pandas处理重复索引：检测、取值与注意事项

s = Series([1,2,3,4,5],index=["a","a","b","b","c"]) 
print(s.index.is_unique) 
#False 

a = np.arange(9).reshape(3,3) 
data = DataFrame(a,index=["a","b","c"],columns=["one","two","one"]) 
#判断行索引是否重复 
print(data.index.is_unique) 
#True 
#判断列索引是否重复 
print(data.columns.is_unique) 
#False 

 s = Series([1, 2, 3, 4, 5], index=["a", "a", "b", "b", "c"])
 print(type(s["a"]))
 #<class 'pandas.core.series.Series'>
 print(s["a"])
 '''
 a 1
 a 2
 '''
 #选取第一个a
 print(s[:1])
 #a 1
 print(s[[0]])
 #a 1

 a = np.arange(9).reshape(3,3)
 data = DataFrame(a,index=["a","b","b"],columns=["one","two","one"])
 #对行进行选取
 print(type(data.ix["b"]))
 #<class 'pandas.core.frame.DataFrame'>
 print(data.ix["b"])#与data.xs("b")等价
 '''
 one two one
 b 3 4 5
 b 6 7 8
 '''
 #选取第二行
 print(type(data.ix[1:2]))#与data[1:2]等价
 #<class 'pandas.core.frame.DataFrame'>
 print(data.ix[1:2])
 #b 3 4 5
 print(data.ix[[1]])
 #b 3 4 5

 #对列进行选取
 print(data["one"])#等价于data.one 或 data.xs("one",axis=1)
 '''
 one one
 a 0 2
 b 3 5
 b 6 8
 '''
 #选取第一列
 print(data.ix[:,0])
 '''
 a 0
 b 3
 b 6
 '''
 print(data.ix[:,:1])
 '''
 one
 a 0
 b 3
 b 6
 '''