{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom sklearn.decomposition import PCA\nfrom sklearn.preprocessing import normalize\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import LinearRegression\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n%matplotlib inline\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f1eb7aca237b3953913607256aa2626bfb3469d6"},"cell_type":"code","source":"PATH = \"../input/\"\n\ntrain = pd.read_csv(PATH+'train.csv')\ntest = pd.read_csv(PATH+'test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c96bb9cbda71e32e2f0b472f7c4b2c63d4945d39"},"cell_type":"code","source":"df = train.copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"60a9d8cb77f43dce413447035e4c5f8b45f2f3bb"},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2eddf2d0ac146e841ea223c1660effa343fd4aab"},"cell_type":"code","source":"df.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e2bfd7493f5ab652d0ca6fbe766d080ad826ae38"},"cell_type":"code","source":"df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ca42f0d6a5266533650ba5e88f451c7158f80909"},"cell_type":"code","source":"df = df[df.target >= -20]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"343bdfce78fe47287148ce46cce6027232e8a237"},"cell_type":"code","source":"df['first_active_month'] = pd.to_datetime(df['first_active_month'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"47810d8f445ec13ca1f433af8141d2411eff7948"},"cell_type":"code","source":"features = pd.get_dummies(df['first_active_month'].dt.month,\n              prefix='month')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"72a9bb97f6b1ebf263e4ba6d68fb6db2cde99ec7"},"cell_type":"code","source":"# features = pd.concat([features, \n#                 pd.get_dummies(df['first_active_month'].dt.year,\n#               prefix='year')], 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fbc11f74493f74a34391fcb12b3ae07f87c6e1a8"},"cell_type":"code","source":"for feature in ['feature_1',\n               'feature_2',\n               'feature_3']:\n    features = pd.concat([features,\n               pd.get_dummies(df[feature],\n                  prefix=feature)], 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d3c9512081c5341c6adb5bca8f94d637e0943106"},"cell_type":"code","source":"features.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"443784baee47a75edf3ea57283f59b23f7f0e458"},"cell_type":"code","source":"sns.distplot(df['target'])\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c430d178ef29f6bee9e7b7f70322e83b28c0c86c"},"cell_type":"code","source":"df.target.quantile(.9995)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7bfb95b556a11128e82e03c1263a2e16d263f342"},"cell_type":"code","source":"sns.distplot(df.target)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5316f1962a81c8076c8ecb5fe5fa8517043845de"},"cell_type":"code","source":"X = normalize(features)\ny = df['target']\npca = PCA(n_components=10)\npca.fit(X)\nprint(pca.explained_variance_ratio_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7b6b9c5e3fdfa150e2ad642d15abb9e77d5c6ef9"},"cell_type":"code","source":"plt.figure(dpi=100, figsize=(10, 8))\nsns.heatmap(features.corr())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"05ab366def57779c642b3dda5c959e9f2c2251d0"},"cell_type":"code","source":"# combine feature_3_0 and feature_3_1\n# features 2_1 and 2_2\n# and features 1_2 and 1_3 with features 3_0 and 3_1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"712b7e0b2f5501e5cccdde767583eed21d8371fc"},"cell_type":"code","source":"features['feature_30_31'] = features['feature_3_0'] + features['feature_3_1']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5052ac40c91192678a9e1fcd76a21ed43889f3e1"},"cell_type":"code","source":"features['feature_21_22'] = features['feature_2_1'] + features['feature_2_2']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"71027e56f6f6392d1efce018585d259e2eeedb30"},"cell_type":"code","source":"features['feature_12_13_21_22'] = features['feature_1_2']+features['feature_1_3']+features['feature_2_1']+features['feature_2_2']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ae92ca1ffa9e688355b02ebc6e54072ec3e179a3"},"cell_type":"code","source":"features = features.drop(['feature_3_0', \n                          'feature_3_1',\n                         'feature_2_1',\n                          'feature_2_2'], 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a5dd7db28604b92f280f093fe1e011dd8ed6e085"},"cell_type":"code","source":"features = features.drop('feature_30_31', 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"aa85a6bf4e088862197e3985710d7a172c144612"},"cell_type":"code","source":"plt.figure(dpi=100, figsize=(10, 8))\nsns.heatmap(features.corr())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"18552941de7fde5e7e58a66b22824b4f1e320ff9"},"cell_type":"code","source":"features['feature_21_22'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0e22264c85392507094957034def384d0bbc2143"},"cell_type":"code","source":"features['feature_2_3'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"42d74ad684f84fcbd9d6a43677ba010e00875ca7"},"cell_type":"code","source":"features['feature_21_22_2_3'] = np.where((features['feature_21_22']==1)|(features['feature_2_3']==1), 1, 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d171e7855c8e2b7eaf18c3f487c0a3c3933d54cd"},"cell_type":"code","source":"features = features.drop(['feature_21_22', 'feature_2_3'], 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"66a61cca3cf29de0c36710546060a1fc5a9c75c5"},"cell_type":"code","source":"plt.figure(dpi=100, figsize=(10, 8))\nsns.heatmap(features.corr())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0b9a2cd12c49eb05198e5d79757e751e7f451733"},"cell_type":"code","source":"X = features\ny = df['target']\n\nlr = LinearRegression().fit(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"09607ce0cb386fff06833cad123c750eaa2f145f"},"cell_type":"code","source":"y_pred = lr.predict(X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"dd993e946c9d0ef9aebd7073416d6d25b18042c1"},"cell_type":"code","source":"mean_squared_error(y, y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3adb02eb8a9ff54e1bdc8f79014f46c421414a3d"},"cell_type":"code","source":"# test ETL\n\ndf = test.copy()\ndf['first_active_month'] = pd.to_datetime(df['first_active_month'])\n\nfeatures = pd.get_dummies(df['first_active_month'].dt.month,\n              prefix='month')\n\nfor feature in ['feature_1',\n               'feature_2',\n               'feature_3']:\n    features = pd.concat([features,\n               pd.get_dummies(df[feature],\n                  prefix=feature)], 1)\n    \nfeatures['feature_30_31'] = features['feature_3_0'] + features['feature_3_1']\n\nfeatures['feature_21_22'] = features['feature_2_1'] + features['feature_2_2']\n\nfeatures['feature_12_13_21_22'] = features['feature_1_2']+features['feature_1_3']+features['feature_2_1']+features['feature_2_2']\n\nfeatures = features.drop(['feature_3_0', \n                          'feature_3_1',\n                         'feature_2_1',\n                          'feature_2_2'], 1)\nfeatures = features.drop('feature_30_31', 1)\n\nfeatures['feature_21_22_2_3'] = np.where((features['feature_21_22']==1)|(features['feature_2_3']==1), 1, 0)\nfeatures = features.drop(['feature_21_22', 'feature_2_3'], 1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"088976186271daa0306ba7f49a59da18a9c482de"},"cell_type":"code","source":"X_test = features\n\ny_pred = lr.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f75fbc00748a7d61f2aaa773f6e2b2af90be3c26"},"cell_type":"code","source":"preds = pd.DataFrame(test['card_id'], columns=['card_id'])\n\npreds['target'] = y_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9fcef7d5768b1892445836b8e38c9b73843ad448"},"cell_type":"code","source":"my_submission = preds.copy()\nmy_submission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"09fdf959f0dfc28a351a048b6c824309450689e8"},"cell_type":"code","source":"from sklearn.ensemble import RandomForestRegressor\n\nrfr = RandomForestRegressor().fit(X, y)\n\nrfr.score(X, y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3058e96e38338834561542bf111ec391dbbdf320"},"cell_type":"code","source":"y_pred = rfr.predict(X_test)\n\npreds = pd.DataFrame(test['card_id'], columns=['card_id'])\n\npreds['target'] = y_pred\n\nmy_submission = preds.copy()\nmy_submission.to_csv('rfr_submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e17c774631dd0c8f0682e92a55e255d1a5742c50"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}