[SPARK-32310][ML][PySpark][3.0] ML params default value parity

mllib/src/main/scala/org/apache/spark/ml/classification/FMClassifier.scala

@@ -86,7 +86,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setFactorSize(value: Int): this.type = set(factorSize, value)
-  setDefault(factorSize -> 8)
 
   /**
    * Set whether to fit intercept term.
@@ -96,7 +95,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
-  setDefault(fitIntercept -> true)
 
   /**
    * Set whether to fit linear term.
@@ -106,7 +104,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setFitLinear(value: Boolean): this.type = set(fitLinear, value)
-  setDefault(fitLinear -> true)
 
   /**
    * Set the L2 regularization parameter.
@@ -116,7 +113,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setRegParam(value: Double): this.type = set(regParam, value)
-  setDefault(regParam -> 0.0)
 
   /**
    * Set the mini-batch fraction parameter.
@@ -126,7 +122,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setMiniBatchFraction(value: Double): this.type = set(miniBatchFraction, value)
-  setDefault(miniBatchFraction -> 1.0)
 
   /**
    * Set the standard deviation of initial coefficients.
@@ -136,7 +131,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setInitStd(value: Double): this.type = set(initStd, value)
-  setDefault(initStd -> 0.01)
 
   /**
    * Set the maximum number of iterations.
@@ -146,7 +140,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
-  setDefault(maxIter -> 100)
 
   /**
    * Set the initial step size for the first step (like learning rate).
@@ -156,7 +149,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setStepSize(value: Double): this.type = set(stepSize, value)
-  setDefault(stepSize -> 1.0)
 
   /**
    * Set the convergence tolerance of iterations.
@@ -166,7 +158,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setTol(value: Double): this.type = set(tol, value)
-  setDefault(tol -> 1E-6)
 
   /**
    * Set the solver algorithm used for optimization.
@@ -177,7 +168,6 @@ class FMClassifier @Since("3.0.0") (
    */
   @Since("3.0.0")
   def setSolver(value: String): this.type = set(solver, value)
-  setDefault(solver -> AdamW)
 
   /**
    * Set the random seed for weight initialization.

mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala

@@ -54,6 +54,9 @@ private[classification] trait LinearSVCParams extends ClassifierParams with HasR
    */
   final override val threshold: DoubleParam = new DoubleParam(this, "threshold",
     "threshold in binary classification prediction applied to rawPrediction")
+
+  setDefault(regParam -> 0.0, maxIter -> 100, fitIntercept -> true, tol -> 1E-6,
+    standardization -> true, threshold -> 0.0, aggregationDepth -> 2)
 }
 
 /**
@@ -81,7 +84,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setRegParam(value: Double): this.type = set(regParam, value)
-  setDefault(regParam -> 0.0)
 
   /**
    * Set the maximum number of iterations.
@@ -91,7 +93,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
-  setDefault(maxIter -> 100)
 
   /**
    * Whether to fit an intercept term.
@@ -101,7 +102,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
-  setDefault(fitIntercept -> true)
 
   /**
    * Set the convergence tolerance of iterations.
@@ -112,7 +112,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setTol(value: Double): this.type = set(tol, value)
-  setDefault(tol -> 1E-6)
 
   /**
    * Whether to standardize the training features before fitting the model.
@@ -122,7 +121,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setStandardization(value: Boolean): this.type = set(standardization, value)
-  setDefault(standardization -> true)
 
   /**
    * Set the value of param [[weightCol]].
@@ -141,7 +139,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setThreshold(value: Double): this.type = set(threshold, value)
-  setDefault(threshold -> 0.0)
 
   /**
    * Suggested depth for treeAggregate (greater than or equal to 2).
@@ -153,7 +150,6 @@ class LinearSVC @Since("2.2.0") (
    */
   @Since("2.2.0")
   def setAggregationDepth(value: Int): this.type = set(aggregationDepth, value)
-  setDefault(aggregationDepth -> 2)
 
   @Since("2.2.0")
   override def copy(extra: ParamMap): LinearSVC = defaultCopy(extra)
@@ -300,7 +296,6 @@ class LinearSVCModel private[classification] (
 
   @Since("2.2.0")
   def setThreshold(value: Double): this.type = set(threshold, value)
-  setDefault(threshold, 0.0)
 
   private val margin: Vector => Double = (features) => {
     BLAS.dot(features, coefficients) + intercept

mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala

@@ -248,6 +248,10 @@ private[classification] trait LogisticRegressionParams extends ProbabilisticClas
       isSet(lowerBoundsOnIntercepts) || isSet(upperBoundsOnIntercepts)
   }
 
+  setDefault(regParam -> 0.0, elasticNetParam -> 0.0, maxIter -> 100, tol -> 1E-6,
+    fitIntercept -> true, family -> "auto", standardization -> true, threshold -> 0.5,
+    aggregationDepth -> 2)
+
   override protected def validateAndTransformSchema(
       schema: StructType,
       fitting: Boolean,
@@ -290,7 +294,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.2.0")
   def setRegParam(value: Double): this.type = set(regParam, value)
-  setDefault(regParam -> 0.0)
 
   /**
    * Set the ElasticNet mixing parameter.
@@ -306,7 +309,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.4.0")
   def setElasticNetParam(value: Double): this.type = set(elasticNetParam, value)
-  setDefault(elasticNetParam -> 0.0)
 
   /**
    * Set the maximum number of iterations.
@@ -316,7 +318,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.2.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
-  setDefault(maxIter -> 100)
 
   /**
    * Set the convergence tolerance of iterations.
@@ -327,7 +328,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.4.0")
   def setTol(value: Double): this.type = set(tol, value)
-  setDefault(tol -> 1E-6)
 
   /**
    * Whether to fit an intercept term.
@@ -337,7 +337,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.4.0")
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
-  setDefault(fitIntercept -> true)
 
   /**
    * Sets the value of param [[family]].
@@ -347,7 +346,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("2.1.0")
   def setFamily(value: String): this.type = set(family, value)
-  setDefault(family -> "auto")
 
   /**
    * Whether to standardize the training features before fitting the model.
@@ -361,11 +359,9 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("1.5.0")
   def setStandardization(value: Boolean): this.type = set(standardization, value)
-  setDefault(standardization -> true)
 
   @Since("1.5.0")
   override def setThreshold(value: Double): this.type = super.setThreshold(value)
-  setDefault(threshold -> 0.5)
 
   @Since("1.5.0")
   override def getThreshold: Double = super.getThreshold
@@ -396,7 +392,6 @@ class LogisticRegression @Since("1.2.0") (
    */
   @Since("2.1.0")
   def setAggregationDepth(value: Int): this.type = set(aggregationDepth, value)
-  setDefault(aggregationDepth -> 2)
 
   /**
    * Set the lower bounds on coefficients if fitting under bound constrained optimization.

mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala

@@ -63,6 +63,8 @@ private[classification] trait NaiveBayesParams extends PredictorParams with HasW
 
   /** @group getParam */
   final def getModelType: String = $(modelType)
+
+  setDefault(smoothing -> 1.0, modelType -> NaiveBayes.Multinomial)
 }
 
 // scalastyle:off line.size.limit
@@ -106,7 +108,6 @@ class NaiveBayes @Since("1.5.0") (
    */
   @Since("1.5.0")
   def setSmoothing(value: Double): this.type = set(smoothing, value)
-  setDefault(smoothing -> 1.0)
 
   /**
    * Set the model type using a string (case-sensitive).
@@ -116,7 +117,6 @@ class NaiveBayes @Since("1.5.0") (
    */
   @Since("1.5.0")
   def setModelType(value: String): this.type = set(modelType, value)
-  setDefault(modelType -> Multinomial)
 
   /**
    * Sets the value of param [[weightCol]].

mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala

@@ -71,6 +71,8 @@ private[clustering] trait BisectingKMeansParams extends Params with HasMaxIter
   @Since("2.0.0")
   def getMinDivisibleClusterSize: Double = $(minDivisibleClusterSize)
 
+  setDefault(k -> 4, maxIter -> 20, minDivisibleClusterSize -> 1.0)
+
   /**
    * Validates and transforms the input schema.
    * @param schema input schema
@@ -225,11 +227,6 @@ class BisectingKMeans @Since("2.0.0") (
     @Since("2.0.0") override val uid: String)
   extends Estimator[BisectingKMeansModel] with BisectingKMeansParams with DefaultParamsWritable {
 
-  setDefault(
-    k -> 4,
-    maxIter -> 20,
-    minDivisibleClusterSize -> 1.0)
-
   @Since("2.0.0")
   override def copy(extra: ParamMap): BisectingKMeans = defaultCopy(extra)
 

mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala

@@ -59,6 +59,8 @@ private[clustering] trait GaussianMixtureParams extends Params with HasMaxIter w
   @Since("2.0.0")
   def getK: Int = $(k)
 
+  setDefault(k -> 2, maxIter -> 100, tol -> 0.01)
+
   /**
    * Validates and transforms the input schema.
    *
@@ -323,11 +325,6 @@ class GaussianMixture @Since("2.0.0") (
     @Since("2.0.0") override val uid: String)
   extends Estimator[GaussianMixtureModel] with GaussianMixtureParams with DefaultParamsWritable {
 
-  setDefault(
-    k -> 2,
-    maxIter -> 100,
-    tol -> 0.01)
-
   @Since("2.0.0")
   override def copy(extra: ParamMap): GaussianMixture = defaultCopy(extra)
 

mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala

@@ -86,6 +86,9 @@ private[clustering] trait KMeansParams extends Params with HasMaxIter with HasFe
   @Since("1.5.0")
   def getInitSteps: Int = $(initSteps)
 
+  setDefault(k -> 2, maxIter -> 20, initMode -> MLlibKMeans.K_MEANS_PARALLEL, initSteps -> 2,
+    tol -> 1e-4, distanceMeasure -> DistanceMeasure.EUCLIDEAN)
+
   /**
    * Validates and transforms the input schema.
    * @param schema input schema
@@ -270,14 +273,6 @@ class KMeans @Since("1.5.0") (
     @Since("1.5.0") override val uid: String)
   extends Estimator[KMeansModel] with KMeansParams with DefaultParamsWritable {
 
-  setDefault(
-    k -> 2,
-    maxIter -> 20,
-    initMode -> MLlibKMeans.K_MEANS_PARALLEL,
-    initSteps -> 2,
-    tol -> 1e-4,
-    distanceMeasure -> DistanceMeasure.EUCLIDEAN)
-
   @Since("1.5.0")
   override def copy(extra: ParamMap): KMeans = defaultCopy(extra)
 

mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala

@@ -199,8 +199,6 @@ private[clustering] trait LDAParams extends Params with HasFeaturesCol with HasM
     " with estimates of the topic mixture distribution for each document (often called \"theta\"" +
     " in the literature).  Returns a vector of zeros for an empty document.")
 
-  setDefault(topicDistributionCol -> "topicDistribution")
-
   /** @group getParam */
   @Since("1.6.0")
   def getTopicDistributionCol: String = $(topicDistributionCol)
@@ -315,6 +313,11 @@ private[clustering] trait LDAParams extends Params with HasFeaturesCol with HasM
   @Since("2.0.0")
   def getKeepLastCheckpoint: Boolean = $(keepLastCheckpoint)
 
+  setDefault(maxIter -> 20, k -> 10, optimizer -> "online", checkpointInterval -> 10,
+    learningOffset -> 1024, learningDecay -> 0.51, subsamplingRate -> 0.05,
+    optimizeDocConcentration -> true, keepLastCheckpoint -> true,
+    topicDistributionCol -> "topicDistribution")
+
   /**
    * Validates and transforms the input schema.
    *
@@ -863,10 +866,6 @@ class LDA @Since("1.6.0") (
   @Since("1.6.0")
   def this() = this(Identifiable.randomUID("lda"))
 
-  setDefault(maxIter -> 20, k -> 10, optimizer -> "online", checkpointInterval -> 10,
-    learningOffset -> 1024, learningDecay -> 0.51, subsamplingRate -> 0.05,
-    optimizeDocConcentration -> true, keepLastCheckpoint -> true)
-
   /**
    * The features for LDA should be a `Vector` representing the word counts in a document.
    * The vector should be of length vocabSize, with counts for each term (word).

mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala

@@ -91,7 +91,7 @@ private[clustering] trait PowerIterationClusteringParams extends Params with Has
   @Since("2.4.0")
   def getDstCol: String = $(dstCol)
 
-  setDefault(srcCol -> "src", dstCol -> "dst")
+  setDefault(srcCol -> "src", dstCol -> "dst", k -> 2, maxIter -> 20, initMode -> "random")
 }
 
 /**
@@ -111,11 +111,6 @@ class PowerIterationClustering private[clustering] (
     @Since("2.4.0") override val uid: String)
   extends PowerIterationClusteringParams with DefaultParamsWritable {
 
-  setDefault(
-    k -> 2,
-    maxIter -> 20,
-    initMode -> "random")
-
   @Since("2.4.0")
   def this() = this(Identifiable.randomUID("PowerIterationClustering"))
 

mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala

@@ -80,8 +80,6 @@ class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override va
   @Since("3.0.0")
   def setNumBins(value: Int): this.type = set(numBins, value)
 
-  setDefault(numBins -> 1000)
-
   /** @group setParam */
   @Since("1.5.0")
   def setRawPredictionCol(value: String): this.type = set(rawPredictionCol, value)
@@ -94,7 +92,7 @@ class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override va
   @Since("3.0.0")
   def setWeightCol(value: String): this.type = set(weightCol, value)
 
-  setDefault(metricName -> "areaUnderROC")
+  setDefault(metricName -> "areaUnderROC", numBins -> 1000)
 
   @Since("2.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {