缺失值处理

找出缺失值

# 处理缺失值
import pandas as pd
import numpy as np

# 创建含有缺失值的DateFrame
df = pd.DataFrame(np.random.randn(10,6))
df.iloc[:4, 1] = None
df.iloc[:2, 4:6] = None
df.iloc[6, 3:5] = None
df.iloc[8, 0:2] = None

print(df)

          0         1         2         3         4         5
0  1.905276       NaN -0.978137  1.682227       NaN       NaN
1  0.164089       NaN -1.373336  1.388321       NaN       NaN
2  0.599135       NaN  2.294221  0.737271  0.238057  0.526875
3 -0.481358       NaN -0.519011  0.214852  0.040489  0.599064
4 -0.358184 -0.794557 -0.454329 -1.024130 -0.090786 -0.018543
5 -0.679481 -0.126602  0.726568  1.432684 -1.403756  0.252173
6 -0.842605  1.192915 -0.831709       NaN       NaN -0.073455
7  2.223354 -1.164356 -1.222986  0.009452  1.687198  0.344141
8       NaN       NaN -1.024819  0.689602  1.210335 -0.714473
9 -0.397766  0.739464 -1.535297 -1.868259  0.724042 -1.714549

# 判断缺失值
# 元素级别的判断，把对应的所有元素的位置都列出来，元素为空或者为NA为True，否则返回False
res = df.isnull()

res