[SPARK-3359] [DOCS] More changes to resolve javadoc 8 errors that will help unidoc/genjavadoc compatibility

graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala

@@ -119,7 +119,7 @@ object GraphGenerators extends Logging {
    * A random graph generator using the R-MAT model, proposed in
    * "R-MAT: A Recursive Model for Graph Mining" by Chakrabarti et al.
    *
-   * See [[http://www.cs.cmu.edu/~christos/PUBLICATIONS/siam04.pdf]].
+   * See http://www.cs.cmu.edu/~christos/PUBLICATIONS/siam04.pdf.
    */
   def rmatGraph(sc: SparkContext, requestedNumVertices: Int, numEdges: Int): Graph[Int, Int] = {
     // let N = requestedNumVertices

mllib-local/src/main/scala/org/apache/spark/ml/linalg/Vectors.scala

@@ -66,7 +66,7 @@ sealed trait Vector extends Serializable {
 
   /**
    * Returns a hash code value for the vector. The hash code is based on its size and its first 128
-   * nonzero entries, using a hash algorithm similar to [[java.util.Arrays.hashCode]].
+   * nonzero entries, using a hash algorithm similar to `java.util.Arrays.hashCode`.
    */
   override def hashCode(): Int = {
     // This is a reference implementation. It calls return in foreachActive, which is slow.

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

@@ -212,7 +212,7 @@ object Pipeline extends MLReadable[Pipeline] {
     }
   }
 
-  /** Methods for [[MLReader]] and [[MLWriter]] shared between [[Pipeline]] and [[PipelineModel]] */
+  /** Methods for `MLReader` and `MLWriter` shared between [[Pipeline]] and [[PipelineModel]] */
   private[ml] object SharedReadWrite {
 
     import org.json4s.JsonDSL._

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

@@ -165,7 +165,7 @@ abstract class PredictionModel[FeaturesType, M <: PredictionModel[FeaturesType,
   }
 
   /**
-   * Transforms dataset by reading from [[featuresCol]], calling [[predict()]], and storing
+   * Transforms dataset by reading from [[featuresCol]], calling `predict`, and storing
    * the predictions as a new column [[predictionCol]].
    *
    * @param dataset input dataset

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

@@ -50,7 +50,7 @@ private[spark] trait ClassifierParams
  * Single-label binary or multiclass classification.
  * Classes are indexed {0, 1, ..., numClasses - 1}.
  *
- * @tparam FeaturesType  Type of input features.  E.g., [[Vector]]
+ * @tparam FeaturesType  Type of input features.  E.g., `Vector`
  * @tparam E  Concrete Estimator type
  * @tparam M  Concrete Model type
  */
@@ -134,7 +134,7 @@ abstract class Classifier[
  * Model produced by a [[Classifier]].
  * Classes are indexed {0, 1, ..., numClasses - 1}.
  *
- * @tparam FeaturesType  Type of input features.  E.g., [[Vector]]
+ * @tparam FeaturesType  Type of input features.  E.g., `Vector`
  * @tparam M  Concrete Model type
  */
 @DeveloperApi
@@ -151,7 +151,7 @@ abstract class ClassificationModel[FeaturesType, M <: ClassificationModel[Featur
    * Transforms dataset by reading from [[featuresCol]], and appending new columns as specified by
    * parameters:
    *  - predicted labels as [[predictionCol]] of type [[Double]]
-   *  - raw predictions (confidences) as [[rawPredictionCol]] of type [[Vector]].
+   *  - raw predictions (confidences) as [[rawPredictionCol]] of type `Vector`.
    *
    * @param dataset input dataset
    * @return transformed dataset

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

@@ -36,7 +36,7 @@ import org.apache.spark.sql.Dataset
 
 
 /**
- * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] learning algorithm
+ * Decision tree learning algorithm (http://en.wikipedia.org/wiki/Decision_tree_learning)
  * for classification.
  * It supports both binary and multiclass labels, as well as both continuous and categorical
  * features.
@@ -135,7 +135,7 @@ object DecisionTreeClassifier extends DefaultParamsReadable[DecisionTreeClassifi
 }
 
 /**
- * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] model for classification.
+ * Decision tree model (http://en.wikipedia.org/wiki/Decision_tree_learning) for classification.
  * It supports both binary and multiclass labels, as well as both continuous and categorical
  * features.
  */

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

@@ -40,7 +40,7 @@ import org.apache.spark.sql.functions._
 import org.apache.spark.sql.types.DoubleType
 
 /**
- * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]]
+ * Gradient-Boosted Trees (GBTs) (http://en.wikipedia.org/wiki/Gradient_boosting)
  * learning algorithm for classification.
  * It supports binary labels, as well as both continuous and categorical features.
  * Note: Multiclass labels are not currently supported.
@@ -158,7 +158,7 @@ object GBTClassifier extends DefaultParamsReadable[GBTClassifier] {
 }
 
 /**
- * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]]
+ * Gradient-Boosted Trees (GBTs) (http://en.wikipedia.org/wiki/Gradient_boosting)
  * model for classification.
  * It supports binary labels, as well as both continuous and categorical features.
  * Note: Multiclass labels are not currently supported.
@@ -233,8 +233,8 @@ class GBTClassificationModel private[ml](
    * The importance vector is normalized to sum to 1. This method is suggested by Hastie et al.
    * (Hastie, Tibshirani, Friedman. "The Elements of Statistical Learning, 2nd Edition." 2001.)
    * and follows the implementation from scikit-learn.
-   *
-   * @see [[DecisionTreeClassificationModel.featureImportances]]
+
+   * See `DecisionTreeClassificationModel.featureImportances`
    */
   @Since("2.0.0")
   lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(trees, numFeatures)

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

@@ -858,18 +858,18 @@ class BinaryLogisticRegressionSummary private[classification] (
    * Returns the receiver operating characteristic (ROC) curve,
    * which is a Dataframe having two fields (FPR, TPR)
    * with (0.0, 0.0) prepended and (1.0, 1.0) appended to it.
+   * See http://en.wikipedia.org/wiki/Receiver_operating_characteristic
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
-   * @see http://en.wikipedia.org/wiki/Receiver_operating_characteristic
    */
   @Since("1.5.0")
   @transient lazy val roc: DataFrame = binaryMetrics.roc().toDF("FPR", "TPR")
 
   /**
    * Computes the area under the receiver operating characteristic (ROC) curve.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
    */
   @Since("1.5.0")
@@ -879,7 +879,7 @@ class BinaryLogisticRegressionSummary private[classification] (
    * Returns the precision-recall curve, which is a Dataframe containing
    * two fields recall, precision with (0.0, 1.0) prepended to it.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
    */
   @Since("1.5.0")
@@ -888,7 +888,7 @@ class BinaryLogisticRegressionSummary private[classification] (
   /**
    * Returns a dataframe with two fields (threshold, F-Measure) curve with beta = 1.0.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
    */
   @Since("1.5.0")
@@ -901,7 +901,7 @@ class BinaryLogisticRegressionSummary private[classification] (
    * Every possible probability obtained in transforming the dataset are used
    * as thresholds used in calculating the precision.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
    */
   @Since("1.5.0")
@@ -914,7 +914,7 @@ class BinaryLogisticRegressionSummary private[classification] (
    * Every possible probability obtained in transforming the dataset are used
    * as thresholds used in calculating the recall.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]].
+   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
    *       This will change in later Spark versions.
    */
   @Since("1.5.0")

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

@@ -45,7 +45,7 @@ private[classification] trait ProbabilisticClassifierParams
  *
  * Single-label binary or multiclass classifier which can output class conditional probabilities.
  *
- * @tparam FeaturesType  Type of input features.  E.g., [[Vector]]
+ * @tparam FeaturesType  Type of input features.  E.g., `Vector`
  * @tparam E  Concrete Estimator type
  * @tparam M  Concrete Model type
  */
@@ -70,7 +70,7 @@ abstract class ProbabilisticClassifier[
  * Model produced by a [[ProbabilisticClassifier]].
  * Classes are indexed {0, 1, ..., numClasses - 1}.
  *
- * @tparam FeaturesType  Type of input features.  E.g., [[Vector]]
+ * @tparam FeaturesType  Type of input features.  E.g., `Vector`
  * @tparam M  Concrete Model type
  */
 @DeveloperApi
@@ -89,8 +89,8 @@ abstract class ProbabilisticClassificationModel[
    * Transforms dataset by reading from [[featuresCol]], and appending new columns as specified by
    * parameters:
    *  - predicted labels as [[predictionCol]] of type [[Double]]
-   *  - raw predictions (confidences) as [[rawPredictionCol]] of type [[Vector]]
-   *  - probability of each class as [[probabilityCol]] of type [[Vector]].
+   *  - raw predictions (confidences) as [[rawPredictionCol]] of type `Vector`
+   *  - probability of each class as [[probabilityCol]] of type `Vector`.
    *
    * @param dataset input dataset
    * @return transformed dataset
@@ -210,7 +210,7 @@ private[ml] object ProbabilisticClassificationModel {
   /**
    * Normalize a vector of raw predictions to be a multinomial probability vector, in place.
    *
-   * The input raw predictions should be >= 0.
+   * The input raw predictions should be nonnegative.
    * The output vector sums to 1, unless the input vector is all-0 (in which case the output is
    * all-0 too).
    *

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

@@ -53,7 +53,7 @@ abstract class Evaluator extends Params {
   def evaluate(dataset: Dataset[_]): Double
 
   /**
-   * Indicates whether the metric returned by [[evaluate()]] should be maximized (true, default)
+   * Indicates whether the metric returned by `evaluate` should be maximized (true, default)
    * or minimized (false).
    * A given evaluator may support multiple metrics which may be maximized or minimized.
    */

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

@@ -42,8 +42,8 @@ private[feature] trait ChiSqSelectorParams extends Params
 
   /**
    * Number of features that selector will select (ordered by statistic value descending). If the
-   * number of features is < numTopFeatures, then this will select all features. The default value
-   * of numTopFeatures is 50.
+   * number of features is less than numTopFeatures, then this will select all features.
+   * The default value of numTopFeatures is 50.
    * @group param
    */
   final val numTopFeatures = new IntParam(this, "numTopFeatures",

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

@@ -552,7 +552,7 @@ trait Params extends Identifiable with Serializable {
    *
    * This only needs to check for interactions between parameters.
    * Parameter value checks which do not depend on other parameters are handled by
-   * [[Param.validate()]].  This method does not handle input/output column parameters;
+   * `Param.validate()`. This method does not handle input/output column parameters;
    * those are checked during schema validation.
    * @deprecated Will be removed in 2.1.0. All the checks should be merged into transformSchema
    */
@@ -580,8 +580,7 @@ trait Params extends Identifiable with Serializable {
   }
 
   /**
-   * Explains all params of this instance.
-   * @see [[explainParam()]]
+   * Explains all params of this instance. See `explainParam()`.
    */
   def explainParams(): String = {
     params.map(explainParam).mkString("\n")
@@ -678,7 +677,7 @@ trait Params extends Identifiable with Serializable {
   /**
    * Sets default values for a list of params.
    *
-   * Note: Java developers should use the single-parameter [[setDefault()]].
+   * Note: Java developers should use the single-parameter `setDefault`.
    *       Annotating this with varargs can cause compilation failures due to a Scala compiler bug.
    *       See SPARK-9268.
    *
@@ -712,8 +711,7 @@ trait Params extends Identifiable with Serializable {
   /**
    * Creates a copy of this instance with the same UID and some extra params.
    * Subclasses should implement this method and set the return type properly.
-   *
-   * @see [[defaultCopy()]]
+   * See `defaultCopy()`.
    */
   def copy(extra: ParamMap): Params
 
@@ -730,7 +728,8 @@ trait Params extends Identifiable with Serializable {
   /**
    * Extracts the embedded default param values and user-supplied values, and then merges them with
    * extra values from input into a flat param map, where the latter value is used if there exist
-   * conflicts, i.e., with ordering: default param values < user-supplied values < extra.
+   * conflicts, i.e., with ordering:
+   * default param values less than user-supplied values less than extra.
    */
   final def extractParamMap(extra: ParamMap): ParamMap = {
     defaultParamMap ++ paramMap ++ extra

mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala

@@ -99,7 +99,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
   with HasPredictionCol with HasCheckpointInterval with HasSeed {
 
   /**
-   * Param for rank of the matrix factorization (>= 1).
+   * Param for rank of the matrix factorization (positive).
    * Default: 10
    * @group param
    */
@@ -109,7 +109,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
   def getRank: Int = $(rank)
 
   /**
-   * Param for number of user blocks (>= 1).
+   * Param for number of user blocks (positive).
    * Default: 10
    * @group param
    */
@@ -120,7 +120,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
   def getNumUserBlocks: Int = $(numUserBlocks)
 
   /**
-   * Param for number of item blocks (>= 1).
+   * Param for number of item blocks (positive).
    * Default: 10
    * @group param
    */
@@ -141,7 +141,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
   def getImplicitPrefs: Boolean = $(implicitPrefs)
 
   /**
-   * Param for the alpha parameter in the implicit preference formulation (>= 0).
+   * Param for the alpha parameter in the implicit preference formulation (nonnegative).
    * Default: 1.0
    * @group param
    */
@@ -174,7 +174,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
 
   /**
    * Param for StorageLevel for intermediate datasets. Pass in a string representation of
-   * [[StorageLevel]]. Cannot be "NONE".
+   * `StorageLevel`. Cannot be "NONE".
    * Default: "MEMORY_AND_DISK".
    *
    * @group expertParam
@@ -188,7 +188,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w
 
   /**
    * Param for StorageLevel for ALS model factors. Pass in a string representation of
-   * [[StorageLevel]].
+   * `StorageLevel`.
    * Default: "MEMORY_AND_DISK".
    *
    * @group expertParam
@@ -351,11 +351,11 @@ object ALSModel extends MLReadable[ALSModel] {
  *
  * For implicit preference data, the algorithm used is based on
  * "Collaborative Filtering for Implicit Feedback Datasets", available at
- * [[http://dx.doi.org/10.1109/ICDM.2008.22]], adapted for the blocked approach used here.
+ * http://dx.doi.org/10.1109/ICDM.2008.22, adapted for the blocked approach used here.
  *
  * Essentially instead of finding the low-rank approximations to the rating matrix `R`,
  * this finds the approximations for a preference matrix `P` where the elements of `P` are 1 if
- * r > 0 and 0 if r <= 0. The ratings then act as 'confidence' values related to strength of
+ * r &gt; 0 and 0 if r &lt;= 0. The ratings then act as 'confidence' values related to strength of
  * indicated user
  * preferences rather than explicit ratings given to items.
  */

mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala

@@ -145,8 +145,8 @@ class LeafNode private[ml] (
  * Internal Decision Tree node.
  * @param prediction  Prediction this node would make if it were a leaf node
  * @param impurity  Impurity measure at this node (for training data)
- * @param gain Information gain value.
- *             Values < 0 indicate missing values; this quirk will be removed with future updates.
+ * @param gain Information gain value. Values less than 0 indicate missing values;
+ *             this quirk will be removed with future updates.
  * @param leftChild  Left-hand child node
  * @param rightChild  Right-hand child node
  * @param split  Information about the test used to split to the left or right child.

mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala

@@ -151,8 +151,8 @@ class CategoricalSplit private[ml] (
 /**
  * Split which tests a continuous feature.
  * @param featureIndex  Index of the feature to test
- * @param threshold  If the feature value is <= this threshold, then the split goes left.
- *                    Otherwise, it goes right.
+ * @param threshold  If the feature value is less than or equal to this threshold, then the
+ *                   split goes left. Otherwise, it goes right.
  */
 class ContinuousSplit private[ml] (override val featureIndex: Int, val threshold: Double)
   extends Split {

mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala

@@ -415,12 +415,12 @@ private[ml] object EnsembleModelReadWrite {
   /**
    * Helper method for loading a tree ensemble from disk.
    * This reconstructs all trees, returning the root nodes.
-   * @param path  Path given to [[saveImpl()]]
+   * @param path  Path given to `saveImpl`
    * @param className  Class name for ensemble model type
    * @param treeClassName  Class name for tree model type in the ensemble
    * @return  (ensemble metadata, array over trees of (tree metadata, root node)),
    *          where the root node is linked with all descendents
-   * @see [[saveImpl()]] for how the model was saved
+   * @see `saveImpl` for how the model was saved
    */
   def loadImpl(
       path: String,

mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala

@@ -173,8 +173,8 @@ object ChiSqSelectorModel extends Loader[ChiSqSelectorModel] {
  * Creates a ChiSquared feature selector.
  * @param numTopFeatures number of features that selector will select
  *                       (ordered by statistic value descending)
- *                       Note that if the number of features is < numTopFeatures, then this will
- *                       select all features.
+ *                       Note that if the number of features is less than numTopFeatures,
+ *                       then this will select all features.
  */
 @Since("1.3.0")
 class ChiSqSelector @Since("1.3.0") (