Skip to content

Conversation

@mgaido91
Copy link
Contributor

What changes were proposed in this pull request?

Using computeCost for evaluating a model is a very poor approach. We should advice the users to a better approach which is available, ie. using the ClusteringEvaluator to evaluate their models. The PR updates the examples for BisectingKMeans in order to do that.

How was this patch tested?

running examples

@mgaido91
Copy link
Contributor Author

cc @cloud-fan @dongjoon-hyun

@SparkQA
Copy link

SparkQA commented Oct 21, 2018

Test build #97681 has finished for PR 22786 at commit 9def7e8.

  • This patch passes all tests.
  • This patch merges cleanly.
  • This patch adds no public classes.

Copy link
Member

@dongjoon-hyun dongjoon-hyun left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The difference from the reverted one is only the commit message, isn't it? Is there another difference in the code, @mgaido91 ?

And, at this time, this should go to master branch only because this is not a blocker issue. Could you review and merge this please, @mengxr ?

@cloud-fan
Copy link
Contributor

also cc @WeichenXu123

@mgaido91
Copy link
Contributor Author

@dongjoon-hyun , no there aren't differences. I resubmitted in answer to #22763 (comment). Thanks.

@mgaido91
Copy link
Contributor Author

any comments on this?

@mgaido91
Copy link
Contributor Author

mgaido91 commented Nov 5, 2018

cc also @holdenk @srowen

@cloud-fan
Copy link
Contributor

cc @dbtsai

@dbtsai
Copy link
Member

dbtsai commented Nov 5, 2018

LGTM. Merged into master. Thanks!

@asfgit asfgit closed this in 0b59170 Nov 5, 2018
jackylee-ch pushed a commit to jackylee-ch/spark that referenced this pull request Feb 18, 2019
…steringEvaluator

## What changes were proposed in this pull request?

Using `computeCost` for evaluating a model is a very poor approach. We should advice the users to a better approach which is available, ie. using the `ClusteringEvaluator` to evaluate their models. The PR updates the examples for `BisectingKMeans` in order to do that.

## How was this patch tested?

running examples

Closes apache#22786 from mgaido91/SPARK-25764.

Authored-by: Marco Gaido <marcogaido91@gmail.com>
Signed-off-by: DB Tsai <d_tsai@apple.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants