pandas中关于nan的处理

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/missyougoon/article/details/83443361

在pandas中有个另类的存在就是nan，解释是：not a number，不是一个数字，但是它的类型确是一个float类型。对于pandas中nan的处理，简单的说有以下几个方法。

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

n = np.nan
print(type(n)) # <class 'float'>

m = 1
print(n+m) # nan 任何数字和nan进行计算，都是nan

# nan in series
s1 = Series([1, 2, np.nan, 3, 4], index=['A', 'B', 'C', 'D', 'E'])
print(s1)
'''
A    1.0
B    2.0
C    NaN
D    3.0
E    4.0
dtype: float64
'''

print(s1.isnull()) # 返回 bool值，是 nan 的话，返回true
'''
A    False
B    False
C     True
D    False
E    False
dtype: bool
'''

print(s1.notnull()) #　非 nan ，　返回ｔｒｕｅ
'''
A     True
B     True
C    False
D     True
E     True
dtype: bool
'''

# 去掉 有 nan 的索引项
print(s1.dropna())
'''
A    1.0
B    2.0
D    3.0
E    4.0
dtype: float64
'''

# nan in dataframe
df = DataFrame([[1, 2, 3], [np.nan, 5, 6], [7, np.nan, 9], [np.nan, np.nan, np.nan]])
print(df)
'''
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0
2  7.0  NaN  9.0
3  NaN  NaN  NaN
'''

print(df.isnull()) # df.notnull() 同理
'''
       0      1      2
0  False  False  False
1   True  False  False
2  False   True  False
3   True   True   True
'''

# 去掉　所有　有　nan 的　行,　axis = 0 表示　行方向
df1 = df.dropna(axis=0)
print(df1)
'''
     0    1    2
0  1.0  2.0  3.0
'''

# 表示在　列　的方向上。
df1 = df.dropna(axis=1)
print(df1)
'''
mpty DataFrame
Columns: []
Index: [0, 1, 2, 3]
'''

# any 只要有 nan 就会删掉。 all　是必须全是nan才删除
df1 = df.dropna(axis=0, how='any')
print(df1)
'''
     0    1    2
0  1.0  2.0  3.0
'''

# any 只要有 nan 就会删掉。 all 全部是nan，才会删除
df1 = df.dropna(axis=0, how='all')
print(df1)
'''
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0
2  7.0  NaN  9.0
'''

df2 = DataFrame([[1, 2, 3, np.nan], [2, np.nan, 5, 6], [np.nan, 7, np.nan, 9], [1, np.nan, np.nan, np.nan]])
print(df2)
'''
     0    1    2    3
0  1.0  2.0  3.0  NaN
1  2.0  NaN  5.0  6.0
2  NaN  7.0  NaN  9.0
3  1.0  NaN  NaN  NaN
'''

print(df2.dropna(thresh=None))
'''
Empty DataFrame
Columns: [0, 1, 2, 3]
Index: []
'''

print(df2.dropna(thresh=2)) #  thresh 表示一个范围，如：每一行的nan > 2，就删除
'''
     0    1    2    3
0  1.0  2.0  3.0  NaN
1  2.0  NaN  5.0  6.0
2  NaN  7.0  NaN  9.0
'''

# 将nan进行填充
print(df2.fillna(value=1))
'''
     0    1    2    3
0  1.0  2.0  3.0  1.0
1  2.0  1.0  5.0  6.0
2  1.0  7.0  1.0  9.0
3  1.0  1.0  1.0  1.0
'''

# 可以 为指定列 填充不同的 数值
print(df2.fillna(value={0: 0, 1: 1, 2: 2, 3: 3})) # 指定每一列 填充的数值
'''
     0    1    2    3
0  1.0  2.0  3.0  3.0
1  2.0  1.0  5.0  6.0
2  0.0  7.0  2.0  9.0
3  1.0  1.0  2.0  3.0
'''


# 以下两个例子需要说明的是：对dataframe进行dropna，原来的dataframe不会改变
print(df1.dropna())
'''
     0    1    2
0  1.0  2.0  3.0
'''
print(df1)
'''
     0    1    2
0  1.0  2.0  3.0
1  NaN  5.0  6.0
2  7.0  NaN  9.0
'''