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: |

The main design elements of your Telegram channel include a name, bio (brief description), and avatar. Your bio should be: Telegram Channels requirements & features bank east asia october 20 kowloon Select: Settings – Manage Channel – Administrators – Add administrator. From your list of subscribers, select the correct user. A new window will appear on the screen. Check the rights you’re willing to give to your administrator. Deputy District Judge Peter Hui sentenced computer technician Ng Man-ho on Thursday, a month after the 27-year-old, who ran a Telegram group called SUCK Channel, was found guilty of seven charges of conspiring to incite others to commit illegal acts during the 2019 extradition bill protests and subsequent months.
from us


Telegram Data Science Archive
FROM American