concatenate主要作用是拼接series和dataframe的数据。
combine_first可以做来填充数据。
其中numpy和panads中都有concatenate()方法,如:np.concatenate([arr1, arr2])、pd.concat([s1, s2])
Series类型可以使用 s2 中的数值来填充 s1,如:s1.combine_first(s2)
Dataframe类型同样可以使用 df2 中的数组来填充 df1, 如:df1.combine_first(df2)
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
# 设置一个随机种子,方便调试
np.random.seed(666)
# Series
arr1 = np.arange(9).reshape(3, 3)
arr2 = np.arange(9).reshape(3, 3)
# numpy的 concatenate 用法
print(np.concatenate([arr1, arr2]))
'''
[[0 1 2]
[3 4 5]
[6 7 8]
[0 1 2]
[3 4 5]
[6 7 8]]
'''
print(np.concatenate([arr1, arr2], axis=1))
'''
[[0 1 2 0 1 2]
[3 4 5 3 4 5]
[6 7 8 6 7 8]]
'''
s1 = Series([1, 2, 3], index=['A', 'B', 'C'])
s2 = Series([4, 5], index=['E', 'F'])
# 可以看出和numpy的效果一样
print(pd.concat([s1, s2]))
'''
A 1
B 2
C 3
E 4
F 5
dtype: int64
'''
# 用法和 np 一样 axis = 1, 等于增加了一列
print(pd.concat([s1, s2], axis=1))
# 但是,返回的是一个 <class 'pandas.core.frame.DataFrame'>
print(type(pd.concat([s1, s2], axis=1)))
'''
0 1
A 1.0 NaN
B 2.0 NaN
C 3.0 NaN
E NaN 4.0
F NaN 5.0
'''
df1 = DataFrame(np.random.randn(4, 3), columns=['X', 'Y', 'Z'])
print(df1)
'''
X Y Z
0 0.824188 0.479966 1.173468
1 0.909048 -0.571721 -0.109497
2 0.019028 -0.943761 0.640573
3 -0.786443 0.608870 -0.931012
'''
df2 = DataFrame(np.random.randn(3, 3), columns=['X', 'Y', 'A'])
print(df2)
'''
X Y A
0 0.978222 -0.736918 -0.298733
1 -0.460587 -1.088793 -0.575771
2 -1.682901 0.229185 -1.756625
'''
print(pd.concat([df1, df2]))
'''
A X Y Z
0 NaN 0.824188 0.479966 1.173468
1 NaN 0.909048 -0.571721 -0.109497
2 NaN 0.019028 -0.943761 0.640573
3 NaN -0.786443 0.608870 -0.931012
0 -0.298733 0.978222 -0.736918 NaN
1 -0.575771 -0.460587 -1.088793 NaN
2 -1.756625 -1.682901 0.229185 NaN
'''
# combine
s1 = Series([2, np.nan, 4, np.nan], index=['A', 'B', 'C', 'D'])
s2 = Series([1, 2, 3, 4], index=['A', 'B', 'C', 'D'])
# 用 s2 中的数值来填充 s1
print(s1.combine_first(s2))
'''
A 2.0
B 2.0
C 4.0
D 4.0
dtype: float64
'''
df1 = DataFrame({
'X':[1, np.nan, 3, np.nan],
'Y':[5, np.nan, 7, np.nan],
'Z':[9, np.nan, 11, np.nan]
})
df2 = DataFrame({
'Z':[np.nan, 10, np.nan, 12],
'A':[1, 2, 3, 4]
})
# 功能同样是填充
print(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
'''