【数据分析可视化】Concatenate和Combine

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

Concatenate

矩阵：Concatenate
Series和DataFrame：concat

# 创建矩阵
arr1 = np.arange(9).reshape(3,3)
arr1

array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

# 创建矩阵
arr2 = np.arange(9).reshape(3,3)
arr2

array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

# 链接两矩阵 默认竖着链接到下边
np.concatenate([arr1,arr1])

array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8],
       [0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

# 链接两矩阵 横向链接
np.concatenate([arr1,arr1],axis=1)

array([[0, 1, 2, 0, 1, 2],
       [3, 4, 5, 3, 4, 5],
       [6, 7, 8, 6, 7, 8]])

# 创建Series
s1 = Series([1,2,3],index=['x','y','z'])
s1

x    1
y    2
z    3
dtype: int64

# 创建Series
s2 = Series([4,5],index=['a','b'])
s2

a    4
b    5
dtype: int64

# concat 竖着连接
pd.concat([s1,s2])

x    1
y    2
z    3
a    4
b    5
dtype: int64

# concat 横着连接 （生成新的DataFrame）
pd.concat([s1,s2],axis=1)

/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:2: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version
of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=False'.

To retain the current behavior and silence the warning, pass 'sort=True'.

​

	0	1
a	NaN	4.0
b	NaN	5.0
x	1.0	NaN
y	2.0	NaN
z	3.0	NaN

# 创建DataFrame
df1 = DataFrame(np.random.rand(4,3), columns=['x','y','z'])
df1

	x	y	z
0	0.118006	0.976428	0.286200
1	0.554356	0.739202	0.441234
2	0.987343	0.032884	0.963760
3	0.730118	0.617397	0.943546

# 创建DataFrame
df2 = DataFrame(np.random.randn(3,3), columns=['x','y','a'])
df2

	x	y	a
0	0.792735	0.927720	1.960326
1	-1.015684	0.524749	1.002970
2	-0.676568	0.378511	0.103341

# 连接 默认竖着
pd.concat([df1,df2])

/Users/bennyrhys/opt/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:2: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version
of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=False'.

To retain the current behavior and silence the warning, pass 'sort=True'.

​

	a	x	y	z
0	NaN	0.118006	0.976428	0.286200
1	NaN	0.554356	0.739202	0.441234
2	NaN	0.987343	0.032884	0.963760
3	NaN	0.730118	0.617397	0.943546
0	1.960326	0.792735	0.927720	NaN
1	1.002970	-1.015684	0.524749	NaN
2	0.103341	-0.676568	0.378511	NaN

Combine

combine_first特点
两组数据，当前一组nan时，后组填充。
合并后组比前组少的数据

s1 = Series([2,np.nan,4,np.nan], index=['A','B','C','D'])
s1

A    2.0
B    NaN
C    4.0
D    NaN
dtype: float64

s2 = Series([1,2,3,4], index=['A','B','C','D'])
s2

A    1
B    2
C    3
D    4
dtype: int64

# 后往前填充value值（当nan时后填充前）
s1.combine_first(s2)

A    2.0
B    2.0
C    4.0
D    4.0
dtype: float64

# 新建DataFrame
df1 = DataFrame({
    'x':[1,np.nan,3,np.nan],
    'y':[5,np.nan,7,np.nan],
    'z':[9,np.nan,11,np.nan]
})
df1

	x	y	z
0	1.0	5.0	9.0
1	NaN	NaN	NaN
2	3.0	7.0	11.0
3	NaN	NaN	NaN

# 新建DataFrame
df2 = DataFrame({
    'z':[np.nan,10,np.nan,12],
    'a':[1,2,3,4]
})
df2

	z	a
0	NaN	1
1	10.0	2
2	NaN	3
3	12.0	4

df1.combine_first(df2)

	a	x	y	z
0	1.0	1.0	5.0	9.0
1	2.0	NaN	NaN	10.0
2	3.0	3.0	7.0	11.0
3	4.0	NaN	NaN	12.0