def checksame(df,colname):
if df[colname].is_unique:
return [1,df]#无重复,返回原df
else:
#将重复数据保留一个(keep='first')
a = df.drop_duplicates(subset=['ts_code'],keep='first')
#将重复数据全部去除(keep=False)
b = df.drop_duplicates(subset=['ts_code'],keep=False)
#做差集得到哪些重复的值
c = a.append(b).drop_duplicates(subset=['ts_code'],keep=False)
return [0,c]#有重复,返回重复数据
Python Dataframe 去重