklearn\\base.py:464: UserWarning: X does not have valid feature names, but RandomForestClassifier was fitted with feature names\n",
      "  warnings.warn(\n",
      "127.0.0.1 - - [09/Jul/2024 20:07:10] \"POST /predict HTTP/1.1\" 200 -\n"
     ]
    }
   ],
   "source": [
    "from flask import Flask, render_template, request, jsonify\n",
    "import numpy as np\n",
    "import pickle\n",
    "\n",
    "app = Flask(__name__)\n",
    "\n",
    "# Load the trained model\n",
    "with open('model.pkl', 'rb') as file:\n",
    "    model = pickle.load(file)\n",
    "\n",
    "@app.route('/')\n",
    "def index():\n",
    "    return render_template('index.html')\n",
    "\n",
    "@app.route('/predict', methods=['POST'])\n",
    "def predict():\n",
    "    # Extract form data\n",
    "    data = request.form.to_dict()\n",
    "    \n",
    "    # Extract numeric features\n",
    "    tsh = float(data.get('tsh', 0))\n",
    "    t3 = float(data.get('t3', 0))\n",
    "    tt4 = float(data.get('tt4', 0))\n",
    "    t4u = float(data.get('t4u', 0))\n",
    "    fti = float(data.get('fti', 0))\n",
    "    \n",
    "    # Extract binary features\n",
    "    sex = data.get('sex', 'male')  # Default to 'male' if not provided\n",
    "    on_thyroxine = 1 if data.get('on_thyroxine') == 'yes' else 0\n",
    "    query_on_thyroxine = 1 if data.get('query_on_thyroxine') == 'yes' else 0\n",
    "    on_antithyroid_medication = 1 if data.get('on_antithyroid_medication') == 'yes' else 0\n",
    "    pregnant = 1 if data.get('pregnant') == 'yes' else 0\n",
    "    thyroid_surgery = 1 if data.get('thyroid_surgery') == 'yes' else 0\n",
    "    query_hypothyroid = 1 if data.get('query_hypothyroid') == 'yes' else 0\n",
    "    query_hyperthyroid = 1 if data.get('query_hyperthyroid') == 'yes' else 0\n",
    "    lithium = 1 if data.get('lithium') == 'yes' else 0\n",
    "    goitre = 1 if data.get('goitre') == 'yes' else 0\n",
    "    tumor = 1 if data.get('tumor') == 'yes' else 0\n",
    "    hypopituitary = 1 if data.get('hypopituitary') == 'yes' else 0\n",
    "    psych = 1 if data.get('psych') == 'yes' else 0\n",
    "    tsh_measured = 1 if data.get('tsh_measured') == 'yes' else 0\n",
    "    t3_measured = 1 if data.get('t3_measured') == 'yes' else 0\n",
    "    tt4_measured = 1 if data.get('tt4_measured') == 'yes' else 0\n",
    "    t4u_measured = 1 if data.get('t4u_measured') == 'yes' else 0\n",
    "    fti_measured = 1 if data.get('fti_measured') == 'yes' else 0\n",
    "    referral_source_SVHC = 1 if data.get('referral_source_SVHC') == 'yes' else 0\n",
    "    referral_source_SVI = 1 if data.get('referral_source_SVI') == 'yes' else 0\n",
    "    referral_source_other = 1 if data.get('referral_source_other') == 'yes' else 0\n",
    "\n",
    "    # Convert to model input format\n",
    "    input_data = np.array([[1 if sex == 'male' else 0, tsh, t3, tt4, t4u, fti,\n",
    "                            on_thyroxine, query_on_thyroxine, on_antithyroid_medication, pregnant,\n",
    "                            thyroid_surgery, query_hypothyroid, query_hyperthyroid,\n",
    "                            lithium, goitre, tumor, hypopituitary, psych,\n",
    "                            tsh_measured, t3_measured, tt4_measured, t4u_measured,\n",
    "                            fti_measured, referral_source_SVHC, referral_source_SVI,\n",
    "                            referral_source_other]])\n",
    "\n",
    "    # Predict\n",
    "    prediction = model.predict(input_data)[0]\n",
    "    result = 'Positive' if prediction == 1 else 'Negative'\n",
    "\n",
    "    return jsonify({'prediction': result})\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    app.run(port=8000)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1d6f3e6f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}