pandas中的merge和concat類似,但主要是用於兩組有key column的數據,統一索引的數據. 通常也被用在Database的處理當中.
1、依據一組key合並
>>> import pandas as pd >>> 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) key A B 0 K0 A0 B0 1 K1 A1 B1 2 K2 A2 B2 3 K3 A3 B3 >>> print(right) key C D 0 K0 C0 D0 1 K1 C1 D1 2 K2 C2 D2 3 K3 C3 D3 #依據key column合並，並打印出 >>> res = pd.merge(left, right, on='key') >>> print(res) 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
2、依據兩組key合並
合並時有4種方法how = ['left', 'right', 'outer', 'inner']，預設值how='inner'
>>> 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)
key1 key2 A B
0 K0 K0 A0 B0
1 K0 K1 A1 B1
2 K1 K0 A2 B2
3 K2 K1 A3 B3
>>> print(right)
key1 key2 C D
0 K0 K0 C0 D0
1 K1 K0 C1 D1
2 K1 K0 C2 D2
3 K2 K0 C3 D3
##依據key1與key2 columns進行合並，並打印出四種結果['left', 'right', 'outer', 'inner']
>>> res = pd.merge(left, right, on=['key1', 'key2'], how='inner')
>>> print(res)
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
>>> res = pd.merge(left, right, on=['key1', 'key2'], how='outer')
>>> print(res)
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
>>> res = pd.merge(left, right, on=['key1', 'key2'], how='left')
>>> print(res)
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
>>> res = pd.merge(left, right, on=['key1', 'key2'], how='right')
>>> print(res)
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
3、Indicator
indicator=True會將合並的記錄放在新的一列。
>>> df1 = pd.DataFrame({'col1':[0,1], 'col_left':['a','b']})
>>> df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]})
>>> print(df1)
col1 col_left
0 0 a
1 1 b
>>> print(df2)
col1 col_right
0 1 2
1 2 2
2 2 2
# 依據col1進行合並，並啟用indicator=True，最后打印出
>>> res = pd.merge(df1, df2, on='col1', how='outer', indicator=True)
>>> print(res)
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
# 自定indicator column的名稱，並打印出
>>> res = pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
>>> print(res)
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
4、依據index合並
>>> 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)
A B
K0 A0 B0
K1 A1 B1
K2 A2 B2
>>> print(right)
C D
K0 C0 D0
K2 C2 D2
K3 C3 D3
#依據左右資料集的index進行合並，how='outer',並打印出
>>> res = pd.merge(left, right, left_index=True, right_index=True, how='outer')
>>> print(res)
A B C D
K0 A0 B0 C0 D0
K1 A1 B1 NaN NaN
K2 A2 B2 C2 D2
K3 NaN NaN C3 D3
#依據左右資料集的index進行合並，how='inner',並打印出
>>> res = pd.merge(left, right, left_index=True, right_index=True, how='inner')
>>> print(res)
A B C D
K0 A0 B0 C0 D0
K2 A2 B2 C2 D2
5、解決overlapping的問題
>>> boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
>>> girls = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'age': [4, 5, 6]})
>>> print(boys)
k age
0 K0 1
1 K1 2
2 K2 3
>>> print(girls)
k age
0 K0 4
1 K0 5
2 K3 6
#使用suffixes解決overlapping的問題
>>> res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')
>>> print(res)
k age_boy age_girl
0 K0 1 4
1 K0 1 5