- pd.merge( df1, df2, on=['key1', 'key2'], left_index=True, right_index=True, how=['left', 'right', 'outer', 'inner'], indicator='indicator_column', suffixes=['_boy', '_girl'] )
from __future__ import print_function
import pandas as pd
merging two df by key/keys， on='key'. (may be used in database)
# merging two df by key/keys. (may be used in database)
# simple example
left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
print(left)
print(right)
res = pd.merge(left, right, on='key') # 基于列标签为‘key’合并
print(res)
> key A B
> 0 K0 A0 B0
> 1 K1 A1 B1
> 2 K2 A2 B2
> 3 K3 A3 B3
> key C D
> 0 K0 C0 D0
> 1 K1 C1 D1
> 2 K2 C2 D2
> 3 K3 C3 D3
> key A B C D
> 0 K0 A0 B0 C0 D0
> 1 K1 A1 B1 C1 D1
> 2 K2 A2 B2 C2 D2
> 3 K3 A3 B3 C3 D3
consider two keys， on=['key1', 'key2']
# consider two keys
left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
'key2': ['K0', 'K1', 'K0', 'K1'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
'key2': ['K0', 'K0', 'K0', 'K0'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
print(left)
print(right)
> key1 key2 A B
> 0 K0 K0 A0 B0
> 1 K0 K1 A1 B1
> 2 K1 K0 A2 B2
> 3 K2 K1 A3 B3
> key1 key2 C D
> 0 K0 K0 C0 D0
> 1 K1 K0 C1 D1
> 2 K1 K0 C2 D2
> 3 K2 K0 C3 D3
res = pd.merge(left, right, on=['key1', 'key2'], how='inner') # default for how='inner'
print(res) # 求交集
res = pd.merge(left, right, on=['key1', 'key2'], how='outer') # default for how='inner'
print(res) # 求并集
> key1 key2 A B C D
> 0 K0 K0 A0 B0 C0 D0
> 1 K1 K0 A2 B2 C1 D1
> 2 K1 K0 A2 B2 C2 D2
> key1 key2 A B C D
> 0 K0 K0 A0 B0 C0 D0
> 1 K0 K1 A1 B1 NaN NaN
> 2 K1 K0 A2 B2 C1 D1
> 3 K1 K0 A2 B2 C2 D2
> 4 K2 K1 A3 B3 NaN NaN
> 5 K2 K0 NaN NaN C3 D3
how = ['left', 'right', 'outer', 'inner']
# how = ['left', 'right', 'outer', 'inner']
res = pd.merge(left, right, on=['key1', 'key2'], how='right')
print(res) # 以右边的数据为标准，来合并
> key1 key2 A B C D
> 0 K0 K0 A0 B0 C0 D0
> 1 K1 K0 A2 B2 C1 D1
> 2 K1 K0 A2 B2 C2 D2
> 3 K2 K0 NaN NaN C3 D3
显示数据的来源，多_merge这一列，默认是false不显示:indicator=True 或 indicator='indicator_column' 自定义indicator列名称
# indicator
df1 = pd.DataFrame({'col1':[0,1], 'col_left':['a','b']})
df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]})
print(df1)
print(df2)
res = pd.merge(df1, df2, on='col1', how='outer', indicator=True)
print(res)
> col1 col_left
> 0 0 a
> 1 1 b
> col1 col_right
> 0 1 2
> 1 2 2
> 2 2 2
> col1 col_left col_right _merge
> 0 0 a NaN left_only
> 1 1 b 2.0 both
> 2 2 NaN 2.0 right_only
> 3 2 NaN 2.0 right_only
# give the indicator a custom name
res = pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
print(res) # 设置这列的标题为'indicator_column'
> col1 col_left col_right indicator_column
> 0 0 a NaN left_only
> 1 1 b 2.0 both
> 2 2 NaN 2.0 right_only
> 3 2 NaN 2.0 right_only
handle overlapping 信息重叠： suffixes=['_boy', '_girl']
# handle overlapping
boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
girls = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'age': [4, 5, 6]})
res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')
print(boys)
print(girls)
print(res)
> k age
> 0 K0 1
> 1 K1 2
> 2 K2 3
> k age
> 0 K0 4
> 1 K0 5
> 2 K3 6
> k age_boy age_girl
> 0 K0 1 4
> 1 K0 1 5
res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='outer')
print(res) # 这里的K0，K1理解成姓名，同一个姓名对应了不同的年龄，说明信息重叠了。
> k age_boy age_girl
> 0 K0 1.0 4.0
> 1 K0 1.0 5.0
> 2 K1 2.0 NaN
> 3 K2 3.0 NaN
> 4 K3 NaN 6.0
merged by index： left_index=True, right_index=True
# merged by index
left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
'B': ['B0', 'B1', 'B2']},
index=['K0', 'K1', 'K2'])
right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],
'D': ['D0', 'D2', 'D3']},
index=['K0', 'K2', 'K3'])
print(left)
print(right)
> A B
> K0 A0 B0
> K1 A1 B1
> K2 A2 B2
> C D
> K0 C0 D0
> K2 C2 D2
> K3 C3 D3
# left_index and right_index 默认是False
res = pd.merge(left, right, left_index=True, right_index=True, how='outer')
print(res) # 并
res = pd.merge(left, right, left_index=True, right_index=True, how='inner')
print(res) # 交
> A B C D
> K0 A0 B0 C0 D0
> K1 A1 B1 NaN NaN
> K2 A2 B2 C2 D2
> K3 NaN NaN C3 D3
> A B C D
> K0 A0 B0 C0 D0
> K2 A2 B2 C2 D2
join：join function in pandas is similar with merge. If know merge, you will understand join
END