{"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":"gpu","dataSources":[{"sourceId":67223,"databundleVersionId":7463838,"sourceType":"competition"}],"dockerImageVersionId":30626,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Benchmarking GBDT for tabular data\n\nTabular data benchmark: ensemble of 5 un-tuned catboost.\nCatboost has been choosen for: best performance out of the box and easy handling of categorical data.","metadata":{}},{"cell_type":"code","source":"%%capture\n!pip install bluecast","metadata":{"execution":{"iopub.status.busy":"2024-01-20T20:07:21.757992Z","iopub.execute_input":"2024-01-20T20:07:21.758670Z","iopub.status.idle":"2024-01-20T20:07:39.343699Z","shell.execute_reply.started":"2024-01-20T20:07:21.758636Z","shell.execute_reply":"2024-01-20T20:07:39.342434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from bluecast.blueprints.cast import BlueCast\nfrom bluecast.blueprints.cast_regression import BlueCastRegression\nfrom bluecast.config.training_config import TrainingConfig\n\nimport numpy as np, pandas as pd\nimport os\nimport json\nfrom sklearn.metrics import log_loss, mean_squared_error\n\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-01-20T20:07:39.346068Z","iopub.execute_input":"2024-01-20T20:07:39.346484Z","iopub.status.idle":"2024-01-20T20:07:46.334834Z","shell.execute_reply.started":"2024-01-20T20:07:39.346447Z","shell.execute_reply":"2024-01-20T20:07:46.333903Z"},"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 = 1 #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        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        for seed in range(n_seeds):\n            train_config = TrainingConfig()\n            #train_config.hypertuning_cv_folds = 5 # default is 1\n            train_config.global_random_state = seed\n            train_config.hyperparameter_tuning_max_runtime_secs = 60 * 10 # 10 minutes\n            \n            if target_type=='num':\n                automl = BlueCastRegression(\n                    class_problem=\"regression\",\n                    target_column=\"ml_target\",\n                   )\n                X[\"ml_target\"] = y.astype(float).values\n            else:\n                automl = BlueCast(\n                    class_problem=\"binary\",\n                    target_column=\"ml_target\",\n                   )\n                \n                X[\"ml_target\"] = y\n            \n            \n            automl.fit(X, target_col=\"ml_target\")\n            \n            if target_type=='num':\n                preds.append(automl.predict(X_test))\n            else:\n                y_probs, y_classes = automl.predict(X_test)\n                preds.append(y_probs)\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":"2024-01-20T20:07:46.336070Z","iopub.execute_input":"2024-01-20T20:07:46.336517Z","iopub.status.idle":"2024-01-20T20:28:40.301263Z","shell.execute_reply.started":"2024-01-20T20:07:46.336491Z","shell.execute_reply":"2024-01-20T20:28:40.299877Z"},"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":"2024-01-20T20:28:40.301937Z","iopub.status.idle":"2024-01-20T20:28:40.302283Z","shell.execute_reply.started":"2024-01-20T20:28:40.302100Z","shell.execute_reply":"2024-01-20T20:28:40.302115Z"},"trusted":true},"execution_count":null,"outputs":[]}]}