spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sean Owen (JIRA)" <>
Subject [jira] [Commented] (SPARK-24431) wrong areaUnderPR calculation in BinaryClassificationEvaluator
Date Wed, 06 Jun 2018 15:37:00 GMT


Sean Owen commented on SPARK-24431:

So, the model makes the same prediction p for all examples? In that case, for points on the
PR curve corresponding to thresholds less than p, everything is classified positive. Recall
is 1 and precision is the fraction of examples that are actually positive. For thresholds
greater than p, all is marked negative. Recall is 0, but, really precision is undefined (0/0).
Yes, see SPARK-21806 for a discussion of the different ways you could try to handle this –
no point for recall = 0, or precision = 0, 1, or p.

We (mostly I) settled on the latter as the least surprising change and one most likely to
produce model comparisons that make intuitive sense. My argument against precision = 0 at
recall = 0 is that it doesn't quite make sense that precision drops as recall decreases, and
that would define precision as the smallest possible value.

You're right that this is a corner case, and there is no really correct way to handle it.
I'd say the issue here is perhaps leaning too much on the area under the PR curve. It doesn't
have as much meaning as the area under the ROC curve. I think it's just the extreme example
of the problem with comparing precision and recall?

> wrong areaUnderPR calculation in BinaryClassificationEvaluator 
> ---------------------------------------------------------------
>                 Key: SPARK-24431
>                 URL:
>             Project: Spark
>          Issue Type: Bug
>          Components: ML
>    Affects Versions: 2.2.0
>            Reporter: Xinyong Tian
>            Priority: Major
> My problem, I am using CrossValidator(estimator=LogisticRegression(...), ...,  evaluator=BinaryClassificationEvaluator(metricName='areaUnderPR')) 
to select best model. when the regParam in logistict regression is very high, no variable
will be selected (no model), ie every row 's prediction is same ,eg. equal event rate (baseline
frequency). But at this point,  BinaryClassificationEvaluator set the areaUnderPR highest.
As a result  best model seleted is a no model. 
> the reason is following.  at time of no model, precision recall curve will be only two
points: at recall =0, precision should be set to  zero , while the software set it to 1.
at recall=1, precision is the event rate. As a result, the areaUnderPR will be close 0.5
(my even rate is very low), which is maximum .
> the solution is to set precision =0 when recall =0.

This message was sent by Atlassian JIRA

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message