{"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":"nvidiaTeslaT4","dataSources":[{"sourceId":104857,"databundleVersionId":12651513,"sourceType":"competition"}],"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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 # linear algebra\nimport 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\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","trusted":true,"execution":{"iopub.status.busy":"2025-06-14T13:23:38.520705Z","iopub.execute_input":"2025-06-14T13:23:38.52093Z","iopub.status.idle":"2025-06-14T13:23:38.873861Z","shell.execute_reply.started":"2025-06-14T13:23:38.520909Z","shell.execute_reply":"2025-06-14T13:23:38.872879Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\ntrain = pd.read_csv('/kaggle/input/burnout-datathon-ieeecsmuj/train.csv')\ntest = pd.read_csv('/kaggle/input/burnout-datathon-ieeecsmuj/test.csv')\nsample = pd.read_csv('/kaggle/input/burnout-datathon-ieeecsmuj/sample_submission.csv')\n\nprint(\"Train shape:\", train.shape)\nprint(\"Test shape:\", test.shape)\ntrain.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:15.01918Z","iopub.execute_input":"2025-06-14T14:31:15.019581Z","iopub.status.idle":"2025-06-14T14:31:30.864591Z","shell.execute_reply.started":"2025-06-14T14:31:15.019556Z","shell.execute_reply":"2025-06-14T14:31:30.863723Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Null Count\nprint(\"Missing values:\\n\", train.isnull().sum().sort_values(ascending=False).head(10))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:33.619341Z","iopub.execute_input":"2025-06-14T14:31:33.61977Z","iopub.status.idle":"2025-06-14T14:31:34.960746Z","shell.execute_reply.started":"2025-06-14T14:31:33.619744Z","shell.execute_reply":"2025-06-14T14:31:34.959561Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"TARGET = 'Lap_Time_Seconds'\n\nDROP_COLS = [\n    'Unique ID', 'rider_name', 'team_name', 'bike_name',\n    'circuit_name', 'points', 'position'\n]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:36.189082Z","iopub.execute_input":"2025-06-14T14:31:36.189402Z","iopub.status.idle":"2025-06-14T14:31:36.193578Z","shell.execute_reply.started":"2025-06-14T14:31:36.189382Z","shell.execute_reply":"2025-06-14T14:31:36.192719Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def add_features(df):\n    df['LapTime_Estimate'] = df['Circuit_Length_km'] / df['Avg_Speed_kmh'] * 3600\n    df['Points_per_Year'] = df['Championship_Points'] / (df['years_active'] + 1)\n    df['Finish_Rate'] = df['finishes'] / (df['starts'] + 1)\n    df['Podium_Rate'] = df['podiums'] / (df['starts'] + 1)\n    df['Win_Rate'] = df['wins'] / (df['starts'] + 1)\n    df['Avg_Temp'] = (df['Ambient_Temperature_Celsius'] + df['Track_Temperature_Celsius']) / 2\n    return df\n\ntrain = add_features(train)\ntest = add_features(test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:38.664369Z","iopub.execute_input":"2025-06-14T14:31:38.664725Z","iopub.status.idle":"2025-06-14T14:31:38.808598Z","shell.execute_reply.started":"2025-06-14T14:31:38.664698Z","shell.execute_reply":"2025-06-14T14:31:38.807712Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\nX = train.drop(DROP_COLS + [TARGET], axis=1)\nX_test = test.drop(DROP_COLS, axis=1)\ny = train[TARGET]\n\n\nall_data = pd.concat([X, X_test], axis=0)\nall_data.fillna(-1, inplace=True)\n\n\ncat_cols = all_data.select_dtypes(include='object').columns\nfor col in cat_cols:\n    all_data[col] = all_data[col].astype('category').cat.codes\n\n\nX = all_data.iloc[:len(train)]\nX_test = all_data.iloc[len(train):]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:40.33383Z","iopub.execute_input":"2025-06-14T14:31:40.334151Z","iopub.status.idle":"2025-06-14T14:31:45.135483Z","shell.execute_reply.started":"2025-06-14T14:31:40.334118Z","shell.execute_reply":"2025-06-14T14:31:45.134479Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:46.999199Z","iopub.execute_input":"2025-06-14T14:31:46.999539Z","iopub.status.idle":"2025-06-14T14:31:48.375635Z","shell.execute_reply.started":"2025-06-14T14:31:46.999514Z","shell.execute_reply":"2025-06-14T14:31:48.374744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from lightgbm import LGBMRegressor\nfrom sklearn.metrics import mean_squared_error","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:51.579126Z","iopub.execute_input":"2025-06-14T14:31:51.579825Z","iopub.status.idle":"2025-06-14T14:31:51.584324Z","shell.execute_reply.started":"2025-06-14T14:31:51.579792Z","shell.execute_reply":"2025-06-14T14:31:51.583378Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train['Speed_Degradation'] = X_train['Avg_Speed_kmh'] * X_train['Tire_Degradation_Factor_per_Lap']\nX_val['Speed_Degradation'] = X_val['Avg_Speed_kmh'] * X_val['Tire_Degradation_Factor_per_Lap']\nX_test['Speed_Degradation'] = X_test['Avg_Speed_kmh'] * X_test['Tire_Degradation_Factor_per_Lap']","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:53.959341Z","iopub.execute_input":"2025-06-14T14:31:53.959719Z","iopub.status.idle":"2025-06-14T14:31:53.978685Z","shell.execute_reply.started":"2025-06-14T14:31:53.959694Z","shell.execute_reply":"2025-06-14T14:31:53.977571Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train['Temp_Condition'] = X_train['Track_Temperature_Celsius'] * X_train['Track_Condition']\nX_val['Temp_Condition'] = X_val['Track_Temperature_Celsius'] * X_val['Track_Condition']\nX_test['Temp_Condition'] = X_test['Track_Temperature_Celsius'] * X_test['Track_Condition']\nX_train = X_train.drop(columns=['Est_Error'], errors='ignore')\nX_val = X_val.drop(columns=['Est_Error'], errors='ignore')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:56.79899Z","iopub.execute_input":"2025-06-14T14:31:56.799391Z","iopub.status.idle":"2025-06-14T14:31:57.72573Z","shell.execute_reply.started":"2025-06-14T14:31:56.799359Z","shell.execute_reply":"2025-06-14T14:31:57.724327Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = LGBMRegressor(\n    n_estimators=1500,\n    learning_rate=0.03,\n    max_depth=10,\n    num_leaves=90,\n    subsample=0.85,\n    colsample_bytree=0.85,\n    random_state=42\n)\n\nmodel.fit(X_train, y_train)\nval_preds = model.predict(X_val)\nrmse = mean_squared_error(y_val, val_preds, squared=False)\nprint(\"Validation RMSE:\", rmse)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:31:59.918859Z","iopub.execute_input":"2025-06-14T14:31:59.919197Z","iopub.status.idle":"2025-06-14T14:34:17.374083Z","shell.execute_reply.started":"2025-06-14T14:31:59.919171Z","shell.execute_reply":"2025-06-14T14:34:17.372676Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Ratio of Circuit length to number of corners\nX_train['Corners_per_Km'] = X_train['Corners_per_Lap'] / (X_train['Circuit_Length_km'] + 1e-3)\nX_val['Corners_per_Km'] = X_val['Corners_per_Lap'] / (X_val['Circuit_Length_km'] + 1e-3)\nX_test['Corners_per_Km'] = X_test['Corners_per_Lap'] / (X_test['Circuit_Length_km'] + 1e-3)\n\n# LapTime Estimate - Actual difference\nX_train['Est_Error'] = X_train['LapTime_Estimate'] - y_train\nX_val['Est_Error'] = X_val['LapTime_Estimate'] - y_val\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T13:30:57.008145Z","iopub.execute_input":"2025-06-14T13:30:57.008614Z","iopub.status.idle":"2025-06-14T13:30:57.045731Z","shell.execute_reply.started":"2025-06-14T13:30:57.008585Z","shell.execute_reply":"2025-06-14T13:30:57.044452Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = LGBMRegressor(\n    n_estimators=2000,\n    learning_rate=0.025,\n    max_depth=12,\n    num_leaves=100,\n    subsample=0.85,\n    colsample_bytree=0.8,\n    reg_alpha=1.5,\n    reg_lambda=2.0,\n    random_state=42\n)\n\nmodel.fit(X_train, y_train)\nval_preds = model.predict(X_val)\nrmse = mean_squared_error(y_val, val_preds, squared=False)\nprint(\"Validation RMSE:\", rmse)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T13:31:01.102369Z","iopub.execute_input":"2025-06-14T13:31:01.102717Z","iopub.status.idle":"2025-06-14T13:37:31.645549Z","shell.execute_reply.started":"2025-06-14T13:31:01.10269Z","shell.execute_reply":"2025-06-14T13:37:31.644532Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from ydata_profiling import ProfileReport\ntrain = pd.read_csv('/kaggle/input/burnout-datathon-ieeecsmuj/train.csv')\nprofile = ProfileReport(train, minimal=True)\nprofile.to_file(\"report.html\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:15:37.365757Z","iopub.execute_input":"2025-06-14T14:15:37.366116Z","iopub.status.idle":"2025-06-14T14:17:06.449548Z","shell.execute_reply.started":"2025-06-14T14:15:37.36609Z","shell.execute_reply":"2025-06-14T14:17:06.448516Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Make final predictions on test data\nfinal_preds = model.predict(X_test)\n\n# Create a DataFrame using the 'Unique ID' column from the original test set\nsubmission = pd.DataFrame({\n    'Unique ID': test['Unique ID'],\n    'Lap_Time_Seconds': final_preds\n})\n\n# Save to CSV\nsubmission.to_csv('solution.csv', index=False)\n\nprint(\"solution.csv has been saved successfully.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:29:50.620567Z","iopub.execute_input":"2025-06-14T14:29:50.620965Z","iopub.status.idle":"2025-06-14T14:29:50.64217Z","shell.execute_reply.started":"2025-06-14T14:29:50.620937Z","shell.execute_reply":"2025-06-14T14:29:50.640884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_test['Speed_Degradation'] = X_test['Avg_Speed_kmh'] * X_test['Tire_Degradation_Factor_per_Lap']\nX_test['Temp_Condition'] = X_test['Track_Temperature_Celsius'] * X_test['Track_Condition']\nX_test['Corners_per_Km'] = X_test['Corners_per_Lap'] / (X_test['Circuit_Length_km'] + 1e-3)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:29:45.960836Z","iopub.execute_input":"2025-06-14T14:29:45.961197Z","iopub.status.idle":"2025-06-14T14:29:46.035255Z","shell.execute_reply.started":"2025-06-14T14:29:45.961177Z","shell.execute_reply":"2025-06-14T14:29:46.034214Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(\"X_train shape:\", X_train.shape)\nprint(\"X_test shape:\", X_test.shape)\n\n# Print names of features in each\nprint(\"Train columns:\")\nprint(X_train.columns.tolist())\n\nprint(\"\\nTest columns:\")\nprint(X_test.columns.tolist())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:30:25.37943Z","iopub.execute_input":"2025-06-14T14:30:25.379814Z","iopub.status.idle":"2025-06-14T14:30:25.386513Z","shell.execute_reply.started":"2025-06-14T14:30:25.379788Z","shell.execute_reply":"2025-06-14T14:30:25.38516Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X_train = X_train.drop(columns=['Est_Error'], errors='ignore')\nX_val = X_val.drop(columns=['Est_Error'], errors='ignore')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:37:14.259067Z","iopub.execute_input":"2025-06-14T14:37:14.259454Z","iopub.status.idle":"2025-06-14T14:37:14.557793Z","shell.execute_reply.started":"2025-06-14T14:37:14.259427Z","shell.execute_reply":"2025-06-14T14:37:14.556837Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Final predictions\nfinal_preds = model.predict(X_test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:42:50.199073Z","iopub.execute_input":"2025-06-14T14:42:50.199386Z","iopub.status.idle":"2025-06-14T14:43:49.002233Z","shell.execute_reply.started":"2025-06-14T14:42:50.199366Z","shell.execute_reply":"2025-06-14T14:43:49.001107Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission = pd.DataFrame({\n    'Unique ID': test['Unique ID'],\n    'Lap_Time_Seconds': final_preds\n})\nsubmission.to_csv('sudarshana_output.csv', index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-14T14:43:58.485343Z","iopub.execute_input":"2025-06-14T14:43:58.485689Z","iopub.status.idle":"2025-06-14T14:43:59.7161Z","shell.execute_reply.started":"2025-06-14T14:43:58.485633Z","shell.execute_reply":"2025-06-14T14:43:59.71533Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}