アリババの年収70万データアナリストが知っておくべき5つのPandasデータマージスキル

pd.concat(
    objs: 'Iterable[NDFrame] | Mapping[Hashable, NDFrame]',
    axis=0,
    join='outer',
    ignore_index: 'bool' = False,
    keys=None,
    levels=None,
    names=None,
    verify_integrity: 'bool' = False,
    sort: 'bool' = False,
    copy: 'bool' = True,
) -> 'FrameOrSeriesUnion'

In [1]: import pandas as pd

In [2]: s1 = pd.Series(['a', 'b'])

In [3]: s2 = pd.Series(['c', 'd'])

In [4]: s1
Out[4]: 
0    a
1    b
dtype: object

In [5]: s2
Out[5]: 
0    c
1    d
dtype: object

In [6]: pd.concat([s1, s2])
Out[6]: 
0    a
1    b
0    c
1    d
dtype: object

In [7]: df1 = pd.DataFrame([['a', 1], ['b', 2]],
   ...:                     columns=['letter', 'number'])

In [8]: df2 = pd.DataFrame([['c', 3], ['d', 4]],
   ...:                     columns=['letter', 'number'])

In [9]: pd.concat([df1, df2])
Out[9]: 
  letter  number
0      a       1
1      b       2
0      c       3
1      d       4

In [10]: pd.concat([df1, df2], axis=1)
Out[10]: 
  letter  number letter  number
0      a       1      c       3
1      b       2      d       4

In [11]: df3 = pd.DataFrame([['c', 3, 'cat'], ['d', 4, 'dog']],
    ...:                     columns=['letter', 'number', 'animal'])

In [12]: df1
Out[12]: 
  letter  number
0      a       1
1      b       2

In [13]: df3
Out[13]: 
  letter  number animal
0      c       3    cat
1      d       4    dog

In [14]: pd.concat([df1, df3], join='inner')
Out[14]: 
  letter  number
0      a       1
1      b       2
0      c       3
1      d       4

In [15]: pd.concat([df1, df3], join='inner', ignore_index=True)
Out[15]: 
  letter  number
0      a       1
1      b       2
2      c       3
3      d       4
# 以下方式和上述的输出结果等价
In [16]: pd.concat([df1, df3], join='inner').reset_index(drop=True)
Out[16]: 
  letter  number
0      a       1
1      b       2
2      c       3
3      d       4

In [17]: pd.concat([df1, df3], keys=['df1','df3'])
Out[17]: 
      letter  number animal
df1 0      a       1    NaN
    1      b       2    NaN
df3 0      c       3    cat
    1      d       4    dog

In [18]: pd.concat([df1, df3], keys=['df1','df3'], names=['df名称','行ID'])
Out[18]: 
         letter  number animal
df名称 行ID                      
df1  0        a       1    NaN
     1        b       2    NaN
df3  0        c       3    cat
     1        d       4    dog

In [19]: pd.concat([df1, df3], verify_integrity=True)
Traceback (most recent call last):
...
ValueError: Indexes have overlapping values: Int64Index([0, 1], dtype='int64')

In [21]: pd.concat([df1, df3], sort=True)
Out[21]: 
  animal letter  number
0    NaN      a       1
1    NaN      b       2
0    cat      c       3
1    dog      d       4

In [22]: pd.concat([df1, s1])
Out[22]: 
  letter  number    0
0      a     1.0  NaN
1      b     2.0  NaN
0    NaN     NaN    a
1    NaN     NaN    b

In [23]: pd.concat([df1, s1], axis=1)
Out[23]: 
  letter  number  0
0      a       1  a
1      b       2  b
# 新增列一般可选以下两种方式
In [24]: df1.assign(新增列=s1)
Out[24]: 
  letter  number 新增列
0      a       1   a
1      b       2   b

In [25]: df1['新增列'] = s1

In [26]: df1
Out[26]: 
  letter  number 新增列
0      a       1   a
1      b       2   b

df.append(
    other,
    ignore_index: 'bool' = False,
    verify_integrity: 'bool' = False,
    sort: 'bool' = False,
) -> 'DataFrame'

In [41]: df1.append(df2)
Out[41]: 
  letter  number
0      a       1
1      b       2
0      c       3
1      d       4

In [42]: df1.append([df1,df2,df3])
Out[42]: 
  letter  number animal
0      a       1    NaN
1      b       2    NaN
0      a       1    NaN
1      b       2    NaN
0      c       3    NaN
1      d       4    NaN
0      c       3    cat
1      d       4    dog

In [43]: df1.append([df1,df2,df3], ignore_index=True)
Out[43]: 
  letter  number animal
0      a       1    NaN
1      b       2    NaN
2      a       1    NaN
3      b       2    NaN
4      c       3    NaN
5      d       4    NaN
6      c       3    cat
7      d       4    dog

In [44]: df1.append([df1,df2], verify_integrity=True)
Traceback (most recent call last):
...
ValueError: Indexes have overlapping values: Int64Index([0, 1], dtype='int64')

In [46]: df1.append([df1,df2,df3], sort=True)
Out[46]: 
  animal letter  number
0    NaN      a       1
1    NaN      b       2
0    NaN      a       1
1    NaN      b       2
0    NaN      c       3
1    NaN      d       4
0    cat      c       3
1    dog      d       4

In [49]: s = pd.Series({'letter':'s1','number':9})

In [50]: s
Out[50]: 
letter    s1
number     9
dtype: object

In [51]: df1.append(s)
Traceback (most recent call last):
...
TypeError: Can only append a Series if ignore_index=True or if the Series has a name

In [53]: df1.append(s, ignore_index=True)
Out[53]: 
  letter  number
0      a       1
1      b       2
2     s1       9

In [54]: dic = {'letter':'s1','number':9}

In [55]: df1.append(dic, ignore_index=True)
Out[55]: 
  letter  number
0      a       1
1      b       2
2     s1       9

pd.merge(
    left: 'DataFrame | Series',
    right: 'DataFrame | Series',
    how: 'str' = 'inner',
    on: 'IndexLabel | None' = None,
    left_on: 'IndexLabel | None' = None,
    right_on: 'IndexLabel | None' = None,
    left_index: 'bool' = False,
    right_index: 'bool' = False,
    sort: 'bool' = False,
    suffixes: 'Suffixes' = ('_x', '_y'),
    copy: 'bool' = True,
    indicator: 'bool' = False,
    validate: 'str | None' = None,
) -> 'DataFrame'

In [55]: df1 = pd.DataFrame({'key': ['foo', 'bar', 'bal'],
    ...:                     'value2': [1, 2, 3]})

In [56]: df2 = pd.DataFrame({'key': ['foo', 'bar', 'baz'],
    ...:                     'value1': [5, 6, 7]})

In [57]: df1.merge(df2)
Out[57]: 
   key  value2  value1
0  foo       1       5
1  bar       2       6

In [58]: df1.merge(df2, how='left')
Out[58]: 
   key  value2  value1
0  foo       1     5.0
1  bar       2     6.0
2  bal       3     NaN

In [59]: df1.merge(df2, how='right')
Out[59]: 
   key  value2  value1
0  foo     1.0       5
1  bar     2.0       6
2  baz     NaN       7

In [60]: df1.merge(df2, how='outer')
Out[60]: 
   key  value2  value1
0  foo     1.0     5.0
1  bar     2.0     6.0
2  bal     3.0     NaN
3  baz     NaN     7.0

In [61]: df1.merge(df2, how='cross')
Out[61]: 
  key_x  value2 key_y  value1
0   foo       1   foo       5
1   foo       1   bar       6
2   foo       1   baz       7
3   bar       2   foo       5
4   bar       2   bar       6
5   bar       2   baz       7
6   bal       3   foo       5
7   bal       3   bar       6
8   bal       3   baz       7

In [62]: df1 = pd.DataFrame({'lkey1': ['foo', 'bar', 'bal'],
    ...:                     'lkey2': ['a', 'b', 'c'],
    ...:                     'value2': [1, 2, 3]})

In [63]: df2 = pd.DataFrame({'rkey1': ['foo', 'bar', 'baz'],
    ...:                     'rkey2': ['a', 'b', 'c'],
    ...:                     'value2': [5, 6, 7]})
    
In [64]: df1
Out[64]: 
  lkey1 lkey2  value2
0   foo     a       1
1   bar     b       2
2   bal     c       3

In [65]: df2
Out[65]: 
  rkey1 rkey2  value2
0   foo     a       5
1   bar     b       6
2   baz     c       7

In [66]: df1.merge(df2, left_on='lkey1', right_on='rkey1')
Out[66]: 
  lkey1 lkey2  value2_x rkey1 rkey2  value2_y
0   foo     a         1   foo     a         5
1   bar     b         2   bar     b         6

In [67]: df1.merge(df2, left_on=['lkey1','lkey2'], right_on=['rkey1','rkey2'])
Out[67]: 
  lkey1 lkey2  value2_x rkey1 rkey2  value2_y
0   foo     a         1   foo     a         5
1   bar     b         2   bar     b         6

Out[68]: df1.merge(df2, left_index=True, right_index=True)
Out[68]: 
  lkey1 lkey2  value2_x rkey1 rkey2  value2_y
0   foo     a         1   foo     a         5
1   bar     b         2   bar     b         6
2   bal     c         3   baz     c         7

In [69]: df1.merge(df2, left_on='lkey1', right_on='rkey1', suffixes=['左','右'])
Out[69]: 
  lkey1 lkey2  value2左 rkey1 rkey2  value2右
0   foo     a        1   foo     a        5
1   bar     b        2   bar     b        6

In [70]: df1.merge(df2, left_on='lkey1', right_on='rkey1', suffixes=['左','右'], how='outer',
    ...:           indicator=True
    ...:       )
Out[70]: 
  lkey1 lkey2  value2左 rkey1 rkey2  value2右      _merge
0   foo     a      1.0   foo     a      5.0        both
1   bar     b      2.0   bar     b      6.0        both
2   bal     c      3.0   NaN   NaN      NaN   left_only
3   NaN   NaN      NaN   baz     c      7.0  right_only

df.join(
    other: 'FrameOrSeriesUnion',
    on: 'IndexLabel | None' = None,
    how: 'str' = 'left',
    lsuffix: 'str' = '',
    rsuffix: 'str' = '',
    sort: 'bool' = False,
) -> 'DataFrame'

In [71]: df = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3', 'K4', 'K5'],
    ...:                     'A': ['A0', 'A1', 'A2', 'A3', 'A4', 'A5']})

In [72]: other = pd.DataFrame({'key': ['K0', 'K1', 'K2'],
    ...:                        'B': ['B0', 'B1', 'B2']})

In [73]: df
Out[73]: 
  key   A
0  K0  A0
1  K1  A1
2  K2  A2
3  K3  A3
4  K4  A4
5  K5  A5

In [74]: other
Out[74]: 
  key   B
0  K0  B0
1  K1  B1
2  K2  B2

In [75]: df.join(other, on='key')
Traceback (most recent call last):
...
ValueError: You are trying to merge on object and int64 columns. If you wish to proceed you should use pd.concat

In [76]: df.set_index('key').join(other.set_index('key'))
Out[76]: 
      A    B
key         
K0   A0   B0
K1   A1   B1
K2   A2   B2
K3   A3  NaN
K4   A4  NaN
K5   A5  NaN

In [77]: df.join(other.set_index('key'), on='key')
Out[77]: 
  key   A    B
0  K0  A0   B0
1  K1  A1   B1
2  K2  A2   B2
3  K3  A3  NaN
4  K4  A4  NaN
5  K5  A5  NaN

In [78]: df.join(other, lsuffix='_左', rsuffix='右')
Out[78]: 
  key_左   A key右    B
0    K0  A0   K0   B0
1    K1  A1   K1   B1
2    K2  A2   K2   B2
3    K3  A3  NaN  NaN
4    K4  A4  NaN  NaN
5    K5  A5  NaN  NaN

df.combine(
    other: 'DataFrame',
    func,
    fill_value=None,
    overwrite: 'bool' = True,
) -> 'DataFrame'

In [79]: df1 = pd.DataFrame({'A': [0, 0], 'B': [4, 4]})

In [80]: df2 = pd.DataFrame({'A': [1, 1], 'B': [3, 3]})

In [81]: df1
Out[81]: 
   A  B
0  0  4
1  0  4

In [82]: df2
Out[82]: 
   A  B
0  1  3
1  1  3

In [83]: take_smaller = lambda s1, s2: s1 if s1.sum() < s2.sum() else s2

In [84]: df1.combine(df2, take_smaller)
Out[84]: 
   A  B
0  0  3
1  0  3

# 也可以调用numpy的函数
In [85]: import numpy as np

In [86]: df1.combine(df2, np.minimum)
Out[86]: 
   A  B
0  0  3
1  0  3

In [87]: df1 = pd.DataFrame({'A': [0, 0], 'B': [None, 4]})

In [87]: df2 = pd.DataFrame({'A': [1, 1], 'B': [3, 3]})

In [88]: df1
Out[88]: 
   A    B
0  0  NaN
1  0  4.0

In [89]: df2
Out[89]: 
   A  B
0  1  3
1  1  3

In [90]: df1.combine(df2, take_smaller, fill_value=-88)
Out[90]: 
   A     B
0  0 -88.0
1  0   4.0

In [91]: df1 = pd.DataFrame({'A': [0, 0], 'B': [4, 4]})

In [92]: df2 = pd.DataFrame({'B': [3, 3], 'C': [-10, 1], }, index=[1, 2])

In [93]: df1
Out[93]: 
   A  B
0  0  4
1  0  4

In [94]: df2
Out[94]: 
   B   C
1  3 -10
2  3   1

In [95]: df1.combine(df2, take_smaller)
Out[95]: 
    A    B     C
0 NaN  NaN   NaN
1 NaN  3.0 -10.0
2 NaN  3.0   1.0
# 保留A列原有的值
In [96]: df1.combine(df2, take_smaller, overwrite=False)
Out[96]: 
     A    B     C
0  0.0  NaN   NaN
1  0.0  3.0 -10.0
2  NaN  3.0   1.0

df.combine_first(other: 'DataFrame') -> 'DataFrame'

In [97]: df1 = pd.DataFrame({'A': [None, 0], 'B': [None, 4]})

In [98]: df2 = pd.DataFrame({'A': [1, 1], 'B': [3, 3]})

In [99]: df1
Out[99]: 
     A    B
0  NaN  NaN
1  0.0  4.0

In [100]: df2
Out[100]: 
   A  B
0  1  3
1  1  3

In [101]: df1.combine_first(df2)
Out[101]: 
     A    B
0  1.0  3.0
1  0.0  4.0

In [102]: df1 = pd.DataFrame({'A': [None, 0], 'B': [4, None]})

In [103]: df2 = pd.DataFrame({'B': [3, 3], 'C': [1, 1]}, index=[1, 2])

In [104]: df1
Out[104]: 
     A    B
0  NaN  4.0
1  0.0  NaN

In [105]: df2
Out[105]: 
   B  C
1  3  1
2  3  1

In [106]: df1.combine_first(df2)
Out[106]: 
     A    B    C
0  NaN  4.0  NaN
1  0.0  3.0  1.0
2  NaN  3.0  1.0