{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"f9426532-c923-cec3-c279-f70a28aed044"},"source":"## "},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c471891c-1807-6416-43f3-1315827b1138"},"outputs":[],"source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\ntrain = pd.read_csv('../input/Train/train.csv')\ntrain.sample(10)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e4fc766f-b741-5b40-6da9-8e236f1464bf"},"outputs":[],"source":"train.mean()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0d5fc905-5d49-e5e3-164b-aca016b4a04e"},"outputs":[],"source":"target_cols = set(train.columns) - {'train_id'}\ntarget_cols"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b191e41d-e212-8758-48d9-72f13330fba2"},"outputs":[],"source":"from sklearn.linear_model import LinearRegression\nfrom sklearn.model_selection import cross_val_score\n\nfor y_col in sorted(target_cols):\n    X = train[list(target_cols - {y_col})].values\n    y = train[y_col].values\n    \n    neg_mse = cross_val_score(LinearRegression(), X, y, cv=4, scoring='neg_mean_squared_error').mean()\n    rmse = np.sqrt(-neg_mse)\n    nrmse = rmse / y.mean()\n    print(\"RMSE to predict column %-14s is %5.2f. Normalized value is %.4f\" % (y_col, rmse, nrmse))\n"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d495b723-9bf8-668f-17b0-f6b942e538ae"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}