Pandas入门系列（七) -- NaN

NaN 意为 Not A Number

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

# nan类型与运算
n = np.nan
type(n)
Out[8]: float
# nan参与运算结果还是nan
m = 1
n+m
Out[11]: nan

# Series 中的 nan使用
s1 = Series([1,2,np.nan,3,4], index=['A','B','C','D','E'])
s1
Out[15]: 
A    1.0
B    2.0
C    NaN
D    3.0
E    4.0
dtype: float64
# 判断是否为nan
s1.isnull()
Out[16]: 
A    False
B    False
C     True
D    False
E    False
dtype: bool
# 判断是否非nan
s1.notnull()
Out[17]: 
A     True
B     True
C    False
D     True
E     True
dtype: bool
# 去掉nan值
s1.dropna()
Out[18]: 
A    1.0
B    2.0
D    3.0
E    4.0
dtype: float64

# DataFrame中nan的使用
dframe = DataFrame([[1,2,3], [np.nan,5,6],[7,8,np.nan],[np.nan,np.nan,np.nan]])

dframe
Out[20]: 
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0
2  7.0  8.0  NaN
3  NaN  NaN  NaN

# 判断是否nan
n [21]: dframe.isnull()
Out[21]: 
       0      1      2
0  False  False  False
1   True  False  False
2  False  False   True
3   True   True   True

dframe.notnull()
Out[22]: 
       0      1      2
0   True   True   True
1  False   True   True
2   True   True  False
3  False  False  False

# 去掉有nan的行
df1 = dframe.dropna(axis=0)
df1
Out[24]: 
     0    1    2
0  1.0  2.0  3.0

# 去掉有nan的列
df1 = dframe.dropna(axis=1)
df1
Out[26]: 
Empty DataFrame   # 空
Columns: []
Index: [0, 1, 2, 3]

# 参数how，any：如果存在nan则去掉，all：如果全为nan则去掉
df1 = dframe.dropna(axis=0, how='any')
df1
Out[28]: 
     0    1    2
0  1.0  2.0  3.0

df1 = dframe.dropna(axis=0, how='all')
df1
Out[30]: 
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0
2  7.0  8.0  NaN

# 参数thresh指定去掉多少个nan，大于等于
dframe = DataFrame([[1,2,3], [np.nan,5,6],[7,np.nan,np.nan],[np.nan,np.nan,np.nan]])
df2 = dframe.dropna(axis=0, thresh=2)
df2
Out[37]: 
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0

# nan填充
dframe.fillna(value=1)
Out[38]: 
     0    1    2
0  1.0  2.0  3.0
1  1.0  5.0  6.0
2  7.0  1.0  1.0
3  1.0  1.0  1.0
# 指定列进行填充，如0列填充0,1列填充1，自己指定
dframe.fillna(value = {0:0, 1:1, 2:2, 3:3})
Out[39]: 
     0    1    2
0  1.0  2.0  3.0
1  0.0  5.0  6.0
2  7.0  1.0  2.0
3  0.0  1.0  2.0