Python处理缺失值

NaN

Not A Number

CSV

comma-separated values

import pandas as pd
from io import StringIO
csv_data = '''A,B,C,D
1.0,2.0,3.0,4.0
5.0,6.0,,8.0
0.0,11.0,12.0,'''
# If you are using Python 2.7, you need
# to convert the string to unicode:
# csv_data = unicode(csv_data)
df = pd.read_csv(StringIO(csv_data))

删除含缺失值的样本

df.isnull()

df.isnull().sum()

df.dropna()

df.dropna(axis = 1)

df.dropna(how = 'all')

df.dropna(thresh = 4)

df.dropna(subset = ['C'])

填充缺失值

数值型数值(

Numerical Data

)

fillna()

df.fillna(0)

df.fillna(method='pad')

df.fillna(df2.mean())

from sklearn.preprocessing import Imputer
imr = Imputer(missing_values='NaN', strategy='mean', axis=0)#均值填充缺失值
imr = imr.fit(df)
imputed_data = imr.transform(df.values)