From 8f49cf5cb21301fa30fc38cd2c96bd477227ee9c Mon Sep 17 00:00:00 2001
From: Holden Karau <holden@pigscanfly.ca>
Date: Thu, 3 Sep 2015 11:51:14 -0700
Subject: [PATCH 1/2] Add defaults to the scaladoc for params in ml/

---
 .../ml/classification/MultilayerPerceptronClassifier.scala     | 2 ++
 .../spark/ml/evaluation/BinaryClassificationEvaluator.scala    | 1 +
 .../ml/evaluation/MulticlassClassificationEvaluator.scala      | 1 +
 .../org/apache/spark/ml/evaluation/RegressionEvaluator.scala   | 1 +
 .../src/main/scala/org/apache/spark/ml/feature/Binarizer.scala | 1 +
 mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala     | 1 +
 .../scala/org/apache/spark/ml/feature/StopWordsRemover.scala   | 2 ++
 .../main/scala/org/apache/spark/ml/feature/StringIndexer.scala | 1 +
 .../main/scala/org/apache/spark/ml/feature/VectorIndexer.scala | 1 +
 .../main/scala/org/apache/spark/ml/feature/VectorSlicer.scala  | 2 ++
 .../src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala  | 3 +++
 .../org/apache/spark/ml/regression/IsotonicRegression.scala    | 1 +
 12 files changed, 17 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
index 1e5b0bc4453e4..82fc80c58054f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
@@ -32,6 +32,7 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams
   with HasSeed with HasMaxIter with HasTol {
   /**
    * Layer sizes including input size and output size.
+   * Default: Array(1, 1)
    * @group param
    */
   final val layers: IntArrayParam = new IntArrayParam(this, "layers",
@@ -50,6 +51,7 @@ private[ml] trait MultilayerPerceptronParams extends PredictorParams
    * Data is stacked within partitions. If block size is more than remaining data in
    * a partition then it is adjusted to the size of this data.
    * Recommended size is between 10 and 1000.
+   * Default: 128
    * @group expertParam
    */
   final val blockSize: IntParam = new IntParam(this, "blockSize",
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
index 56419a0a15952..08df2919a8a87 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala
@@ -38,6 +38,7 @@ class BinaryClassificationEvaluator(override val uid: String)
 
   /**
    * param for metric name in evaluation
+   * Default: areaUnderROC
    * @group param
    */
   val metricName: Param[String] = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
index f73d2345078e6..458ca0de32d6a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
@@ -38,6 +38,7 @@ class MulticlassClassificationEvaluator (override val uid: String)
   /**
    * param for metric name in evaluation (supports `"f1"` (default), `"precision"`, `"recall"`,
    * `"weightedPrecision"`, `"weightedRecall"`)
+   * Default: f1
    * @group param
    */
   val metricName: Param[String] = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
index d21c88ab9b109..f77b7661cfb88 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
@@ -41,6 +41,7 @@ final class RegressionEvaluator(override val uid: String)
    * Because we will maximize evaluation value (ref: `CrossValidator`),
    * when we evaluate a metric that is needed to minimize (e.g., `"rmse"`, `"mse"`, `"mae"`),
    * we take and output the negative of this metric.
+   * Default: rmse
    * @group param
    */
   val metricName: Param[String] = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
index 46314854d5e3a..edad754436455 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
@@ -41,6 +41,7 @@ final class Binarizer(override val uid: String)
    * Param for threshold used to binarize continuous features.
    * The features greater than the threshold, will be binarized to 1.0.
    * The features equal to or less than the threshold, will be binarized to 0.0.
+   * Default: 0.0
    * @group param
    */
   val threshold: DoubleParam =
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
index 938447447a0a2..4c36df75d8aa0 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
@@ -35,6 +35,7 @@ private[feature] trait IDFBase extends Params with HasInputCol with HasOutputCol
 
   /**
    * The minimum of documents in which a term should appear.
+   * Default: 0
    * @group param
    */
   final val minDocFreq = new IntParam(
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 7da430c7d16df..622c7c02da55f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -98,6 +98,7 @@ class StopWordsRemover(override val uid: String)
 
   /**
    * the stop words set to be filtered out
+   * Default: StopWords.English
    * @group param
    */
   val stopWords: StringArrayParam = new StringArrayParam(this, "stopWords", "stop words")
@@ -110,6 +111,7 @@ class StopWordsRemover(override val uid: String)
 
   /**
    * whether to do a case sensitive comparison over the stop words
+   * Default: false
    * @group param
    */
   val caseSensitive: BooleanParam = new BooleanParam(this, "caseSensitive",
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 24250e4c4cf92..a073faa5dcf30 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
@@ -214,6 +214,7 @@ class IndexToString private[ml] (
    * Param for array of labels.
    * Optional labels to be provided by the user, if not supplied column
    * metadata is read for labels.
+   * Default: Empty array, resulting in metadata used for labels.
    * @group param
    */
   final val labels: StringArrayParam = new StringArrayParam(this, "labels",
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
index 61b925c0fdc07..52e0599e38d83 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
@@ -43,6 +43,7 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu
    * Must be >= 2.
    *
    * (default = 20)
+   * @group param
    */
   val maxCategories = new IntParam(this, "maxCategories",
     "Threshold for the number of values a categorical feature can take (>= 2)." +
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
index c5c2272270792..fb3387d4aa9be 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
@@ -49,6 +49,7 @@ final class VectorSlicer(override val uid: String)
   /**
    * An array of indices to select features from a vector column.
    * There can be no overlap with [[names]].
+   * Default: Empty array
    * @group param
    */
   val indices = new IntArrayParam(this, "indices",
@@ -67,6 +68,7 @@ final class VectorSlicer(override val uid: String)
    * An array of feature names to select features from a vector column.
    * These names must be specified by ML [[org.apache.spark.ml.attribute.Attribute]]s.
    * There can be no overlap with [[indices]].
+   * Default: Empty Array
    * @group param
    */
   val names = new StringArrayParam(this, "names",
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
index 5af775a4159ad..9edab3af913ca 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
@@ -39,6 +39,7 @@ private[feature] trait Word2VecBase extends Params
 
   /**
    * The dimension of the code that you want to transform from words.
+   * Default: 100
    * @group param
    */
   final val vectorSize = new IntParam(
@@ -50,6 +51,7 @@ private[feature] trait Word2VecBase extends Params
 
   /**
    * Number of partitions for sentences of words.
+   * Default: 1
    * @group param
    */
   final val numPartitions = new IntParam(
@@ -62,6 +64,7 @@ private[feature] trait Word2VecBase extends Params
   /**
    * The minimum number of times a token must appear to be included in the word2vec model's
    * vocabulary.
+   * Default: 5
    * @group param
    */
   final val minCount = new IntParam(this, "minCount", "the minimum number of times a token must " +
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
index 0f33bae30e622..d43a3447d3975 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala
@@ -40,6 +40,7 @@ private[regression] trait IsotonicRegressionBase extends Params with HasFeatures
   /**
    * Param for whether the output sequence should be isotonic/increasing (true) or
    * antitonic/decreasing (false).
+   * Default: true
    * @group param
    */
   final val isotonic: BooleanParam =

From 16c972e2f6582def635cb4157fefbd0e98c58406 Mon Sep 17 00:00:00 2001
From: Holden Karau <holden@pigscanfly.ca>
Date: Fri, 4 Sep 2015 14:50:18 -0700
Subject: [PATCH 2/2] CR feedback

---
 .../ml/evaluation/MulticlassClassificationEvaluator.scala    | 1 -
 .../org/apache/spark/ml/evaluation/RegressionEvaluator.scala | 1 -
 .../scala/org/apache/spark/ml/feature/StopWordsRemover.scala | 2 +-
 .../scala/org/apache/spark/ml/feature/StringIndexer.scala    | 5 ++---
 4 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
index 458ca0de32d6a..f73d2345078e6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/MulticlassClassificationEvaluator.scala
@@ -38,7 +38,6 @@ class MulticlassClassificationEvaluator (override val uid: String)
   /**
    * param for metric name in evaluation (supports `"f1"` (default), `"precision"`, `"recall"`,
    * `"weightedPrecision"`, `"weightedRecall"`)
-   * Default: f1
    * @group param
    */
   val metricName: Param[String] = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
index f77b7661cfb88..d21c88ab9b109 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/RegressionEvaluator.scala
@@ -41,7 +41,6 @@ final class RegressionEvaluator(override val uid: String)
    * Because we will maximize evaluation value (ref: `CrossValidator`),
    * when we evaluate a metric that is needed to minimize (e.g., `"rmse"`, `"mse"`, `"mae"`),
    * we take and output the negative of this metric.
-   * Default: rmse
    * @group param
    */
   val metricName: Param[String] = {
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 622c7c02da55f..2a79582625e9a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -98,7 +98,7 @@ class StopWordsRemover(override val uid: String)
 
   /**
    * the stop words set to be filtered out
-   * Default: StopWords.English
+   * Default: [[StopWords.English]]
    * @group param
    */
   val stopWords: StringArrayParam = new StringArrayParam(this, "stopWords", "stop words")
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 a073faa5dcf30..77aeed0ab0370 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
@@ -212,9 +212,8 @@ class IndexToString private[ml] (
 
   /**
    * Param for array of labels.
-   * Optional labels to be provided by the user, if not supplied column
-   * metadata is read for labels.
-   * Default: Empty array, resulting in metadata used for labels.
+   * Optional labels to be provided by the user.
+   * Default: Empty array, in which case column metadata is used for labels.
    * @group param
    */
   final val labels: StringArrayParam = new StringArrayParam(this, "labels",