pandas检测缺失值、处理缺失值

import numpy as np
import pandas as pd

#一、处理缺失数据
data1 = pd.Series(['a','b',np.nan,'d'])
#
# ##检测缺失值
print(data1.isnull()) #判断是否null值

data1[0] = None #这个也是null值
print(data1.isnull())

##处理缺失值
#方法1
print(data1.dropna())

#方法2
print(data1[data1.notnull()])

data2 = pd.DataFrame([[1.,6.5,3.],[1.,np.nan,np.nan],[np.nan,np.nan,np.nan],[np.nan,6.7,7.]])

print(data2.dropna()) #dropna会丢弃任何含有缺失值的行
'''
     0    1    2
0  1.0  6.5  3.0
'''

print(data2.dropna(how='all'))  #how='all' 丢弃全为nan的行
'''
     0    1    2
0  1.0  6.5  3.0
1  1.0  NaN  NaN
3  NaN  6.7  7.0
'''
print(data2.dropna(axis=1,how='all'))
'''
     0    1    2
0  1.0  6.5  3.0
1  1.0  NaN  NaN
2  NaN  NaN  NaN
3  NaN  6.7  7.0
'''

df = pd.DataFrame(np.random.randn(7,3))
# print(df)

df.iloc[:4,1] = np.nan
print(df)

df.iloc[:2,2] = np.nan

print(df.dropna(thresh=2))  #删除缺失值为2的数据
'''
          0         1         2
2 -0.020213       NaN -0.574773
3  0.209291       NaN  0.647866
4  1.790216 -1.095708 -0.511631
5 -1.427289  0.660130 -1.234292
6  0.133132 -1.020107  0.770566
'''

##填充数据
print(df.fillna(0))  #用0填充

print(df.fillna({1:0.9,2:0}))  #列索引为1的用0.9填充，列索引为2的用0填充

df.fillna({1:0.9,2:0},inplace=True) #inplace=True就地修改

df2 = pd.DataFrame(np.random.randn(6,3))


df2.iloc[2:,1] = np.nan
df2.iloc[4:,2] = np.nan

print(df2)

print(df2.fillna(method='ffill'))   #用本列中 最后一个非nan值填充
# FutureWarning: DataFrame.fillna with 'method' is deprecated and will raise in a future version. Use obj.ffill() or obj.bfill() instead.

print(df2.ffill()) #效果同上

print(df2.fillna(method='ffill',limit=2))

print(df2.ffill(limit=2))  #效果同上