pandas（四）唯一值、值计数以及成员资格详解大数据

>>> obj = Series(['c','a','d','a','a','b','b','c','c']) 
>>> obj.unique() 
array(['c', 'a', 'd', 'b'], dtype=object) 
>>> obj 
0    c 
1    a 
2    d 
3    a 
4    a 
5    b 
6    b 
7    c 
8    c 
dtype: object 
>>> type(obj.unique()) 
<class 'numpy.ndarray'>#注意这里返回的不再是Series对象，而是ndarray的一维数组

>>> new_array = obj.unique() 
>>> new_array 
array(['c', 'a', 'd', 'b'], dtype=object) 
>>> new_array.sort() 
>>> new_array 
array(['a', 'b', 'c', 'd'], dtype=object) 
>>> import numpy as np 
>>> new_array = obj.unique() 
>>> new_array 
array(['c', 'a', 'd', 'b'], dtype=object) 
>>> na = np.sort(new_array) 
>>> na 
array(['a', 'b', 'c', 'd'], dtype=object)

>>> obj 
0    c 
1    a 
2    d 
3    a 
4    a 
5    b 
6    b 
7    c 
8    c 
dtype: object 
>>> obj_c= obj.value_counts() 
>>> obj_c 
c    3 
a    3 
b    2 
d    1 
dtype: int64 
>>> pd.value_counts(obj)#默认是降序 
c    3 
a    3 
b    2 
d    1 
dtype: int64 
>>> pd.value_counts(obj,sort =False)#对统计结果不排序 
a    3 
b    2 
d    1 
c    3 
dtype: int64

>>> mask = obj.isin(['a','c']) 
>>> mask 
0     True 
1     True 
2    False 
3     True 
4     True 
5    False 
6    False 
7     True 
8     True 
dtype: bool 
>>> obj[mask] 
0    c 
1    a 
3    a 
4    a 
7    c 
8    c 
dtype: object