You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Simon Tao (Jira)" <ji...@apache.org> on 2021/11/11 07:56:00 UTC
[jira] [Created] (SPARK-37285) Add Weight of Evidence and
Information value to ml.feature
Simon Tao created SPARK-37285:
---------------------------------
Summary: Add Weight of Evidence and Information value to ml.feature
Key: SPARK-37285
URL: https://issues.apache.org/jira/browse/SPARK-37285
Project: Spark
Issue Type: New Feature
Components: ML
Affects Versions: 3.2.0
Reporter: Simon Tao
The weight of evidence (WOE) and information value (IV) provide a great framework for exploratory analysis and variable screening for binary classifiers as well as beneficial and help us analyze multiple points as listed below:
1. Helps check the linear relationship of a feature with its dependent feature to be used in the model.
2. Is a good variable transformation method for both continuous and categorical features.
3. Is better than on-hot encoding as this method of variable transformation does not increase the complexity of the model.
4. Detect linear and non-linear relationships.
5. Be useful in feature selection.
6. Is a good measure of the predictive power of a feature and it also helps point out the suspicious feature.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org