处理缺失值

import pandas as pd
import numpy as np

df1 = pd.DataFrame(np.random.rand(4, 3), index=['a', 'b', 'c', 'd'], columns=['first', 'second', 'third'])
df1

	first	second	third
a	0.913249	0.970337	0.471116
b	0.710308	0.178931	0.797251
c	0.053555	0.138023	0.984439
d	0.887249	0.602075	0.364529

df2 = pd.DataFrame(np.random.rand(3, 2), index=['a', 'b', 'c'], columns=['first', 'second'])
df2

	first	second
a	0.250653	0.421736
b	0.574175	0.030342
c	0.812355	0.096477

# 两个dataframe运算，无对应元素则为NaN
df = df1 - df2
df

	first	second	third
a	0.662596	0.548601	NaN
b	0.136133	0.148589	NaN
c	-0.758799	0.041547	NaN
d	NaN	NaN	NaN

# 查看各元素是否为NaN
df.isnull()

	first	second	third
a	False	False	True
b	False	False	True
c	False	False	True
d	True	True	True

# axis=1代表针对列，thresh=2表示删除有效数据小于2的列
df.dropna(axis=1, thresh=2, inplace=True)
df

	first	second
a	0.662596	0.548601
b	0.136133	0.148589
c	-0.758799	0.041547
d	NaN	NaN

# 用0填充缺失值
df.fillna(0)

	first	second
a	0.662596	0.548601
b	0.136133	0.148589
c	-0.758799	0.041547
d	0.000000	0.000000

df

	first	second
a	0.662596	0.548601
b	0.136133	0.148589
c	-0.758799	0.041547
d	NaN	NaN

# 向前填充
df.fillna(method='ffill')

	first	second
a	0.662596	0.548601
b	0.136133	0.148589
c	-0.758799	0.041547
d	-0.758799	0.041547