{"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 \nimport os\nimport time","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/vulcanic-preprocessing/train_sample.csv')\ntest_df = pd.read_csv('../input/vulcanic-preprocessing/test.csv')\ntest_df.drop(test_df.columns[0], axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x = train_df.to_numpy()\ntest_x = test_df.to_numpy()\ntrain_y = pd.read_csv('../input/vulcanic-preprocessing/targets.csv').to_numpy()\ntrain_y = train_y.ravel()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntrain_x.shape, test_x.shape, train_y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import cross_val_score\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.feature_selection import SelectKBest,f_regression\nfrom sklearn.pipeline import Pipeline\n\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.svm import SVR\nfrom sklearn.ensemble import GradientBoostingRegressor\nimport xgboost as xgb\nimport lightgbm as lgb","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rf = RandomForestRegressor()\nrf.n_jobs = -1\nstart = time.time()\nrf.fit(train_x, train_y)\nrf_score = cross_val_score(rf,train_x,train_y,scoring= 'neg_mean_squared_error', cv=3)\nrf_train_rmse_score = np.sqrt(-rf_score)\n\ntrain_r2_score = rf.score(train_x, train_y) \n\nend = time.time()\nelapsed = (end - start) // 60, (end - start) % 60  \nprint(f'train RMSE: {rf_train_rmse_score.mean()}, train R2: {train_r2_score}, elapsed time: {elapsed[0]} mins, {elapsed[1]} secs')\n    \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tree = DecisionTreeRegressor()\ntree.n_jobs = -1\nstart = time.time()\ntree.fit(train_x, train_y)\ntree_score = cross_val_score(tree,train_x,train_y,scoring= 'neg_mean_squared_error', cv=3)\ntree_train_rmse_score = np.sqrt(-tree_score)\n\ntrain_r2_score = tree.score(train_x, train_y) \n\nend = time.time()\nelapsed = (end - start) // 60, (end - start) % 60  \nprint(f'train RMSE: {tree_train_rmse_score.mean()}, train R2: {train_r2_score}, elapsed time: {elapsed[0]} mins, {elapsed[1]} secs')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xgb_model = xgb.XGBRegressor()\nstart = time.time()\nxgb_model.fit(train_x, train_y)\nxgb_score = cross_val_score(xgb_model,train_x,train_y,scoring= 'neg_mean_squared_error', cv=3)\nxgb_train_rmse_score = np.sqrt(-xgb_score)\n\ntrain_r2_score = xgb_model.score(train_x, train_y) \n\nend = time.time()\nelapsed = (end - start) // 60, (end - start) % 60  \nprint(f'train RMSE: {xgb_train_rmse_score.mean()}, train R2: {train_r2_score}, elapsed time: {elapsed[0]} mins, {elapsed[1]} secs')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lgb_model = lgb.LGBMRegressor()\nstart = time.time()\nlgb_model.fit(train_x, train_y)\nlgb_score = cross_val_score(lgb_model,train_x,train_y,scoring= 'neg_mean_squared_error', cv=3)\nlgb_train_rmse_score = np.sqrt(-lgb_score)\n\ntrain_r2_score = lgb_model.score(train_x, train_y) \n\nend = time.time()\nelapsed = (end - start) // 60, (end - start) % 60  \nprint(f'train RMSE: {lgb_train_rmse_score.mean()}, train R2: {train_r2_score}, elapsed time: {elapsed[0]} mins, {elapsed[1]} secs')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lgb_model.predict(test_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}