{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":104857,"databundleVersionId":12651513,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\n\n# Load the CSV files\ntrain = pd.read_csv('/kaggle/input//kaggle/input/burnout-datathon-ieeecsmuj/train.csv')\ntest = pd.read_csv('/kaggle/input//kaggle/input/burnout-datathon-ieeecsmuj/test.csv')\nsample = pd.read_csv('/kaggle/input//kaggle/input/burnout-datathon-ieeecsmuj/sample_submission.csv')\n\ntrain.head()\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.791003Z","iopub.execute_input":"2025-06-14T06:16:09.791435Z","iopub.status.idle":"2025-06-14T06:16:09.894934Z","shell.execute_reply.started":"2025-06-14T06:16:09.791397Z","shell.execute_reply":"2025-06-14T06:16:09.893271Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.info()\ntrain.describe()\ntrain.isnull().sum()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.896504Z","iopub.status.idle":"2025-06-14T06:16:09.896868Z","shell.execute_reply.started":"2025-06-14T06:16:09.896727Z","shell.execute_reply":"2025-06-14T06:16:09.896744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Replace with your actual target column name\ntarget = 'final_time'\n\nX = train.drop(columns=[target])\ny = train[target]\n\n# Convert text to numbers (if needed)\nX = pd.get_dummies(X)\ntest = pd.get_dummies(test)\n\n# Match columns between X and test\nX, test = X.align(test, join='left', axis=1, fill_value=0)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.897541Z","iopub.status.idle":"2025-06-14T06:16:09.897811Z","shell.execute_reply.started":"2025-06-14T06:16:09.897692Z","shell.execute_reply":"2025-06-14T06:16:09.897704Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.metrics import mean_squared_error\n\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\nmodel = RandomForestRegressor()\nmodel.fit(X_train, y_train)\n\ny_pred = model.predict(X_val)\nprint(\"Validation RMSE:\", mean_squared_error(y_val, y_pred, squared=False))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.898867Z","iopub.status.idle":"2025-06-14T06:16:09.89915Z","shell.execute_reply.started":"2025-06-14T06:16:09.899023Z","shell.execute_reply":"2025-06-14T06:16:09.899037Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_preds = model.predict(test)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.900703Z","iopub.status.idle":"2025-06-14T06:16:09.901132Z","shell.execute_reply.started":"2025-06-14T06:16:09.900965Z","shell.execute_reply":"2025-06-14T06:16:09.900983Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sample = pd.read_csv('/kaggle/input/your-dataset/sample_submission.csv')\n\n# Assume test_preds is the output of model.predict(test)\nsample['final_time'] = test_preds  # <-- match column name\n\nsample.to_csv('solution.csv', index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T06:16:09.902665Z","iopub.status.idle":"2025-06-14T06:16:09.902968Z","shell.execute_reply.started":"2025-06-14T06:16:09.902848Z","shell.execute_reply":"2025-06-14T06:16:09.902861Z"}},"outputs":[],"execution_count":null}]}