import numpy as np
import pandas as pd 
#标记DataFrame重复例子
df = pd.DataFrame({'col1': ['one', 'one', 'two', 'two', 'two', 'three', 'four'], 'col2': [1, 2, 1, 2, 1, 1, 1],
   'col3':['AA','BB','CC','DD','EE','FF','GG']},index=['a', 'a', 'b', 'c', 'b', 'a','c'])
#duplicated(self, subset=None, keep='first')
#根据列名标记
#keep='first'
df.duplicated()#默认所有列，无重复记录
df.duplicated('col1')#第二、四、五行被标记为重复
df.duplicated(['col1','col2'])#第五行被标记为重复
#keep='last'
df.duplicated('col1','last')#第一、三、四行被标记重复
df.duplicated(['col1','col2'],keep='last')#第三行被标记为重复
#keep=False
df.duplicated('col1',False)#Series([True,True,True,True,True,False,False],index=['a','a','b','c','b','a','c'])
df.duplicated(['col1','col2'],keep=False)#在col1和col2列上出现相同的，都被标记为重复
type(df.duplicated(['col1','col2'],keep=False))#pandas.core.series.Series
#根据索引标记
df.index.duplicated()#默认keep='first',第二、五、七行被标记为重复
df.index.duplicated(keep='last')#第一、二、三、四被标记为重复
df[df.index.duplicated()]#获取重复记录行
df[~df.index.duplicated('last')]#获取不重复记录行
#标记Series重复例子
#duplicated(self, keep='first')
s = pd.Series(['one', 'one', 'two', 'two', 'two', 'three', 'four'] ,index= ['a', 'a', 'b', 'c', 'b', 'a','c'],name='sname')
s.duplicated()
s.duplicated('last')
s.duplicated(False)
#根据索引标记
s.index.duplicated()
s.index.duplicated('last')
s.index.duplicated(False)

#删除DataFrame重复记录例子 
#drop_duplicates(self, subset=None, keep='first', inplace=False) 
df.drop_duplicates() 
df.drop_duplicates('col1')#删除了df.duplicated('col1')标记的重复记录 
df.drop_duplicates('col1','last')#删除了df.duplicated('col1','last')标记的重复记录 
df1.drop_duplicates(['col1','col2'])#删除了df.duplicated(['col1','col2'])标记的重复记录 
df.drop_duplicates('col1',keep='last',inplace=True)#inplace=True表示在原DataFrame上执行删除操作 
df.drop_duplicates('col1',keep='last',inplace=False)#inplace=False返回一个副本 
#删除Series重复记录例子 
#drop_duplicates(self, keep='first', inplace=False) 
s.drop_duplicates()