详解Pandas 处理缺失值指令大全

import pandas as pd
import numpy as np
string_data = pd.Series(['Benzema', 'Messi', np.nan, 'Ronaldo'])
string_data.isnull()

string_data = None

from numpy import nan as NA
import pandas as pd
data = pd.Series([1,NA,4.5,NA,5])
data.dropna()

data[data.notnull()]

data = pd.DataFrame([[1., 6.5, 3.], [1., NA, NA],
           [NA, NA, NA], [NA, 6.5, 3.]])
data
data.dropna()

data.dropna(how = 'all')

data[4] = NA
data
data.dropna(axis=1, how = 'all')

df = pd.DataFrame(np.random.randn(7, 3))
df.iloc[:4, 1] = NA
df.iloc[:2, 2] = NA
df
df.dropna(thresh = 2)

df = pd.DataFrame(np.random.randn(7, 3))
df.fillna(0)

df.fillna({{1 : 0.2,2 : 0.3}})

df.fillna(0, inplace = True)

data = pd.DataFrame({'k1': ['one', 'two'] * 3 + ['two'],
           'k2': [1, 1, 2, 3, 3, 4, 4]})
data.duplicated()

data.drop_duplicates()

data['k3'] = range(7)
data.duplicated(['k1'])

data.drop_duplicates(['k1'], keep = 'last')

list(map(lambda x : 2 * x , range(10)))

data = pd.Series([1., -999., 2., -999., -1000., 3.])
data.replace(-999.0, np.nan) #替换单个值
data.replace([-999.0, -1000.0], np.nan) #用一个值替换多个值
data.replace([-999.0, -1000.0],[np.nan, 0]) # 用不同值替换不同值
data.replace({-999.0 : 0, -1000.0 : np.nan}) # 格式为字典

data.rename(index=str.title, columns=str.upper)

data.rename(index = {'OHIO': 'INDIANA'}, columns = {'three': 'peekaboo'})

data.rename(index = {'OHIO': 'INDIANA'}, columns = {'three': 'peekaboo'}, inplace = True)
data

df = pd.DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'b'],
          'data1': range(6)})
pd.get_dummies(df['key']) # 分解了key 列，分开了三个属性

dummies = pd.get_dummies(df['key'], prefix = 'key')
df_with_dummies = df['data1'].join(dummies)
df_with_dummies