pandas DataFrame 交集并集补集的实现
人气:01.场景,对于colums都相同的dataframe做过滤的时候
例如:
df1 = DataFrame([['a', 10, '男'], ['b', 11, '男'], ['c', 11, '女'], ['a', 10, '女'], ['c', 11, '男']], columns=['name', 'age', 'sex']) df2 = DataFrame([['a', 10, '男'], ['b', 11, '女']], columns=['name', 'age', 'sex'])
取交集:print(pd.merge(df1,df2,on=['name', 'age', 'sex']))
取并集:print(pd.merge(df1,df2,on=['name', 'age', 'sex'], how='outer'))
取差集(从df1中过滤df1在df2中存在的行):
df1 = df1.append(df2) df1 = df1.append(df2) df1 = df1.drop_duplicates(subset=['name', 'age', 'sex'],keep=False) print(df1)
代码:
# -*- coding:utf-8 -*- __version__ = '1.0.0.0' """ @brief : 简介 @details: 详细信息 @author : zhphuang @date : 2018-10-29 """ import pandas as pd from pandas import * df1 = DataFrame([['a', 10, '男'], ['b', 11, '男'], ['c', 11, '女'], ['a', 10, '女'], ['c', 11, '男']], columns=['name', 'age', 'sex']) print("df1:\n%s\n\n" % df1) df2 = DataFrame([['a', 10, '男'], ['b', 11, '女']], columns=['name', 'age', 'sex']) print("df2:\n%s\n\n" % df2) # 取交集 print("交集:\n%s\n\n" % pd.merge(df1,df2,on=['name', 'age', 'sex'])) # 取并集 print("并集:\n%s\n\n" % pd.merge(df1,df2,on=['name', 'age', 'sex'], how='outer')) # 从df1中过滤df1在df2中存在的行,也就是取补集 df1 = df1.append(df2) df1 = df1.append(df2) print("补集(从df1中过滤df1在df2中存在的行):\n%s\n\n" % df1.drop_duplicates(subset=['name', 'age', 'sex'],keep=False))
截图
您可能感兴趣的文章:
加载全部内容