scrape_ratings_threaded.py 文件源码

def load_pkl():
    '''
    loads a pickled DataFrame with the employers to scrape ratings for.

    INPUT:
        None

    OUTPUT:
        df: pandas DataFrame
        split: threshold of good/bad employer ratings
    '''
    df = pd.read_pickle(os.path.join('data', 'clean_employers.pkl'))
    df['company_id'] = df['company_id'].astype(int)
    df['num_ratings'] = df['num_ratings'].astype(int)
    split = df['overall_rating'].mean()
    return df, split