DATASCIENCEARCHIVE Telegram 114
Forwarded from Data Science Archive (小熊猫)
说到特征降维/选择的问题,大部分EDA的套路都是从model训练的loss来判断feature importance。其实有一个简单易行而且很有效的办法是在CV里面用做feature permutation,对原始特征shuffle得到shadow(也可以加一些噪音),在通过zscore比较两者差异来判断importance,不断遍历筛选。在ESLII中593页有提到这个办法。R里面有一个包Boruta可以做这件事,py也有:https://github.com/scikit-learn-contrib/boruta_py



tgoop.com/DataScienceArchive/114
Create:
Last Update:

说到特征降维/选择的问题,大部分EDA的套路都是从model训练的loss来判断feature importance。其实有一个简单易行而且很有效的办法是在CV里面用做feature permutation,对原始特征shuffle得到shadow(也可以加一些噪音),在通过zscore比较两者差异来判断importance,不断遍历筛选。在ESLII中593页有提到这个办法。R里面有一个包Boruta可以做这件事,py也有:https://github.com/scikit-learn-contrib/boruta_py

BY Data Science Archive


Share with your friend now:
tgoop.com/DataScienceArchive/114

View MORE
Open in Telegram


Telegram News

Date: |

Choose quality over quantity. Remember that one high-quality post is better than five short publications of questionable value. Avoid compound hashtags that consist of several words. If you have a hashtag like #marketingnewsinusa, split it into smaller hashtags: “#marketing, #news, #usa. Add the logo from your device. Adjust the visible area of your image. Congratulations! Now your Telegram channel has a face Click “Save”.! The group also hosted discussions on committing arson, Judge Hui said, including setting roadblocks on fire, hurling petrol bombs at police stations and teaching people to make such weapons. The conversation linked to arson went on for two to three months, Hui said. Telegram channels fall into two types:
from us


Telegram Data Science Archive
FROM American