Pandas——merge（合併）

1.前言

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.

2.通過key合併

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)
print('\n')
print(right)
print('\n')
res = pd.merge(left, right, on = "key")    #依據key column合併，並打印出
print(res)

#輸出
  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

3.Indicator

indicator=True會將合併的記錄放在新的一列。

res = pd.merge(df1,df2,on = 'col1',how = 'outer',indicator = True)   # 依據col1進行合併，並啓用indicator=True，最後打印出
print(res)
print('\n')
res_self = pd.merge(df1,df2,on = 'col1',how = 'outer',indicator = 'indicator_column')   # 自定indicator column的名稱，並打印出
print(res_self)

#輸出
   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     3      NaN        2.0  right_only


   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     3      NaN        2.0       right_only

4.根據index合併

import pandas as pd

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('\n')
print(right)
print('\n')
res_outer = pd.merge(left,right,left_index=True,right_index=True,how='outer') #依據左右資料集的index進行合併，how='outer',並打印出
print(res_outer)
print('\n')
res_inner = pd.merge(left,right,left_index=True,right_index=True,how='inner') #依據左右資料集的index進行合併，how='inner',並打印出
print(res_inner)

#輸出
     A   B
K0  A0  B0
K1  A1  B1
K2  A2  B2


     C   D
K0  C0  D0
K2  C2  D2
K3  C3  D3


      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

5.解決overlapping的問題

import pandas as pd


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') ##使用suffixes解決overlapping的問題
print(res)

#輸出
    k  age_boy  age_girl
0  K0        1         4
1  K0        1         5