随机森林回归的 3D 输入

Question

Problem

Looking at examples of Sklearn's random forest regression, such as with the IRIS dataset, the inputs are vectors of size [n_samples, n_features] :

slen   swid    plen    pwid
5.1     3.5     1.4     0.2 
4.9     3.0     1.4     0.2

For my data, however, I have multiple values per feature:

slen         swid         plen        pwid
[2,5,1]     [4,2,3]     [1,2,3]     [4,3,2] 
[5,3,2]     [7,3,1]     [3,2,1]     [1,5,2]

Is it still possible to use Sklearn's RFR with this kind of dataset?

The input is now [n_samples, n_values_per_feature, n_features] . Note that for my data, the order of the matrices, like [2,5,1] , matters.

Answer 1

it is possible just to make then all a one

 slen1    slen2       swid1     swid2      plen1    plen2       pwid1     pwid2 
[2,5,1]  [5,3,2]     [4,2,3]   [7,3,1]    [1,2,3]  [3,2,1]     [4,3,2]   [1,5,2]

it is possible to scroll the values over some spots. and interchange the positions. I guess it will average up.