gen_sku_fea.py 文件源码

def get_comment_product_fea(endtime):
    enddt = pd.to_datetime(endtime,format = '%Y-%m-%d')
    if enddt == pd.to_datetime('2016-04-15',format = '%Y-%m-%d'):
        commentdata = pd.read_csv(FilePath + CommentFile)
        commentdata = commentdata[(commentdata["dt"] == "2016-04-15")]
        commentdata = commentdata.sort_values(by="sku_id").reset_index()[["sku_id", "comment_num", "has_bad_comment", "bad_comment_rate"]]
        return commentdata
    else:
        startdt = enddt - pd.Timedelta(days=7)
        commentpath = FilePath + CommentFile
        commentdata_ALL = pd.read_csv(commentpath)  # ?Jdatya_comment.csv??????
        commentdata_ALL.dt = pd.to_datetime(commentdata_ALL.dt, format='%Y-%m-%d')  # ?dt????date??
        comment = commentdata_ALL[(commentdata_ALL.dt <= enddt) & (commentdata_ALL.dt > startdt)]
        df = pd.get_dummies(comment['comment_num'], prefix='comment_num')
        comment = pd.concat([comment, df], axis=1)
        comment = comment[['sku_id', 'has_bad_comment', 'bad_comment_rate', 'comment_num_1', 'comment_num_2', 'comment_num_3','comment_num_4']]
        sorted_comment = comment.sort_values(by=['sku_id']).reset_index().drop('index',1)
        #sorted_comment.to_csv(FilePath + 'skuFeaInComment_before'+str(enddt), index=False)
        return sorted_comment

# ????????