house_prices.py 文件源码

def one_hot_encoder(df, estimated_var):
        df_class = df.copy()
        ohe = OneHotEncoder()
        label_classes = df_class[estimated_var].factorize()[1]
        new_one_hot_encoded_features = [''.join([estimated_var, '_', x]) for x in label_classes]
        mask = ~df[estimated_var].isnull()
        feature_var_values = ohe.fit_transform(np.reshape(np.array(df[''.join([estimated_var, 'Num'])][mask].values),
                                                          (df[mask].shape[0], 1))).toarray().astype(int)
        # Create new feature_var columns with one-hot encoded values
        for ite in new_one_hot_encoded_features:
            df[ite] = df[estimated_var]
        df.loc[mask, tuple(new_one_hot_encoded_features)] = feature_var_values