srowen commented on a change in pull request #26135: [SPARK-29489][ML][PySpark]
ml.evaluation support log-loss
URL: https://github.com/apache/spark/pull/26135#discussion_r335589736
##########
File path: python/pyspark/ml/evaluation.py
##########
@@ -365,18 +375,25 @@ class MulticlassClassificationEvaluator(JavaEvaluator,
HasLabelCol, HasPredictio
"The beta value used in weightedFMeasure|fMeasureByLabel."
" Must be > 0. The default value is 1.",
typeConverter=TypeConverters.toFloat)
+ eps = Param(Params._dummy(), "eps",
Review comment:
Do we really need this? it's kind of arbitrary. Do other libs have an
epsilon for computing log loss? if a classifier is returning 1 or 0 the log
loss really is undefined.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
