Categorical_encoding default/auto one_hot_internal to be explicit in the documentation

Description

Question:
“The Xgboost manual ‘auto’ suggest the auto of the Cat Encoding is default/auto to one hot encoding but paragraph at the bottom suggest it’s auto to label encoder. Which one is true?label encoder or one hot encoding ”

http://h2o-release.s3.amazonaws.com/h2o/rel-yu/1/docs-website/h2o-docs/data-science/xgboost.html
its is not consistence what categorical_encoding uses for default XGBoost, (see Note under categorical_encoding where it suggest default is label_encoder)

however :
https://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/algo-params/categorical_encoding.html
in ^^ this documentation there is NO note for XGBoost, only note explaining default is for deep learning.

please set the XGBoost categorical_encoding default as one hot encoding, explicitly in the documentation.

Assignee

hannah.tillman

Fix versions

Reporter

Retima Dangol

Support ticket URL

Labels

None

Affected Spark version

None

Customer Request Type

None

Task progress

None

ReleaseNotesHidden

None

CustomerVisible

No

Priority

Major
Configure