[jira] [Commented] (SPARK-6164) CrossValidatorModel should keep stats from fitting
[ https://issues.apache.org/jira/browse/SPARK-6164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14569714#comment-14569714 ] Leah McGuire commented on SPARK-6164: - I fixed the merge conflict. Should be good to go now. > CrossValidatorModel should keep stats from fitting > -- > > Key: SPARK-6164 > URL: https://issues.apache.org/jira/browse/SPARK-6164 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 1.4.0 >Reporter: Joseph K. Bradley >Priority: Minor > > CrossValidator computes stats for each (model, fold) pair, but they are > thrown out by the created model. CrossValidatorModel should keep this info > and expose it to users. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-6164) CrossValidatorModel should keep stats from fitting
[ https://issues.apache.org/jira/browse/SPARK-6164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14568562#comment-14568562 ] Justin Yip commented on SPARK-6164: --- Hello, May I know the progress of this issue? It is important to keep stats calculated from fitting, in order to guide the next grid search. Looks like PR5915 cannot be merged due to code refactoring. I can send a PR with code that inject the stats into CrossValidationModel, if no one objects. Thanks. Justin > CrossValidatorModel should keep stats from fitting > -- > > Key: SPARK-6164 > URL: https://issues.apache.org/jira/browse/SPARK-6164 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 1.4.0 >Reporter: Joseph K. Bradley >Priority: Minor > > CrossValidator computes stats for each (model, fold) pair, but they are > thrown out by the created model. CrossValidatorModel should keep this info > and expose it to users. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-6164) CrossValidatorModel should keep stats from fitting
[ https://issues.apache.org/jira/browse/SPARK-6164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14529110#comment-14529110 ] Leah McGuire commented on SPARK-6164: - Closed this - accidentally pulled in pieces of another request > CrossValidatorModel should keep stats from fitting > -- > > Key: SPARK-6164 > URL: https://issues.apache.org/jira/browse/SPARK-6164 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 1.4.0 >Reporter: Joseph K. Bradley >Priority: Minor > > CrossValidator computes stats for each (model, fold) pair, but they are > thrown out by the created model. CrossValidatorModel should keep this info > and expose it to users. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-6164) CrossValidatorModel should keep stats from fitting
[ https://issues.apache.org/jira/browse/SPARK-6164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14529105#comment-14529105 ] Apache Spark commented on SPARK-6164: - User 'leahmcguire' has created a pull request for this issue: https://github.com/apache/spark/pull/5915 > CrossValidatorModel should keep stats from fitting > -- > > Key: SPARK-6164 > URL: https://issues.apache.org/jira/browse/SPARK-6164 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 1.4.0 >Reporter: Joseph K. Bradley >Priority: Minor > > CrossValidator computes stats for each (model, fold) pair, but they are > thrown out by the created model. CrossValidatorModel should keep this info > and expose it to users. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-6164) CrossValidatorModel should keep stats from fitting
[ https://issues.apache.org/jira/browse/SPARK-6164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14528805#comment-14528805 ] Apache Spark commented on SPARK-6164: - User 'leahmcguire' has created a pull request for this issue: https://github.com/apache/spark/pull/5911 > CrossValidatorModel should keep stats from fitting > -- > > Key: SPARK-6164 > URL: https://issues.apache.org/jira/browse/SPARK-6164 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 1.4.0 >Reporter: Joseph K. Bradley >Priority: Minor > > CrossValidator computes stats for each (model, fold) pair, but they are > thrown out by the created model. CrossValidatorModel should keep this info > and expose it to users. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org