ml.py 文件源码

def normalise(csv_filepath):
    """
    load csv data and normalize it
    :param csv_filepath:
    :return:
    """
    df = pd.read_csv(csv_filepath)[[
        'companyScore', 'describeScore', 'comprehensiveScore', 'interviewerScore', 'usefulCount', 'myScore',
        'replyCount', 'isAnonymous']][1:]
    senti_df = pd.read_csv(csv_filepath)['sentiment'][1:]
    labels_ = [1 if _ > 0.9 else 0 for _ in senti_df]
    df['isAnonymous'] = [int(_) for _ in df['isAnonymous']]
    df_scaled = pd.DataFrame(preprocessing.scale(df))

    return df_scaled, labels_