python - Is it necessary to onehot discrete variables in tree models?
黄舟2017-05-18 10:46:59
0
1
857
Specifically, take sklearn's GBDT as an example If the data is all discrete, can it be trained directly? If there is continuity in the data, can it be trained directly?
![[Web front-end] Node.js quick start](https://img.php.cn/upload/course/000/000/067/662b5d34ba7c0227.png)
The tree model can originally be applied to discrete variables, while continuous variables are regression trees