#Pandas具有全功能的，高效能記憶體中連線操作，與Sql關係資料庫非常相似
import numpy as np
import pandas as pd
​
In [18]:

#合併  連線   去重    替換
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']})
In [20]:

#合併    on='key'是參考鍵
print(df1)
print(df2)
print(pd.merge(df1,df2,on='key'))
    A   B key
0  A0  B0  K0
1  A1  B1  K1
2  A2  B2  K2
3  A3  B3  K3
    C   D key
0  C0  D0  K0
1  C1  D1  K1
2  C2  D2  K2
3  C3  D3  K3
    A   B key   C   D
0  A0  B0  K0  C0  D0
1  A1  B1  K1  C1  D1
2  A2  B2  K2  C2  D2
3  A3  B3  K3  C3  D3
In [21]:

print(pd.merge(df3,df4,on=['key1','key2']))
print(df3)
print(df4)
print(pd.merge(df3,df4,on=['key1','key2']))
    A   B key1 key2
0  A0  B0   K0   K0
1  A1  B1   K0   K1
2  A2  B2   K1   K0
3  A3  B3   K2   K1
    C   D key1 key2
0  C0  D0   K0   K0
1  C1  D1   K1   K0
2  C2  D2   K1   K0
3  C3  D3   K2   K0
    A   B key1 key2   C   D
0  A0  B0   K0   K0  C0  D0
1  A2  B2   K1   K0  C1  D1
2  A2  B2   K1   K0  C2  D2
In [23]:

#引數how 合併方式
​
#交集
print(pd.merge(df3,df4,on=['key1','key2'],how = 'inner'))
​
#並集
print(pd.merge(df3,df4,on=['key1','key2'],how = 'outer'))
​
#以df3為參考進行合併，資料缺失為NaN
print(pd.merge(df3,df4,on=['key1','key2'],how = 'left'))
#以df4為參考進行合併，資料缺失為NaN
print(pd.merge(df3,df4,on=['key1','key2'],how = 'right'))
    A   B key1 key2   C   D
0  A0  B0   K0   K0  C0  D0
1  A2  B2   K1   K0  C1  D1
2  A2  B2   K1   K0  C2  D2
     A    B key1 key2    C    D
0   A0   B0   K0   K0   C0   D0
1   A1   B1   K0   K1  NaN  NaN
2   A2   B2   K1   K0   C1   D1
3   A2   B2   K1   K0   C2   D2
4   A3   B3   K2   K1  NaN  NaN
5  NaN  NaN   K2   K0   C3   D3
    A   B key1 key2    C    D
0  A0  B0   K0   K0   C0   D0
1  A1  B1   K0   K1  NaN  NaN
2  A2  B2   K1   K0   C1   D1
3  A2  B2   K1   K0   C2   D2
4  A3  B3   K2   K1  NaN  NaN
     A    B key1 key2   C   D
0   A0   B0   K0   K0  C0  D0
1   A2   B2   K1   K0  C1  D1
2   A2   B2   K1   K0  C2  D2
3  NaN  NaN   K2   K0  C3  D3
In [28]:

left_on  right_on  left_index  right_on 
#引數 left_on  right_on  left_index  right_on   當鍵不為一個列時，可以單獨設定左鍵與右鍵
df1 = pd.DataFrame({'lkey':list('bbacaab'),
                   'data1':range(7)})
df2 = pd.DataFrame({'rkey':list('abd'),
                   'data2':range(3)})
print(df1)
print(df2)
print(pd.merge(df1,df2,left_on = 'lkey',right_on='rkey'))
#df1 以lkey為鍵，df2 以rkey為鍵
   data1 lkey
0      0    b
1      1    b
2      2    a
3      3    c
4      4    a
5      5    a
6      6    b
   data2 rkey
0      0    a
1      1    b
2      2    d
   data1 lkey  data2 rkey
0      0    b      1    b
1      1    b      1    b
2      6    b      1    b
3      2    a      0    a
4      4    a      0    a
5      5    a      0    a
In [43]:

right
df1 = pd.DataFrame({'key':list('abcdefg'),
                   'data':range(7)})
df2 = pd.DataFrame({'data1':range(100,105)},
                   index = list('abcde'))
print(df1)
print(df2)
print(pd.merge(df1,df2,left_on='key',right_index=True))
#df1 以key為按鍵   df2 以index為按鍵
#left_index   為True時，第一個df以index為鍵，預設為False
#right_index   為True時，第二個df以index為鍵，預設為False
#可以相互組合   left_on  right_on  left_index  right_on
#left_on+right_on  left_index+right_index  right_on+left_index  left_on+right_index
   data key
0     0   a
1     1   b
2     2   c
3     3   d
4     4   e
5     5   f
6     6   g
   data1
a    100
b    101
c    102
d    103
e    104
   data key  data1
0     0   a    100
1     1   b    101
2     2   c    102
3     3   d    103
4     4   e    104
In [52]:

 
#concat   axis = 1 列+列   axis = 0 行+行
s1 = pd.Series([1,2,3])
s2 = pd.Series([2,3,4])
print(s1)
print(s2)
print(pd.concat([s1,s2]).sort_index())
print(pd.concat([s1,s2]))
0    1
1    2
2    3
dtype: int64
0    2
1    3
2    4
dtype: int64
0    1
0    2
1    2
1    3
2    3
2    4
dtype: int64
0    1
1    2
2    3
0    2
1    3
2    4
dtype: int64
In [58]:

去掉重複
#去重
s = pd.Series([1,2,3,4,5,6,7,8,9,1,2,3,4,5,6])
print(s)
print(s.duplicated())
#判斷是否重複
​
#去掉重複
print(s.drop_duplicates())
0     1
1     2
2     3
3     4
4     5
5     6
6     7
7     8
8     9
9     1
10    2
11    3
12    4
13    5
14    6
dtype: int64
0     False
1     False
2     False
3     False
4     False
5     False
6     False
7     False
8     False
9      True
10     True
11     True
12     True
13     True
14     True
dtype: bool
0    1
1    2
2    3
3    4
4    5
5    6
6    7
7    8
8    9
dtype: int64
In [62]:

'
#替換
s = pd.Series(list('ascaazsd'))
print(s)
print(s.replace('a','z'))
0    a
1    s
2    c
3    a
4    a
5    z
6    s
7    d
dtype: object
0    z
1    s
2    c
3    z
4    z
5    z
6    s
7    d
dtype: object