{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":67223,"databundleVersionId":7463838,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np, pandas as pd\nimport os, json, warnings\n\nwarnings.filterwarnings(\"ignore\")\n\nfrom sklearn.linear_model import LinearRegression, LogisticRegression\nfrom sklearn.metrics import log_loss, mean_squared_error\nfrom sklearn.preprocessing import OneHotEncoder","metadata":{"execution":{"iopub.status.busy":"2024-01-15T20:22:19.544370Z","iopub.execute_input":"2024-01-15T20:22:19.544777Z","iopub.status.idle":"2024-01-15T20:22:19.551086Z","shell.execute_reply.started":"2024-01-15T20:22:19.544743Z","shell.execute_reply":"2024-01-15T20:22:19.549843Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"path = '/kaggle/input/bench-tab-v1/'\n\ntasks = json.load(open(f'{path}train/dict_task.json'))\nsuits = json.load(open(f'{path}train/dict_suit.json'))\n\nDEBUG = False\nsuits = {'334': [361110, 361111], '335': [361093]} if DEBUG else suits\n\ndef prepare_sub(data, identifier):\n    data = pd.DataFrame(data)\n    data.columns = ['target']\n    data['ID'] =  identifier + '_' + data.index.astype(str)\n    columns = ['ID','target']\n    return data[columns]\n\nres_gbdt = {}\nsub = []\n\nfor t in suits:\n    print(t)\n    for suit in suits[t]:\n        \n        identifier = f'{t}_{suit}'\n        task_type = tasks[t]\n        var_type = task_type['features']\n        target_type = task_type['target']\n\n        X = pd.read_parquet(f'{path}train/{identifier}/data_train.parquet')\n        X_test = pd.read_parquet(f'{path}train/{identifier}/data_test.parquet')\n        y = pd.read_parquet(f'{path}train/{identifier}/target_train.parquet')\n        idx_test = X_test.index\n        \n        names = json.load(open(f'{path}train/{identifier}/attribute_names.json'))\n        cat_indicator = json.load(open(f'{path}train/{identifier}/categorical_indicator.json'))\n        \n        preds = []\n        \n        if var_type == 'num+cat':\n            enc = OneHotEncoder(handle_unknown='ignore')\n            X_cat = enc.fit_transform(X.loc[:,cat_indicator].copy())\n            X_test_cat = enc.transform(X_test.loc[:,cat_indicator].copy())            \n            X = pd.concat([X.loc[:,[not c for c in cat_indicator]].reset_index(drop=True).copy(), pd.DataFrame(X_cat.toarray())],axis=1)\n            X_test = pd.concat([X_test.loc[:,[not c for c in cat_indicator]].reset_index(drop=True).copy(), pd.DataFrame(X_test_cat.toarray())],axis=1)\n            X.columns = X.columns.astype(str)\n            X_test.columns = X_test.columns.astype(str)\n        \n        base_model = LinearRegression() if target_type=='num' else LogisticRegression()\n        base_model = base_model.fit(X.fillna(X.mean()), y.values)\n        \n        if target_type=='num':\n            preds = base_model.predict(X_test)\n        else:\n            preds = base_model.predict_proba(X_test)[:,1]\n        \n        preds = pd.DataFrame(preds)\n        preds.index = idx_test\n        \n        # appends empty tests / solutions\n        sub.append(prepare_sub(preds, identifier))\n        \n        print('')\n        print(f'{identifier=} {var_type=} {target_type=}')\n\n","metadata":{"execution":{"iopub.status.busy":"2024-01-15T20:22:19.566447Z","iopub.execute_input":"2024-01-15T20:22:19.567245Z","iopub.status.idle":"2024-01-15T20:23:45.829785Z","shell.execute_reply.started":"2024-01-15T20:22:19.567203Z","shell.execute_reply":"2024-01-15T20:23:45.828223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.concat(sub).reset_index(drop=True)\ndisplay(sub.head())\nsub.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-15T20:23:45.838720Z","iopub.execute_input":"2024-01-15T20:23:45.844407Z","iopub.status.idle":"2024-01-15T20:24:18.297665Z","shell.execute_reply.started":"2024-01-15T20:23:45.844329Z","shell.execute_reply":"2024-01-15T20:24:18.296449Z"},"trusted":true},"execution_count":null,"outputs":[]}]}