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 a4d242753a789..1511cb61b8b30 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
@@ -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.
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 905789090d625..88621b34beb13 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
@@ -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
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 50c14d086957f..a61eb329977cd 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
@@ -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.
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 94681ae9ef796..409a39c5b8ca9 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
@@ -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]].
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 6c7112b80569f..b649b1dd95231 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
@@ -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)
 
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 d779e602545cf..26a866bbecaeb 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
@@ -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)
 
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 a42c920e24987..5370318bc6adb 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
@@ -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)
 
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 4e86b3b247ace..c1b76fb40b2f6 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
@@ -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).
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala
index 812a426a062c1..1466b32bef530 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/clustering/PowerIterationClustering.scala
+++ b/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"))
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
index 7733225c0c4d5..cbec87d7dd715 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
+++ b/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 = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
index 1d6540e970383..3bf115e72b431 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
@@ -63,8 +63,6 @@ class MulticlassClassificationEvaluator @Since("1.5.0") (@Since("1.5.0") overrid
   @Since("1.5.0")
   def setMetricName(value: String): this.type = set(metricName, value)
 
-  setDefault(metricName -> "f1")
-
   /** @group setParam */
   @Since("1.5.0")
   def setPredictionCol(value: String): this.type = set(predictionCol, value)
@@ -104,8 +102,6 @@ class MulticlassClassificationEvaluator @Since("1.5.0") (@Since("1.5.0") overrid
   @Since("3.0.0")
   def setMetricLabel(value: Double): this.type = set(metricLabel, value)
 
-  setDefault(metricLabel -> 0.0)
-
   /**
    * The beta value, which controls precision vs recall weighting,
    * used in `"weightedFMeasure"`, `"fMeasureByLabel"`.
@@ -127,8 +123,6 @@ class MulticlassClassificationEvaluator @Since("1.5.0") (@Since("1.5.0") overrid
   @Since("3.0.0")
   def setBeta(value: Double): this.type = set(beta, value)
 
-  setDefault(beta -> 1.0)
-
   /**
    * param for eps. log-loss is undefined for p=0 or p=1, so probabilities are clipped to
    * max(eps, min(1 - eps, p)). Must be in range (0, 0.5). The default value is 1e-15.
@@ -149,7 +143,7 @@ class MulticlassClassificationEvaluator @Since("1.5.0") (@Since("1.5.0") overrid
   @Since("3.0.0")
   def setEps(value: Double): this.type = set(eps, value)
 
-  setDefault(eps -> 1e-15)
+  setDefault(metricName -> "f1", eps -> 1e-15, metricLabel -> 0.0, beta -> 1.0)
 
   @Since("2.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala
index a8db5452bd56c..632e67c59696c 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala
@@ -65,8 +65,6 @@ class MultilabelClassificationEvaluator @Since("3.0.0") (@Since("3.0.0") overrid
   @Since("3.0.0")
   def setMetricName(value: String): this.type = set(metricName, value)
 
-  setDefault(metricName -> "f1Measure")
-
   /**
    * param for the class whose metric will be computed in `"precisionByLabel"`, `"recallByLabel"`,
    * `"f1MeasureByLabel"`.
@@ -86,8 +84,6 @@ class MultilabelClassificationEvaluator @Since("3.0.0") (@Since("3.0.0") overrid
   /** @group setParam */
   def setMetricLabel(value: Double): this.type = set(metricLabel, value)
 
-  setDefault(metricLabel -> 0.0)
-
   /** @group setParam */
   @Since("3.0.0")
   def setPredictionCol(value: String): this.type = set(predictionCol, value)
@@ -96,6 +92,8 @@ class MultilabelClassificationEvaluator @Since("3.0.0") (@Since("3.0.0") overrid
   @Since("3.0.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
+  setDefault(metricLabel -> 0.0, metricName -> "f1Measure")
+
   @Since("3.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {
     val schema = dataset.schema
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala
index c5dea6c177e21..3a2ddf4d97ee3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RankingEvaluator.scala
@@ -61,8 +61,6 @@ class RankingEvaluator @Since("3.0.0") (@Since("3.0.0") override val uid: String
   @Since("3.0.0")
   def setMetricName(value: String): this.type = set(metricName, value)
 
-  setDefault(metricName -> "meanAveragePrecision")
-
   /**
    * param for ranking position value used in `"meanAveragePrecisionAtK"`, `"precisionAtK"`,
    * `"ndcgAtK"`, `"recallAtK"`. Must be > 0. The default value is 10.
@@ -83,8 +81,6 @@ class RankingEvaluator @Since("3.0.0") (@Since("3.0.0") override val uid: String
   @Since("3.0.0")
   def setK(value: Int): this.type = set(k, value)
 
-  setDefault(k -> 10)
-
   /** @group setParam */
   @Since("3.0.0")
   def setPredictionCol(value: String): this.type = set(predictionCol, value)
@@ -93,6 +89,8 @@ class RankingEvaluator @Since("3.0.0") (@Since("3.0.0") override val uid: String
   @Since("3.0.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
+  setDefault(k -> 10, metricName -> "meanAveragePrecision")
+
   @Since("3.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {
     val schema = dataset.schema
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
index 18a8dda0c76ef..de256600982e5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
@@ -79,8 +79,6 @@ final class RegressionEvaluator @Since("1.4.0") (@Since("1.4.0") override val ui
   @Since("3.0.0")
   def setThroughOrigin(value: Boolean): this.type = set(throughOrigin, value)
 
-  setDefault(throughOrigin -> false)
-
   /** @group setParam */
   @Since("1.4.0")
   def setPredictionCol(value: String): this.type = set(predictionCol, value)
@@ -93,7 +91,7 @@ final class RegressionEvaluator @Since("1.4.0") (@Since("1.4.0") override val ui
   @Since("3.0.0")
   def setWeightCol(value: String): this.type = set(weightCol, value)
 
-  setDefault(metricName -> "rmse")
+  setDefault(metricName -> "rmse", throughOrigin -> false)
 
   @Since("2.0.0")
   override def evaluate(dataset: Dataset[_]): Double = {
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 76f4f944f11d5..c582d92ec538b 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
@@ -54,7 +54,6 @@ private[feature] trait ChiSqSelectorParams extends Params
     "Number of features that selector will select, ordered by ascending p-value. If the" +
       " number of features is < numTopFeatures, then this will select all features.",
     ParamValidators.gtEq(1))
-  setDefault(numTopFeatures -> 50)
 
   /** @group getParam */
   @Since("1.6.0")
@@ -70,7 +69,6 @@ private[feature] trait ChiSqSelectorParams extends Params
   final val percentile = new DoubleParam(this, "percentile",
     "Percentile of features that selector will select, ordered by ascending p-value.",
     ParamValidators.inRange(0, 1))
-  setDefault(percentile -> 0.1)
 
   /** @group getParam */
   @Since("2.1.0")
@@ -85,7 +83,6 @@ private[feature] trait ChiSqSelectorParams extends Params
   @Since("2.1.0")
   final val fpr = new DoubleParam(this, "fpr", "The highest p-value for features to be kept.",
     ParamValidators.inRange(0, 1))
-  setDefault(fpr -> 0.05)
 
   /** @group getParam */
   @Since("2.1.0")
@@ -100,7 +97,6 @@ private[feature] trait ChiSqSelectorParams extends Params
   @Since("2.2.0")
   final val fdr = new DoubleParam(this, "fdr",
     "The upper bound of the expected false discovery rate.", ParamValidators.inRange(0, 1))
-  setDefault(fdr -> 0.05)
 
   /** @group getParam */
   def getFdr: Double = $(fdr)
@@ -114,7 +110,6 @@ private[feature] trait ChiSqSelectorParams extends Params
   @Since("2.2.0")
   final val fwe = new DoubleParam(this, "fwe",
     "The upper bound of the expected family-wise error rate.", ParamValidators.inRange(0, 1))
-  setDefault(fwe -> 0.05)
 
   /** @group getParam */
   def getFwe: Double = $(fwe)
@@ -129,11 +124,13 @@ private[feature] trait ChiSqSelectorParams extends Params
     "The selector type of the ChisqSelector. " +
       "Supported options: " + OldChiSqSelector.supportedSelectorTypes.mkString(", "),
     ParamValidators.inArray[String](OldChiSqSelector.supportedSelectorTypes))
-  setDefault(selectorType -> OldChiSqSelector.NumTopFeatures)
 
   /** @group getParam */
   @Since("2.1.0")
   def getSelectorType: String = $(selectorType)
+
+  setDefault(numTopFeatures -> 50, percentile -> 0.1, fpr -> 0.05, fdr -> 0.05, fwe -> 0.05,
+    selectorType -> OldChiSqSelector.NumTopFeatures)
 }
 
 /**
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 64f1722f5fcb8..ad1010da5c104 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
@@ -64,6 +64,8 @@ private[feature] trait ImputerParams extends Params with HasInputCol with HasInp
   /** @group getParam */
   def getMissingValue: Double = $(missingValue)
 
+  setDefault(strategy -> Imputer.mean, missingValue -> Double.NaN)
+
   /** Returns the input and output column names corresponding in pair. */
   private[feature] def getInOutCols(): (Array[String], Array[String]) = {
     if (isSet(inputCol)) {
@@ -144,8 +146,6 @@ class Imputer @Since("2.2.0") (@Since("2.2.0") override val uid: String)
   @Since("3.0.0")
   def setRelativeError(value: Double): this.type = set(relativeError, value)
 
-  setDefault(strategy -> Imputer.mean, missingValue -> Double.NaN)
-
   override def fit(dataset: Dataset[_]): ImputerModel = {
     transformSchema(dataset.schema, logging = true)
     val spark = dataset.sparkSession
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 c84892c974b90..56798a8e61a61 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
@@ -58,6 +58,8 @@ private[feature] trait MinMaxScalerParams extends Params with HasInputCol with H
   /** @group getParam */
   def getMax: Double = $(max)
 
+  setDefault(min -> 0.0, max -> 1.0)
+
   /** Validates and transforms the input schema. */
   protected def validateAndTransformSchema(schema: StructType): StructType = {
     require($(min) < $(max), s"The specified min(${$(min)}) is larger or equal to max(${$(max)})")
@@ -93,8 +95,6 @@ class MinMaxScaler @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   @Since("1.5.0")
   def this() = this(Identifiable.randomUID("minMaxScal"))
 
-  setDefault(min -> 0.0, max -> 1.0)
-
   /** @group setParam */
   @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
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 0ef092f6be463..5a500fefb57ec 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
@@ -53,8 +53,6 @@ private[ml] trait OneHotEncoderBase extends Params with HasHandleInvalid
     "during fitting, invalid data will result in an error.",
     ParamValidators.inArray(OneHotEncoder.supportedHandleInvalids))
 
-  setDefault(handleInvalid, OneHotEncoder.ERROR_INVALID)
-
   /**
    * Whether to drop the last category in the encoded vector (default: true)
    * @group param
@@ -62,12 +60,13 @@ private[ml] trait OneHotEncoderBase extends Params with HasHandleInvalid
   @Since("2.3.0")
   final val dropLast: BooleanParam =
     new BooleanParam(this, "dropLast", "whether to drop the last category")
-  setDefault(dropLast -> true)
 
   /** @group getParam */
   @Since("2.3.0")
   def getDropLast: Boolean = $(dropLast)
 
+  setDefault(handleInvalid -> OneHotEncoder.ERROR_INVALID, dropLast -> true)
+
   /** Returns the input and output column names corresponding in pair. */
   private[feature] def getInOutCols(): (Array[String], Array[String]) = {
     if (isSet(inputCol)) {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
index 4eedfc4dc0efa..b93c9b1fcd204 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
@@ -46,7 +46,6 @@ private[feature] trait QuantileDiscretizerBase extends Params
   val numBuckets = new IntParam(this, "numBuckets", "Number of buckets (quantiles, or " +
     "categories) into which data points are grouped. Must be >= 2.",
     ParamValidators.gtEq(2))
-  setDefault(numBuckets -> 2)
 
   /** @group getParam */
   def getNumBuckets: Int = getOrDefault(numBuckets)
@@ -82,7 +81,8 @@ private[feature] trait QuantileDiscretizerBase extends Params
     "how to handle invalid entries. Options are skip (filter out rows with invalid values), " +
     "error (throw an error), or keep (keep invalid values in a special additional bucket).",
     ParamValidators.inArray(Bucketizer.supportedHandleInvalids))
-  setDefault(handleInvalid, Bucketizer.ERROR_INVALID)
+
+  setDefault(handleInvalid -> Bucketizer.ERROR_INVALID, numBuckets -> 2)
 }
 
 /**
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 7ccfafa4ac813..b8da020017f12 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
@@ -60,7 +60,6 @@ private[feature] trait RFormulaBase extends HasFeaturesCol with HasLabelCol with
   @Since("2.1.0")
   val forceIndexLabel: BooleanParam = new BooleanParam(this, "forceIndexLabel",
     "Force to index label whether it is numeric or string")
-  setDefault(forceIndexLabel -> false)
 
   /** @group getParam */
   @Since("2.1.0")
@@ -80,7 +79,6 @@ private[feature] trait RFormulaBase extends HasFeaturesCol with HasLabelCol with
     "type. Options are 'skip' (filter out rows with invalid data), error (throw an error), " +
     "or 'keep' (put invalid data in a special additional bucket, at index numLabels).",
     ParamValidators.inArray(StringIndexer.supportedHandleInvalids))
-  setDefault(handleInvalid, StringIndexer.ERROR_INVALID)
 
   /**
    * Param for how to order categories of a string FEATURE column used by `StringIndexer`.
@@ -113,12 +111,14 @@ private[feature] trait RFormulaBase extends HasFeaturesCol with HasLabelCol with
     "The default value is 'frequencyDesc'. When the ordering is set to 'alphabetDesc', " +
     "RFormula drops the same category as R when encoding strings.",
     ParamValidators.inArray(StringIndexer.supportedStringOrderType))
-  setDefault(stringIndexerOrderType, StringIndexer.frequencyDesc)
 
   /** @group getParam */
   @Since("2.3.0")
   def getStringIndexerOrderType: String = $(stringIndexerOrderType)
 
+  setDefault(forceIndexLabel -> false, handleInvalid -> StringIndexer.ERROR_INVALID,
+    stringIndexerOrderType -> StringIndexer.frequencyDesc)
+
   protected def hasLabelCol(schema: StructType): Boolean = {
     schema.map(_.name).contains($(labelCol))
   }
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 bd9be779fedbd..12aba69528891 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
@@ -50,8 +50,6 @@ private[feature] trait RobustScalerParams extends Params with HasInputCol with H
   /** @group getParam */
   def getLower: Double = $(lower)
 
-  setDefault(lower -> 0.25)
-
   /**
    * Upper quantile to calculate quantile range, shared by all features
    * Default: 0.75
@@ -64,8 +62,6 @@ private[feature] trait RobustScalerParams extends Params with HasInputCol with H
   /** @group getParam */
   def getUpper: Double = $(upper)
 
-  setDefault(upper -> 0.75)
-
   /**
    * Whether to center the data with median before scaling.
    * It will build a dense output, so take care when applying to sparse input.
@@ -78,8 +74,6 @@ private[feature] trait RobustScalerParams extends Params with HasInputCol with H
   /** @group getParam */
   def getWithCentering: Boolean = $(withCentering)
 
-  setDefault(withCentering -> false)
-
   /**
    * Whether to scale the data to quantile range.
    * Default: true
@@ -91,7 +85,7 @@ private[feature] trait RobustScalerParams extends Params with HasInputCol with H
   /** @group getParam */
   def getWithScaling: Boolean = $(withScaling)
 
-  setDefault(withScaling -> true)
+  setDefault(withScaling -> true, lower -> 0.25, upper -> 0.75, withCentering -> false)
 
   /** Validates and transforms the input schema. */
   protected def validateAndTransformSchema(schema: StructType): StructType = {
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 be32f44287b6a..77e3d902e0456 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
@@ -56,8 +56,6 @@ private[feature] trait StringIndexerBase extends Params with HasHandleInvalid wi
     "or 'keep' (put invalid data in a special additional bucket, at index numLabels).",
     ParamValidators.inArray(StringIndexer.supportedHandleInvalids))
 
-  setDefault(handleInvalid, StringIndexer.ERROR_INVALID)
-
   /**
    * Param for how to order labels of string column. The first label after ordering is assigned
    * an index of 0.
@@ -84,6 +82,9 @@ private[feature] trait StringIndexerBase extends Params with HasHandleInvalid wi
   @Since("2.3.0")
   def getStringOrderType: String = $(stringOrderType)
 
+  setDefault(handleInvalid -> StringIndexer.ERROR_INVALID,
+    stringOrderType -> StringIndexer.frequencyDesc)
+
   /** Returns the input and output column names corresponding in pair. */
   private[feature] def getInOutCols(): (Array[String], Array[String]) = {
     ParamValidators.checkSingleVsMultiColumnParams(this, Seq(outputCol), Seq(outputCols))
@@ -155,7 +156,6 @@ class StringIndexer @Since("1.4.0") (
   /** @group setParam */
   @Since("2.3.0")
   def setStringOrderType(value: String): this.type = set(stringOrderType, value)
-  setDefault(stringOrderType, StringIndexer.frequencyDesc)
 
   /** @group setParam */
   @Since("1.4.0")
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 866074fb1453e..b7cf4392cd177 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
@@ -60,8 +60,6 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu
     "number of categories of the feature).",
     ParamValidators.inArray(VectorIndexer.supportedHandleInvalids))
 
-  setDefault(handleInvalid, VectorIndexer.ERROR_INVALID)
-
   /**
    * Threshold for the number of values a categorical feature can take.
    * If a feature is found to have {@literal >} maxCategories values, then it is declared
@@ -75,10 +73,10 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu
       " If a feature is found to have > maxCategories values, then it is declared continuous.",
     ParamValidators.gtEq(2))
 
-  setDefault(maxCategories -> 20)
-
   /** @group getParam */
   def getMaxCategories: Int = $(maxCategories)
+
+  setDefault(maxCategories -> 20, handleInvalid -> VectorIndexer.ERROR_INVALID)
 }
 
 /**
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
index be91844ba39e6..3590b9118f3b8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
@@ -57,8 +57,6 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
     "An array of indices to select features from a vector column." +
       " There can be no overlap with names.", VectorSlicer.validIndices)
 
-  setDefault(indices -> Array.emptyIntArray)
-
   /** @group getParam */
   @Since("1.5.0")
   def getIndices: Array[Int] = $(indices)
@@ -79,8 +77,6 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
     "An array of feature names to select features from a vector column." +
       " There can be no overlap with indices.", VectorSlicer.validNames)
 
-  setDefault(names -> Array.empty[String])
-
   /** @group getParam */
   @Since("1.5.0")
   def getNames: Array[String] = $(names)
@@ -97,6 +93,8 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
   @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
+  setDefault(indices -> Array.emptyIntArray, names -> Array.empty[String])
+
   @Since("2.0.0")
   override def transform(dataset: Dataset[_]): DataFrame = {
     // Validity checks
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 bbfcbfbe038ef..287fce4243743 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
@@ -47,7 +47,6 @@ private[feature] trait Word2VecBase extends Params
   final val vectorSize = new IntParam(
     this, "vectorSize", "the dimension of codes after transforming from words (> 0)",
     ParamValidators.gt(0))
-  setDefault(vectorSize -> 100)
 
   /** @group getParam */
   def getVectorSize: Int = $(vectorSize)
@@ -60,7 +59,6 @@ private[feature] trait Word2VecBase extends Params
   final val windowSize = new IntParam(
     this, "windowSize", "the window size (context words from [-window, window]) (> 0)",
     ParamValidators.gt(0))
-  setDefault(windowSize -> 5)
 
   /** @group expertGetParam */
   def getWindowSize: Int = $(windowSize)
@@ -73,7 +71,6 @@ private[feature] trait Word2VecBase extends Params
   final val numPartitions = new IntParam(
     this, "numPartitions", "number of partitions for sentences of words (> 0)",
     ParamValidators.gt(0))
-  setDefault(numPartitions -> 1)
 
   /** @group getParam */
   def getNumPartitions: Int = $(numPartitions)
@@ -86,7 +83,6 @@ private[feature] trait Word2VecBase extends Params
    */
   final val minCount = new IntParam(this, "minCount", "the minimum number of times a token must " +
     "appear to be included in the word2vec model's vocabulary (>= 0)", ParamValidators.gtEq(0))
-  setDefault(minCount -> 5)
 
   /** @group getParam */
   def getMinCount: Int = $(minCount)
@@ -101,13 +97,12 @@ private[feature] trait Word2VecBase extends Params
   final val maxSentenceLength = new IntParam(this, "maxSentenceLength", "Maximum length " +
     "(in words) of each sentence in the input data. Any sentence longer than this threshold will " +
     "be divided into chunks up to the size (> 0)", ParamValidators.gt(0))
-  setDefault(maxSentenceLength -> 1000)
 
   /** @group getParam */
   def getMaxSentenceLength: Int = $(maxSentenceLength)
 
-  setDefault(stepSize -> 0.025)
-  setDefault(maxIter -> 1)
+  setDefault(vectorSize -> 100, windowSize -> 5, numPartitions -> 1, minCount -> 5,
+    maxSentenceLength -> 1000, stepSize -> 0.025, maxIter -> 1)
 
   /**
    * Validate and transform the input schema.
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 e50d4255b1f37..de9d57e400551 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
@@ -50,7 +50,6 @@ private[fpm] trait FPGrowthParams extends Params with HasPredictionCol {
    */
   @Since("2.2.0")
   val itemsCol: Param[String] = new Param[String](this, "itemsCol", "items column name")
-  setDefault(itemsCol -> "items")
 
   /** @group getParam */
   @Since("2.2.0")
@@ -66,7 +65,6 @@ private[fpm] trait FPGrowthParams extends Params with HasPredictionCol {
   val minSupport: DoubleParam = new DoubleParam(this, "minSupport",
     "the minimal support level of a frequent pattern",
     ParamValidators.inRange(0.0, 1.0))
-  setDefault(minSupport -> 0.3)
 
   /** @group getParam */
   @Since("2.2.0")
@@ -95,12 +93,13 @@ private[fpm] trait FPGrowthParams extends Params with HasPredictionCol {
   val minConfidence: DoubleParam = new DoubleParam(this, "minConfidence",
     "minimal confidence for generating Association Rule",
     ParamValidators.inRange(0.0, 1.0))
-  setDefault(minConfidence -> 0.8)
 
   /** @group getParam */
   @Since("2.2.0")
   def getMinConfidence: Double = $(minConfidence)
 
+  setDefault(minSupport -> 0.3, itemsCol -> "items", minConfidence -> 0.8)
+
   /**
    * Validates and transforms the input schema.
    * @param schema input schema
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 2da65a0bcf790..86989c54bde3c 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
@@ -59,7 +59,6 @@ private[regression] trait AFTSurvivalRegressionParams extends PredictorParams
   /** @group getParam */
   @Since("1.6.0")
   def getCensorCol: String = $(censorCol)
-  setDefault(censorCol -> "censor")
 
   /**
    * Param for quantile probabilities array.
@@ -75,7 +74,6 @@ private[regression] trait AFTSurvivalRegressionParams extends PredictorParams
   /** @group getParam */
   @Since("1.6.0")
   def getQuantileProbabilities: Array[Double] = $(quantileProbabilities)
-  setDefault(quantileProbabilities -> Array(0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99))
 
   /**
    * Param for quantiles column name.
@@ -94,6 +92,10 @@ private[regression] trait AFTSurvivalRegressionParams extends PredictorParams
     isDefined(quantilesCol) && $(quantilesCol).nonEmpty
   }
 
+  setDefault(censorCol -> "censor",
+    quantileProbabilities -> Array(0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99),
+    fitIntercept -> true, maxIter -> 100, tol -> 1E-6, aggregationDepth -> 2)
+
   /**
    * Validates and transforms the input schema with the provided param map.
    * @param schema input schema
@@ -150,7 +152,6 @@ class AFTSurvivalRegression @Since("1.6.0") (@Since("1.6.0") override val uid: S
    */
   @Since("1.6.0")
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
-  setDefault(fitIntercept -> true)
 
   /**
    * Set the maximum number of iterations.
@@ -159,7 +160,6 @@ class AFTSurvivalRegression @Since("1.6.0") (@Since("1.6.0") override val uid: S
    */
   @Since("1.6.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
-  setDefault(maxIter -> 100)
 
   /**
    * Set the convergence tolerance of iterations.
@@ -169,7 +169,6 @@ class AFTSurvivalRegression @Since("1.6.0") (@Since("1.6.0") override val uid: S
    */
   @Since("1.6.0")
   def setTol(value: Double): this.type = set(tol, value)
-  setDefault(tol -> 1E-6)
 
   /**
    * Suggested depth for treeAggregate (greater than or equal to 2).
@@ -180,7 +179,6 @@ class AFTSurvivalRegression @Since("1.6.0") (@Since("1.6.0") override val uid: S
    */
   @Since("2.1.0")
   def setAggregationDepth(value: Int): this.type = set(aggregationDepth, value)
-  setDefault(aggregationDepth -> 2)
 
   /**
    * Extract [[featuresCol]], [[labelCol]] and [[censorCol]] from input dataset,
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 64e5e191ffd17..354c583ecc9ae 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
@@ -104,6 +104,10 @@ private[regression] trait LinearRegressionParams extends PredictorParams
   @Since("2.3.0")
   def getEpsilon: Double = $(epsilon)
 
+  setDefault(regParam -> 0.0, fitIntercept -> true, standardization -> true,
+    elasticNetParam -> 0.0, maxIter -> 100, tol -> 1E-6, solver -> Auto,
+    aggregationDepth -> 2, loss -> SquaredError, epsilon -> 1.35)
+
   override protected def validateAndTransformSchema(
       schema: StructType,
       fitting: Boolean,
@@ -190,7 +194,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.3.0")
   def setRegParam(value: Double): this.type = set(regParam, value)
-  setDefault(regParam -> 0.0)
 
   /**
    * Set if we should fit the intercept.
@@ -200,7 +203,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.5.0")
   def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
-  setDefault(fitIntercept -> true)
 
   /**
    * Whether to standardize the training features before fitting the model.
@@ -216,7 +218,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.5.0")
   def setStandardization(value: Boolean): this.type = set(standardization, value)
-  setDefault(standardization -> true)
 
   /**
    * Set the ElasticNet mixing parameter.
@@ -232,7 +233,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.4.0")
   def setElasticNetParam(value: Double): this.type = set(elasticNetParam, value)
-  setDefault(elasticNetParam -> 0.0)
 
   /**
    * Set the maximum number of iterations.
@@ -242,7 +242,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.3.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
-  setDefault(maxIter -> 100)
 
   /**
    * Set the convergence tolerance of iterations.
@@ -253,7 +252,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.4.0")
   def setTol(value: Double): this.type = set(tol, value)
-  setDefault(tol -> 1E-6)
 
   /**
    * Whether to over-/under-sample training instances according to the given weights in weightCol.
@@ -282,7 +280,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("1.6.0")
   def setSolver(value: String): this.type = set(solver, value)
-  setDefault(solver -> Auto)
 
   /**
    * Suggested depth for treeAggregate (greater than or equal to 2).
@@ -294,7 +291,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("2.1.0")
   def setAggregationDepth(value: Int): this.type = set(aggregationDepth, value)
-  setDefault(aggregationDepth -> 2)
 
   /**
    * Sets the value of param [[loss]].
@@ -304,7 +300,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("2.3.0")
   def setLoss(value: String): this.type = set(loss, value)
-  setDefault(loss -> SquaredError)
 
   /**
    * Sets the value of param [[epsilon]].
@@ -314,7 +309,6 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
    */
   @Since("2.3.0")
   def setEpsilon(value: Double): this.type = set(epsilon, value)
-  setDefault(epsilon -> 1.35)
 
   override protected def train(dataset: Dataset[_]): LinearRegressionModel = instrumented { instr =>
     // Extract the number of features before deciding optimization solver.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala
index 7e2c287f146fb..19ea8ae4775d8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/treeParams.scala
@@ -333,8 +333,6 @@ private[ml] trait TreeEnsembleParams extends DecisionTreeParams {
     "Fraction of the training data used for learning each decision tree, in range (0, 1].",
     ParamValidators.inRange(0, 1, lowerInclusive = false, upperInclusive = true))
 
-  setDefault(subsamplingRate -> 1.0)
-
   /** @group getParam */
   final def getSubsamplingRate: Double = $(subsamplingRate)
 
@@ -386,10 +384,10 @@ private[ml] trait TreeEnsembleParams extends DecisionTreeParams {
       || Try(value.toInt).filter(_ > 0).isSuccess
       || Try(value.toDouble).filter(_ > 0).filter(_ <= 1.0).isSuccess)
 
-  setDefault(featureSubsetStrategy -> "auto")
-
   /** @group getParam */
   final def getFeatureSubsetStrategy: String = $(featureSubsetStrategy).toLowerCase(Locale.ROOT)
+
+  setDefault(subsamplingRate -> 1.0, featureSubsetStrategy -> "auto")
 }
 
 /**
@@ -448,8 +446,6 @@ private[ml] trait RandomForestParams extends TreeEnsembleParams {
     new IntParam(this, "numTrees", "Number of trees to train (at least 1)",
     ParamValidators.gtEq(1))
 
-  setDefault(numTrees -> 20)
-
   /** @group getParam */
   final def getNumTrees: Int = $(numTrees)
 
@@ -461,11 +457,11 @@ private[ml] trait RandomForestParams extends TreeEnsembleParams {
   final val bootstrap: BooleanParam = new BooleanParam(this, "bootstrap",
     "Whether bootstrap samples are used when building trees.")
 
-  setDefault(bootstrap -> true)
-
   /** @group getParam */
   @Since("3.0.0")
   final def getBootstrap: Boolean = $(bootstrap)
+
+  setDefault(numTrees -> 20, bootstrap -> true)
 }
 
 private[ml] trait RandomForestClassifierParams
@@ -518,9 +514,7 @@ private[ml] trait GBTParams extends TreeEnsembleParams with HasMaxIter with HasS
     "(a.k.a. learning rate) in interval (0, 1] for shrinking the contribution of each estimator.",
     ParamValidators.inRange(0, 1, lowerInclusive = false, upperInclusive = true))
 
-  setDefault(maxIter -> 20, stepSize -> 0.1, validationTol -> 0.01)
-
-  setDefault(featureSubsetStrategy -> "all")
+  setDefault(maxIter -> 20, stepSize -> 0.1, validationTol -> 0.01, featureSubsetStrategy -> "all")
 
   /** (private[ml]) Create a BoostingStrategy instance to use with the old API. */
   private[ml] def getOldBoostingStrategy(
diff --git a/mllib/src/test/scala/org/apache/spark/ml/util/DefaultReadWriteTest.scala b/mllib/src/test/scala/org/apache/spark/ml/util/DefaultReadWriteTest.scala
index 4d9e664850c12..dd0139b94f098 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/util/DefaultReadWriteTest.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/util/DefaultReadWriteTest.scala
@@ -63,6 +63,9 @@ trait DefaultReadWriteTest extends TempDirectory { self: Suite =>
           (instance.getOrDefault(p), newInstance.getOrDefault(p)) match {
             case (Array(values), Array(newValues)) =>
               assert(values === newValues, s"Values do not match on param ${p.name}.")
+            case (value: Double, newValue: Double) =>
+              assert(value.isNaN && newValue.isNaN || value == newValue,
+                s"Values do not match on param ${p.name}.")
             case (value, newValue) =>
               assert(value === newValue, s"Values do not match on param ${p.name}.")
           }
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index 369761e8f6fa7..c8e15ca1568cc 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -178,6 +178,11 @@ class _LinearSVCParams(_JavaClassifierParams, HasRegParam, HasMaxIter, HasFitInt
                       " all predictions 0.0 and -Inf will make all predictions 1.0.",
                       typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_LinearSVCParams, self).__init__(*args)
+        self._setDefault(maxIter=100, regParam=0.0, tol=1e-6, fitIntercept=True,
+                         standardization=True, threshold=0.0, aggregationDepth=2)
+
 
 @inherit_doc
 class LinearSVC(JavaClassifier, _LinearSVCParams, JavaMLWritable, JavaMLReadable):
@@ -244,6 +249,8 @@ class LinearSVC(JavaClassifier, _LinearSVCParams, JavaMLWritable, JavaMLReadable
     True
     >>> model.intercept == model2.intercept
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 2.2.0
     """
@@ -262,8 +269,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(LinearSVC, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.LinearSVC", self.uid)
-        self._setDefault(maxIter=100, regParam=0.0, tol=1e-6, fitIntercept=True,
-                         standardization=True, threshold=0.0, aggregationDepth=2)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -427,6 +432,10 @@ class _LogisticRegressionParams(_JavaProbabilisticClassifierParams, HasRegParam,
                                     "classes for multinomial regression.",
                                     typeConverter=TypeConverters.toVector)
 
+    def __init__(self, *args):
+        super(_LogisticRegressionParams, self).__init__(*args)
+        self._setDefault(maxIter=100, regParam=0.0, tol=1E-6, threshold=0.5, family="auto")
+
     @since("1.4.0")
     def setThreshold(self, value):
         """
@@ -616,6 +625,8 @@ class LogisticRegression(JavaProbabilisticClassifier, _LogisticRegressionParams,
     True
     >>> model2
     LogisticRegressionModel: uid=..., numClasses=2, numFeatures=2
+    >>> blorModel.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 1.3.0
     """
@@ -642,7 +653,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(LogisticRegression, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.LogisticRegression", self.uid)
-        self._setDefault(maxIter=100, regParam=0.0, tol=1E-6, threshold=0.5, family="auto")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
         self._checkThresholdConsistency()
@@ -1130,7 +1140,12 @@ class _DecisionTreeClassifierParams(_DecisionTreeParams, _TreeClassifierParams):
     """
     Params for :py:class:`DecisionTreeClassifier` and :py:class:`DecisionTreeClassificationModel`.
     """
-    pass
+
+    def __init__(self, *args):
+        super(_DecisionTreeClassifierParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+                         impurity="gini", leafCol="", minWeightFractionPerNode=0.0)
 
 
 @inherit_doc
@@ -1197,7 +1212,8 @@ class DecisionTreeClassifier(JavaProbabilisticClassifier, _DecisionTreeClassifie
     >>> model2 = DecisionTreeClassificationModel.load(model_path)
     >>> model.featureImportances == model2.featureImportances
     True
-
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> df3 = spark.createDataFrame([
     ...     (1.0, 0.2, Vectors.dense(1.0)),
     ...     (1.0, 0.8, Vectors.dense(1.0)),
@@ -1229,9 +1245,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(DecisionTreeClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.DecisionTreeClassifier", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
-                         impurity="gini", leafCol="", minWeightFractionPerNode=0.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1365,7 +1378,14 @@ class _RandomForestClassifierParams(_RandomForestParams, _TreeClassifierParams):
     """
     Params for :py:class:`RandomForestClassifier` and :py:class:`RandomForestClassificationModel`.
     """
-    pass
+
+    def __init__(self, *args):
+        super(_RandomForestClassifierParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+                         impurity="gini", numTrees=20, featureSubsetStrategy="auto",
+                         subsamplingRate=1.0, leafCol="", minWeightFractionPerNode=0.0,
+                         bootstrap=True)
 
 
 @inherit_doc
@@ -1437,6 +1457,8 @@ class RandomForestClassifier(JavaProbabilisticClassifier, _RandomForestClassifie
     >>> model2 = RandomForestClassificationModel.load(model_path)
     >>> model.featureImportances == model2.featureImportances
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -1459,11 +1481,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(RandomForestClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.RandomForestClassifier", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
-                         impurity="gini", numTrees=20, featureSubsetStrategy="auto",
-                         subsamplingRate=1.0, leafCol="", minWeightFractionPerNode=0.0,
-                         bootstrap=True)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1633,6 +1650,14 @@ class _GBTClassifierParams(_GBTParams, _HasVarianceImpurity):
                      "Supported options: " + ", ".join(supportedLossTypes),
                      typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_GBTClassifierParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+                         lossType="logistic", maxIter=20, stepSize=0.1, subsamplingRate=1.0,
+                         impurity="variance", featureSubsetStrategy="all", validationTol=0.01,
+                         leafCol="", minWeightFractionPerNode=0.0)
+
     @since("1.4.0")
     def getLossType(self):
         """
@@ -1724,6 +1749,8 @@ class GBTClassifier(JavaProbabilisticClassifier, _GBTClassifierParams,
     True
     >>> model.treeWeights == model2.treeWeights
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> model.trees
     [DecisionTreeRegressionModel...depth=..., DecisionTreeRegressionModel...]
     >>> validation = spark.createDataFrame([(0.0, Vectors.dense(-1.0),)],
@@ -1760,11 +1787,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(GBTClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.GBTClassifier", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
-                         lossType="logistic", maxIter=20, stepSize=0.1, subsamplingRate=1.0,
-                         impurity="variance", featureSubsetStrategy="all", validationTol=0.01,
-                         leafCol="", minWeightFractionPerNode=0.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1962,6 +1984,10 @@ class _NaiveBayesParams(_JavaPredictorParams, HasWeightCol):
                       "and gaussian.",
                       typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_NaiveBayesParams, self).__init__(*args)
+        self._setDefault(smoothing=1.0, modelType="multinomial")
+
     @since("1.5.0")
     def getSmoothing(self):
         """
@@ -2045,6 +2071,8 @@ class NaiveBayes(JavaProbabilisticClassifier, _NaiveBayesParams, HasThresholds,
     True
     >>> model.theta == model2.theta
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> nb = nb.setThresholds([0.01, 10.00])
     >>> model3 = nb.fit(df)
     >>> result = model3.transform(test0).head()
@@ -2080,7 +2108,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(NaiveBayes, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.NaiveBayes", self.uid)
-        self._setDefault(smoothing=1.0, modelType="multinomial")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -2172,8 +2199,8 @@ class _MultilayerPerceptronParams(_JavaProbabilisticClassifierParams, HasSeed, H
     initialWeights = Param(Params._dummy(), "initialWeights", "The initial weights of the model.",
                            typeConverter=TypeConverters.toVector)
 
-    def __init__(self):
-        super(_MultilayerPerceptronParams, self).__init__()
+    def __init__(self, *args):
+        super(_MultilayerPerceptronParams, self).__init__(*args)
         self._setDefault(maxIter=100, tol=1E-6, blockSize=128, stepSize=0.03, solver="l-bfgs")
 
     @since("1.6.0")
@@ -2255,6 +2282,8 @@ class MultilayerPerceptronClassifier(JavaProbabilisticClassifier, _MultilayerPer
     True
     >>> model.weights == model2.weights
     True
+    >>> model.transform(testDF).take(1) == model2.transform(testDF).take(1)
+    True
     >>> mlp2 = mlp2.setInitialWeights(list(range(0, 12)))
     >>> model3 = mlp2.fit(df)
     >>> model3.weights != model2.weights
@@ -2429,6 +2458,8 @@ class OneVsRest(Estimator, _OneVsRestParams, HasParallelism, JavaMLReadable, Jav
     >>> model2 = OneVsRestModel.load(model_path)
     >>> model2.transform(test0).head().newPrediction
     0.0
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> model.transform(test2).columns
     ['features', 'rawPrediction', 'newPrediction']
 
@@ -2854,6 +2885,17 @@ class FMClassifier(JavaProbabilisticClassifier, _FactorizationMachinesParams, Ja
     DenseVector([14.8232])
     >>> model.factors
     DenseMatrix(1, 2, [0.0163, -0.0051], 1)
+    >>> model_path = temp_path + "/fm_model"
+    >>> model.save(model_path)
+    >>> model2 = FMClassificationModel.load(model_path)
+    >>> model2.intercept
+    -7.316665276826291
+    >>> model2.linear
+    DenseVector([14.8232])
+    >>> model2.factors
+    DenseMatrix(1, 2, [0.0163, -0.0051], 1)
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 3.0.0
     """
diff --git a/python/pyspark/ml/clustering.py b/python/pyspark/ml/clustering.py
index e1c2732af31b9..2060bbc625a02 100644
--- a/python/pyspark/ml/clustering.py
+++ b/python/pyspark/ml/clustering.py
@@ -108,6 +108,10 @@ class _GaussianMixtureParams(HasMaxIter, HasFeaturesCol, HasSeed, HasPredictionC
     k = Param(Params._dummy(), "k", "Number of independent Gaussians in the mixture model. " +
               "Must be > 1.", typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_GaussianMixtureParams, self).__init__(*args)
+        self._setDefault(k=2, tol=0.01, maxIter=100, aggregationDepth=2)
+
     @since("2.0.0")
     def getK(self):
         """
@@ -321,6 +325,8 @@ class GaussianMixture(JavaEstimator, _GaussianMixtureParams, JavaMLWritable, Jav
     Row(mean=DenseVector([0.825, 0.8675]))
     >>> model2.gaussiansDF.select("cov").head()
     Row(cov=DenseMatrix(2, 2, [0.0056, -0.0051, -0.0051, 0.0046], False))
+    >>> model.transform(df).take(1) == model2.transform(df).take(1)
+    True
     >>> gm2.setWeightCol("weight")
     GaussianMixture...
 
@@ -339,7 +345,6 @@ def __init__(self, featuresCol="features", predictionCol="prediction", k=2,
         super(GaussianMixture, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.clustering.GaussianMixture",
                                             self.uid)
-        self._setDefault(k=2, tol=0.01, maxIter=100, aggregationDepth=2)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -493,6 +498,11 @@ class _KMeansParams(HasMaxIter, HasFeaturesCol, HasSeed, HasPredictionCol, HasTo
     initSteps = Param(Params._dummy(), "initSteps", "The number of steps for k-means|| " +
                       "initialization mode. Must be > 0.", typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_KMeansParams, self).__init__(*args)
+        self._setDefault(k=2, initMode="k-means||", initSteps=2, tol=1e-4, maxIter=20,
+                         distanceMeasure="euclidean")
+
     @since("1.5.0")
     def getK(self):
         """
@@ -622,6 +632,8 @@ class KMeans(JavaEstimator, _KMeansParams, JavaMLWritable, JavaMLReadable):
     array([ True,  True], dtype=bool)
     >>> model.clusterCenters()[1] == model2.clusterCenters()[1]
     array([ True,  True], dtype=bool)
+    >>> model.transform(df).take(1) == model2.transform(df).take(1)
+    True
 
     .. versionadded:: 1.5.0
     """
@@ -637,8 +649,6 @@ def __init__(self, featuresCol="features", predictionCol="prediction", k=2,
         """
         super(KMeans, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.clustering.KMeans", self.uid)
-        self._setDefault(k=2, initMode="k-means||", initSteps=2, tol=1e-4, maxIter=20,
-                         distanceMeasure="euclidean")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -747,6 +757,10 @@ class _BisectingKMeansParams(HasMaxIter, HasFeaturesCol, HasSeed, HasPredictionC
                                     "proportion of points (if < 1.0) of a divisible cluster.",
                                     typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_BisectingKMeansParams, self).__init__(*args)
+        self._setDefault(maxIter=20, k=4, minDivisibleClusterSize=1.0)
+
     @since("2.0.0")
     def getK(self):
         """
@@ -897,6 +911,8 @@ class BisectingKMeans(JavaEstimator, _BisectingKMeansParams, JavaMLWritable, Jav
     array([ True,  True], dtype=bool)
     >>> model.clusterCenters()[1] == model2.clusterCenters()[1]
     array([ True,  True], dtype=bool)
+    >>> model.transform(df).take(1) == model2.transform(df).take(1)
+    True
 
     .. versionadded:: 2.0.0
     """
@@ -913,7 +929,6 @@ def __init__(self, featuresCol="features", predictionCol="prediction", maxIter=2
         super(BisectingKMeans, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.clustering.BisectingKMeans",
                                             self.uid)
-        self._setDefault(maxIter=20, k=4, minDivisibleClusterSize=1.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1056,6 +1071,13 @@ class _LDAParams(HasMaxIter, HasFeaturesCol, HasSeed, HasCheckpointInterval):
                                " partition is lost, so set this bit with care.",
                                TypeConverters.toBoolean)
 
+    def __init__(self, *args):
+        super(_LDAParams, self).__init__(*args)
+        self._setDefault(maxIter=20, checkpointInterval=10,
+                         k=10, optimizer="online", learningOffset=1024.0, learningDecay=0.51,
+                         subsamplingRate=0.05, optimizeDocConcentration=True,
+                         topicDistributionCol="topicDistribution", keepLastCheckpoint=True)
+
     @since("2.0.0")
     def getK(self):
         """
@@ -1366,6 +1388,8 @@ class LDA(JavaEstimator, _LDAParams, JavaMLReadable, JavaMLWritable):
     >>> local_model_path = temp_path + "/lda_local_model"
     >>> localModel.save(local_model_path)
     >>> sameLocalModel = LocalLDAModel.load(local_model_path)
+    >>> model.transform(df).take(1) == sameLocalModel.transform(df).take(1)
+    True
 
     .. versionadded:: 2.0.0
     """
@@ -1385,10 +1409,6 @@ def __init__(self, featuresCol="features", maxIter=20, seed=None, checkpointInte
         """
         super(LDA, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.clustering.LDA", self.uid)
-        self._setDefault(maxIter=20, checkpointInterval=10,
-                         k=10, optimizer="online", learningOffset=1024.0, learningDecay=0.51,
-                         subsamplingRate=0.05, optimizeDocConcentration=True,
-                         topicDistributionCol="topicDistribution", keepLastCheckpoint=True)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1581,6 +1601,10 @@ class _PowerIterationClusteringParams(HasMaxIter, HasWeightCol):
                    "Name of the input column for destination vertex IDs.",
                    typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_PowerIterationClusteringParams, self).__init__(*args)
+        self._setDefault(k=2, maxIter=20, initMode="random", srcCol="src", dstCol="dst")
+
     @since("2.4.0")
     def getK(self):
         """
@@ -1654,6 +1678,8 @@ class PowerIterationClustering(_PowerIterationClusteringParams, JavaParams, Java
     2
     >>> pic2.getMaxIter()
     40
+    >>> pic2.assignClusters(df).take(6) == assignments.take(6)
+    True
 
     .. versionadded:: 2.4.0
     """
@@ -1668,7 +1694,6 @@ def __init__(self, k=2, maxIter=20, initMode="random", srcCol="src", dstCol="dst
         super(PowerIterationClustering, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.clustering.PowerIterationClustering", self.uid)
-        self._setDefault(k=2, maxIter=20, initMode="random", srcCol="src", dstCol="dst")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 6df2f74bcfc9d..4f42bb337fe48 100755
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -94,6 +94,8 @@ class Binarizer(JavaTransformer, HasThreshold, HasThresholds, HasInputCol, HasOu
     >>> loadedBinarizer = Binarizer.load(binarizerPath)
     >>> loadedBinarizer.getThreshold() == binarizer.getThreshold()
     True
+    >>> loadedBinarizer.transform(df).take(1) == binarizer.transform(df).take(1)
+    True
     >>> df2 = spark.createDataFrame([(0.5, 0.3)], ["values1", "values2"])
     >>> binarizer2 = Binarizer(thresholds=[0.0, 1.0])
     >>> binarizer2.setInputCols(["values1", "values2"]).setOutputCols(["output1", "output2"])
@@ -197,6 +199,10 @@ class _LSHParams(HasInputCol, HasOutputCol):
                           "and decreasing it improves the running performance.",
                           typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_LSHParams, self).__init__(*args)
+        self._setDefault(numHashTables=1)
+
     def getNumHashTables(self):
         """
         Gets the value of numHashTables or its default value.
@@ -392,7 +398,6 @@ def __init__(self, inputCol=None, outputCol=None, seed=None, numHashTables=1,
         super(BucketedRandomProjectionLSH, self).__init__()
         self._java_obj = \
             self._new_java_obj("org.apache.spark.ml.feature.BucketedRandomProjectionLSH", self.uid)
-        self._setDefault(numHashTables=1)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -479,6 +484,8 @@ class Bucketizer(JavaTransformer, HasInputCol, HasOutputCol, HasInputCols, HasOu
     >>> loadedBucketizer = Bucketizer.load(bucketizerPath)
     >>> loadedBucketizer.getSplits() == bucketizer.getSplits()
     True
+    >>> loadedBucketizer.transform(df).take(1) == bucketizer.transform(df).take(1)
+    True
     >>> bucketed = bucketizer.setHandleInvalid("skip").transform(df).collect()
     >>> len(bucketed)
     4
@@ -735,6 +742,8 @@ class CountVectorizer(JavaEstimator, _CountVectorizerParams, JavaMLReadable, Jav
     >>> loadedModel = CountVectorizerModel.load(modelPath)
     >>> loadedModel.vocabulary == model.vocabulary
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
     >>> fromVocabModel = CountVectorizerModel.from_vocabulary(["a", "b", "c"],
     ...     inputCol="raw", outputCol="vectors")
     >>> fromVocabModel.transform(df).show(truncate=False)
@@ -922,6 +931,8 @@ class DCT(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWrit
     >>> dctPath = temp_path + "/dct"
     >>> dct.save(dctPath)
     >>> loadedDtc = DCT.load(dctPath)
+    >>> loadedDtc.transform(df1).take(1) == dct.transform(df1).take(1)
+    True
     >>> loadedDtc.getInverse()
     False
 
@@ -1005,6 +1016,8 @@ class ElementwiseProduct(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReada
     >>> loadedEp = ElementwiseProduct.load(elementwiseProductPath)
     >>> loadedEp.getScalingVec() == ep.getScalingVec()
     True
+    >>> loadedEp.transform(df).take(1) == ep.transform(df).take(1)
+    True
 
     .. versionadded:: 1.5.0
     """
@@ -1203,6 +1216,8 @@ class HashingTF(JavaTransformer, HasInputCol, HasOutputCol, HasNumFeatures, Java
     >>> loadedHashingTF = HashingTF.load(hashingTFPath)
     >>> loadedHashingTF.getNumFeatures() == hashingTF.getNumFeatures()
     True
+    >>> loadedHashingTF.transform(df).take(1) == hashingTF.transform(df).take(1)
+    True
     >>> hashingTF.indexOf("b")
     5
 
@@ -1287,6 +1302,10 @@ class _IDFParams(HasInputCol, HasOutputCol):
                        "minimum number of documents in which a term should appear for filtering",
                        typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_IDFParams, self).__init__(*args)
+        self._setDefault(minDocFreq=0)
+
     @since("1.4.0")
     def getMinDocFreq(self):
         """
@@ -1347,7 +1366,6 @@ def __init__(self, minDocFreq=0, inputCol=None, outputCol=None):
         """
         super(IDF, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.IDF", self.uid)
-        self._setDefault(minDocFreq=0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1447,6 +1465,10 @@ class _ImputerParams(HasInputCol, HasInputCols, HasOutputCol, HasOutputCols, Has
                          "The placeholder for the missing values. All occurrences of missingValue "
                          "will be imputed.", typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_ImputerParams, self).__init__(*args)
+        self._setDefault(strategy="mean", missingValue=float("nan"), relativeError=0.001)
+
     @since("2.2.0")
     def getStrategy(self):
         """
@@ -1584,7 +1606,6 @@ def __init__(self, strategy="mean", missingValue=float("nan"), inputCols=None,
         """
         super(Imputer, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.Imputer", self.uid)
-        self._setDefault(strategy="mean", missingValue=float("nan"), relativeError=0.001)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1813,6 +1834,8 @@ class MaxAbsScaler(JavaEstimator, _MaxAbsScalerParams, JavaMLReadable, JavaMLWri
     >>> loadedModel = MaxAbsScalerModel.load(modelPath)
     >>> loadedModel.maxAbs == model.maxAbs
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 2.0.0
     """
@@ -1953,7 +1976,6 @@ def __init__(self, inputCol=None, outputCol=None, seed=None, numHashTables=1):
         """
         super(MinHashLSH, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.MinHashLSH", self.uid)
-        self._setDefault(numHashTables=1)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -2004,6 +2026,10 @@ class _MinMaxScalerParams(HasInputCol, HasOutputCol):
     max = Param(Params._dummy(), "max", "Upper bound of the output feature range",
                 typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_MinMaxScalerParams, self).__init__(*args)
+        self._setDefault(min=0.0, max=1.0)
+
     @since("1.6.0")
     def getMin(self):
         """
@@ -2067,6 +2093,8 @@ class MinMaxScaler(JavaEstimator, _MinMaxScalerParams, JavaMLReadable, JavaMLWri
     True
     >>> loadedModel.originalMax == model.originalMax
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 1.6.0
     """
@@ -2078,7 +2106,6 @@ def __init__(self, min=0.0, max=1.0, inputCol=None, outputCol=None):
         """
         super(MinMaxScaler, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.MinMaxScaler", self.uid)
-        self._setDefault(min=0.0, max=1.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -2212,6 +2239,8 @@ class NGram(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWr
     >>> loadedNGram = NGram.load(ngramPath)
     >>> loadedNGram.getN() == ngram.getN()
     True
+    >>> loadedNGram.transform(df).take(1) == ngram.transform(df).take(1)
+    True
 
     .. versionadded:: 1.5.0
     """
@@ -2292,6 +2321,8 @@ class Normalizer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable, Jav
     >>> loadedNormalizer = Normalizer.load(normalizerPath)
     >>> loadedNormalizer.getP() == normalizer.getP()
     True
+    >>> loadedNormalizer.transform(df).take(1) == normalizer.transform(df).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -2365,6 +2396,10 @@ class _OneHotEncoderParams(HasInputCol, HasInputCols, HasOutputCol, HasOutputCol
     dropLast = Param(Params._dummy(), "dropLast", "whether to drop the last category",
                      typeConverter=TypeConverters.toBoolean)
 
+    def __init__(self, *args):
+        super(_OneHotEncoderParams, self).__init__(*args)
+        self._setDefault(handleInvalid="error", dropLast=True)
+
     @since("2.3.0")
     def getDropLast(self):
         """
@@ -2425,6 +2460,8 @@ class OneHotEncoder(JavaEstimator, _OneHotEncoderParams, JavaMLReadable, JavaMLW
     >>> loadedModel = OneHotEncoderModel.load(modelPath)
     >>> loadedModel.categorySizes == model.categorySizes
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 2.3.0
     """
@@ -2439,7 +2476,6 @@ def __init__(self, inputCols=None, outputCols=None, handleInvalid="error", dropL
         super(OneHotEncoder, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.feature.OneHotEncoder", self.uid)
-        self._setDefault(handleInvalid="error", dropLast=True)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -2586,6 +2622,8 @@ class PolynomialExpansion(JavaTransformer, HasInputCol, HasOutputCol, JavaMLRead
     >>> loadedPx = PolynomialExpansion.load(polyExpansionPath)
     >>> loadedPx.getDegree() == px.getDegree()
     True
+    >>> loadedPx.transform(df).take(1) == px.transform(df).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -2882,6 +2920,11 @@ class _RobustScalerParams(HasInputCol, HasOutputCol, HasRelativeError):
     withScaling = Param(Params._dummy(), "withScaling", "Whether to scale the data to "
                         "quantile range", typeConverter=TypeConverters.toBoolean)
 
+    def __init__(self, *args):
+        super(_RobustScalerParams, self).__init__(*args)
+        self._setDefault(lower=0.25, upper=0.75, withCentering=False, withScaling=True,
+                         relativeError=0.001)
+
     @since("3.0.0")
     def getLower(self):
         """
@@ -2957,6 +3000,8 @@ class RobustScaler(JavaEstimator, _RobustScalerParams, JavaMLReadable, JavaMLWri
     True
     >>> loadedModel.range == model.range
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 3.0.0
     """
@@ -2970,8 +3015,6 @@ def __init__(self, lower=0.25, upper=0.75, withCentering=False, withScaling=True
         """
         super(RobustScaler, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.RobustScaler", self.uid)
-        self._setDefault(lower=0.25, upper=0.75, withCentering=False, withScaling=True,
-                         relativeError=0.001)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -3117,6 +3160,8 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable,
     True
     >>> loadedReTokenizer.getGaps() == reTokenizer.getGaps()
     True
+    >>> loadedReTokenizer.transform(df).take(1) == reTokenizer.transform(df).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -3241,6 +3286,8 @@ class SQLTransformer(JavaTransformer, JavaMLReadable, JavaMLWritable):
     >>> loadedSqlTrans = SQLTransformer.load(sqlTransformerPath)
     >>> loadedSqlTrans.getStatement() == sqlTrans.getStatement()
     True
+    >>> loadedSqlTrans.transform(df).take(1) == sqlTrans.transform(df).take(1)
+    True
 
     .. versionadded:: 1.6.0
     """
@@ -3295,6 +3342,10 @@ class _StandardScalerParams(HasInputCol, HasOutputCol):
     withStd = Param(Params._dummy(), "withStd", "Scale to unit standard deviation",
                     typeConverter=TypeConverters.toBoolean)
 
+    def __init__(self, *args):
+        super(_StandardScalerParams, self).__init__(*args)
+        self._setDefault(withMean=False, withStd=True)
+
     @since("1.4.0")
     def getWithMean(self):
         """
@@ -3352,6 +3403,8 @@ class StandardScaler(JavaEstimator, _StandardScalerParams, JavaMLReadable, JavaM
     True
     >>> loadedModel.mean == model.mean
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -3363,7 +3416,6 @@ def __init__(self, withMean=False, withStd=True, inputCol=None, outputCol=None):
         """
         super(StandardScaler, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.StandardScaler", self.uid)
-        self._setDefault(withMean=False, withStd=True)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -3512,6 +3564,8 @@ class StringIndexer(JavaEstimator, _StringIndexerParams, JavaMLReadable, JavaMLW
     >>> loadedModel = StringIndexerModel.load(modelPath)
     >>> loadedModel.labels == model.labels
     True
+    >>> loadedModel.transform(stringIndDf).take(1) == model.transform(stringIndDf).take(1)
+    True
     >>> indexToStringPath = temp_path + "/index-to-string"
     >>> inverter.save(indexToStringPath)
     >>> loadedInverter = IndexToString.load(indexToStringPath)
@@ -3802,6 +3856,8 @@ class StopWordsRemover(JavaTransformer, HasInputCol, HasOutputCol, HasInputCols,
     True
     >>> loadedRemover.getCaseSensitive() == remover.getCaseSensitive()
     True
+    >>> loadedRemover.transform(df).take(1) == remover.transform(df).take(1)
+    True
     >>> df2 = spark.createDataFrame([(["a", "b", "c"], ["a", "b"])], ["text1", "text2"])
     >>> remover2 = StopWordsRemover(stopWords=["b"])
     >>> remover2.setInputCols(["text1", "text2"]).setOutputCols(["words1", "words2"])
@@ -4114,6 +4170,10 @@ class _VectorIndexerParams(HasInputCol, HasOutputCol, HasHandleInvalid):
                           "of categories of the feature).",
                           typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_VectorIndexerParams, self).__init__(*args)
+        self._setDefault(maxCategories=20, handleInvalid="error")
+
     @since("1.4.0")
     def getMaxCategories(self):
         """
@@ -4194,6 +4254,8 @@ class VectorIndexer(JavaEstimator, _VectorIndexerParams, JavaMLReadable, JavaMLW
     True
     >>> loadedModel.categoryMaps == model.categoryMaps
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
     >>> dfWithInvalid = spark.createDataFrame([(Vectors.dense([3.0, 1.0]),)], ["a"])
     >>> indexer.getHandleInvalid()
     'error'
@@ -4214,7 +4276,6 @@ def __init__(self, maxCategories=20, inputCol=None, outputCol=None, handleInvali
         """
         super(VectorIndexer, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.VectorIndexer", self.uid)
-        self._setDefault(maxCategories=20, handleInvalid="error")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -4337,6 +4398,8 @@ class VectorSlicer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable, J
     True
     >>> loadedVs.getNames() == vs.getNames()
     True
+    >>> loadedVs.transform(df).take(1) == vs.transform(df).take(1)
+    True
 
     .. versionadded:: 1.6.0
     """
@@ -4436,6 +4499,11 @@ class _Word2VecParams(HasStepSize, HasMaxIter, HasSeed, HasInputCol, HasOutputCo
                               "be divided into chunks up to the size.",
                               typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_Word2VecParams, self).__init__(*args)
+        self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
+                         windowSize=5, maxSentenceLength=1000)
+
     @since("1.4.0")
     def getVectorSize(self):
         """
@@ -4530,6 +4598,8 @@ class Word2Vec(JavaEstimator, _Word2VecParams, JavaMLReadable, JavaMLWritable):
     True
     >>> loadedModel.getVectors().first().vector == model.getVectors().first().vector
     True
+    >>> loadedModel.transform(doc).take(1) == model.transform(doc).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -4543,8 +4613,6 @@ def __init__(self, vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025,
         """
         super(Word2Vec, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.Word2Vec", self.uid)
-        self._setDefault(vectorSize=100, minCount=5, numPartitions=1, stepSize=0.025, maxIter=1,
-                         windowSize=5, maxSentenceLength=1000)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -4736,6 +4804,8 @@ class PCA(JavaEstimator, _PCAParams, JavaMLReadable, JavaMLWritable):
     True
     >>> loadedModel.explainedVariance == model.explainedVariance
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 1.5.0
     """
@@ -4852,6 +4922,11 @@ class _RFormulaParams(HasFeaturesCol, HasLabelCol, HasHandleInvalid):
                           "additional bucket, at index numLabels).",
                           typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_RFormulaParams, self).__init__(*args)
+        self._setDefault(forceIndexLabel=False, stringIndexerOrderType="frequencyDesc",
+                         handleInvalid="error")
+
     @since("1.5.0")
     def getFormula(self):
         """
@@ -4954,8 +5029,6 @@ def __init__(self, formula=None, featuresCol="features", labelCol="label",
         """
         super(RFormula, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.RFormula", self.uid)
-        self._setDefault(forceIndexLabel=False, stringIndexerOrderType="frequencyDesc",
-                         handleInvalid="error")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -5064,6 +5137,11 @@ class _ChiSqSelectorParams(HasFeaturesCol, HasOutputCol, HasLabelCol):
     fwe = Param(Params._dummy(), "fwe", "The upper bound of the expected family-wise error rate.",
                 typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_ChiSqSelectorParams, self).__init__(*args)
+        self._setDefault(numTopFeatures=50, selectorType="numTopFeatures", percentile=0.1,
+                         fpr=0.05, fdr=0.05, fwe=0.05)
+
     @since("2.1.0")
     def getSelectorType(self):
         """
@@ -5160,6 +5238,8 @@ class ChiSqSelector(JavaEstimator, _ChiSqSelectorParams, JavaMLReadable, JavaMLW
     >>> loadedModel = ChiSqSelectorModel.load(modelPath)
     >>> loadedModel.selectedFeatures == model.selectedFeatures
     True
+    >>> loadedModel.transform(df).take(1) == model.transform(df).take(1)
+    True
 
     .. versionadded:: 2.0.0
     """
@@ -5175,8 +5255,6 @@ def __init__(self, numTopFeatures=50, featuresCol="features", outputCol=None,
         """
         super(ChiSqSelector, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.ChiSqSelector", self.uid)
-        self._setDefault(numTopFeatures=50, selectorType="numTopFeatures", percentile=0.1,
-                         fpr=0.05, fdr=0.05, fwe=0.05)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
diff --git a/python/pyspark/ml/fpm.py b/python/pyspark/ml/fpm.py
index 7d933daf9e032..0e302d53d97e7 100644
--- a/python/pyspark/ml/fpm.py
+++ b/python/pyspark/ml/fpm.py
@@ -56,6 +56,11 @@ class _FPGrowthParams(HasPredictionCol):
         "but will affect the association rules generation.",
         typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_FPGrowthParams, self).__init__(*args)
+        self._setDefault(minSupport=0.3, minConfidence=0.8,
+                         itemsCol="items", predictionCol="prediction")
+
     def getItemsCol(self):
         """
         Gets the value of itemsCol or its default value.
@@ -194,6 +199,11 @@ class FPGrowth(JavaEstimator, _FPGrowthParams, JavaMLWritable, JavaMLReadable):
     >>> new_data = spark.createDataFrame([(["t", "s"], )], ["items"])
     >>> sorted(fpm.transform(new_data).first().newPrediction)
     [u'x', u'y', u'z']
+    >>> model_path = temp_path + "/fpm_model"
+    >>> fpm.save(model_path)
+    >>> model2 = FPGrowthModel.load(model_path)
+    >>> fpm.transform(data).take(1) == model2.transform(data).take(1)
+    True
 
     .. versionadded:: 2.2.0
     """
@@ -206,8 +216,6 @@ def __init__(self, minSupport=0.3, minConfidence=0.8, itemsCol="items",
         """
         super(FPGrowth, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.fpm.FPGrowth", self.uid)
-        self._setDefault(minSupport=0.3, minConfidence=0.8,
-                         itemsCol="items", predictionCol="prediction")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
diff --git a/python/pyspark/ml/recommendation.py b/python/pyspark/ml/recommendation.py
index 99d80aa867bda..62b856046234a 100644
--- a/python/pyspark/ml/recommendation.py
+++ b/python/pyspark/ml/recommendation.py
@@ -46,6 +46,10 @@ class _ALSModelParams(HasPredictionCol, HasBlockSize):
                               "Supported values: 'nan', 'drop'.",
                               typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_ALSModelParams, self).__init__(*args)
+        self._setDefault(blockSize=4096)
+
     @since("1.4.0")
     def getUserCol(self):
         """
@@ -99,6 +103,14 @@ class _ALSParams(_ALSModelParams, HasMaxIter, HasRegParam, HasCheckpointInterval
                               "StorageLevel for ALS model factors.",
                               typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_ALSParams, self).__init__(*args)
+        self._setDefault(rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
+                         implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item",
+                         ratingCol="rating", nonnegative=False, checkpointInterval=10,
+                         intermediateStorageLevel="MEMORY_AND_DISK",
+                         finalStorageLevel="MEMORY_AND_DISK", coldStartStrategy="nan")
+
     @since("1.4.0")
     def getRank(self):
         """
@@ -275,6 +287,8 @@ class ALS(JavaEstimator, _ALSParams, JavaMLWritable, JavaMLReadable):
     True
     >>> sorted(model.itemFactors.collect()) == sorted(model2.itemFactors.collect())
     True
+    >>> model.transform(test).take(1) == model2.transform(test).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -294,12 +308,6 @@ def __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemB
         """
         super(ALS, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.recommendation.ALS", self.uid)
-        self._setDefault(rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
-                         implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item",
-                         ratingCol="rating", nonnegative=False, checkpointInterval=10,
-                         intermediateStorageLevel="MEMORY_AND_DISK",
-                         finalStorageLevel="MEMORY_AND_DISK", coldStartStrategy="nan",
-                         blockSize=4096)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index 9c3c1e6ca01ae..550efb27c1e97 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -79,6 +79,10 @@ class _LinearRegressionParams(_JavaPredictorParams, HasRegParam, HasElasticNetPa
                     "robustness. Must be > 1.0. Only valid when loss is huber",
                     typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_LinearRegressionParams, self).__init__(*args)
+        self._setDefault(maxIter=100, regParam=0.0, tol=1e-6, loss="squaredError", epsilon=1.35)
+
     @since("2.3.0")
     def getEpsilon(self):
         """
@@ -158,6 +162,8 @@ class LinearRegression(JavaRegressor, _LinearRegressionParams, JavaMLWritable, J
     True
     >>> model.intercept == model2.intercept
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> model.numFeatures
     1
     >>> model.write().format("pmml").save(model_path + "_2")
@@ -179,7 +185,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(LinearRegression, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.LinearRegression", self.uid)
-        self._setDefault(maxIter=100, regParam=0.0, tol=1e-6, loss="squaredError", epsilon=1.35)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -584,6 +589,10 @@ class _IsotonicRegressionParams(HasFeaturesCol, HasLabelCol, HasPredictionCol, H
         "The index of the feature if featuresCol is a vector column, no effect otherwise.",
         typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_IsotonicRegressionParams, self).__init__(*args)
+        self._setDefault(isotonic=True, featureIndex=0)
+
     def getIsotonic(self):
         """
         Gets the value of isotonic or its default value.
@@ -633,6 +642,8 @@ class IsotonicRegression(JavaEstimator, _IsotonicRegressionParams, HasWeightCol,
     True
     >>> model.predictions == model2.predictions
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 1.6.0
     """
@@ -646,7 +657,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(IsotonicRegression, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.IsotonicRegression", self.uid)
-        self._setDefault(isotonic=True, featureIndex=0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -773,7 +783,11 @@ class _DecisionTreeRegressorParams(_DecisionTreeParams, _TreeRegressorParams, Ha
     .. versionadded:: 3.0.0
     """
 
-    pass
+    def __init__(self, *args):
+        super(_DecisionTreeRegressorParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+                         impurity="variance", leafCol="", minWeightFractionPerNode=0.0)
 
 
 @inherit_doc
@@ -829,6 +843,8 @@ class DecisionTreeRegressor(JavaRegressor, _DecisionTreeRegressorParams, JavaMLW
     True
     >>> model.depth == model2.depth
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> model.transform(test1).head().variance
     0.0
 
@@ -860,9 +876,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(DecisionTreeRegressor, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.DecisionTreeRegressor", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
-                         impurity="variance", leafCol="", minWeightFractionPerNode=0.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1017,7 +1030,14 @@ class _RandomForestRegressorParams(_RandomForestParams, _TreeRegressorParams):
 
     .. versionadded:: 3.0.0
     """
-    pass
+
+    def __init__(self, *args):
+        super(_RandomForestRegressorParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
+                         impurity="variance", subsamplingRate=1.0, numTrees=20,
+                         featureSubsetStrategy="auto", leafCol="", minWeightFractionPerNode=0.0,
+                         bootstrap=True)
 
 
 @inherit_doc
@@ -1078,6 +1098,8 @@ class RandomForestRegressor(JavaRegressor, _RandomForestRegressorParams, JavaMLW
     >>> model2 = RandomForestRegressionModel.load(model_path)
     >>> model.featureImportances == model2.featureImportances
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 1.4.0
     """
@@ -1100,11 +1122,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(RandomForestRegressor, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.RandomForestRegressor", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
-                         impurity="variance", subsamplingRate=1.0, numTrees=20,
-                         featureSubsetStrategy="auto", leafCol="", minWeightFractionPerNode=0.0,
-                         bootstrap=True)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1275,6 +1292,14 @@ class _GBTRegressorParams(_GBTParams, _TreeRegressorParams):
                      "Supported options: " + ", ".join(supportedLossTypes),
                      typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_GBTRegressorParams, self).__init__(*args)
+        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
+                         maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0,
+                         checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1,
+                         impurity="variance", featureSubsetStrategy="all", validationTol=0.01,
+                         leafCol="", minWeightFractionPerNode=0.0)
+
     @since("1.4.0")
     def getLossType(self):
         """
@@ -1338,6 +1363,8 @@ class GBTRegressor(JavaRegressor, _GBTRegressorParams, JavaMLWritable, JavaMLRea
     True
     >>> model.treeWeights == model2.treeWeights
     True
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
     >>> model.trees
     [DecisionTreeRegressionModel...depth=..., DecisionTreeRegressionModel...]
     >>> validation = spark.createDataFrame([(0.0, Vectors.dense(-1.0))],
@@ -1372,11 +1399,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         """
         super(GBTRegressor, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.regression.GBTRegressor", self.uid)
-        self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
-                         maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0,
-                         checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1,
-                         impurity="variance", featureSubsetStrategy="all", validationTol=0.01,
-                         leafCol="", minWeightFractionPerNode=0.0)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1595,6 +1617,12 @@ class _AFTSurvivalRegressionParams(_JavaPredictorParams, HasMaxIter, HasTol, Has
         "corresponding quantileProbabilities if it is set.",
         typeConverter=TypeConverters.toString)
 
+    def __init__(self, *args):
+        super(_AFTSurvivalRegressionParams, self).__init__(*args)
+        self._setDefault(censorCol="censor",
+                         quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99],
+                         maxIter=100, tol=1E-6)
+
     @since("1.6.0")
     def getCensorCol(self):
         """
@@ -1667,6 +1695,8 @@ class AFTSurvivalRegression(JavaRegressor, _AFTSurvivalRegressionParams,
     True
     >>> model.scale == model2.scale
     True
+    >>> model.transform(df).take(1) == model2.transform(df).take(1)
+    True
 
     .. versionadded:: 1.6.0
     """
@@ -1685,9 +1715,6 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
         super(AFTSurvivalRegression, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.regression.AFTSurvivalRegression", self.uid)
-        self._setDefault(censorCol="censor",
-                         quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99],
-                         maxIter=100, tol=1E-6)
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1847,8 +1874,8 @@ class _GeneralizedLinearRegressionParams(_JavaPredictorParams, HasFitIntercept,
                       "or empty, we treat all instance offsets as 0.0",
                       typeConverter=TypeConverters.toString)
 
-    def __init__(self):
-        super(_GeneralizedLinearRegressionParams, self).__init__()
+    def __init__(self, *args):
+        super(_GeneralizedLinearRegressionParams, self).__init__(*args)
         self._setDefault(family="gaussian", maxIter=25, tol=1e-6, regParam=0.0, solver="irls",
                          variancePower=0.0, aggregationDepth=2)
 
@@ -1966,6 +1993,8 @@ class GeneralizedLinearRegression(JavaRegressor, _GeneralizedLinearRegressionPar
     True
     >>> model.coefficients[0] == model2.coefficients[0]
     True
+    >>> model.transform(df).take(1) == model2.transform(df).take(1)
+    True
 
     .. versionadded:: 2.0.0
     """
@@ -2357,8 +2386,8 @@ class _FactorizationMachinesParams(_JavaPredictorParams, HasMaxIter, HasStepSize
     solver = Param(Params._dummy(), "solver", "The solver algorithm for optimization. Supported " +
                    "options: gd, adamW. (Default adamW)", typeConverter=TypeConverters.toString)
 
-    def __init__(self):
-        super(_FactorizationMachinesParams, self).__init__()
+    def __init__(self, *args):
+        super(_FactorizationMachinesParams, self).__init__(*args)
         self._setDefault(factorSize=8, fitIntercept=True, fitLinear=True, regParam=0.0,
                          miniBatchFraction=1.0, initStd=0.01, maxIter=100, stepSize=1.0,
                          tol=1e-6, solver="adamW")
@@ -2436,6 +2465,17 @@ class FMRegressor(JavaRegressor, _FactorizationMachinesParams, JavaMLWritable, J
     DenseVector([0.9978])
     >>> model.factors
     DenseMatrix(1, 2, [0.0173, 0.0021], 1)
+    >>> model_path = temp_path + "/fm_model"
+    >>> model.save(model_path)
+    >>> model2 = FMRegressionModel.load(model_path)
+    >>> model2.intercept
+    -0.0032501766849261557
+    >>> model2.linear
+    DenseVector([0.9978])
+    >>> model2.factors
+    DenseMatrix(1, 2, [0.0173, 0.0021], 1)
+    >>> model.transform(test0).take(1) == model2.transform(test0).take(1)
+    True
 
     .. versionadded:: 3.0.0
     """
diff --git a/python/pyspark/ml/tests/test_param.py b/python/pyspark/ml/tests/test_param.py
index 777b4930ce8c9..2b119ea866236 100644
--- a/python/pyspark/ml/tests/test_param.py
+++ b/python/pyspark/ml/tests/test_param.py
@@ -366,15 +366,14 @@ def test_java_params(self):
                 if not name.endswith('Model') and not name.endswith('Params') \
                         and issubclass(cls, JavaParams) and not inspect.isabstract(cls) \
                         and not name.startswith('Java') and name != '_LSH':
-                    # NOTE: disable check_params_exist until there is parity with Scala API
-                    check_params(self, cls(), check_params_exist=False)
+                    check_params(self, cls(), check_params_exist=True)
 
         # Additional classes that need explicit construction
         from pyspark.ml.feature import CountVectorizerModel, StringIndexerModel
         check_params(self, CountVectorizerModel.from_vocabulary(['a'], 'input'),
-                     check_params_exist=False)
+                     check_params_exist=True)
         check_params(self, StringIndexerModel.from_labels(['a', 'b'], 'input'),
-                     check_params_exist=False)
+                     check_params_exist=True)
 
 
 if __name__ == "__main__":
diff --git a/python/pyspark/ml/tuning.py b/python/pyspark/ml/tuning.py
index cb4542c5d025f..e564ff7a10448 100644
--- a/python/pyspark/ml/tuning.py
+++ b/python/pyspark/ml/tuning.py
@@ -200,6 +200,10 @@ class _CrossValidatorParams(_ValidatorParams):
     numFolds = Param(Params._dummy(), "numFolds", "number of folds for cross validation",
                      typeConverter=TypeConverters.toInt)
 
+    def __init__(self, *args):
+        super(_CrossValidatorParams, self).__init__(*args)
+        self._setDefault(numFolds=3)
+
     @since("1.4.0")
     def getNumFolds(self):
         """
@@ -249,6 +253,8 @@ class CrossValidator(Estimator, _CrossValidatorParams, HasParallelism, HasCollec
     [0.5, ...
     >>> evaluator.evaluate(cvModel.transform(dataset))
     0.8333...
+    >>> evaluator.evaluate(cvModelRead.transform(dataset))
+    0.8333...
 
     .. versionadded:: 1.4.0
     """
@@ -261,7 +267,7 @@ def __init__(self, estimator=None, estimatorParamMaps=None, evaluator=None, numF
                  seed=None, parallelism=1, collectSubModels=False)
         """
         super(CrossValidator, self).__init__()
-        self._setDefault(numFolds=3, parallelism=1)
+        self._setDefault(parallelism=1)
         kwargs = self._input_kwargs
         self._set(**kwargs)
 
@@ -545,6 +551,10 @@ class _TrainValidationSplitParams(_ValidatorParams):
     trainRatio = Param(Params._dummy(), "trainRatio", "Param for ratio between train and\
      validation data. Must be between 0 and 1.", typeConverter=TypeConverters.toFloat)
 
+    def __init__(self, *args):
+        super(_TrainValidationSplitParams, self).__init__(*args)
+        self._setDefault(trainRatio=0.75)
+
     @since("2.0.0")
     def getTrainRatio(self):
         """
@@ -590,6 +600,8 @@ class TrainValidationSplit(Estimator, _TrainValidationSplitParams, HasParallelis
     [0.5, ...
     >>> evaluator.evaluate(tvsModel.transform(dataset))
     0.833...
+    >>> evaluator.evaluate(tvsModelRead.transform(dataset))
+    0.833...
 
     .. versionadded:: 2.0.0
     """
@@ -602,7 +614,7 @@ def __init__(self, estimator=None, estimatorParamMaps=None, evaluator=None, trai
                  parallelism=1, collectSubModels=False, seed=None)
         """
         super(TrainValidationSplit, self).__init__()
-        self._setDefault(trainRatio=0.75, parallelism=1)
+        self._setDefault(parallelism=1)
         kwargs = self._input_kwargs
         self._set(**kwargs)