{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd  \nfrom sklearn.metrics import mean_absolute_error\nfrom catboost import CatBoostRegressor, Pool\nimport os\nprint(os.listdir(\"../input\"))\n","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"def new_column(tr):\n    add_X = []\n    add_X.append(tr.values[0])\n    add_X.append(tr.values[-1])\n    add_X.append(tr.mean())\n    add_X.append(tr.count())\n    add_X.append(tr.sum())\n    add_X.append(tr.std())\n    add_X.append(tr.median())\n    add_X.append(tr.min())\n    add_X.append(tr.max())\n    add_X.append(tr.kurtosis())\n    add_X.append(tr.skew())\n    return pd.Series(add_X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#%time\ntr_data = pd.read_csv(\"../input/train.csv\", iterator=True, chunksize=600_000)\nx_tr_data = pd.DataFrame()\ny_tr_data = pd.Series()\nfor data in tr_data:\n    add_tr = new_column(data['acoustic_data'])\n    x_tr_data = x_tr_data.append(add_tr, ignore_index=True)\n    y_tr_data = y_tr_data.append(pd.Series(data['time_to_failure'].values[-1]))\n    \ndel tr_data\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_pool = Pool(x_tr_data, y_tr_data)\nmy_model = CatBoostRegressor(iterations=1000, loss_function='MAE', boosting_type='Ordered')\nmy_model.fit(x_tr_data, y_tr_data, silent=True)\nmy_model.best_score_","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/sample_submission.csv', index_col='seg_id')\ntest_data = pd.DataFrame(columns=x_tr_data.columns, dtype=np.float64, index=submission.index)\nfor seg_id in test_data.index:\n    seg = pd.read_csv('../input/test/' + seg_id + '.csv')\n    \n    add_tr = new_column(seg['acoustic_data'])\n    test_data.loc[seg_id]= add_tr    \n    \nsubmission['time_to_failure'] = my_model.predict(test_data)\nsubmission.to_csv('submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir(\"../input\"))\n\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}