This is an automated email from the ASF dual-hosted git repository.
ruifengz pushed a commit to branch branch-4.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.0 by this push:
new a6298d1e97a5 [SPARK-51217][ML][CONNECT] ML model helper constructor
clean up
a6298d1e97a5 is described below
commit a6298d1e97a5d5e5a4ad1bd9a235e03be9f727a5
Author: Ruifeng Zheng <ruife...@apache.org>
AuthorDate: Mon Feb 17 11:07:07 2025 +0800
[SPARK-51217][ML][CONNECT] ML model helper constructor clean up
### What changes were proposed in this pull request?
ML model helper constructor clean up:
1, add comments;
2, set invalid values, e.g. empty uid, NaN efficient
### Why are the changes needed?
1, to avoid unintentionally incorrect usage;
2, to differentiate from normal models;
### Does this PR introduce _any_ user-facing change?
no, internal change
### How was this patch tested?
existing tests
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #49956 from zhengruifeng/ml_connect_const.
Authored-by: Ruifeng Zheng <ruife...@apache.org>
Signed-off-by: Ruifeng Zheng <ruife...@apache.org>
(cherry picked from commit d75a7d6fbe4ab97dbaa78200e5d01a4bfce13736)
Signed-off-by: Ruifeng Zheng <ruife...@apache.org>
---
.../org/apache/spark/ml/classification/DecisionTreeClassifier.scala | 3 +--
.../scala/org/apache/spark/ml/classification/FMClassifier.scala | 4 ++--
.../scala/org/apache/spark/ml/classification/GBTClassifier.scala | 5 ++---
.../main/scala/org/apache/spark/ml/classification/LinearSVC.scala | 3 ++-
.../org/apache/spark/ml/classification/LogisticRegression.scala | 3 +--
.../spark/ml/classification/MultilayerPerceptronClassifier.scala | 3 ++-
.../main/scala/org/apache/spark/ml/classification/NaiveBayes.scala | 4 ++--
.../org/apache/spark/ml/classification/RandomForestClassifier.scala | 3 +--
.../main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala | 5 ++---
.../main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala | 4 ++--
mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala | 4 +---
mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala | 6 ++++--
.../org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala | 3 ++-
.../src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala | 4 ++--
.../main/scala/org/apache/spark/ml/feature/CountVectorizer.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala | 3 ++-
.../src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala | 4 +---
mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala | 3 ++-
.../src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala | 3 ++-
.../src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala | 3 +--
.../src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala | 3 ++-
.../org/apache/spark/ml/feature/UnivariateFeatureSelector.scala | 4 ++--
.../org/apache/spark/ml/feature/VarianceThresholdSelector.scala | 4 ++--
.../src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala | 3 ++-
mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala | 3 +--
.../org/apache/spark/ml/regression/AFTSurvivalRegression.scala | 4 ++--
.../org/apache/spark/ml/regression/DecisionTreeRegressor.scala | 3 +--
.../src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala | 4 ++--
.../main/scala/org/apache/spark/ml/regression/GBTRegressor.scala | 4 +---
.../apache/spark/ml/regression/GeneralizedLinearRegression.scala | 3 ++-
.../scala/org/apache/spark/ml/regression/IsotonicRegression.scala | 3 ++-
.../scala/org/apache/spark/ml/regression/LinearRegression.scala | 3 +--
.../org/apache/spark/ml/regression/RandomForestRegressor.scala | 3 +--
41 files changed, 73 insertions(+), 68 deletions(-)
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
index 761741e7f42d..2c9f518c772c 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
@@ -193,8 +193,7 @@ class DecisionTreeClassificationModel private[ml] (
this(Identifiable.randomUID("dtc"), rootNode, numFeatures, numClasses)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Node.dummyNode, 0, 0)
+ private[ml] def this() = this("", Node.dummyNode, -1, -1)
override def predict(features: Vector): Double = {
rootNode.predictImpl(features).prediction
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala
index 0ef16cb42776..3e88a6d10bcd 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala
@@ -259,8 +259,8 @@ class FMClassificationModel private[classification] (
with FMClassifierParams with MLWritable
with HasTrainingSummary[FMClassificationTrainingSummary]{
- private[ml] def this() = this(Identifiable.randomUID("fmc"),
- Double.NaN, Vectors.empty, Matrices.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Double.NaN, Vectors.empty, Matrices.empty)
@Since("3.0.0")
override val numClasses: Int = 2
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
index 8ed52d5e09e0..9f2c2c85115b 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
@@ -273,9 +273,8 @@ class GBTClassificationModel private[ml](
this(uid, _trees, _treeWeights, -1, 2)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("gbtc"),
- Array(new DecisionTreeRegressionModel), Array(0.0))
+ private[ml] def this() = this("",
+ Array(new DecisionTreeRegressionModel), Array(Double.NaN), -1, -1)
@Since("1.4.0")
override def trees: Array[DecisionTreeRegressionModel] = _trees
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
index 6fa7f4d5d493..522db5f15fe3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
@@ -365,7 +365,8 @@ class LinearSVCModel private[classification] (
extends ClassificationModel[Vector, LinearSVCModel]
with LinearSVCParams with MLWritable with
HasTrainingSummary[LinearSVCTrainingSummary] {
- private[ml] def this() = this(Identifiable.randomUID("linearsvc"),
Vectors.empty, 0.0)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Double.NaN)
@Since("2.2.0")
override val numClasses: Int = 2
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
index 8a162d97384b..c6fa15aaf919 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
@@ -1077,8 +1077,7 @@ class LogisticRegressionModel private[spark] (
Vectors.dense(intercept), 2, isMultinomial = false)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("logreg"),
Vectors.empty, 0)
+ private[ml] def this() = this("", Matrices.empty, Vectors.empty, -1, false)
/**
* A vector of model coefficients for "binomial" logistic regression. If
this model was trained
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
index a09bf7a7aa36..73db8f189f81 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
@@ -283,7 +283,8 @@ class MultilayerPerceptronClassificationModel private[ml] (
with MultilayerPerceptronParams with Serializable with MLWritable
with HasTrainingSummary[MultilayerPerceptronClassificationTrainingSummary]{
- private[ml] def this() = this(Identifiable.randomUID("mlpc"), Vectors.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty)
@Since("1.6.0")
override lazy val numFeatures: Int = $(layers).head
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
index de2023899ee5..513b6e676e5d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
@@ -401,8 +401,8 @@ class NaiveBayesModel private[ml] (
import NaiveBayes._
- private[ml] def this() = this(Identifiable.randomUID("nb"),
- Vectors.empty, Matrices.empty, Matrices.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Matrices.empty,
Matrices.empty)
/**
* mllib NaiveBayes is a wrapper of ml implementation currently.
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
index 0833ad0d402b..24dd7095513a 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
@@ -256,8 +256,7 @@ class RandomForestClassificationModel private[ml] (
this(Identifiable.randomUID("rfc"), trees, numFeatures, numClasses)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Array(new DecisionTreeClassificationModel), 0,
0)
+ private[ml] def this() = this("", Array(new
DecisionTreeClassificationModel), -1, -1)
@Since("1.4.0")
override def trees: Array[DecisionTreeClassificationModel] = _trees
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
index c1ef69e8b047..f1cd126a6406 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala
@@ -96,9 +96,8 @@ class BisectingKMeansModel private[ml] (
extends Model[BisectingKMeansModel] with BisectingKMeansParams with
MLWritable
with HasTrainingSummary[BisectingKMeansSummary] {
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("bisecting-kmeans"),
- new MLlibBisectingKMeansModel(null))
+ // For ml connect only
+ private[ml] def this() = this("", null)
@Since("3.0.0")
lazy val numFeatures: Int = parentModel.clusterCenters.head.size
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala
b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala
index ad1533cd37a9..42ce5d329ce0 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala
@@ -93,8 +93,8 @@ class GaussianMixtureModel private[ml] (
extends Model[GaussianMixtureModel] with GaussianMixtureParams with
MLWritable
with HasTrainingSummary[GaussianMixtureSummary] {
- private[ml] def this() = this(Identifiable.randomUID("gmm"),
- Array.emptyDoubleArray, Array.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Array.emptyDoubleArray, Array.empty)
@Since("3.0.0")
lazy val numFeatures: Int = gaussians.head.mean.size
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
index e878e12f4df4..0821d9a841cc 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
@@ -139,9 +139,7 @@ class KMeansModel private[ml] (
with HasTrainingSummary[KMeansSummary] {
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("kmeans"),
- new MLlibKMeansModel(clusterCenters = null))
+ private[ml] def this() = this("", null)
@Since("3.0.0")
lazy val numFeatures: Int = parentModel.clusterCenters.head.size
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala
b/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala
index 3fce96fbfbb0..3ea1c8594e1f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala
@@ -617,7 +617,8 @@ class LocalLDAModel private[ml] (
sparkSession: SparkSession)
extends LDAModel(uid, vocabSize, sparkSession) {
- private[ml] def this() = this(Identifiable.randomUID("lda"), -1, null, null)
+ // For ml connect only
+ private[ml] def this() = this("", -1, null, null)
oldLocalModel.setSeed(getSeed)
@@ -715,7 +716,8 @@ class DistributedLDAModel private[ml] (
private var oldLocalModelOption: Option[OldLocalLDAModel])
extends LDAModel(uid, vocabSize, sparkSession) {
- private[ml] def this() = this(Identifiable.randomUID("lda"), -1, null, null,
None)
+ // For ml connect only
+ private[ml] def this() = this("", -1, null, null, None)
override private[clustering] def oldLocalModel: OldLocalLDAModel = {
if (oldLocalModelOption.isEmpty) {
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala
index 5037ac941afb..c429788ee368 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/feature/BucketedRandomProjectionLSH.scala
@@ -68,7 +68,8 @@ class BucketedRandomProjectionLSHModel private[ml](
private[ml] val randMatrix: Matrix)
extends LSHModel[BucketedRandomProjectionLSHModel] with
BucketedRandomProjectionLSHParams {
- private[ml] def this() = this(Identifiable.randomUID("brp-lsh"),
Matrices.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Matrices.empty)
private[ml] def this(uid: String, randUnitVectors: Array[Vector]) = {
this(uid, Matrices.fromVectors(randUnitVectors.toImmutableArraySeq))
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
index e93d96cf9717..ff18efb14939 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
@@ -137,8 +137,8 @@ final class ChiSqSelectorModel private[ml] (
import ChiSqSelectorModel._
- private[ml] def this() = this(
- Identifiable.randomUID("chiSqSelector"), Array.emptyIntArray)
+ // For ml connect only
+ private[ml] def this() = this("", Array.emptyIntArray)
override protected def isNumericAttribute = false
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
index 95788be6bd2b..34465248f20d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
@@ -277,7 +277,8 @@ class CountVectorizerModel(
import CountVectorizerModel._
- private[ml] def this() = this(Identifiable.randomUID("cntVecModel"),
Array.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Array.empty)
@Since("1.5.0")
def this(vocabulary: Array[String]) = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
index 5459bb3f31da..c2b7ff7b00a3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
@@ -121,7 +121,8 @@ class IDFModel private[ml] (
import IDFModel._
- private[ml] def this() = this(Identifiable.randomUID("idf"), null)
+ // For ml connect only
+ private[ml] def this() = this("", null)
/** @group setParam */
@Since("1.4.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala
index 2f51ae2d7fe3..4e169ab178b9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala
@@ -246,7 +246,8 @@ class ImputerModel private[ml] (
import ImputerModel._
- private[ml] def this() = this(Identifiable.randomUID("imputer"), null)
+ // For ml connect only
+ private[ml] def this() = this("", null)
/** @group setParam */
@Since("3.0.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
index 66dbabc6187e..a9f1cd34ba3e 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
@@ -107,7 +107,8 @@ class MaxAbsScalerModel private[ml] (
import MaxAbsScalerModel._
- private[ml] def this() = this(Identifiable.randomUID("maxAbsScal"),
Vectors.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty)
/** @group setParam */
@Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala
index d077b0a4a022..96d341b16347 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinHashLSH.scala
@@ -48,7 +48,8 @@ class MinHashLSHModel private[ml](
private[ml] val randCoefficients: Array[(Int, Int)])
extends LSHModel[MinHashLSHModel] {
- private[ml] def this() = this(Identifiable.randomUID("mh-lsh"), Array.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Array.empty)
/** @group setParam */
@Since("2.4.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
index e3b0590524f3..c54e64f97953 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
@@ -154,7 +154,8 @@ class MinMaxScalerModel private[ml] (
import MinMaxScalerModel._
- private[ml] def this() = this(Identifiable.randomUID("minMaxScal"),
Vectors.empty, Vectors.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Vectors.empty)
/** @group setParam */
@Since("1.5.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
index 25bcdc9a1c29..3eaff518e8fc 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
@@ -234,7 +234,8 @@ class OneHotEncoderModel private[ml] (
import OneHotEncoderModel._
- private[ml] def this() = this(Identifiable.randomUID("oneHotEncoder)"),
Array.emptyIntArray)
+ // For ml connect only
+ private[ml] def this() = this("", Array.emptyIntArray)
// Returns the category size for each index with `dropLast` and
`handleInvalid`
// taken into account.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
index 67c8fcf15eec..6b61e761f589 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
@@ -128,9 +128,7 @@ class PCAModel private[ml] (
import PCAModel._
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("pca"),
- DenseMatrix.zeros(1, 1), Vectors.empty)
+ private[ml] def this() = this("", Matrices.empty, Vectors.empty)
/** @group setParam */
@Since("1.5.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index 2eb37fd65d7f..d2191185dddd 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -349,7 +349,8 @@ class RFormulaModel private[feature](
private[ml] val pipelineModel: PipelineModel)
extends Model[RFormulaModel] with RFormulaBase with MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("rFormula"), null, null)
+ // For ml connect only
+ private[ml] def this() = this("", null, null)
@Since("2.0.0")
override def transform(dataset: Dataset[_]): DataFrame = {
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala
index c77f7008d05a..1779f0d6278f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RobustScaler.scala
@@ -230,7 +230,8 @@ class RobustScalerModel private[ml] (
import RobustScalerModel._
- private[ml] def this() = this(Identifiable.randomUID("robustScal"),
Vectors.empty, Vectors.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Vectors.empty)
/** @group setParam */
def setInputCol(value: String): this.type = set(inputCol, value)
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
index 546463c15844..c1ac1fdbba7d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
@@ -147,7 +147,8 @@ class StandardScalerModel private[ml] (
import StandardScalerModel._
- private[ml] def this() = this(Identifiable.randomUID("stdScal"),
Vectors.empty, Vectors.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Vectors.empty)
/** @group setParam */
@Since("1.2.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
index 8b643372ec93..06a88e9b1c49 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
@@ -302,8 +302,7 @@ class StringIndexerModel (
def this(labelsArray: Array[Array[String]]) =
this(Identifiable.randomUID("strIdx"), labelsArray)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(labels = Array.empty)
+ private[ml] def this() = this("", Array.empty[Array[String]])
@deprecated("`labels` is deprecated and will be removed in 3.1.0. Use
`labelsArray` " +
"instead.", "3.0.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala
index 31504fead161..39ffaf32a1f3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala
@@ -286,7 +286,8 @@ class TargetEncoderModel private[ml] (
@Since("4.0.0") private[ml] val stats: Array[Map[Double, (Double,
Double)]])
extends Model[TargetEncoderModel] with TargetEncoderBase with MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("TargetEncoder"),
Array.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Array.empty)
/** @group setParam */
@Since("4.0.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala
index d845e2887a64..704166d9b657 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/feature/UnivariateFeatureSelector.scala
@@ -289,8 +289,8 @@ class UnivariateFeatureSelectorModel private[ml](
extends Model[UnivariateFeatureSelectorModel] with
UnivariateFeatureSelectorParams
with MLWritable {
- private[ml] def this() = this(
- Identifiable.randomUID("UnivariateFeatureSelector"), Array.emptyIntArray)
+ // For ml connect only
+ private[ml] def this() = this("", Array.emptyIntArray)
/** @group setParam */
@Since("3.1.1")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala
index 23ea1ee3066e..cd1905b90ace 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/feature/VarianceThresholdSelector.scala
@@ -126,8 +126,8 @@ class VarianceThresholdSelectorModel private[ml](
extends Model[VarianceThresholdSelectorModel] with
VarianceThresholdSelectorParams
with MLWritable {
- private[ml] def this() = this(
- Identifiable.randomUID("VarianceThresholdSelector"), Array.emptyIntArray)
+ // For ml connect only
+ private[ml] def this() = this("", Array.emptyIntArray)
if (selectedFeatures.length >= 2) {
require(selectedFeatures.sliding(2).forall(l => l(0) < l(1)),
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
index 5063f15302a3..091e20922782 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
@@ -298,7 +298,8 @@ class VectorIndexerModel private[ml] (
import VectorIndexerModel._
- private[ml] def this() = this(Identifiable.randomUID("vecIdx"), -1,
Map.empty)
+ // For ml connect only
+ private[ml] def this() = this("", -1, Map.empty)
/** Java-friendly version of [[categoryMaps]] */
@Since("1.4.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
index c3eeb394c5d4..7d6765b231b5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
@@ -211,7 +211,8 @@ class Word2VecModel private[ml] (
import Word2VecModel._
- private[ml] def this() = this(Identifiable.randomUID("w2v"), null)
+ // For ml connect only
+ private[ml] def this() = this("", null)
/**
* Returns a dataframe with two fields, "word" and "vector", with "word"
being a String and
diff --git a/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala
b/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala
index d90124c62d54..0b75753695fd 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala
@@ -223,7 +223,8 @@ class FPGrowthModel private[ml] (
private val numTrainingRecords: Long)
extends Model[FPGrowthModel] with FPGrowthParams with MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("fpgrowth"), null,
Map.empty, 0L)
+ // For ml connect only
+ private[ml] def this() = this("", null, Map.empty, -1L)
/** @group setParam */
@Since("2.2.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
index 4120e16794a8..95c47531720d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala
@@ -281,8 +281,7 @@ class ALSModel private[ml] (
extends Model[ALSModel] with ALSModelParams with MLWritable {
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("als"), 0, null, null)
+ private[ml] def this() = this("", -1, null, null)
/** @group setParam */
@Since("1.4.0")
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
index d9f7af73ce33..8bc0f641aaad 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala
@@ -371,8 +371,8 @@ class AFTSurvivalRegressionModel private[ml] (
extends RegressionModel[Vector, AFTSurvivalRegressionModel] with
AFTSurvivalRegressionParams
with MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("aftSurvReg"),
- Vectors.empty, Double.NaN, Double.NaN)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Double.NaN, Double.NaN)
@Since("3.0.0")
override def numFeatures: Int = coefficients.size
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
index 2c692d33a38d..4f38d8757413 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
@@ -188,8 +188,7 @@ class DecisionTreeRegressionModel private[ml] (
this(Identifiable.randomUID("dtr"), rootNode, numFeatures)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Node.dummyNode, 0)
+ private[ml] def this() = this("", Node.dummyNode, -1)
override def predict(features: Vector): Double = {
rootNode.predictImpl(features).prediction
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala
index 02ef1df2c44e..994ee3f77f3c 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala
@@ -461,8 +461,8 @@ class FMRegressionModel private[regression] (
extends RegressionModel[Vector, FMRegressionModel]
with FMRegressorParams with MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("fmr"),
- Double.NaN, Vectors.empty, Matrices.empty)
+ // For ml connect only
+ private[ml] def this() = this("", Double.NaN, Vectors.empty, Matrices.empty)
@Since("3.0.0")
override val numFeatures: Int = linear.size
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
index c2c672a7fa60..f71eea6c6293 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
@@ -243,9 +243,7 @@ class GBTRegressionModel private[ml](
this(uid, _trees, _treeWeights, -1)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("gbtr"),
- Array(new DecisionTreeRegressionModel), Array(0.0))
+ private[ml] def this() = this("", Array(new DecisionTreeRegressionModel),
Array(Double.NaN), -1)
@Since("1.4.0")
override def trees: Array[DecisionTreeRegressionModel] = _trees
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 dea182902ace..d5141ec4ccee 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
@@ -1009,7 +1009,8 @@ class GeneralizedLinearRegressionModel private[ml] (
with GeneralizedLinearRegressionBase with MLWritable
with HasTrainingSummary[GeneralizedLinearRegressionTrainingSummary] {
- private[ml] def this() = this(Identifiable.randomUID("glm"), Vectors.empty,
Double.NaN)
+ // For ml connect only
+ private[ml] def this() = this("", Vectors.empty, Double.NaN)
/**
* Sets the link prediction (linear predictor) column name.
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
index 53850089a5a4..e1bfff068cfe 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
@@ -213,7 +213,8 @@ class IsotonicRegressionModel private[ml] (
private val oldModel: MLlibIsotonicRegressionModel)
extends Model[IsotonicRegressionModel] with IsotonicRegressionBase with
MLWritable {
- private[ml] def this() = this(Identifiable.randomUID("isoReg"), null)
+ // For ml connect only
+ private[ml] def this() = this("", null)
/** @group setParam */
@Since("1.5.0")
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 b9cd138a51ec..b20c09db1fa7 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
@@ -703,8 +703,7 @@ class LinearRegressionModel private[ml] (
this(uid, coefficients, intercept, 1.0)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Identifiable.randomUID("linReg"),
Vectors.empty, 0.0, 0.0)
+ private[ml] def this() = this("", Vectors.empty, Double.NaN, Double.NaN)
override val numFeatures: Int = coefficients.size
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
index b0409c916a05..97d0f54d0eca 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
@@ -213,8 +213,7 @@ class RandomForestRegressionModel private[ml] (
this(Identifiable.randomUID("rfr"), trees, numFeatures)
// For ml connect only
- @Since("4.0.0")
- private[ml] def this() = this(Array(new DecisionTreeRegressionModel), 0)
+ private[ml] def this() = this("", Array(new DecisionTreeRegressionModel), -1)
@Since("1.4.0")
override def trees: Array[DecisionTreeRegressionModel] = _trees
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
