Addressing issue #215 - G-mean for multi-class problems #219
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for the PR. I will have to check if the IBA can be used with all the metrics. |
christophe-rannou
pushed a commit
to christophe-rannou/imbalanced-learn
that referenced
this pull request
Apr 3, 2017
…oblems (scikit-learn-contrib#219) * Added option to calculate G-mean for multiclass problems without averaging one-vs-rest results (scikit-learn-contrib#215). * Addressing issue scikit-learn-contrib#215. (removed unnecessary import) * Fixed line length to be in accordance with PEP 8.
glemaitre
pushed a commit
to glemaitre/imbalanced-learn
that referenced
this pull request
Jun 15, 2017
…oblems (scikit-learn-contrib#219) * Added option to calculate G-mean for multiclass problems without averaging one-vs-rest results (scikit-learn-contrib#215). * Addressing issue scikit-learn-contrib#215. (removed unnecessary import) * Fixed line length to be in accordance with PEP 8.
glemaitre
pushed a commit
to glemaitre/imbalanced-learn
that referenced
this pull request
Jun 15, 2017
…oblems (scikit-learn-contrib#219) * Added option to calculate G-mean for multiclass problems without averaging one-vs-rest results (scikit-learn-contrib#215). * Addressing issue scikit-learn-contrib#215. (removed unnecessary import) * Fixed line length to be in accordance with PEP 8.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Reference Issue
Fixes #215
What does this implement/fix? Explain your changes.
Adds the possibility of calculating G-mean for multi-class problems without resorting to averaging binary G-mean values. At the same time G-mean can still be average on a class-wise basis. This implementation also adds the possibility of "correcting" unrecognized class recalls from zero to a user-specified value. This is only works when
average == 'multiclass'.Additional comment
In the
report_imbalanced_multiclass()I left the resulting report as it was, since it is designed to show the results separately for each class. You may, however, consider to extend this report to have a header with overall accuracy and overall G-mean (as single lines above the table). I'm not sure if you want to add that, especially that accuracy works a little bit differently than the measures you implemented in themetricsmodule. Therefore maybe it is best to leave this as it is.