pandas中Series与DataFrame的唯一值、值计数及成员资格判定详解

 s = Series([3,3,1,2,4,3,4,6,5,6])
 #判断Series中的值是否重复,False表示重复
 print(s.is_unique)
 #False
 #输出Series中不重复的值,返回值没有排序，返回值的类型为数组
 print(s.unique())
 #[3 1 2 4 6 5]
 print(type(s.unique()))
 #<class 'numpy.ndarray'>
 #统计Series中重复值出现的次数,默认是按出现次数降序排序
 print(s.value_counts())
 '''
 3 3
 6 2
 4 2
 5 1
 2 1
 1 1
 '''
 #按照重复值的大小排序输出频率
 print(s.value_counts(sort=False))
 '''
 1 1
 2 1
 3 3
 4 2
 5 1
 6 2
 '''

 s = Series([5,5,6,1,1])
 print(s)
 '''
 0 5
 1 5
 2 6
 3 1
 4 1
 '''
 #判断矢量化集合的成员资格,返回一个bool类型的Series
 print(s.isin([5]))
 '''
 0  True
 1  True
 2 False
 3 False
 4 False
 '''
 print(type(s.isin([5])))
 #<class 'pandas.core.series.Series'>
 #通过成员资格方法选取Series中的数据子集
 print(s[s.isin([5])])
 '''
 0 5
 1 5
 '''

 a = [[3,2,6],[2,1,4],[6,2,5]]
 data = DataFrame(a,index=["a","b","c"],columns=["one","two","three"])
 print(data)
 '''
  one two three
 a 3 2  6
 b 2 1  4
 c 6 2  5
 '''
 #返回一个bool的DataFrame
 print(data.isin([1]))
 '''
   one two three
 a False False False
 b False True False
 c False False False
 '''
 #选取DataFrame中值为1的数，其他的为NaN
 print(data[data.isin([1])])
 '''
  one two three
 a NaN NaN NaN
 b NaN 1.0 NaN
 c NaN NaN NaN
 '''
 #将NaN用0进行填充
 print(data[data.isin([1])].fillna(0))
 '''
  one two three
 a 0.0 0.0 0.0
 b 0.0 1.0 0.0
 c 0.0 0.0 0.0
 '''