DATASCIENCEARCHIVE Telegram 94
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/94
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/94

View MORE
Open in Telegram


Telegram News

Date: |

2How to set up a Telegram channel? (A step-by-step tutorial) The SUCK Channel on Telegram, with a message saying some content has been removed by the police. Photo: Telegram screenshot. Although some crypto traders have moved toward screaming as a coping mechanism, several mental health experts call this therapy a pseudoscience. The crypto community finds its way to engage in one or the other way and share its feelings with other fellow members. Telegram desktop app: In the upper left corner, click the Menu icon (the one with three lines). Select “New Channel” from the drop-down menu. Select “New Channel”
from us


Telegram Data Science Archive
FROM American