{"cells":[{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","collapsed":true,"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport os\nprint(os.listdir(\"../input\"))\n\ntrain_transformed = pd.read_csv(\"../input/avito-data-translation-and-transformation/train_transformed.csv\")\ntest_transformed = pd.read_csv(\"../input/avito-data-translation-and-transformation/test_transformed.csv\")\ntest_transformed.head(5)\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"fb93d985-6c1e-45bf-a7a1-28969b0ec621","_uuid":"085df0ab3cea67a8b3e47903c71991a80869401b","collapsed":true,"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestRegressor\nfrom sklearn.datasets import make_regression\n\nX,y = train_transformed.iloc[:, [3,4,5,6,7,8,9,10,11,12,14,17]], train_transformed.iloc[:,[18]]\n#X, y = shuffle(boston.data, boston.target, random_state=13)\nX = X.fillna(value=0)\nX = X.astype(np.float32)\ny = y.values.ravel()\n\nregr = RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=10,\n           max_features='auto', max_leaf_nodes=None,\n           min_impurity_decrease=0.0, min_impurity_split=None,\n           min_samples_leaf=1, min_samples_split=2,\n           min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1,\n           oob_score=False, random_state=10, verbose=0, warm_start=False)\n\nregr.fit(X, y)\n\nprint(regr.feature_importances_)\nregr.score(X,y)","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"352c9685-52a6-48a1-8f21-b4b1663992b8","_uuid":"24d61febc9b3a7216e8196d03003004bcf117242","collapsed":true,"trusted":true},"cell_type":"code","source":"deal_probability = regr.predict(test_transformed.iloc[:, [3,4,5,6,7,8,9,10,11,12,14,17]].fillna(value=0))\ndeal_prob = [x if x>0 else 0 for x in deal_probability]\n\n#print deal_prob\n#submission_op = pd.DataFrame(user_id = test_transformed['user_id'], deal_probability=deal_probability)\nsubmission_op = pd.DataFrame({'item_id': test_transformed['item_id'], 'deal_probability': deal_prob})\nsubmission_op = submission_op[['item_id', 'deal_probability']]\nsubmission_op.to_csv('submission.csv', index=False)\n","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}