You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ru...@apache.org on 2026/08/20 10:30:40 UTC
(spark) branch master updated: [SPARK-58898][ML] Use Identifiable for temporary ML column names
This is an automated email from the ASF dual-hosted git repository.
zhengruifeng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 5254d42ab1a8 [SPARK-58898][ML] Use Identifiable for temporary ML column names
5254d42ab1a8 is described below
commit 5254d42ab1a89cfc9f057b20849cdac2bd504729
Author: Ruifeng Zheng <ru...@apache.org>
AuthorDate: Thu Aug 20 18:30:27 2026 +0800
[SPARK-58898][ML] Use Identifiable for temporary ML column names
### What changes were proposed in this pull request?
This PR replaces ad hoc UUID concatenation for Scala ML temporary and fallback column names
with `Identifiable.randomUID(prefix)`.
The updated paths cover classification/regression summary fallback output columns and
`OneVsRestModel` intermediate columns.
### Why are the changes needed?
Scala ML code already uses `Identifiable.randomUID` for collision-resistant generated names.
Using it in these remaining column-name paths keeps the Scala side consistent and avoids direct
`java.util.UUID` usage for temporary ML columns.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Manually checked with:
```
git diff --check
grep -rn -P "[^\x00-\x7F]" mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
```
Unit tests were not run because this is a small internal refactor of generated column names.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Codex (GPT-5)
Closes #58151 from zhengruifeng/unify-ml-temp-cols-identifiable.
Authored-by: Ruifeng Zheng <ru...@apache.org>
Signed-off-by: Ruifeng Zheng <ru...@foxmail.com>
---
.../scala/org/apache/spark/ml/classification/Classifier.scala | 9 ++++-----
.../scala/org/apache/spark/ml/classification/OneVsRest.scala | 6 ++----
.../spark/ml/classification/ProbabilisticClassifier.scala | 10 +++++-----
.../spark/ml/regression/GeneralizedLinearRegression.scala | 4 ++--
.../org/apache/spark/ml/regression/LinearRegression.scala | 3 +--
5 files changed, 14 insertions(+), 18 deletions(-)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala
index e713eec4f2d5..2772bdb8c3f6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala
@@ -199,13 +199,12 @@ abstract class ClassificationModel[FeaturesType, M <: ClassificationModel[Featur
(ClassificationModel[FeaturesType, M], String, String) = {
val model = if ($(rawPredictionCol).isEmpty && $(predictionCol).isEmpty) {
copy(ParamMap.empty)
- .setRawPredictionCol("rawPrediction_" + java.util.UUID.randomUUID.toString)
- .setPredictionCol("prediction_" + java.util.UUID.randomUUID.toString)
+ .setRawPredictionCol(Identifiable.randomUID("rawPrediction"))
+ .setPredictionCol(Identifiable.randomUID("prediction"))
} else if ($(rawPredictionCol).isEmpty) {
- copy(ParamMap.empty).setRawPredictionCol("rawPrediction_" +
- java.util.UUID.randomUUID.toString)
+ copy(ParamMap.empty).setRawPredictionCol(Identifiable.randomUID("rawPrediction"))
} else if ($(predictionCol).isEmpty) {
- copy(ParamMap.empty).setPredictionCol("prediction_" + java.util.UUID.randomUUID.toString)
+ copy(ParamMap.empty).setPredictionCol(Identifiable.randomUID("prediction"))
} else {
this
}
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
index 42c6cf69600b..f81926623809 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
@@ -17,8 +17,6 @@
package org.apache.spark.ml.classification
-import java.util.UUID
-
import scala.concurrent.Future
import scala.concurrent.duration.Duration
import scala.language.existentials
@@ -201,10 +199,10 @@ final class OneVsRestModel private[ml] (
val isProbModel = models.head.isInstanceOf[ProbabilisticClassificationModel[_, _]]
// use a temporary raw prediction column to avoid column conflict
- val tmpRawPredName = "mbc$raw" + UUID.randomUUID().toString
+ val tmpRawPredName = Identifiable.randomUID("mbc$raw")
// add an accumulator column to store predictions of all the models
- val accColName = "mbc$acc" + UUID.randomUUID().toString
+ val accColName = Identifiable.randomUID("mbc$acc")
val newDataset = dataset.withColumn(accColName, lit(Array.emptyDoubleArray))
val columns = newDataset.schema.fieldNames.map(col)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala
index 925f26501edd..a6648f4fab7b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala
@@ -22,7 +22,7 @@ import org.apache.spark.internal.{LogKeys}
import org.apache.spark.ml.linalg.{DenseVector, SQLDataTypes, Vector}
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.param.shared._
-import org.apache.spark.ml.util.SchemaUtils
+import org.apache.spark.ml.util.{Identifiable, SchemaUtils}
import org.apache.spark.sql.{DataFrame, Dataset}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{DataType, StructType}
@@ -241,12 +241,12 @@ abstract class ProbabilisticClassificationModel[
(ProbabilisticClassificationModel[FeaturesType, M], String, String) = {
val model = if ($(probabilityCol).isEmpty && $(predictionCol).isEmpty) {
copy(ParamMap.empty)
- .setProbabilityCol("probability_" + java.util.UUID.randomUUID.toString)
- .setPredictionCol("prediction_" + java.util.UUID.randomUUID.toString)
+ .setProbabilityCol(Identifiable.randomUID("probability"))
+ .setPredictionCol(Identifiable.randomUID("prediction"))
} else if ($(probabilityCol).isEmpty) {
- copy(ParamMap.empty).setProbabilityCol("probability_" + java.util.UUID.randomUUID.toString)
+ copy(ParamMap.empty).setProbabilityCol(Identifiable.randomUID("probability"))
} else if ($(predictionCol).isEmpty) {
- copy(ParamMap.empty).setPredictionCol("prediction_" + java.util.UUID.randomUUID.toString)
+ copy(ParamMap.empty).setPredictionCol(Identifiable.randomUID("prediction"))
} else {
this
}
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
index de10d1e7aed7..ac9363511320 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
@@ -1282,7 +1282,7 @@ class GeneralizedLinearRegressionSummary private[regression] (
if (origModel.isDefined(origModel.predictionCol) && origModel.getPredictionCol.nonEmpty) {
origModel.getPredictionCol
} else {
- "prediction_" + java.util.UUID.randomUUID.toString
+ Identifiable.randomUID("prediction")
}
}
@@ -1456,7 +1456,7 @@ class GeneralizedLinearRegressionSummary private[regression] (
link.link(glrSummary.getDouble(4))
} else {
// Create empty feature column and fit intercept only model using param setting from model
- val featureNull = "feature_" + java.util.UUID.randomUUID.toString
+ val featureNull = Identifiable.randomUID("feature")
val paramMap = model.extractParamMap()
paramMap.put(model.featuresCol, featureNull)
if (family.name != "tweedie") {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala
index 822df270c0bf..89e29a7fb26d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala
@@ -742,7 +742,7 @@ class LinearRegressionModel private[ml] (
private[regression] def findSummaryModelAndPredictionCol(): (LinearRegressionModel, String) = {
$(predictionCol) match {
case "" =>
- val predictionColName = "prediction_" + java.util.UUID.randomUUID.toString
+ val predictionColName = Identifiable.randomUID("prediction")
(copy(ParamMap.empty).setPredictionCol(predictionColName), predictionColName)
case p => (this, p)
}
@@ -1160,4 +1160,3 @@ class LinearRegressionSummary private[regression] (
}
}
}
-
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org