You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Tobi Bosede (JIRA)" <ji...@apache.org> on 2016/09/29 03:22:20 UTC
[jira] [Updated] (SPARK-17718) Update MLib Classification
Documentation
[ https://issues.apache.org/jira/browse/SPARK-17718?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tobi Bosede updated SPARK-17718:
--------------------------------
Summary: Update MLib Classification Documentation (was: MLib Classification Documentation Update Needed)
> Update MLib Classification Documentation
> -----------------------------------------
>
> Key: SPARK-17718
> URL: https://issues.apache.org/jira/browse/SPARK-17718
> Project: Spark
> Issue Type: Improvement
> Reporter: Tobi Bosede
> Priority: Minor
>
> https://spark.apache.org/docs/1.6.0/mllib-linear-methods.html#mjx-eqn-eqregPrimal
> The loss function here for logistic regression is confusing. It seems to imply that spark uses only -1 and 1 class labels. However it uses 0,1. Note below needs to make this point more visible to avoid confusion.
> "Note that, in the mathematical formulation in this guide, a binary label
> y is denoted as either +1 (positive) or −1 (negative), which is convenient
> for the formulation. However, the negative label is represented by 0 in
> spark.mllib instead of −1, to be consistent with multiclass labeling."
> Better yet, the loss function should be replaced with that for 0, 1 despite mathematical inconvenience, since that is what is actually implemented.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org