quora_predictor.py 文件源码

def trainModel(self):
        df = pd.read_pickle("./train_features.pkl")
        x_df = pd.concat([df.iloc[:,4:6],df.iloc[:,8]],axis=1)
        y_df = df.iloc[:,9]

        print(x_df)
        print(len(x_df))
        print(len(y_df))

        train_no = int(0.8 * len(df))
        #train_no = 100000
        print(train_no)

        train_df = x_df.iloc[0:train_no,:]
        train_labels = y_df.iloc[0:train_no]
        test_df = x_df.iloc[train_no:,:]
        test_labels = y_df.iloc[train_no:]

        self.model = LogisticClassifier(3)
        self.model.trainModel(train_df,train_labels)
        self.model.validateModel(test_df,test_labels)