{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.linear_model import LogisticRegression\np = '../input/cat-in-the-dat-ii/'\nX = pd.concat([pd.read_csv(p+'train.csv').iloc[:,1:-1],\n               pd.read_csv(p+'test.csv').iloc[:,1:]]).astype('str')\ny = pd.read_csv(p+'train.csv').target\nsample = pd.read_csv(p+'sample_submission.csv') \nX = OneHotEncoder().fit_transform(X)\ntrain,test = X[:600000],X[600000:]\nsample['target'] = LogisticRegression(max_iter=1e5,C=0.06).fit(train,y).predict_proba(test)[:,1]\nsample.to_csv('submission.csv',index=False)","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}