bos=[‘61,181’,‘44,303’,‘42,439’,‘22,984’,‘13,979’,‘61,181’,‘44,303’,‘41,439’,‘20,984’,‘19,979’]
persons=[‘31’,‘23’,‘56’,‘17’,‘9’,‘31’,‘23’,‘56’,‘17’,‘9’]
prices=[‘51’,‘43’,‘56’,‘57’,‘49’,‘51’,‘43’,‘56’,‘57’,‘49’]
showdate=[‘2022-12-03’,‘2022-12-05’,‘2022-12-01’,‘2022-12-02’,‘2022-11-05’,‘2022-12-03’,‘2022-12-05’,‘2022-12-01’,‘2022-12-02’,‘2022-11-05’]
ftypes=[‘剧情’,‘动作’,‘喜剧’,‘剧情’,‘剧情’,‘爱情’,‘动作’,‘动画’,‘动画’,‘动画’]
points=[‘8.1’,‘9.0’,‘7.9’,‘6.7’,‘3.8’,‘8.1’,‘9.0’,‘7.9’,‘6.7’,‘3.8’]
filmdescript={
‘ftypes’:ftypes,
‘bos’:bos,
‘prices’:prices,
‘persons’:persons,
‘regions’:regions,
‘showdate’:showdate,
‘points’:points
}
import numpy as np
import pandas as pd
cnbo2021top5=pd.DataFrame(filmdescript,index=films)
cnbo2021top5[[‘prices’,‘persons’]]=cnbo2021top5[[‘prices’,‘persons’]].astype(int)
cnbo2021top5[‘bos’]=cnbo2021top5[‘bos’].str.replace(‘,’,‘’).astype(int)
cnbo2021top5[‘showdate’]=cnbo2021top5[‘showdate’].astype(‘datetime64’)
cnbo2021top5[‘points’]=cnbo2021top5[‘points’].apply(lambda x:float(x) if x!=‘’ else 0)
关于cnboo1.xlsx
,我放在我的码云里,需要的朋友自行下载:cnboo1.xlsx
读取并初步整理数据集
import pandas as pd
cnbodf=pd.read_excel(‘cnboo1.xlsx’)
cnbodfsort=cnbodf.sort_values(by=[‘BO’],ascending=False)
def mkpoints(x,y): # 编写points评分
return len(str(