[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2015-01-21 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-70892730 @tolgap ANNClassifier will create 10 output neurons for mnist, 10 is the number of distinct labels derived from the data. Each class usually is encoded with a separate o

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2015-01-21 Thread tolgap
Github user tolgap commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-70801697 @avulanov How many neurons does the output layer have in this case? 1 or 10? Because my current implementation has an output layer of 10 neurons, e.g: ```scala

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2015-01-20 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-70714725 @tolgap As documentation suggests, `MulticlassMetrics` accepts `predictionAndLabels`, an RDD of (prediction, label) pairs, where `prediction` is the predicted class/labe

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2015-01-19 Thread tolgap
Github user tolgap commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-70509594 @avulanov You have added a class called `MulticlassMetrics`, but I do not understand how it operates on multiclass classification? I would understand the usage if it accep

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49058671 Thanks! I'll be glad to contribute more. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49051002 Merged. Thanks for your contribution! --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread asfgit
Github user asfgit closed the pull request at: https://github.com/apache/spark/pull/1155 --- 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 enab

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49020152 QA results for PR 1155:- This patch PASSES unit tests.- This patch merges cleanly- This patch adds the following public classes (experimental):class MulticlassMetrics(pre

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49012327 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16671/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49012039 @mengxr done! --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49011680 @avulanov I made some minor updates and send you a PR at https://github.com/avulanov/spark/pull/1 . If it looks good to you, please merge that PR and the changes should sh

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49009683 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16670/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-15 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-49009673 @mengxr I've addressed your comments. Thanks for pointing me to the Scala issue --- If your project is set up for it, you can reply to this email and have your reply ap

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14891003 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,182 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14890904 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,182 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48930159 @avulanov In Scala, "for" is slower than "while". See https://issues.scala-lang.org/browse/SI-1338 for example. So please replace the for loop with two while loops in your

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48890147 QA results for PR 1155:- This patch PASSES unit tests.- This patch merges cleanly- This patch adds the following public classes (experimental):class MulticlassMetrics(pre

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48882753 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16619/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48882671 @mengxr I addressed your comments, except the one above which I commented. --- If your project is set up for it, you can reply to this email and have your reply appear o

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-14 Thread avulanov
Github user avulanov commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14870864 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,183 @@ +/* + * Licensed to the Apache Softwa

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14848222 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,183 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14848121 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,183 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48720849 QA results for PR 1155:- This patch FAILED unit tests.- This patch merges cleanly- This patch adds the following public classes (experimental):class MulticlassMetrics(pre

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48715008 @mengxr I've addressed you comments, except the one with import which I commented above. I've posted a question about feature selection interface. Could you

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread avulanov
Github user avulanov commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14814439 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Softwa

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-11 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48714186 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16566/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48636028 The raw scores are not scalars but a vector indicating confidence for each class. Let's freeze the features for this PR in order to get it in quickly. It is fine to keep t

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779492 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48635224 @avulanov Please check the code style before commit. It seems that your IDE auto-formats the code. --- If your project is set up for it, you can reply to this email and h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779320 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779230 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779242 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779220 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14779197 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,181 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48605627 All automated tests passed. Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16500/ --- If your project

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48605625 Merged build finished. All automated tests passed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. I

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48603453 QA results for PR 1155:- This patch PASSES unit tests.- This patch merges cleanly- This patch adds the following public classes (experimental):class MulticlassMetrics(pre

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48598989 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16500/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48598875 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48598882 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48595010 Merged build finished. All automated tests passed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. I

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48595012 All automated tests passed. Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16498/ --- If your project

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48592365 QA results for PR 1155:- This patch PASSES unit tests.- This patch merges cleanly- This patch adds the following public classes (experimental):class MulticlassMetrics(pre

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48590095 @mengxr I've addressed your comments. I've also added weighted true positive and false positive and confusion matrix. Regarding raw scores, as you asked in

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread SparkQA
Github user SparkQA commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48589183 QA tests have started for PR 1155. This patch merges cleanly. View progress: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16498/consoleFull --- If

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48589088 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-10 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48589094 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745605 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,76 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745593 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,151 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745559 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,151 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745524 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,76 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745520 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,76 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745516 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,151 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745517 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,151 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14745522 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,76 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48546713 Merged build finished. --- 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 hav

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48546716 Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16478/ --- If your project is set up for it, you can

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48534124 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48534115 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48533944 Jenkins, retest this please. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48464916 Merged build finished. --- 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 hav

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48464919 Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16457/ --- If your project is set up for it, you can

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48459590 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48459596 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-09 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48459362 @mengxr I've addressed your comments. Added: FP rate and TP rate. Do you think I should add confusion matrix as well? --- If your project is set up for it, you can

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14676283 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,127 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14676038 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,127 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14676033 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,127 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48318579 Merged build finished. All automated tests passed. --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. I

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48318580 All automated tests passed. Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16404/ --- If your project

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48291055 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48291038 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-08 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48290945 @mengxr Thanks! I've addressed all your comments. Btw., I'm working on one-vs-all decomposition for multi-label training and hope to share the code in near futu

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48207510 @avulanov Adding Experimental to the class is sufficient. The micro* metrics are generally not applied to all labels but a subset of labels. This is why

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608068 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608058 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608045 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608042 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608051 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608034 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608040 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608037 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14608017 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-07 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14607992 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,119 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-04 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48044059 Merged build finished. --- 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 hav

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-04 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48044062 Refer to this link for build results: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/16347/ --- If your project is set up for it, you can

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-04 Thread avulanov
Github user avulanov commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48035031 @mengxr Thanks for your review! I've addressed all suggestions, except: 1)I used Experimental annotation for the whole class only. Do I need to annotate each method? 2)I

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-04 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48034013 Merged build started. --- 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

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-04 Thread AmplabJenkins
Github user AmplabJenkins commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-48034005 Merged build triggered. --- 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 h

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on the pull request: https://github.com/apache/spark/pull/1155#issuecomment-47886626 @avulanov Thanks for adding metrics for multiclass classification! I made one pass. Besides the inline comments, how can we handle models that output raw scores for each c

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14505016 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14505019 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14505009 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14505018 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/evaluation/MulticlassMetricsSuite.scala --- @@ -0,0 +1,71 @@ +/* + * Licensed to the Apache Soft

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504967 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504960 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504938 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504928 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504933 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

[GitHub] spark pull request: [MLLIB] [SPARK-2222] Add multiclass evaluation...

2014-07-03 Thread mengxr
Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/1155#discussion_r14504942 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/evaluation/MulticlassMetrics.scala --- @@ -0,0 +1,134 @@ +/* + * Licensed to the Apache Software

  1   2   >