Telegram Group & Telegram Channel
单纯的 Boruta 判断特征的时候会依照二项分布的接受或者拒绝来判定对前面生成的影子特征进行筛选。所以如果把 Boruta 的第二阶段(特征metric排序以及筛选)单独拿出来,其实是可以用别的方案进行替换的,比如 SHAP(这里的引用来源也是我之前推荐的一本电子书《interpretable-ML》,强烈推荐)。也确实有轮子在做这样的事情,我自己找了一个 Kaggle 上的 Tabular Dataset 试了一下独立工作效果不太明显,不过提供另外一种特征筛选的方法来做 ensemble 应该是有提升的(吧)。轮子在这里:BorutaShap https://github.com/Ekeany/Boruta-Shap



tg-me.com/DataScienceArchive/113
Create:
Last Update:

单纯的 Boruta 判断特征的时候会依照二项分布的接受或者拒绝来判定对前面生成的影子特征进行筛选。所以如果把 Boruta 的第二阶段(特征metric排序以及筛选)单独拿出来,其实是可以用别的方案进行替换的,比如 SHAP(这里的引用来源也是我之前推荐的一本电子书《interpretable-ML》,强烈推荐)。也确实有轮子在做这样的事情,我自己找了一个 Kaggle 上的 Tabular Dataset 试了一下独立工作效果不太明显,不过提供另外一种特征筛选的方法来做 ensemble 应该是有提升的(吧)。轮子在这里:BorutaShap https://github.com/Ekeany/Boruta-Shap

BY Data Science Archive


Warning: Undefined variable $i in /var/www/tg-me/post.php on line 283

Share with your friend now:
tg-me.com/DataScienceArchive/113

View MORE
Open in Telegram


Data Science Archive Telegram | DID YOU KNOW?

Date: |

Tata Power whose core business is to generate, transmit and distribute electricity has made no money to investors in the last one decade. That is a big blunder considering it is one of the largest power generation companies in the country. One of the reasons is the company's huge debt levels which stood at ₹43,559 crore at the end of March 2021 compared to the company’s market capitalisation of ₹44,447 crore.

Data Science Archive from us


Telegram Data Science Archive
FROM USA