Mailing-List: contact reviews-help@spark.apache.org; run by ezmlm
Precedence: bulk
From: sethah <git@git.apache.org>
To: reviews@spark.apache.org
Reply-To: reviews@spark.apache.org
References: <git-pr-11989-spark@git.apache.org>
In-Reply-To: <git-pr-11989-spark@git.apache.org>
Subject: [GitHub] spark pull request: [SPARK-3724][ML] RandomForest: More
 options fo...
Content-Type: text/plain
Message-Id: <20160404161054.97474DFC6E@git1-us-west.apache.org>
Date: Mon,  4 Apr 2016 16:10:54 +0000 (UTC)

Github user sethah commented on a diff in the pull request:

    https://github.com/apache/spark/pull/11989#discussion_r58402045
  
    --- Diff: mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala ---
    @@ -343,6 +343,8 @@ private[ml] trait RandomForestParams extends TreeEnsembleParams {
        *  - "onethird": use 1/3 of the features
        *  - "sqrt": use sqrt(number of features)
        *  - "log2": use log2(number of features)
    +   *  - "(0.0-1.0]": use the specified fraction of features
    +   *  - "[1-n]": use the specified number of features
    --- End diff --
    
    This note is a bit confusing. It isn't clear what n is and we don't mention that it should be smaller than `(number of features)`. I can't think of a great wording for this that is also concise. One option:
    `"n": use n features, for integer 0 < n <= (number of features)`
    
    I'm open to better wordings.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org