{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "75418eb6",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2023-07-06T13:42:23.141738Z",
     "iopub.status.busy": "2023-07-06T13:42:23.141143Z",
     "iopub.status.idle": "2023-07-06T13:42:23.155666Z",
     "shell.execute_reply": "2023-07-06T13:42:23.154445Z"
    },
    "papermill": {
     "duration": 0.021833,
     "end_time": "2023-07-06T13:42:23.158621",
     "exception": false,
     "start_time": "2023-07-06T13:42:23.136788",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/kaggle/input/icr-identify-age-related-conditions/sample_submission.csv\n",
      "/kaggle/input/icr-identify-age-related-conditions/greeks.csv\n",
      "/kaggle/input/icr-identify-age-related-conditions/train.csv\n",
      "/kaggle/input/icr-identify-age-related-conditions/test.csv\n"
     ]
    }
   ],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "         print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "21694925",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-07-06T13:42:23.164800Z",
     "iopub.status.busy": "2023-07-06T13:42:23.164345Z",
     "iopub.status.idle": "2023-07-06T13:43:47.729268Z",
     "shell.execute_reply": "2023-07-06T13:43:47.728318Z"
    },
    "papermill": {
     "duration": 84.570727,
     "end_time": "2023-07-06T13:43:47.731786",
     "exception": false,
     "start_time": "2023-07-06T13:42:23.161059",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.impute import SimpleImputer\n",
    "from imblearn.over_sampling import RandomOverSampler\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, VotingClassifier\n",
    "\n",
    "# Open file with pd.read_csv\n",
    "df_train = pd.read_csv(\"/kaggle/input/icr-identify-age-related-conditions/train.csv\")\n",
    "df_test = pd.read_csv(\"/kaggle/input/icr-identify-age-related-conditions/test.csv\")\n",
    "\n",
    "# Convert 'A' and 'B' values in 'EJ' column to 0 and 1 respectively\n",
    "df_train['EJ'] = df_train['EJ'].map({'A': 0, 'B': 1})\n",
    "df_test['EJ'] = df_test['EJ'].map({'A': 0, 'B': 1})\n",
    "\n",
    "# Split the training data into features (X) and target variable (y)\n",
    "X_train = df_train.drop([\"Class\", \"Id\"], axis=1)  # Exclude non-numeric columns\n",
    "y_train = df_train[\"Class\"]\n",
    "\n",
    "# Split the test data into features (X_test)\n",
    "X_test = df_test.drop(\"Id\", axis=1)\n",
    "\n",
    "# Identify columns with missing values\n",
    "columns_with_missing = X_train.columns[X_train.isna().any()].tolist()\n",
    "\n",
    "# Impute missing values with the mean of each column\n",
    "imputer = SimpleImputer(strategy='mean')\n",
    "X_train_imputed = imputer.fit_transform(X_train)\n",
    "X_test_imputed = imputer.transform(X_test)\n",
    "\n",
    "# Scale the features using StandardScaler\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train_imputed)\n",
    "X_test_scaled = scaler.transform(X_test_imputed)\n",
    "\n",
    "# Handling class imbalance using oversampling\n",
    "oversampler = RandomOverSampler(random_state=42)\n",
    "X_train_scaled, y_train = oversampler.fit_resample(X_train_scaled, y_train)\n",
    "\n",
    "# Hyperparameter tuning for Random Forest Classifier\n",
    "rfc = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "param_grid = {'max_depth': [None, 5, 10], 'min_samples_split': [2, 5, 10]}\n",
    "grid_search = GridSearchCV(rfc, param_grid, cv=5, scoring='neg_log_loss')\n",
    "grid_search.fit(X_train_scaled, y_train)\n",
    "best_rfc = grid_search.best_estimator_\n",
    "\n",
    "# Hyperparameter tuning for Gradient Boosting Classifier\n",
    "gbc = GradientBoostingClassifier(n_estimators=100, random_state=42)\n",
    "param_grid = {'max_depth': [3, 5, 7], 'learning_rate': [0.01, 0.1, 1.0]}\n",
    "grid_search = GridSearchCV(gbc, param_grid, cv=5, scoring='neg_log_loss')\n",
    "grid_search.fit(X_train_scaled, y_train)\n",
    "best_gbc = grid_search.best_estimator_\n",
    "\n",
    "# Ensemble of models\n",
    "ensemble_model = VotingClassifier(estimators=[('rfc', best_rfc), ('gbc', best_gbc)], voting='soft')\n",
    "ensemble_model.fit(X_train_scaled, y_train)\n",
    "\n",
    "# Predict probabilities for each class in the test set\n",
    "ensemble_pred_proba = ensemble_model.predict_proba(X_test_scaled)\n",
    "\n",
    "# Create a DataFrame to store the predictions\n",
    "predictions_df = pd.DataFrame({'Id': df_test['Id'],\n",
    "                               'class_0': ensemble_pred_proba[:, 0],\n",
    "                               'class_1': ensemble_pred_proba[:, 1]})\n",
    "\n",
    "# Save the predictions to a CSV file\n",
    "predictions_df.to_csv('submission.csv', index=False)\n",
    "                                                       "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.10"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 97.427632,
   "end_time": "2023-07-06T13:43:48.755891",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2023-07-06T13:42:11.328259",
   "version": "2.4.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}