1 In [16]: testset
2 Out[16]:
3 index uid iid rating timestamp
4 0 2 22 377 1 878887116
5 1 4 166 346 1 886397596
6 2 8 305 451 3 886324817
7 3 15 303 785 3 879485318
8 4 23 291 118 2 874833878
9 ... ... ... ... ... ...
10 19995 99980 864 685 4 888891900
11 19996 99982 279 64 1 875308510
12 19997 99983 646 750 3 888528902
13 19998 99990 806 421 4 882388897
14 19999 99999 12 203 3 879959583
15
16 [20000 rows x 5 columns]
17 #reset_index():从0开始重新设置dataframe的索引
18 In [17]: testset.reset_index()
19 Out[17]:
20 level_0 index uid iid rating timestamp
21 0 0 2 22 377 1 878887116
22 1 1 4 166 346 1 886397596
23 2 2 8 305 451 3 886324817
24 3 3 15 303 785 3 879485318
25 4 4 23 291 118 2 874833878
26 ... ... ... ... ... ... ...
27 19995 19995 99980 864 685 4 888891900
28 19996 19996 99982 279 64 1 875308510
29 19997 19997 99983 646 750 3 888528902
30 19998 19998 99990 806 421 4 882388897
31 19999 19999 99999 12 203 3 879959583
32
33 [20000 rows x 6 columns]
34 # drop属性：默认值为False，不删除原来的索引列
35 In [18]: testset.reset_index(drop=True)
36 Out[18]:
37 index uid iid rating timestamp
38 0 2 22 377 1 878887116
39 1 4 166 346 1 886397596
40 2 8 305 451 3 886324817
41 3 15 303 785 3 879485318
42 4 23 291 118 2 874833878
43 ... ... ... ... ... ...
44 19995 99980 864 685 4 888891900
45 19996 99982 279 64 1 875308510
46 19997 99983 646 750 3 888528902
47 19998 99990 806 421 4 882388897
48 19999 99999 12 203 3 879959583
49
50 [20000 rows x 5 columns]
