From d5b1d5fc80153571c308130833d0c0774de62c92 Mon Sep 17 00:00:00 2001
From: hyukjinkwon <gurwls223@gmail.com>
Date: Sat, 19 Nov 2016 11:24:15 +0000
Subject: [SPARK-18445][BUILD][DOCS] Fix the markdown for `Note:`/`NOTE:`/`Note
 that`/`'''Note:'''` across Scala/Java API documentation

## What changes were proposed in this pull request?

It seems in Scala/Java,

- `Note:`
- `NOTE:`
- `Note that`
- `'''Note:'''`
- `note`

This PR proposes to fix those to `note` to be consistent.

**Before**

- Scala
  ![2016-11-17 6 16 39](https://cloud.githubusercontent.com/assets/6477701/20383180/1a7aed8c-acf2-11e6-9611-5eaf6d52c2e0.png)

- Java
  ![2016-11-17 6 14 41](https://cloud.githubusercontent.com/assets/6477701/20383096/c8ffc680-acf1-11e6-914a-33460bf1401d.png)

**After**

- Scala
  ![2016-11-17 6 16 44](https://cloud.githubusercontent.com/assets/6477701/20383167/09940490-acf2-11e6-937a-0d5e1dc2cadf.png)

- Java
  ![2016-11-17 6 13 39](https://cloud.githubusercontent.com/assets/6477701/20383132/e7c2a57e-acf1-11e6-9c47-b849674d4d88.png)

## How was this patch tested?

The notes were found via

```bash
grep -r "NOTE: " . | \ # Note:|NOTE:|Note that|'''Note:'''
grep -v "// NOTE: " | \  # starting with // does not appear in API documentation.
grep -E '.scala|.java' | \ # java/scala files
grep -v Suite | \ # exclude tests
grep -v Test | \ # exclude tests
grep -e 'org.apache.spark.api.java' \ # packages appear in API documenation
-e 'org.apache.spark.api.java.function' \ # note that this is a regular expression. So actual matches were mostly `org/apache/spark/api/java/functions ...`
-e 'org.apache.spark.api.r' \
...
```

```bash
grep -r "Note that " . | \ # Note:|NOTE:|Note that|'''Note:'''
grep -v "// Note that " | \  # starting with // does not appear in API documentation.
grep -E '.scala|.java' | \ # java/scala files
grep -v Suite | \ # exclude tests
grep -v Test | \ # exclude tests
grep -e 'org.apache.spark.api.java' \ # packages appear in API documenation
-e 'org.apache.spark.api.java.function' \
-e 'org.apache.spark.api.r' \
...
```

```bash
grep -r "Note: " . | \ # Note:|NOTE:|Note that|'''Note:'''
grep -v "// Note: " | \  # starting with // does not appear in API documentation.
grep -E '.scala|.java' | \ # java/scala files
grep -v Suite | \ # exclude tests
grep -v Test | \ # exclude tests
grep -e 'org.apache.spark.api.java' \ # packages appear in API documenation
-e 'org.apache.spark.api.java.function' \
-e 'org.apache.spark.api.r' \
...
```

```bash
grep -r "'''Note:'''" . | \ # Note:|NOTE:|Note that|'''Note:'''
grep -v "// '''Note:''' " | \  # starting with // does not appear in API documentation.
grep -E '.scala|.java' | \ # java/scala files
grep -v Suite | \ # exclude tests
grep -v Test | \ # exclude tests
grep -e 'org.apache.spark.api.java' \ # packages appear in API documenation
-e 'org.apache.spark.api.java.function' \
-e 'org.apache.spark.api.r' \
...
```

And then fixed one by one comparing with API documentation/access modifiers.

After that, manually tested via `jekyll build`.

Author: hyukjinkwon <gurwls223@gmail.com>

Closes #15889 from HyukjinKwon/SPARK-18437.
---
 .../src/main/scala/org/apache/spark/ml/Model.scala |  2 +-
 .../ml/classification/DecisionTreeClassifier.scala |  6 ++--
 .../spark/ml/classification/GBTClassifier.scala    |  6 ++--
 .../ml/classification/LogisticRegression.scala     | 36 +++++++++++-----------
 .../spark/ml/clustering/GaussianMixture.scala      |  6 ++--
 .../org/apache/spark/ml/feature/MinMaxScaler.scala |  3 +-
 .../apache/spark/ml/feature/OneHotEncoder.scala    |  3 +-
 .../scala/org/apache/spark/ml/feature/PCA.scala    |  5 +--
 .../apache/spark/ml/feature/StopWordsRemover.scala |  5 ++-
 .../apache/spark/ml/feature/StringIndexer.scala    |  6 ++--
 .../scala/org/apache/spark/ml/param/params.scala   |  2 +-
 .../ml/regression/DecisionTreeRegressor.scala      |  6 ++--
 .../regression/GeneralizedLinearRegression.scala   |  4 +--
 .../spark/ml/regression/LinearRegression.scala     | 28 +++++++++--------
 .../spark/ml/source/libsvm/LibSVMDataSource.scala  |  2 +-
 .../spark/ml/tree/impl/GradientBoostedTrees.scala  |  4 +--
 .../scala/org/apache/spark/ml/util/ReadWrite.scala |  2 +-
 .../mllib/classification/LogisticRegression.scala  | 28 ++++++++++-------
 .../apache/spark/mllib/classification/SVM.scala    | 20 +++++++-----
 .../spark/mllib/clustering/GaussianMixture.scala   |  8 ++---
 .../org/apache/spark/mllib/clustering/KMeans.scala |  8 +++--
 .../org/apache/spark/mllib/clustering/LDA.scala    |  4 +--
 .../apache/spark/mllib/clustering/LDAModel.scala   |  2 +-
 .../spark/mllib/clustering/LDAOptimizer.scala      |  6 ++--
 .../spark/mllib/evaluation/AreaUnderCurve.scala    |  2 +-
 .../org/apache/spark/mllib/linalg/Vectors.scala    |  6 ++--
 .../mllib/linalg/distributed/BlockMatrix.scala     |  2 +-
 .../linalg/distributed/IndexedRowMatrix.scala      |  5 +--
 .../spark/mllib/linalg/distributed/RowMatrix.scala | 21 +++++++------
 .../apache/spark/mllib/optimization/Gradient.scala |  3 +-
 .../org/apache/spark/mllib/rdd/RDDFunctions.scala  |  2 +-
 .../recommendation/MatrixFactorizationModel.scala  |  6 ++--
 .../org/apache/spark/mllib/stat/Statistics.scala   | 34 ++++++++++----------
 .../org/apache/spark/mllib/tree/DecisionTree.scala | 32 +++++++++----------
 .../org/apache/spark/mllib/tree/loss/Loss.scala    | 12 +++++---
 .../mllib/tree/model/treeEnsembleModels.scala      |  4 +--
 36 files changed, 185 insertions(+), 146 deletions(-)

(limited to 'mllib/src')

diff --git a/mllib/src/main/scala/org/apache/spark/ml/Model.scala b/mllib/src/main/scala/org/apache/spark/ml/Model.scala
index 252acc1565..c581fed177 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/Model.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/Model.scala
@@ -30,7 +30,7 @@ import org.apache.spark.ml.param.ParamMap
 abstract class Model[M <: Model[M]] extends Transformer {
   /**
    * The parent estimator that produced this model.
-   * Note: For ensembles' component Models, this value can be null.
+   * @note For ensembles' component Models, this value can be null.
    */
   @transient var parent: Estimator[M] = _
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
index bb192ab5f2..7424031ed4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
@@ -207,9 +207,9 @@ class DecisionTreeClassificationModel private[ml] (
    *     where gain is scaled by the number of instances passing through node
    *   - Normalize importances for tree to sum to 1.
    *
-   * Note: Feature importance for single decision trees can have high variance due to
-   *       correlated predictor variables. Consider using a [[RandomForestClassifier]]
-   *       to determine feature importance instead.
+   * @note Feature importance for single decision trees can have high variance due to
+   * correlated predictor variables. Consider using a [[RandomForestClassifier]]
+   * to determine feature importance instead.
    */
   @Since("2.0.0")
   lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(this, numFeatures)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
index f8f164e8c1..52f93f5a6b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
@@ -43,7 +43,6 @@ import org.apache.spark.sql.types.DoubleType
  * 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.
  *
  * The implementation is based upon: J.H. Friedman. "Stochastic Gradient Boosting." 1999.
  *
@@ -54,6 +53,8 @@ import org.apache.spark.sql.types.DoubleType
  *    based on the loss function, whereas the original gradient boosting method does not.
  *  - We expect to implement TreeBoost in the future:
  *    [https://issues.apache.org/jira/browse/SPARK-4240]
+ *
+ * @note Multiclass labels are not currently supported.
  */
 @Since("1.4.0")
 class GBTClassifier @Since("1.4.0") (
@@ -169,10 +170,11 @@ object GBTClassifier extends DefaultParamsReadable[GBTClassifier] {
  * 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.
  *
  * @param _trees  Decision trees in the ensemble.
  * @param _treeWeights  Weights for the decision trees in the ensemble.
+ *
+ * @note Multiclass labels are not currently supported.
  */
 @Since("1.6.0")
 class GBTClassificationModel private[ml](
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 18b9b3043d..71a7fe53c1 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
@@ -1191,8 +1191,8 @@ class BinaryLogisticRegressionSummary private[classification] (
    * 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`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   @transient lazy val roc: DataFrame = binaryMetrics.roc().toDF("FPR", "TPR")
@@ -1200,8 +1200,8 @@ class BinaryLogisticRegressionSummary private[classification] (
   /**
    * Computes the area under the receiver operating characteristic (ROC) curve.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   lazy val areaUnderROC: Double = binaryMetrics.areaUnderROC()
@@ -1210,8 +1210,8 @@ 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`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   @transient lazy val pr: DataFrame = binaryMetrics.pr().toDF("recall", "precision")
@@ -1219,8 +1219,8 @@ 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`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   @transient lazy val fMeasureByThreshold: DataFrame = {
@@ -1232,8 +1232,8 @@ 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`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   @transient lazy val precisionByThreshold: DataFrame = {
@@ -1245,8 +1245,8 @@ 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`.
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`.
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   @transient lazy val recallByThreshold: DataFrame = {
@@ -1401,18 +1401,18 @@ class BinaryLogisticRegressionSummary private[classification] (
  *    $$
  * </blockquote></p>
  *
- * @note In order to avoid unnecessary computation during calculation of the gradient updates
- *       we lay out the coefficients in column major order during training. This allows us to
- *       perform feature standardization once, while still retaining sequential memory access
- *       for speed. We convert back to row major order when we create the model,
- *       since this form is optimal for the matrix operations used for prediction.
- *
  * @param bcCoefficients The broadcast coefficients corresponding to the features.
  * @param bcFeaturesStd The broadcast standard deviation values of the features.
  * @param numClasses the number of possible outcomes for k classes classification problem in
  *                   Multinomial Logistic Regression.
  * @param fitIntercept Whether to fit an intercept term.
  * @param multinomial Whether to use multinomial (softmax) or binary loss
+ *
+ * @note In order to avoid unnecessary computation during calculation of the gradient updates
+ * we lay out the coefficients in column major order during training. This allows us to
+ * perform feature standardization once, while still retaining sequential memory access
+ * for speed. We convert back to row major order when we create the model,
+ * since this form is optimal for the matrix operations used for prediction.
  */
 private class LogisticAggregator(
     bcCoefficients: Broadcast[Vector],
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 a0bd66e731..c6035cc4c9 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
@@ -268,9 +268,9 @@ object GaussianMixtureModel extends MLReadable[GaussianMixtureModel] {
  * While this process is generally guaranteed to converge, it is not guaranteed
  * to find a global optimum.
  *
- * Note: For high-dimensional data (with many features), this algorithm may perform poorly.
- *       This is due to high-dimensional data (a) making it difficult to cluster at all (based
- *       on statistical/theoretical arguments) and (b) numerical issues with Gaussian distributions.
+ * @note For high-dimensional data (with many features), this algorithm may perform poorly.
+ * This is due to high-dimensional data (a) making it difficult to cluster at all (based
+ * on statistical/theoretical arguments) and (b) numerical issues with Gaussian distributions.
  */
 @Since("2.0.0")
 @Experimental
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 28cbe1cb01..ccfb0ce8f8 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
@@ -85,7 +85,8 @@ private[feature] trait MinMaxScalerParams extends Params with HasInputCol with H
  * </blockquote></p>
  *
  * For the case $E_{max} == E_{min}$, $Rescaled(e_i) = 0.5 * (max + min)$.
- * Note that since zero values will probably be transformed to non-zero values, output of the
+ *
+ * @note Since zero values will probably be transformed to non-zero values, output of the
  * transformer will be DenseVector even for sparse input.
  */
 @Since("1.5.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
index e8e28ba29c..ea401216ae 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
@@ -36,7 +36,8 @@ import org.apache.spark.sql.types.{DoubleType, NumericType, StructType}
  * The last category is not included by default (configurable via [[OneHotEncoder!.dropLast]]
  * because it makes the vector entries sum up to one, and hence linearly dependent.
  * So an input value of 4.0 maps to `[0.0, 0.0, 0.0, 0.0]`.
- * Note that this is different from scikit-learn's OneHotEncoder, which keeps all categories.
+ *
+ * @note This is different from scikit-learn's OneHotEncoder, which keeps all categories.
  * The output vectors are sparse.
  *
  * @see [[StringIndexer]] for converting categorical values into category indices
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
index 1e49352b85..6e08bf0591 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
@@ -142,8 +142,9 @@ class PCAModel private[ml] (
 
   /**
    * Transform a vector by computed Principal Components.
-   * NOTE: Vectors to be transformed must be the same length
-   * as the source vectors given to [[PCA.fit()]].
+   *
+   * @note Vectors to be transformed must be the same length as the source vectors given
+   * to [[PCA.fit()]].
    */
   @Since("2.0.0")
   override def transform(dataset: Dataset[_]): DataFrame = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
index 666070037c..0ced21365f 100755
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -28,7 +28,10 @@ import org.apache.spark.sql.types.{ArrayType, StringType, StructType}
 
 /**
  * A feature transformer that filters out stop words from input.
- * Note: null values from input array are preserved unless adding null to stopWords explicitly.
+ *
+ * @note null values from input array are preserved unless adding null to stopWords
+ * explicitly.
+ *
  * @see [[http://en.wikipedia.org/wiki/Stop_words]]
  */
 @Since("1.5.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
index 80fe46796f..8b155f0001 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
@@ -113,11 +113,11 @@ object StringIndexer extends DefaultParamsReadable[StringIndexer] {
 /**
  * Model fitted by [[StringIndexer]].
  *
- * NOTE: During transformation, if the input column does not exist,
+ * @param labels  Ordered list of labels, corresponding to indices to be assigned.
+ *
+ * @note During transformation, if the input column does not exist,
  * [[StringIndexerModel.transform]] would return the input dataset unmodified.
  * This is a temporary fix for the case when target labels do not exist during prediction.
- *
- * @param labels  Ordered list of labels, corresponding to indices to be assigned.
  */
 @Since("1.4.0")
 class StringIndexerModel (
diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala
index 9245931b27..96206e0b7a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala
@@ -533,7 +533,7 @@ trait Params extends Identifiable with Serializable {
    * Returns all params sorted by their names. The default implementation uses Java reflection to
    * list all public methods that have no arguments and return [[Param]].
    *
-   * Note: Developer should not use this method in constructor because we cannot guarantee that
+   * @note Developer should not use this method in constructor because we cannot guarantee that
    * this variable gets initialized before other params.
    */
   lazy val params: Array[Param[_]] = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
index ebc6c12ddc..1419da8747 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
@@ -207,9 +207,9 @@ class DecisionTreeRegressionModel private[ml] (
    *     where gain is scaled by the number of instances passing through node
    *   - Normalize importances for tree to sum to 1.
    *
-   * Note: Feature importance for single decision trees can have high variance due to
-   *       correlated predictor variables. Consider using a [[RandomForestRegressor]]
-   *       to determine feature importance instead.
+   * @note Feature importance for single decision trees can have high variance due to
+   * correlated predictor variables. Consider using a [[RandomForestRegressor]]
+   * to determine feature importance instead.
    */
   @Since("2.0.0")
   lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(this, numFeatures)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
index 1d2961e027..736fd3b9e0 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
@@ -879,8 +879,8 @@ class GeneralizedLinearRegressionSummary private[regression] (
    * Private copy of model to ensure Params are not modified outside this class.
    * Coefficients is not a deep copy, but that is acceptable.
    *
-   * NOTE: [[predictionCol]] must be set correctly before the value of [[model]] is set,
-   *       and [[model]] must be set before [[predictions]] is set!
+   * @note [[predictionCol]] must be set correctly before the value of [[model]] is set,
+   * and [[model]] must be set before [[predictions]] is set!
    */
   protected val model: GeneralizedLinearRegressionModel =
     origModel.copy(ParamMap.empty).setPredictionCol(predictionCol)
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 71c542adf6..da7ce6b46f 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
@@ -103,11 +103,13 @@ class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String
   /**
    * Whether to standardize the training features before fitting the model.
    * The coefficients of models will be always returned on the original scale,
-   * so it will be transparent for users. Note that with/without standardization,
-   * the models should be always converged to the same solution when no regularization
-   * is applied. In R's GLMNET package, the default behavior is true as well.
+   * so it will be transparent for users.
    * Default is true.
    *
+   * @note With/without standardization, the models should be always converged
+   * to the same solution when no regularization is applied. In R's GLMNET package,
+   * the default behavior is true as well.
+   *
    * @group setParam
    */
   @Since("1.5.0")
@@ -624,8 +626,8 @@ class LinearRegressionSummary private[regression] (
    * explainedVariance = 1 - variance(y - \hat{y}) / variance(y)
    * Reference: [[http://en.wikipedia.org/wiki/Explained_variation]]
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   val explainedVariance: Double = metrics.explainedVariance
@@ -634,8 +636,8 @@ class LinearRegressionSummary private[regression] (
    * Returns the mean absolute error, which is a risk function corresponding to the
    * expected value of the absolute error loss or l1-norm loss.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   val meanAbsoluteError: Double = metrics.meanAbsoluteError
@@ -644,8 +646,8 @@ class LinearRegressionSummary private[regression] (
    * Returns the mean squared error, which is a risk function corresponding to the
    * expected value of the squared error loss or quadratic loss.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   val meanSquaredError: Double = metrics.meanSquaredError
@@ -654,8 +656,8 @@ class LinearRegressionSummary private[regression] (
    * Returns the root mean squared error, which is defined as the square root of
    * the mean squared error.
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   val rootMeanSquaredError: Double = metrics.rootMeanSquaredError
@@ -664,8 +666,8 @@ class LinearRegressionSummary private[regression] (
    * Returns R^2^, the coefficient of determination.
    * Reference: [[http://en.wikipedia.org/wiki/Coefficient_of_determination]]
    *
-   * Note: This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
-   *       This will change in later Spark versions.
+   * @note This ignores instance weights (setting all to 1.0) from [[LinearRegression.weightCol]].
+   * This will change in later Spark versions.
    */
   @Since("1.5.0")
   val r2: Double = metrics.r2
diff --git a/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala
index 73d813064d..e137692703 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala
@@ -48,7 +48,7 @@ import org.apache.spark.sql.{DataFrame, DataFrameReader}
  *    inconsistent feature dimensions.
  *  - "vectorType": feature vector type, "sparse" (default) or "dense".
  *
- * Note that this class is public for documentation purpose. Please don't use this class directly.
+ * @note This class is public for documentation purpose. Please don't use this class directly.
  * Rather, use the data source API as illustrated above.
  *
  * @see [[https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/ LIBSVM datasets]]
diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala
index ede0a060ee..0a0bc4c006 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala
@@ -98,7 +98,7 @@ private[spark] object GradientBoostedTrees extends Logging {
    * @param initTreeWeight: learning rate assigned to the first tree.
    * @param initTree: first DecisionTreeModel.
    * @param loss: evaluation metric.
-   * @return a RDD with each element being a zip of the prediction and error
+   * @return an RDD with each element being a zip of the prediction and error
    *         corresponding to every sample.
    */
   def computeInitialPredictionAndError(
@@ -121,7 +121,7 @@ private[spark] object GradientBoostedTrees extends Logging {
    * @param treeWeight: Learning rate.
    * @param tree: Tree using which the prediction and error should be updated.
    * @param loss: evaluation metric.
-   * @return a RDD with each element being a zip of the prediction and error
+   * @return an RDD with each element being a zip of the prediction and error
    *         corresponding to each sample.
    */
   def updatePredictionError(
diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala b/mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala
index bc4f9e6716..e5fa5d53e3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala
@@ -221,7 +221,7 @@ trait MLReadable[T] {
   /**
    * Reads an ML instance from the input path, a shortcut of `read.load(path)`.
    *
-   * Note: Implementing classes should override this to be Java-friendly.
+   * @note Implementing classes should override this to be Java-friendly.
    */
   @Since("1.6.0")
   def load(path: String): T = read.load(path)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
index d851b98334..4b65000073 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
@@ -202,9 +202,11 @@ object LogisticRegressionModel extends Loader[LogisticRegressionModel] {
  * Train a classification model for Binary Logistic Regression
  * using Stochastic Gradient Descent. By default L2 regularization is used,
  * which can be changed via `LogisticRegressionWithSGD.optimizer`.
- * NOTE: Labels used in Logistic Regression should be {0, 1, ..., k - 1}
- * for k classes multi-label classification problem.
+ *
  * Using [[LogisticRegressionWithLBFGS]] is recommended over this.
+ *
+ * @note Labels used in Logistic Regression should be {0, 1, ..., k - 1}
+ * for k classes multi-label classification problem.
  */
 @Since("0.8.0")
 class LogisticRegressionWithSGD private[mllib] (
@@ -239,7 +241,8 @@ class LogisticRegressionWithSGD private[mllib] (
 
 /**
  * Top-level methods for calling Logistic Regression using Stochastic Gradient Descent.
- * NOTE: Labels used in Logistic Regression should be {0, 1}
+ *
+ * @note Labels used in Logistic Regression should be {0, 1}
  */
 @Since("0.8.0")
 @deprecated("Use ml.classification.LogisticRegression or LogisticRegressionWithLBFGS", "2.0.0")
@@ -252,7 +255,6 @@ object LogisticRegressionWithSGD {
    * number of iterations of gradient descent using the specified step size. Each iteration uses
    * `miniBatchFraction` fraction of the data to calculate the gradient. The weights used in
    * gradient descent are initialized using the initial weights provided.
-   * NOTE: Labels used in Logistic Regression should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
@@ -260,6 +262,8 @@ object LogisticRegressionWithSGD {
    * @param miniBatchFraction Fraction of data to be used per iteration.
    * @param initialWeights Initial set of weights to be used. Array should be equal in size to
    *        the number of features in the data.
+   *
+   * @note Labels used in Logistic Regression should be {0, 1}
    */
   @Since("1.0.0")
   def train(
@@ -276,13 +280,13 @@ object LogisticRegressionWithSGD {
    * Train a logistic regression model given an RDD of (label, features) pairs. We run a fixed
    * number of iterations of gradient descent using the specified step size. Each iteration uses
    * `miniBatchFraction` fraction of the data to calculate the gradient.
-   * NOTE: Labels used in Logistic Regression should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
    * @param stepSize Step size to be used for each iteration of gradient descent.
-
    * @param miniBatchFraction Fraction of data to be used per iteration.
+   *
+   * @note Labels used in Logistic Regression should be {0, 1}
    */
   @Since("1.0.0")
   def train(
@@ -298,13 +302,13 @@ object LogisticRegressionWithSGD {
    * Train a logistic regression model given an RDD of (label, features) pairs. We run a fixed
    * number of iterations of gradient descent using the specified step size. We use the entire data
    * set to update the gradient in each iteration.
-   * NOTE: Labels used in Logistic Regression should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param stepSize Step size to be used for each iteration of Gradient Descent.
-
    * @param numIterations Number of iterations of gradient descent to run.
    * @return a LogisticRegressionModel which has the weights and offset from training.
+   *
+   * @note Labels used in Logistic Regression should be {0, 1}
    */
   @Since("1.0.0")
   def train(
@@ -318,11 +322,12 @@ object LogisticRegressionWithSGD {
    * Train a logistic regression model given an RDD of (label, features) pairs. We run a fixed
    * number of iterations of gradient descent using a step size of 1.0. We use the entire data set
    * to update the gradient in each iteration.
-   * NOTE: Labels used in Logistic Regression should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
    * @return a LogisticRegressionModel which has the weights and offset from training.
+   *
+   * @note Labels used in Logistic Regression should be {0, 1}
    */
   @Since("1.0.0")
   def train(
@@ -335,8 +340,6 @@ object LogisticRegressionWithSGD {
 /**
  * Train a classification model for Multinomial/Binary Logistic Regression using
  * Limited-memory BFGS. Standard feature scaling and L2 regularization are used by default.
- * NOTE: Labels used in Logistic Regression should be {0, 1, ..., k - 1}
- * for k classes multi-label classification problem.
  *
  * Earlier implementations of LogisticRegressionWithLBFGS applies a regularization
  * penalty to all elements including the intercept. If this is called with one of
@@ -344,6 +347,9 @@ object LogisticRegressionWithSGD {
  * into a call to ml.LogisticRegression, otherwise this will use the existing mllib
  * GeneralizedLinearAlgorithm trainer, resulting in a regularization penalty to the
  * intercept.
+ *
+ * @note Labels used in Logistic Regression should be {0, 1, ..., k - 1}
+ * for k classes multi-label classification problem.
  */
 @Since("1.1.0")
 class LogisticRegressionWithLBFGS
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
index 7c3ccbb40b..aec1526b55 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/SVM.scala
@@ -125,7 +125,8 @@ object SVMModel extends Loader[SVMModel] {
 /**
  * Train a Support Vector Machine (SVM) using Stochastic Gradient Descent. By default L2
  * regularization is used, which can be changed via [[SVMWithSGD.optimizer]].
- * NOTE: Labels used in SVM should be {0, 1}.
+ *
+ * @note Labels used in SVM should be {0, 1}.
  */
 @Since("0.8.0")
 class SVMWithSGD private (
@@ -158,7 +159,9 @@ class SVMWithSGD private (
 }
 
 /**
- * Top-level methods for calling SVM. NOTE: Labels used in SVM should be {0, 1}.
+ * Top-level methods for calling SVM.
+ *
+ * @note Labels used in SVM should be {0, 1}.
  */
 @Since("0.8.0")
 object SVMWithSGD {
@@ -169,8 +172,6 @@ object SVMWithSGD {
    * `miniBatchFraction` fraction of the data to calculate the gradient. The weights used in
    * gradient descent are initialized using the initial weights provided.
    *
-   * NOTE: Labels used in SVM should be {0, 1}.
-   *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
    * @param stepSize Step size to be used for each iteration of gradient descent.
@@ -178,6 +179,8 @@ object SVMWithSGD {
    * @param miniBatchFraction Fraction of data to be used per iteration.
    * @param initialWeights Initial set of weights to be used. Array should be equal in size to
    *        the number of features in the data.
+   *
+   * @note Labels used in SVM should be {0, 1}.
    */
   @Since("0.8.0")
   def train(
@@ -195,7 +198,8 @@ object SVMWithSGD {
    * Train a SVM model given an RDD of (label, features) pairs. We run a fixed number
    * of iterations of gradient descent using the specified step size. Each iteration uses
    * `miniBatchFraction` fraction of the data to calculate the gradient.
-   * NOTE: Labels used in SVM should be {0, 1}
+   *
+   * @note Labels used in SVM should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
@@ -217,13 +221,14 @@ object SVMWithSGD {
    * Train a SVM model given an RDD of (label, features) pairs. We run a fixed number
    * of iterations of gradient descent using the specified step size. We use the entire data set to
    * update the gradient in each iteration.
-   * NOTE: Labels used in SVM should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param stepSize Step size to be used for each iteration of Gradient Descent.
    * @param regParam Regularization parameter.
    * @param numIterations Number of iterations of gradient descent to run.
    * @return a SVMModel which has the weights and offset from training.
+   *
+   * @note Labels used in SVM should be {0, 1}
    */
   @Since("0.8.0")
   def train(
@@ -238,11 +243,12 @@ object SVMWithSGD {
    * Train a SVM model given an RDD of (label, features) pairs. We run a fixed number
    * of iterations of gradient descent using a step size of 1.0. We use the entire data set to
    * update the gradient in each iteration.
-   * NOTE: Labels used in SVM should be {0, 1}
    *
    * @param input RDD of (label, array of features) pairs.
    * @param numIterations Number of iterations of gradient descent to run.
    * @return a SVMModel which has the weights and offset from training.
+   *
+   * @note Labels used in SVM should be {0, 1}
    */
   @Since("0.8.0")
   def train(input: RDD[LabeledPoint], numIterations: Int): SVMModel = {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala
index 43193adf3e..56cdeea5f7 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala
@@ -41,14 +41,14 @@ import org.apache.spark.util.Utils
  * While this process is generally guaranteed to converge, it is not guaranteed
  * to find a global optimum.
  *
- * Note: For high-dimensional data (with many features), this algorithm may perform poorly.
- *       This is due to high-dimensional data (a) making it difficult to cluster at all (based
- *       on statistical/theoretical arguments) and (b) numerical issues with Gaussian distributions.
- *
  * @param k Number of independent Gaussians in the mixture model.
  * @param convergenceTol Maximum change in log-likelihood at which convergence
  *                       is considered to have occurred.
  * @param maxIterations Maximum number of iterations allowed.
+ *
+ * @note For high-dimensional data (with many features), this algorithm may perform poorly.
+ * This is due to high-dimensional data (a) making it difficult to cluster at all (based
+ * on statistical/theoretical arguments) and (b) numerical issues with Gaussian distributions.
  */
 @Since("1.3.0")
 class GaussianMixture private (
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
index ed9c064879..fa72b72e2d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -56,14 +56,18 @@ class KMeans private (
   def this() = this(2, 20, KMeans.K_MEANS_PARALLEL, 2, 1e-4, Utils.random.nextLong())
 
   /**
-   * Number of clusters to create (k). Note that it is possible for fewer than k clusters to
+   * Number of clusters to create (k).
+   *
+   * @note It is possible for fewer than k clusters to
    * be returned, for example, if there are fewer than k distinct points to cluster.
    */
   @Since("1.4.0")
   def getK: Int = k
 
   /**
-   * Set the number of clusters to create (k). Note that it is possible for fewer than k clusters to
+   * Set the number of clusters to create (k).
+   *
+   * @note It is possible for fewer than k clusters to
    * be returned, for example, if there are fewer than k distinct points to cluster. Default: 2.
    */
   @Since("0.8.0")
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala
index d999b9be8e..7c52abdeaa 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala
@@ -175,7 +175,7 @@ class LDA private (
    *
    * This is the parameter to a symmetric Dirichlet distribution.
    *
-   * Note: The topics' distributions over terms are called "beta" in the original LDA paper
+   * @note The topics' distributions over terms are called "beta" in the original LDA paper
    * by Blei et al., but are called "phi" in many later papers such as Asuncion et al., 2009.
    */
   @Since("1.3.0")
@@ -187,7 +187,7 @@ class LDA private (
    *
    * This is the parameter to a symmetric Dirichlet distribution.
    *
-   * Note: The topics' distributions over terms are called "beta" in the original LDA paper
+   * @note The topics' distributions over terms are called "beta" in the original LDA paper
    * by Blei et al., but are called "phi" in many later papers such as Asuncion et al., 2009.
    *
    * If set to -1, then topicConcentration is set automatically.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala
index 90d8a558f1..b5b0e64a2a 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala
@@ -66,7 +66,7 @@ abstract class LDAModel private[clustering] extends Saveable {
    *
    * This is the parameter to a symmetric Dirichlet distribution.
    *
-   * Note: The topics' distributions over terms are called "beta" in the original LDA paper
+   * @note The topics' distributions over terms are called "beta" in the original LDA paper
    * by Blei et al., but are called "phi" in many later papers such as Asuncion et al., 2009.
    */
   @Since("1.5.0")
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala
index ae324f86fe..7365ea1f20 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala
@@ -93,9 +93,11 @@ final class EMLDAOptimizer extends LDAOptimizer {
   /**
    * If using checkpointing, this indicates whether to keep the last checkpoint (vs clean up).
    * Deleting the checkpoint can cause failures if a data partition is lost, so set this bit with
-   * care.  Note that checkpoints will be cleaned up via reference counting, regardless.
+   * care.
    *
    * Default: true
+   *
+   * @note Checkpoints will be cleaned up via reference counting, regardless.
    */
   @Since("2.0.0")
   def setKeepLastCheckpoint(keepLastCheckpoint: Boolean): this.type = {
@@ -348,7 +350,7 @@ final class OnlineLDAOptimizer extends LDAOptimizer {
    * Mini-batch fraction in (0, 1], which sets the fraction of document sampled and used in
    * each iteration.
    *
-   * Note that this should be adjusted in synch with [[LDA.setMaxIterations()]]
+   * @note This should be adjusted in synch with [[LDA.setMaxIterations()]]
    * so the entire corpus is used.  Specifically, set both so that
    * maxIterations * miniBatchFraction >= 1.
    *
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/AreaUnderCurve.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/AreaUnderCurve.scala
index f0779491e6..003d1411a9 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/AreaUnderCurve.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/AreaUnderCurve.scala
@@ -39,7 +39,7 @@ private[evaluation] object AreaUnderCurve {
   /**
    * Returns the area under the given curve.
    *
-   * @param curve a RDD of ordered 2D points stored in pairs representing a curve
+   * @param curve an RDD of ordered 2D points stored in pairs representing a curve
    */
   def of(curve: RDD[(Double, Double)]): Double = {
     curve.sliding(2).aggregate(0.0)(
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
index fbd217af74..c94d7890cf 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
@@ -40,7 +40,7 @@ import org.apache.spark.sql.types._
 /**
  * Represents a numeric vector, whose index type is Int and value type is Double.
  *
- * Note: Users should not implement this interface.
+ * @note Users should not implement this interface.
  */
 @SQLUserDefinedType(udt = classOf[VectorUDT])
 @Since("1.0.0")
@@ -132,7 +132,9 @@ sealed trait Vector extends Serializable {
 
   /**
    * Number of active entries.  An "active entry" is an element which is explicitly stored,
-   * regardless of its value.  Note that inactive entries have value 0.
+   * regardless of its value.
+   *
+   * @note Inactive entries have value 0.
    */
   @Since("1.4.0")
   def numActives: Int
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
index 377be6bfb9..03866753b5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala
@@ -451,7 +451,7 @@ class BlockMatrix @Since("1.3.0") (
    * [[BlockMatrix]] will only consist of blocks of [[DenseMatrix]]. This may cause
    * some performance issues until support for multiplying two sparse matrices is added.
    *
-   * Note: The behavior of multiply has changed in 1.6.0. `multiply` used to throw an error when
+   * @note The behavior of multiply has changed in 1.6.0. `multiply` used to throw an error when
    * there were blocks with duplicate indices. Now, the blocks with duplicate indices will be added
    * with each other.
    */
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
index b03b3ecde9..809906a158 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
@@ -188,8 +188,9 @@ class IndexedRowMatrix @Since("1.0.0") (
   }
 
   /**
-   * Computes the Gramian matrix `A^T A`. Note that this cannot be
-   * computed on matrices with more than 65535 columns.
+   * Computes the Gramian matrix `A^T A`.
+   *
+   * @note This cannot be computed on matrices with more than 65535 columns.
    */
   @Since("1.0.0")
   def computeGramianMatrix(): Matrix = {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
index ec32e37afb..4b120332ab 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
@@ -106,8 +106,9 @@ class RowMatrix @Since("1.0.0") (
   }
 
   /**
-   * Computes the Gramian matrix `A^T A`. Note that this cannot be computed on matrices with
-   * more than 65535 columns.
+   * Computes the Gramian matrix `A^T A`.
+   *
+   * @note This cannot be computed on matrices with more than 65535 columns.
    */
   @Since("1.0.0")
   def computeGramianMatrix(): Matrix = {
@@ -168,9 +169,6 @@ class RowMatrix @Since("1.0.0") (
    * ARPACK is set to 300 or k * 3, whichever is larger. The numerical tolerance for ARPACK's
    * eigen-decomposition is set to 1e-10.
    *
-   * @note The conditions that decide which method to use internally and the default parameters are
-   *       subject to change.
-   *
    * @param k number of leading singular values to keep (0 &lt; k &lt;= n).
    *          It might return less than k if
    *          there are numerically zero singular values or there are not enough Ritz values
@@ -180,6 +178,9 @@ class RowMatrix @Since("1.0.0") (
    * @param rCond the reciprocal condition number. All singular values smaller than rCond * sigma(0)
    *              are treated as zero, where sigma(0) is the largest singular value.
    * @return SingularValueDecomposition(U, s, V). U = null if computeU = false.
+   *
+   * @note The conditions that decide which method to use internally and the default parameters are
+   * subject to change.
    */
   @Since("1.0.0")
   def computeSVD(
@@ -319,9 +320,11 @@ class RowMatrix @Since("1.0.0") (
   }
 
   /**
-   * Computes the covariance matrix, treating each row as an observation. Note that this cannot
-   * be computed on matrices with more than 65535 columns.
+   * Computes the covariance matrix, treating each row as an observation.
+   *
    * @return a local dense matrix of size n x n
+   *
+   * @note This cannot be computed on matrices with more than 65535 columns.
    */
   @Since("1.0.0")
   def computeCovariance(): Matrix = {
@@ -369,12 +372,12 @@ class RowMatrix @Since("1.0.0") (
    * The row data do not need to be "centered" first; it is not necessary for
    * the mean of each column to be 0.
    *
-   * Note that this cannot be computed on matrices with more than 65535 columns.
-   *
    * @param k number of top principal components.
    * @return a matrix of size n-by-k, whose columns are principal components, and
    * a vector of values which indicate how much variance each principal component
    * explains
+   *
+   * @note This cannot be computed on matrices with more than 65535 columns.
    */
   @Since("1.6.0")
   def computePrincipalComponentsAndExplainedVariance(k: Int): (Matrix, Vector) = {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
index 81e64de4e5..c49e72646b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
@@ -305,7 +305,8 @@ class LeastSquaresGradient extends Gradient {
  * :: DeveloperApi ::
  * Compute gradient and loss for a Hinge loss function, as used in SVM binary classification.
  * See also the documentation for the precise formulation.
- * NOTE: This assumes that the labels are {0,1}
+ *
+ * @note This assumes that the labels are {0,1}
  */
 @DeveloperApi
 class HingeGradient extends Gradient {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/rdd/RDDFunctions.scala b/mllib/src/main/scala/org/apache/spark/mllib/rdd/RDDFunctions.scala
index 0f7857b8d8..005119616f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/rdd/RDDFunctions.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/rdd/RDDFunctions.scala
@@ -31,7 +31,7 @@ import org.apache.spark.rdd.RDD
 class RDDFunctions[T: ClassTag](self: RDD[T]) extends Serializable {
 
   /**
-   * Returns a RDD from grouping items of its parent RDD in fixed size blocks by passing a sliding
+   * Returns an RDD from grouping items of its parent RDD in fixed size blocks by passing a sliding
    * window over them. The ordering is first based on the partition index and then the ordering of
    * items within each partition. This is similar to sliding in Scala collections, except that it
    * becomes an empty RDD if the window size is greater than the total number of items. It needs to
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
index c642573ccb..24e4dcccc8 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
@@ -43,14 +43,14 @@ import org.apache.spark.storage.StorageLevel
 /**
  * Model representing the result of matrix factorization.
  *
- * Note: If you create the model directly using constructor, please be aware that fast prediction
- * requires cached user/product features and their associated partitioners.
- *
  * @param rank Rank for the features in this model.
  * @param userFeatures RDD of tuples where each tuple represents the userId and
  *                     the features computed for this user.
  * @param productFeatures RDD of tuples where each tuple represents the productId
  *                        and the features computed for this product.
+ *
+ * @note If you create the model directly using constructor, please be aware that fast prediction
+ * requires cached user/product features and their associated partitioners.
  */
 @Since("0.8.0")
 class MatrixFactorizationModel @Since("0.8.0") (
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala
index f3159f7e72..925fdf4d7e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/Statistics.scala
@@ -60,15 +60,15 @@ object Statistics {
    * Compute the correlation matrix for the input RDD of Vectors using the specified method.
    * Methods currently supported: `pearson` (default), `spearman`.
    *
-   * Note that for Spearman, a rank correlation, we need to create an RDD[Double] for each column
-   * and sort it in order to retrieve the ranks and then join the columns back into an RDD[Vector],
-   * which is fairly costly. Cache the input RDD before calling corr with `method = "spearman"` to
-   * avoid recomputing the common lineage.
-   *
    * @param X an RDD[Vector] for which the correlation matrix is to be computed.
    * @param method String specifying the method to use for computing correlation.
    *               Supported: `pearson` (default), `spearman`
    * @return Correlation matrix comparing columns in X.
+   *
+   * @note For Spearman, a rank correlation, we need to create an RDD[Double] for each column
+   * and sort it in order to retrieve the ranks and then join the columns back into an RDD[Vector],
+   * which is fairly costly. Cache the input RDD before calling corr with `method = "spearman"` to
+   * avoid recomputing the common lineage.
    */
   @Since("1.1.0")
   def corr(X: RDD[Vector], method: String): Matrix = Correlations.corrMatrix(X, method)
@@ -77,12 +77,12 @@ object Statistics {
    * Compute the Pearson correlation for the input RDDs.
    * Returns NaN if either vector has 0 variance.
    *
-   * Note: the two input RDDs need to have the same number of partitions and the same number of
-   * elements in each partition.
-   *
    * @param x RDD[Double] of the same cardinality as y.
    * @param y RDD[Double] of the same cardinality as x.
    * @return A Double containing the Pearson correlation between the two input RDD[Double]s
+   *
+   * @note The two input RDDs need to have the same number of partitions and the same number of
+   * elements in each partition.
    */
   @Since("1.1.0")
   def corr(x: RDD[Double], y: RDD[Double]): Double = Correlations.corr(x, y)
@@ -98,15 +98,15 @@ object Statistics {
    * Compute the correlation for the input RDDs using the specified method.
    * Methods currently supported: `pearson` (default), `spearman`.
    *
-   * Note: the two input RDDs need to have the same number of partitions and the same number of
-   * elements in each partition.
-   *
    * @param x RDD[Double] of the same cardinality as y.
    * @param y RDD[Double] of the same cardinality as x.
    * @param method String specifying the method to use for computing correlation.
    *               Supported: `pearson` (default), `spearman`
    * @return A Double containing the correlation between the two input RDD[Double]s using the
    *         specified method.
+   *
+   * @note The two input RDDs need to have the same number of partitions and the same number of
+   * elements in each partition.
    */
   @Since("1.1.0")
   def corr(x: RDD[Double], y: RDD[Double], method: String): Double = Correlations.corr(x, y, method)
@@ -122,15 +122,15 @@ object Statistics {
    * Conduct Pearson's chi-squared goodness of fit test of the observed data against the
    * expected distribution.
    *
-   * Note: the two input Vectors need to have the same size.
-   *       `observed` cannot contain negative values.
-   *       `expected` cannot contain nonpositive values.
-   *
    * @param observed Vector containing the observed categorical counts/relative frequencies.
    * @param expected Vector containing the expected categorical counts/relative frequencies.
    *                 `expected` is rescaled if the `expected` sum differs from the `observed` sum.
    * @return ChiSquaredTest object containing the test statistic, degrees of freedom, p-value,
    *         the method used, and the null hypothesis.
+   *
+   * @note The two input Vectors need to have the same size.
+   * `observed` cannot contain negative values.
+   * `expected` cannot contain nonpositive values.
    */
   @Since("1.1.0")
   def chiSqTest(observed: Vector, expected: Vector): ChiSqTestResult = {
@@ -141,11 +141,11 @@ object Statistics {
    * Conduct Pearson's chi-squared goodness of fit test of the observed data against the uniform
    * distribution, with each category having an expected frequency of `1 / observed.size`.
    *
-   * Note: `observed` cannot contain negative values.
-   *
    * @param observed Vector containing the observed categorical counts/relative frequencies.
    * @return ChiSquaredTest object containing the test statistic, degrees of freedom, p-value,
    *         the method used, and the null hypothesis.
+   *
+   * @note `observed` cannot contain negative values.
    */
   @Since("1.1.0")
   def chiSqTest(observed: Vector): ChiSqTestResult = ChiSqTest.chiSquared(observed)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
index 36feab7859..d846c43cf2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
@@ -75,10 +75,6 @@ object DecisionTree extends Serializable with Logging {
    * Method to train a decision tree model.
    * The method supports binary and multiclass classification and regression.
    *
-   * Note: Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
-   *       and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
-   *       is recommended to clearly separate classification and regression.
-   *
    * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
    *              For classification, labels should take values {0, 1, ..., numClasses-1}.
    *              For regression, labels are real numbers.
@@ -86,6 +82,10 @@ object DecisionTree extends Serializable with Logging {
    *                 of decision tree (classification or regression), feature type (continuous,
    *                 categorical), depth of the tree, quantile calculation strategy, etc.
    * @return DecisionTreeModel that can be used for prediction.
+   *
+   * @note Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
+   * and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
+   * is recommended to clearly separate classification and regression.
    */
   @Since("1.0.0")
   def train(input: RDD[LabeledPoint], strategy: Strategy): DecisionTreeModel = {
@@ -96,10 +96,6 @@ object DecisionTree extends Serializable with Logging {
    * Method to train a decision tree model.
    * The method supports binary and multiclass classification and regression.
    *
-   * Note: Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
-   *       and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
-   *       is recommended to clearly separate classification and regression.
-   *
    * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
    *              For classification, labels should take values {0, 1, ..., numClasses-1}.
    *              For regression, labels are real numbers.
@@ -108,6 +104,10 @@ object DecisionTree extends Serializable with Logging {
    * @param maxDepth Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means
    *                 1 internal node + 2 leaf nodes).
    * @return DecisionTreeModel that can be used for prediction.
+   *
+   * @note Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
+   * and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
+   * is recommended to clearly separate classification and regression.
    */
   @Since("1.0.0")
   def train(
@@ -123,10 +123,6 @@ object DecisionTree extends Serializable with Logging {
    * Method to train a decision tree model.
    * The method supports binary and multiclass classification and regression.
    *
-   * Note: Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
-   *       and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
-   *       is recommended to clearly separate classification and regression.
-   *
    * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
    *              For classification, labels should take values {0, 1, ..., numClasses-1}.
    *              For regression, labels are real numbers.
@@ -136,6 +132,10 @@ object DecisionTree extends Serializable with Logging {
    *                 1 internal node + 2 leaf nodes).
    * @param numClasses Number of classes for classification. Default value of 2.
    * @return DecisionTreeModel that can be used for prediction.
+   *
+   * @note Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
+   * and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
+   * is recommended to clearly separate classification and regression.
    */
   @Since("1.2.0")
   def train(
@@ -152,10 +152,6 @@ object DecisionTree extends Serializable with Logging {
    * Method to train a decision tree model.
    * The method supports binary and multiclass classification and regression.
    *
-   * Note: Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
-   *       and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
-   *       is recommended to clearly separate classification and regression.
-   *
    * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
    *              For classification, labels should take values {0, 1, ..., numClasses-1}.
    *              For regression, labels are real numbers.
@@ -170,6 +166,10 @@ object DecisionTree extends Serializable with Logging {
    *                                indicates that feature n is categorical with k categories
    *                                indexed from 0: {0, 1, ..., k-1}.
    * @return DecisionTreeModel that can be used for prediction.
+   *
+   * @note Using [[org.apache.spark.mllib.tree.DecisionTree$#trainClassifier]]
+   * and [[org.apache.spark.mllib.tree.DecisionTree$#trainRegressor]]
+   * is recommended to clearly separate classification and regression.
    */
   @Since("1.0.0")
   def train(
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/loss/Loss.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/loss/Loss.scala
index de14ddf024..09274a2e1b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/loss/Loss.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/loss/Loss.scala
@@ -42,11 +42,13 @@ trait Loss extends Serializable {
 
   /**
    * Method to calculate error of the base learner for the gradient boosting calculation.
-   * Note: This method is not used by the gradient boosting algorithm but is useful for debugging
-   * purposes.
+   *
    * @param model Model of the weak learner.
    * @param data Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
    * @return Measure of model error on data
+   *
+   * @note This method is not used by the gradient boosting algorithm but is useful for debugging
+   * purposes.
    */
   @Since("1.2.0")
   def computeError(model: TreeEnsembleModel, data: RDD[LabeledPoint]): Double = {
@@ -55,11 +57,13 @@ trait Loss extends Serializable {
 
   /**
    * Method to calculate loss when the predictions are already known.
-   * Note: This method is used in the method evaluateEachIteration to avoid recomputing the
-   * predicted values from previously fit trees.
+   *
    * @param prediction Predicted label.
    * @param label True label.
    * @return Measure of model error on datapoint.
+   *
+   * @note This method is used in the method evaluateEachIteration to avoid recomputing the
+   * predicted values from previously fit trees.
    */
   private[spark] def computeError(prediction: Double, label: Double): Double
 }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala
index 657ed0a8ec..299950785e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala
@@ -187,7 +187,7 @@ object GradientBoostedTreesModel extends Loader[GradientBoostedTreesModel] {
    * @param initTreeWeight: learning rate assigned to the first tree.
    * @param initTree: first DecisionTreeModel.
    * @param loss: evaluation metric.
-   * @return a RDD with each element being a zip of the prediction and error
+   * @return an RDD with each element being a zip of the prediction and error
    *         corresponding to every sample.
    */
   @Since("1.4.0")
@@ -213,7 +213,7 @@ object GradientBoostedTreesModel extends Loader[GradientBoostedTreesModel] {
    * @param treeWeight: Learning rate.
    * @param tree: Tree using which the prediction and error should be updated.
    * @param loss: evaluation metric.
-   * @return a RDD with each element being a zip of the prediction and error
+   * @return an RDD with each element being a zip of the prediction and error
    *         corresponding to each sample.
    */
   @Since("1.4.0")
-- 
cgit v1.2.3