{"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":30626,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Benchmarking Vowpal Wabbit for tabular data\n\nTabular data benchmark: ensemble of 5 un-tuned vowalpal wabbit.\nVowpal is a fast online learner.","metadata":{}},{"cell_type":"code","source":"from category_encoders import (\n    GLMMEncoder,\n    LeaveOneOutEncoder,\n    OneHotEncoder,\n    OrdinalEncoder,\n    TargetEncoder,\n    WOEEncoder,\n)\n\nimport numpy as np, pandas as pd\nimport os\nimport json\nfrom sklearn.metrics import log_loss, mean_squared_error\nfrom vowpalwabbit.sklearn_vw import VWRegressor, VWClassifier","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-01-17T07:38:01.016773Z","iopub.execute_input":"2024-01-17T07:38:01.017309Z","iopub.status.idle":"2024-01-17T07:38:04.159035Z","shell.execute_reply.started":"2024-01-17T07:38:01.017264Z","shell.execute_reply":"2024-01-17T07:38:04.157807Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#help(VWClassifier)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-01-17T07:38:04.161564Z","iopub.execute_input":"2024-01-17T07:38:04.162536Z","iopub.status.idle":"2024-01-17T07:38:04.185361Z","shell.execute_reply.started":"2024-01-17T07:38:04.162489Z","shell.execute_reply":"2024-01-17T07:38:04.184378Z"},"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\nn_seeds = 2 if DEBUG else 5\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        \n        for column_name in X.columns:\n            # Check if the column has uint dtype\n            if X[column_name].dtype in ['uint', 'uint8', 'uint32', 'uint64']:\n                # Convert uint to int32\n                X[column_name] = X[column_name].astype('int32')\n                X_test[column_name] = X_test[column_name].astype('int32')\n        \n        y = pd.read_parquet(f'{path}train/{identifier}/target_train.parquet')\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        #TO DO: random train / test split + custom metric\n        \n        preds = []\n        \n        params = {\n                \"learning_rate\": 0.3,\n                #\"l1\": 1e-8,\n                #\"l2\": 1e-8,\n                #\"power_t\": 0.1,\n                #\"initial_t\": 0.1,\n                #\"bit_precision\": 28\n            }\n        \n        for seed in range(n_seeds):\n            # target encode categories\n            enc = TargetEncoder(cols=X.columns[cat_indicator].to_list())\n            X.loc[:, X.columns[cat_indicator].to_list()] = enc.fit_transform(\n                X.loc[:, X.columns[cat_indicator].to_list()], y\n            )\n            \n            params[\"learning_rate\"] *= (seed + 1)\n            \n        \n            vowpal_model = VWRegressor(convert_labels=False, hash_seed=seed, **params) if target_type=='num' else VWClassifier(convert_labels=False, hash_seed=seed, **params)  \n            vowpal_model = vowpal_model.fit(X, y.values)\n            \n            X_test.loc[:, X.columns[cat_indicator].to_list()] = enc.transform(X_test.loc[:, X.columns[cat_indicator].to_list()])\n            \n            if target_type=='num':\n                preds.append(vowpal_model.predict(X_test))\n            else:\n                preds.append(vowpal_model.predict_proba(X_test)[:,1])\n            \n        preds = np.mean(np.array(preds),axis=0)\n\n        preds = pd.DataFrame(preds)\n        preds.index = X_test.index\n        \n        # appends empty tests / solutions\n        sub.append(prepare_sub(preds, identifier))\n        \n        print('')\n        print(f'{identifier=} {var_type=} {target_type=}')","metadata":{"execution":{"iopub.status.busy":"2024-01-17T07:38:04.189067Z","iopub.execute_input":"2024-01-17T07:38:04.190004Z"},"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}