add doc groups to spark.ml components

Author: mengxr

mllib/src/main/scala/org/apache/spark/ml/Transformer.scala

@@ -62,7 +62,10 @@ abstract class Transformer extends PipelineStage with Params {
 private[ml] abstract class UnaryTransformer[IN, OUT, T <: UnaryTransformer[IN, OUT, T]]
   extends Transformer with HasInputCol with HasOutputCol with Logging {
 
+  /** @group setParam */
   def setInputCol(value: String): T = set(inputCol, value).asInstanceOf[T]
+
+  /** @group setParam */
   def setOutputCol(value: String): T = set(outputCol, value).asInstanceOf[T]
 
   /**

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

@@ -66,6 +66,7 @@ private[spark] abstract class Classifier[
   extends Predictor[FeaturesType, E, M]
   with ClassifierParams {
 
+  /** @group setParam */
   def setRawPredictionCol(value: String): E =
     set(rawPredictionCol, value).asInstanceOf[E]
 
@@ -87,6 +88,7 @@ private[spark]
 abstract class ClassificationModel[FeaturesType, M <: ClassificationModel[FeaturesType, M]]
   extends PredictionModel[FeaturesType, M] with ClassifierParams {
 
+  /** @group setParam */
   def setRawPredictionCol(value: String): M = set(rawPredictionCol, value).asInstanceOf[M]
 
   /** Number of classes (values which the label can take). */

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

@@ -49,8 +49,13 @@ class LogisticRegression
   setMaxIter(100)
   setThreshold(0.5)
 
+  /** @group setParam */
   def setRegParam(value: Double): this.type = set(regParam, value)
+
+  /** @group setParam */
   def setMaxIter(value: Int): this.type = set(maxIter, value)
+
+  /** @group setParam */
   def setThreshold(value: Double): this.type = set(threshold, value)
 
   override protected def train(dataset: DataFrame, paramMap: ParamMap): LogisticRegressionModel = {
@@ -93,6 +98,7 @@ class LogisticRegressionModel private[ml] (
 
   setThreshold(0.5)
 
+  /** @group setParam */
   def setThreshold(value: Double): this.type = set(threshold, value)
 
   private val margin: Vector => Double = (features) => {

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

@@ -61,6 +61,7 @@ private[spark] abstract class ProbabilisticClassifier[
     M <: ProbabilisticClassificationModel[FeaturesType, M]]
   extends Classifier[FeaturesType, E, M] with ProbabilisticClassifierParams {
 
+  /** @group setParam */
   def setProbabilityCol(value: String): E = set(probabilityCol, value).asInstanceOf[E]
 }
 
@@ -82,6 +83,7 @@ private[spark] abstract class ProbabilisticClassificationModel[
     M <: ProbabilisticClassificationModel[FeaturesType, M]]
   extends ClassificationModel[FeaturesType, M] with ProbabilisticClassifierParams {
 
+  /** @group setParam */
   def setProbabilityCol(value: String): M = set(probabilityCol, value).asInstanceOf[M]
 
   /**

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

@@ -35,13 +35,23 @@ import org.apache.spark.sql.types.DoubleType
 class BinaryClassificationEvaluator extends Evaluator with Params
   with HasRawPredictionCol with HasLabelCol {
 
-  /** param for metric name in evaluation */
+  /**
+   * param for metric name in evaluation
+   * @group param
+   */
   val metricName: Param[String] = new Param(this, "metricName",
     "metric name in evaluation (areaUnderROC|areaUnderPR)", Some("areaUnderROC"))
+
+  /** @group getParam */
   def getMetricName: String = get(metricName)
+
+  /** @group setParam */
   def setMetricName(value: String): this.type = set(metricName, value)
 
+  /** @group setParam */
   def setScoreCol(value: String): this.type = set(rawPredictionCol, value)
+
+  /** @group setParam */
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
   override def evaluate(dataset: DataFrame, paramMap: ParamMap): Double = {

mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala

@@ -31,11 +31,18 @@ import org.apache.spark.sql.types.DataType
 @AlphaComponent
 class HashingTF extends UnaryTransformer[Iterable[_], Vector, HashingTF] {
 
-  /** number of features */
+  /**
+   * number of features
+   * @group param
+   */
   val numFeatures = new IntParam(this, "numFeatures", "number of features", Some(1 << 18))
-  def setNumFeatures(value: Int) = set(numFeatures, value)
+
+  /** @group getParam */
   def getNumFeatures: Int = get(numFeatures)
 
+  /** @group setParam */
+  def setNumFeatures(value: Int) = set(numFeatures, value)
+
   override protected def createTransformFunc(paramMap: ParamMap): Iterable[_] => Vector = {
     val hashingTF = new feature.HashingTF(paramMap(numFeatures))
     hashingTF.transform

mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala

@@ -39,7 +39,10 @@ private[feature] trait StandardScalerParams extends Params with HasInputCol with
 @AlphaComponent
 class StandardScaler extends Estimator[StandardScalerModel] with StandardScalerParams {
 
+  /** @group setParam */
   def setInputCol(value: String): this.type = set(inputCol, value)
+
+  /** @group setParam */
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   override def fit(dataset: DataFrame, paramMap: ParamMap): StandardScalerModel = {
@@ -75,7 +78,10 @@ class StandardScalerModel private[ml] (
     scaler: feature.StandardScalerModel)
   extends Model[StandardScalerModel] with StandardScalerParams {
 
+  /** @group setParam */
   def setInputCol(value: String): this.type = set(inputCol, value)
+
+  /** @group setParam */
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   override def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame = {

mllib/src/main/scala/org/apache/spark/ml/impl/estimator/Predictor.scala

@@ -85,8 +85,13 @@ private[spark] abstract class Predictor[
     M <: PredictionModel[FeaturesType, M]]
   extends Estimator[M] with PredictorParams {
 
+  /** @group setParam */
   def setLabelCol(value: String): Learner = set(labelCol, value).asInstanceOf[Learner]
+
+  /** @group setParam */
   def setFeaturesCol(value: String): Learner = set(featuresCol, value).asInstanceOf[Learner]
+
+  /** @group setParam */
   def setPredictionCol(value: String): Learner = set(predictionCol, value).asInstanceOf[Learner]
 
   override def fit(dataset: DataFrame, paramMap: ParamMap): M = {
@@ -160,8 +165,10 @@ private[spark] abstract class Predictor[
 private[spark] abstract class PredictionModel[FeaturesType, M <: PredictionModel[FeaturesType, M]]
   extends Model[M] with PredictorParams {
 
+  /** @group setParam */
   def setFeaturesCol(value: String): M = set(featuresCol, value).asInstanceOf[M]
 
+  /** @group setParam */
   def setPredictionCol(value: String): M = set(predictionCol, value).asInstanceOf[M]
 
   /**

mllib/src/main/scala/org/apache/spark/ml/package.scala

@@ -20,5 +20,19 @@ package org.apache.spark
 /**
  * Spark ML is an ALPHA component that adds a new set of machine learning APIs to let users quickly
  * assemble and configure practical machine learning pipelines.
+ *
+ * @groupname param Parameters
+ * @groupdesc param A list of (hyper-)parameter keys this algorithm can take. Users can set and get
+ *            the parameter values through setters and getters, respectively.
+ * @groupprio param -5
+ *
+ * @groupname setParam Parameter setters
+ * @groupprio setParam 5
+ *
+ * @groupname getParam Parameter getters
+ * @groupprio getParam 6
+ *
+ * @groupname Ungrouped Members
+ * @groupprio Ungrouped 0
  */
 package object ml

mllib/src/main/scala/org/apache/spark/ml/param/sharedParams.scala

@@ -24,67 +24,117 @@ package org.apache.spark.ml.param
  */
 
 private[ml] trait HasRegParam extends Params {
-  /** param for regularization parameter */
+  /**
+   * param for regularization parameter
+   * @group param
+   */
   val regParam: DoubleParam = new DoubleParam(this, "regParam", "regularization parameter")
+
+  /** @group getParam */
   def getRegParam: Double = get(regParam)
 }
 
 private[ml] trait HasMaxIter extends Params {
-  /** param for max number of iterations */
+  /**
+   * param for max number of iterations
+   * @group param
+   */
   val maxIter: IntParam = new IntParam(this, "maxIter", "max number of iterations")
+
+  /** @group getParam */
   def getMaxIter: Int = get(maxIter)
 }
 
 private[ml] trait HasFeaturesCol extends Params {
-  /** param for features column name */
+  /**
+   * param for features column name
+   * @group param
+   */
   val featuresCol: Param[String] =
     new Param(this, "featuresCol", "features column name", Some("features"))
+
+  /** @group getParam */
   def getFeaturesCol: String = get(featuresCol)
 }
 
 private[ml] trait HasLabelCol extends Params {
-  /** param for label column name */
+  /**
+   * param for label column name
+   * @group param
+   */
   val labelCol: Param[String] = new Param(this, "labelCol", "label column name", Some("label"))
+
+  /** @group getParam */
   def getLabelCol: String = get(labelCol)
 }
 
 private[ml] trait HasPredictionCol extends Params {
-  /** param for prediction column name */
+  /**
+   * param for prediction column name
+   * @group param
+   */
   val predictionCol: Param[String] =
     new Param(this, "predictionCol", "prediction column name", Some("prediction"))
+
+  /** @group getParam */
   def getPredictionCol: String = get(predictionCol)
 }
 
 private[ml] trait HasRawPredictionCol extends Params {
-  /** param for raw prediction column name */
+  /**
+   * param for raw prediction column name
+   * @group param
+   */
   val rawPredictionCol: Param[String] =
     new Param(this, "rawPredictionCol", "raw prediction (a.k.a. confidence) column name",
       Some("rawPrediction"))
+
+  /** @group getParam */
   def getRawPredictionCol: String = get(rawPredictionCol)
 }
 
 private[ml] trait HasProbabilityCol extends Params {
-  /** param for predicted class conditional probabilities column name */
+  /**
+   * param for predicted class conditional probabilities column name
+   * @group param
+   */
   val probabilityCol: Param[String] =
     new Param(this, "probabilityCol", "column name for predicted class conditional probabilities",
       Some("probability"))
+
+  /** @group getParam */
   def getProbabilityCol: String = get(probabilityCol)
 }
 
 private[ml] trait HasThreshold extends Params {
-  /** param for threshold in (binary) prediction */
+  /**
+   * param for threshold in (binary) prediction
+   * @group param
+   */
   val threshold: DoubleParam = new DoubleParam(this, "threshold", "threshold in prediction")
+
+  /** @group getParam */
   def getThreshold: Double = get(threshold)
 }
 
 private[ml] trait HasInputCol extends Params {
-  /** param for input column name */
+  /**
+   * param for input column name
+   * @group param
+   */
   val inputCol: Param[String] = new Param(this, "inputCol", "input column name")
+
+  /** @group getParam */
   def getInputCol: String = get(inputCol)
 }
 
 private[ml] trait HasOutputCol extends Params {
-  /** param for output column name */
+  /**
+   * param for output column name
+   * @group param
+   */
   val outputCol: Param[String] = new Param(this, "outputCol", "output column name")
+
+  /** @group getParam */
   def getOutputCol: String = get(outputCol)
 }