{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":84253,"databundleVersionId":9421888,"sourceType":"competition"}],"dockerImageVersionId":30761,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","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\nimport numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import KFold\nfrom sklearn.linear_model import LinearRegression, Lasso, Ridge, RidgeCV\nfrom sklearn.ensemble import RandomForestRegressor, StackingRegressor\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn import feature_selection\n\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\nimport os\nfor 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-08-25T09:36:45.121456Z","iopub.execute_input":"2024-08-25T09:36:45.121900Z","iopub.status.idle":"2024-08-25T09:36:47.358984Z","shell.execute_reply.started":"2024-08-25T09:36:45.121858Z","shell.execute_reply":"2024-08-25T09:36:47.357657Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/first-steps-in-data-science-new/train (7).csv')\ntest = pd.read_csv('/kaggle/input/first-steps-in-data-science-new/test (4).csv')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.shape","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.describe().iloc[:, [0, -1]]","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"n_folds = 30\nweights = []\nkf = KFold(n_splits=n_folds, shuffle=True, random_state=42)\ntrain_data = train.iloc[:, :-1]\ntrain_target = train.iloc[:, -1]\n\n# Feature selection\nestimator = LinearRegression()\nselector = feature_selection.RFECV(estimator)\nselector.fit(train_data, train_target)\nrfe_train_data = train_data.iloc[:, selector.support_]\ntest_data = test.iloc[:, selector.support_]\ntest_preds = np.zeros((test_data.shape[0],))\n\n# Define base models\nbase_models = [\n    ('lr', LinearRegression()),\n    ('ridge', RidgeCV(alphas=(0.1, 1.0, 10.0, 30.0))),\n    ('rf', RandomForestRegressor(random_state=69))\n]\n\n# Define the stacking model\nstacking_model = StackingRegressor(\n    estimators=base_models,\n    final_estimator=LinearRegression()  # You can change this to another model if needed\n)\n\n# Cross-validation and prediction\nfor fold, (train_idx, val_idx) in enumerate(kf.split(train)):\n    X_train, y_train = rfe_train_data.iloc[train_idx], train_target[train_idx]\n    X_val, y_val = rfe_train_data.iloc[val_idx], train_target[val_idx]\n\n    stacking_model.fit(X_train, y_train)\n\n    val_preds = stacking_model.predict(X_val)\n    fold_rmse = mean_squared_error(y_val, val_preds, squared=False)\n    weights.append(1 / fold_rmse)\n    print(f'Fold {fold+1} RMSE: {fold_rmse}')\n    test_preds += stacking_model.predict(test_data) * weights[fold]\n\ntest_preds /= sum(weights)\n\n\n\nprint(test_preds)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('/kaggle/input/first-steps-in-data-science-new/sample.csv')\nsubmission['target'] = test_preds\nsubmission.to_csv('submission.csv', index = False)","metadata":{},"execution_count":null,"outputs":[]}]}