xgb_feature.py 文件源码

def get_comments_product_feat(start_date, end_date):
    dump_path = './cache/comments_accumulate_%s_%s.pkl' % (start_date, end_date)
    if os.path.exists(dump_path):
        comments = pickle.load(open(dump_path))
    else:
        comments = pd.read_csv(comment_path)
        comment_date_end = end_date
        comment_date_begin = comment_date[0]
        for date in reversed(comment_date):
            if date < comment_date_end:
                comment_date_begin = date
                break
        comments = comments[(comments.dt >= comment_date_begin) & (comments.dt < comment_date_end)]
        df = pd.get_dummies(comments['comment_num'], prefix='comment_num')
        comments = pd.concat([comments, df], axis=1)  # type: pd.DataFrame
        # del comments['dt']
        # del comments['comment_num']
        comments = comments[
            ['sku_id', 'has_bad_comment', 'bad_comment_rate', 'comment_num_1', 'comment_num_2', 'comment_num_3',
             'comment_num_4']]
        pickle.dump(comments, open(dump_path, 'w'))
    return comments