You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by yanboliang <gi...@git.apache.org> on 2016/04/10 15:36:06 UTC
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
GitHub user yanboliang opened a pull request:
https://github.com/apache/spark/pull/12287
[SPARK-14479] [ML] GLM supports output link prediction
## What changes were proposed in this pull request?
GLM supports output link prediction.
## How was this patch tested?
unit test.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/yanboliang/spark spark-14479
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/12287.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #12287
----
commit 869d65e9d0cb230d7a3ef9520e605d0cab43d9bb
Author: Yanbo Liang <yb...@gmail.com>
Date: 2016-04-10T13:00:25Z
GLM supoort link prediction
commit db1b1228022777c1fe49d1125852739f45cbd2d6
Author: Yanbo Liang <yb...@gmail.com>
Date: 2016-04-10T13:28:36Z
fix doc of test
----
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by yanboliang <gi...@git.apache.org>.
Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60379579
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -93,7 +107,12 @@ private[regression] trait GeneralizedLinearRegressionBase extends PredictorParam
Family.fromName($(family)) -> Link.fromName($(link))), "Generalized Linear Regression " +
s"with ${$(family)} family does not support ${$(link)} link function.")
}
- super.validateAndTransformSchema(schema, fitting, featuresDataType)
+ val newSchema = super.validateAndTransformSchema(schema, fitting, featuresDataType)
+ if ($(linkPredictionCol).nonEmpty) {
--- End diff --
The check ```$(linkPredictionCol).nonEmpty``` can be omitted, because we already have empty check in the next line [```SchemaUtils.appendColumn```](https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala#L90). This issue exists in lots of place of the ML code base. I can do some clean up in the a separate PR.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60306765
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -93,7 +106,12 @@ private[regression] trait GeneralizedLinearRegressionBase extends PredictorParam
Family.fromName($(family)) -> Link.fromName($(link))), "Generalized Linear Regression " +
s"with ${$(family)} family does not support ${$(link)} link function.")
}
- super.validateAndTransformSchema(schema, fitting, featuresDataType)
+ val newSchema = super.validateAndTransformSchema(schema, fitting, featuresDataType)
--- End diff --
This assumes `predictionCol` is always set. We can either keep this assumption or fix it.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208923905
**[Test build #55609 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55609/consoleFull)** for PR 12287 at commit [`e5aea09`](https://github.com/apache/spark/commit/e5aea09d3eedaa37fb3d3b873be602bcf5308c0f).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-207991894
**[Test build #55480 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55480/consoleFull)** for PR 12287 at commit [`db1b122`](https://github.com/apache/spark/commit/db1b1228022777c1fe49d1125852739f45cbd2d6).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit closed the pull request at:
https://github.com/apache/spark/pull/12287
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208948492
**[Test build #55613 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55613/consoleFull)** for PR 12287 at commit [`e5aea09`](https://github.com/apache/spark/commit/e5aea09d3eedaa37fb3d3b873be602bcf5308c0f).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by yanboliang <gi...@git.apache.org>.
Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60377428
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -675,10 +707,32 @@ class GeneralizedLinearRegressionModel private[ml] (
lazy val familyAndLink = new FamilyAndLink(familyObj, linkObj)
override protected def predict(features: Vector): Double = {
- val eta = BLAS.dot(features, coefficients) + intercept
+ val eta = predictLink(features)
familyAndLink.fitted(eta)
}
+ protected def predictLink(features: Vector): Double = {
+ BLAS.dot(features, coefficients) + intercept
+ }
+
+ override def transform(dataset: Dataset[_]): DataFrame = {
+ transformSchema(dataset.schema)
+ transformImpl(dataset)
+ }
+
+ override protected def transformImpl(dataset: Dataset[_]): DataFrame = {
+ val predictUDF = udf { (features: Vector) => predict(features) }
+ val predictLinkUDF = udf { (features: Vector) => predictLink(features) }
+ var output = dataset
+ if ($(predictionCol).nonEmpty) {
--- End diff --
Because we checked ```$(predictionCol).isEmpty``` when transform schema, we also need to check it when actually transform the dataset.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-207985899
**[Test build #55480 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55480/consoleFull)** for PR 12287 at commit [`db1b122`](https://github.com/apache/spark/commit/db1b1228022777c1fe49d1125852739f45cbd2d6).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-207992037
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/55480/
Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60306750
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -675,10 +707,32 @@ class GeneralizedLinearRegressionModel private[ml] (
lazy val familyAndLink = new FamilyAndLink(familyObj, linkObj)
override protected def predict(features: Vector): Double = {
- val eta = BLAS.dot(features, coefficients) + intercept
+ val eta = predictLink(features)
familyAndLink.fitted(eta)
}
+ protected def predictLink(features: Vector): Double = {
--- End diff --
* This could be a private method.
* Missing doc.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208926416
**[Test build #55609 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55609/consoleFull)** for PR 12287 at commit [`e5aea09`](https://github.com/apache/spark/commit/e5aea09d3eedaa37fb3d3b873be602bcf5308c0f).
* This patch **fails MiMa tests**.
* This patch merges cleanly.
* This patch adds no public classes.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208948692
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/55613/
Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208914202
**[Test build #55607 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55607/consoleFull)** for PR 12287 at commit [`e202039`](https://github.com/apache/spark/commit/e2020394750e324a44064fb263c8db26bd604e91).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60306779
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -675,10 +707,32 @@ class GeneralizedLinearRegressionModel private[ml] (
lazy val familyAndLink = new FamilyAndLink(familyObj, linkObj)
override protected def predict(features: Vector): Double = {
- val eta = BLAS.dot(features, coefficients) + intercept
+ val eta = predictLink(features)
familyAndLink.fitted(eta)
}
+ protected def predictLink(features: Vector): Double = {
+ BLAS.dot(features, coefficients) + intercept
+ }
+
+ override def transform(dataset: Dataset[_]): DataFrame = {
+ transformSchema(dataset.schema)
+ transformImpl(dataset)
+ }
+
+ override protected def transformImpl(dataset: Dataset[_]): DataFrame = {
+ val predictUDF = udf { (features: Vector) => predict(features) }
+ val predictLinkUDF = udf { (features: Vector) => predictLink(features) }
+ var output = dataset
+ if ($(predictionCol).nonEmpty) {
--- End diff --
See my previous comment about the assumption on `predictionCol`.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-207992035
Merged build finished. Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-212354438
Merged build finished. Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208916608
**[Test build #55607 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55607/consoleFull)** for PR 12287 at commit [`e202039`](https://github.com/apache/spark/commit/e2020394750e324a44064fb263c8db26bd604e91).
* This patch **fails to build**.
* This patch merges cleanly.
* This patch adds no public classes.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208926470
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/55609/
Test FAILed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-212340056
**[Test build #56347 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/56347/consoleFull)** for PR 12287 at commit [`cb1b5e6`](https://github.com/apache/spark/commit/cb1b5e6a5fbea84d8493d649aa8b931c1bb6841f).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208926466
Merged build finished. Test FAILed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60306758
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -78,6 +78,19 @@ private[regression] trait GeneralizedLinearRegressionBase extends PredictorParam
@Since("2.0.0")
def getLink: String = $(link)
+ /**
+ * Param for link prediction (linear predictor) column name.
--- End diff --
Mention the default value in the doc.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by yanboliang <gi...@git.apache.org>.
Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/12287#discussion_r60374814
--- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala ---
@@ -93,7 +106,12 @@ private[regression] trait GeneralizedLinearRegressionBase extends PredictorParam
Family.fromName($(family)) -> Link.fromName($(link))), "Generalized Linear Regression " +
s"with ${$(family)} family does not support ${$(link)} link function.")
}
- super.validateAndTransformSchema(schema, fitting, featuresDataType)
+ val newSchema = super.validateAndTransformSchema(schema, fitting, featuresDataType)
--- End diff --
We do not assume ```predictionCol``` is always set. If we set ```predictionCol = ""```, we will not output ```predictionCol```. We checked ```colName.isEmpty``` at [here](https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala#L90).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-212354286
**[Test build #56347 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/56347/consoleFull)** for PR 12287 at commit [`cb1b5e6`](https://github.com/apache/spark/commit/cb1b5e6a5fbea84d8493d649aa8b931c1bb6841f).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208916624
Merged build finished. Test FAILed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208931037
**[Test build #55613 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/55613/consoleFull)** for PR 12287 at commit [`e5aea09`](https://github.com/apache/spark/commit/e5aea09d3eedaa37fb3d3b873be602bcf5308c0f).
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208916631
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/55607/
Test FAILed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208948690
Merged build finished. Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-212118646
Made one pass.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-212354441
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/56347/
Test PASSed.
---
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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by yanboliang <gi...@git.apache.org>.
Github user yanboliang commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-208929797
Jenkins, test 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 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
[GitHub] spark pull request: [SPARK-14479] [ML] GLM supports output link pr...
Posted by mengxr <gi...@git.apache.org>.
Github user mengxr commented on the pull request:
https://github.com/apache/spark/pull/12287#issuecomment-213175477
LGTM. Merged into master. Thanks!
---
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