import pandas as pd

df1 = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                     'B': ['B0', 'B1', 'B2', 'B3']})
df2 = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                      'C': ['C0', 'C1', 'C2', 'C3'],
                      'D': ['D0', 'D1', 'D2', 'D3']})
df3 = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                    'key2': ['K0', 'K1', 'K0', 'K1'],
                    'A': ['A0', 'A1', 'A2', 'A3'],
                    'B': ['B0', 'B1', 'B2', 'B3']})
df4 = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                    'key2': ['K0', 'K0', 'K0', 'K0'],
                    'C': ['C0', 'C1', 'C2', 'C3'],
                    'D': ['D0', 'D1', 'D2', 'D3']})
print('-'*10,'df1','-'*10)
print(df1)
print('-'*10,'df2','-'*10)
print(df2)
print('-'*10,'df3','-'*10)
print(df3)
print('-'*10,'df4','-'*10)
print(df4)

print("-----pd.merge(df1, df2, on='key')-----")
print(pd.merge(df1, df2, on='key'))
print("-----pd.merge(df3, df4, on=['key1','key2'])-----")
print(pd.merge(df3, df4, on=['key1','key2']))

 

 

 

 

# 参数 left_on, right_on, left_index, right_index → 当键不为一个列时，可以单独设置左键与右键

df1 = pd.DataFrame({'lkey':list('bbacaab'),
                   'data1':range(7)})
df2 = pd.DataFrame({'rkey':list('abd'),
                   'date2':range(3)})
print(pd.merge(df1, df2, left_on='lkey', right_on='rkey'))
print('------')
# df1以‘lkey’为键，df2以‘rkey’为键

df1 = pd.DataFrame({'key':list('abcdfeg'),
                   'data1':range(7)})
df2 = pd.DataFrame({'date2':range(100,105)},
                  index = list('abcde'))
print(pd.merge(df1, df2, left_on='key', right_index=True))
# df1以‘key’为键，df2以index为键
# left_index：为True时，第一个df以index为键，默认False
# right_index：为True时，第二个df以index为键，默认False

# 所以left_on, right_on, left_index, right_index可以相互组合：
# left_on + right_on, left_on + right_index, left_index + right_on, left_index + right_index