Python中Merge使用的示例详解

merge(left, right, how=‘inner', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=True,
suffixes=('_x', ‘_y'), copy=True, indicator=False)

#coding=utf-8
import pandas as pd
import numpy as np

class PanMerge():
    def PanMer(self):
        data =  pd.DataFrame([{"id": 0, "name": 'lxh', "age": 20, "cp": 'lm'}, {"id": 1, "name": 'xiao', "age": 40, "cp": 'ly'},{"id": 2, "name": 'hua', "age": 4, "cp": 'yry'}, {"id": 3, "name": 'be', "age": 70, "cp": 'old'}])
        data1 = pd.DataFrame([{"id": 100, "name": 'lxh', 'cs': 10}, {"id": 101, "name": 'xiao', 'cs': 40},{"id": 102, "name": 'hua2', 'cs': 50}])
        data2 = pd.DataFrame([{"id": 0, "name": 'lxh', 'cs': 10}, {"id": 101, "name": 'xiao', 'cs': 40},{"id": 102, "name": 'hua2', 'cs': 50}])
        data3 = pd.DataFrame([{"mid": 0, "mname": 'lxh', 'cs': 10}, {"mid": 101, "mname": 'xiao', 'cs': 40},{"mid": 102, "mname": 'hua2', 'cs': 50}])
        # print(data)
        # print(data1)
        # print(data2)
        df1 = pd.merge(data,data1,on="name",how="left",suffixes=('_a','_b'))#相同的其他类名用_a和_b标注
        df2 = pd.merge(data, data2, on=("name", "id")) #多列名做为内链接的连接键
        df3 = pd.merge(data, data2)  #不指定on则以两个DataFrame的列名交集做为连接键

        # 使用右边的DataFrame的行索引做为连接键
        indexed_data1 = data1.set_index("name")##设置行索引名称
        # print(indexed_data1)
        df5 = pd. merge(data, indexed_data1, left_on='name', right_index=True) #"使用右边的DataFrame的行索引做为连接键\r\n"
        print(df5)
        print('左外连接\r\n',pd.merge(data,data1,on="name",how="left",suffixes=('_a','_b')))
        print('左外连接1\r\n',pd.merge(data1,data,on="name",how="left"))
        print ('右外连接\r\n',pd.merge(data,data1,on="name",how="right"))

        # 当左右两个DataFrame的列名不同，当又想做为连接键时可以使用left_on与right_on来指定连接键
        df6=pd.merge(data,data3,left_on=["name","id"],right_on=["mname","mid"])
        print(df6)

 dj1=pd.DataFrame([{"id":0,"name":'lxh',"age":20,"cp":'lm'},{"id":1,"name":'xiao',"age":40,"cp":'ly'},{"id":2,"name":'hua',"age":4,"cp":'yry'},{"id":3,"name":'be',"age":70,"cp":'old'}],index=['a','b','c','d'])
    dj2=pd.DataFrame([{"sex":0},{"sex":1},{"sex":2}],index=['a','b','e'])
    print(dj1)
    print(dj2)
    df7= dj1.join(dj2)
    print(df7)

    print('使用右连接\r\n', dj1.join(dj2, how="right") ) # 这里出自动屏蔽了data1中没有index=c,d的那行数据；等价于data1.join(data)
    print('使用内连接\r\n', dj1.join(dj2, how='inner'))
    print('使用全外连接\r\n', dj1.join(dj2, how='outer'))

     dc1 = pd.DataFrame({'city': ['Chicago', 'San Francisco', 'New York City'], 'rank': range(1, 4)})
        dc2 = pd.DataFrame({'city': ['Chicago', 'Boston', 'Los Angeles'], 'rank': [1, 4, 5]})
        print(dc1)
        print(dc2)
        # print('按轴进行内连接\r\n', pd.concat([dc1, dc2], join="inner", axis=0))
        dc3=pd.concat([dc1,dc2],join="inner", axis=0) #axis=1横向操作，axis=0纵向操作
        print(dc3)
        dc4=pd.concat([dc1,dc2],keys=['a','b']) #进行外连接并指定keys(行索引) 用a，b 进行标识
        print(dc4)

        dc5 = pd.concat([dc1,dc2],ignore_index=True).drop_duplicates() #完全一样时候，去重数据
        print(dc5)


if __name__ == '__main__':
    PanMerge().PanMer()