倒排索引实现方式

Posted 2023-01-16 身带吴钩

def inverted_index_test():
    df1 = pd.DataFrame("A":[\'a c a\',\'b d\'],"B":[\'a d a\',\'c a\'])
    print(df1)
    print("A分割操作")
    df2 = df1[\'A\'].str.split(\' \',expand=True)
    print(df2)
    print("堆叠操作")
    df3 = df2.stack()
    print(df3)
    print("修剪索引")
    df4 = df3.reset_index(level=1,drop=True)#level 会删除对应的mutil值
    df4 = pd.DataFrame(df4)
    print(df4.index)
    print(df4)
    print("执行join操作")
    df5 = df4.join(df1)
    print(df5)

　　输出内容：

Python 3.9.12 (main, Apr  5 2022, 06:56:58) 
[GCC 7.5.0] on linux
       A      B
0  a c a  a d a
1    b d    c a
A分割操作
   0  1     2
0  a  c     a
1  b  d  None
堆叠操作
0  0    a
   1    c
   2    a
1  0    b
   1    d
dtype: object
修剪索引
Int64Index([0, 0, 0, 1, 1], dtype=\'int64\')
   0
0  a
0  c
0  a
1  b
1  d
执行join操作
   0      A      B
0  a  a c a  a d a
0  c  a c a  a d a
0  a  a c a  a d a
1  b    b d    c a
1  d    b d    c a