spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sean Owen (JIRA)" <>
Subject [jira] [Commented] (SPARK-16768) pyspark calls incorrect version of logistic regression
Date Mon, 01 Aug 2016 17:21:20 GMT


Sean Owen commented on SPARK-16768:

The .mllib code still exists. It does still work, and that's what you find, right? Results
will differ across runs due to things like random seeds; it's also possible implementations
shift a little. That's not a problem, but it's also not what was reported in this JIRA.

> pyspark calls incorrect version of logistic regression
> ------------------------------------------------------
>                 Key: SPARK-16768
>                 URL:
>             Project: Spark
>          Issue Type: Bug
>          Components: MLlib, PySpark
>         Environment: Linux openSUSE Leap 42.1 Gnome
>            Reporter: Colin Beckingham
> PySpark call with Spark 1.6.2 "LogisticRegressionWithLBFGS.train()"  runs "treeAggregate
at LBFGS.scala:218" but the same command in pyspark with Spark 2.1 runs "treeAggregate at
LogisticRegression.scala:1092". This non-optimized version is much slower and produces a different
answer from LBFGS.

This message was sent by Atlassian JIRA

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

View raw message