[
https://issues.apache.org/jira/browse/SPARK-26721?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Daniel Jumper updated SPARK-26721:
----------------------------------
Description:
The feature importance calculation in
org.apache.spark.ml.classification.GBTClassificationModel.featureImportances
follows a flawed implementation from scikit-learn. An error was recently
discovered and updated in scikit-learn version 0.20.0. This error is inherited
in the spark implementation and needs to be fixed here as well.
As described in the scikit-learn release notes
([https://scikit-learn.org/stable/whats_new.html#version-0-20-0]):
{quote}Fix Fixed a bug in ensemble.GradientBoostingRegressor and
ensemble.GradientBoostingClassifier to have feature importances summed and then
normalized, rather than normalizing on a per-tree basis. The previous behavior
over-weighted the Gini importance of features that appear in later stages. This
issue only affected feature importances. #11176 by Gil Forsyth.
{quote}
Full discussion of this error and debate ultimately validating the correctness
of the change can be found in the comment thread of the scikit-learn pull
request: [https://github.com/scikit-learn/scikit-learn/pull/11176]
I believe the main change required would be to the featureImportances function
in mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala , however, I
do not have the experience to make this change myself.
was:
The feature importance calculation in
org.apache.spark.ml.classification.GBTClassificationModel.featureImportances
follows a flawed implementation from scikit-learn. An error was recently
discovered and updated in scikit-learn version 0.20.0. This error is inherited
in the spark implementation and needs to be fixed here as well.
As described in the [scikit-learn release
notes|[https://scikit-learn.org/stable/whats_new.html#version-0-20-0]|https://scikit-learn.org/stable/whats_new.html#version-0-20-0]:]
:
{quote}
Fix Fixed a bug in ensemble.GradientBoostingRegressor and
ensemble.GradientBoostingClassifier to have feature importances summed and then
normalized, rather than normalizing on a per-tree basis. The previous behavior
over-weighted the Gini importance of features that appear in later stages. This
issue only affected feature importances. #11176 by Gil Forsyth.
{quote}
Full discussion of this error and debate ultimately validating the correctness
of the change can be found in the comment thread of the scikit-learn pull
request: [https://github.com/scikit-learn/scikit-learn/pull/11176]
I believe the main change required would be to the featureImportances function
in mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala , however, I
do not have the experience to make this change myself.
> Bug in feature importance calculation in GBM (and possibly other decision
> tree classifiers)
> -------------------------------------------------------------------------------------------
>
> Key: SPARK-26721
> URL: https://issues.apache.org/jira/browse/SPARK-26721
> Project: Spark
> Issue Type: Bug
> Components: ML
> Affects Versions: 2.4.0
> Reporter: Daniel Jumper
> Priority: Critical
>
> The feature importance calculation in
> org.apache.spark.ml.classification.GBTClassificationModel.featureImportances
> follows a flawed implementation from scikit-learn. An error was recently
> discovered and updated in scikit-learn version 0.20.0. This error is
> inherited in the spark implementation and needs to be fixed here as well.
> As described in the scikit-learn release notes
> ([https://scikit-learn.org/stable/whats_new.html#version-0-20-0]):
> {quote}Fix Fixed a bug in ensemble.GradientBoostingRegressor and
> ensemble.GradientBoostingClassifier to have feature importances summed and
> then normalized, rather than normalizing on a per-tree basis. The previous
> behavior over-weighted the Gini importance of features that appear in later
> stages. This issue only affected feature importances. #11176 by Gil Forsyth.
> {quote}
> Full discussion of this error and debate ultimately validating the
> correctness of the change can be found in the comment thread of the
> scikit-learn pull request:
> [https://github.com/scikit-learn/scikit-learn/pull/11176]
>
> I believe the main change required would be to the featureImportances
> function in mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala ,
> however, I do not have the experience to make this change myself.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
