[DOC][MINOR] ml.feature Scala and Python API sync

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

@@ -38,12 +38,12 @@ import org.apache.spark.sql.types.StructType
 private[feature] trait IDFBase extends Params with HasInputCol with HasOutputCol {
 
   /**
-   * The minimum of documents in which a term should appear.
+   * The minimum number of documents in which a term should appear.
    * Default: 0
    * @group param
    */
   final val minDocFreq = new IntParam(
-    this, "minDocFreq", "minimum of documents in which a term should appear for filtering")
+    this, "minDocFreq", "minimum number of documents in which a term should appear for filtering")
 
   setDefault(minDocFreq -> 0)
 

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

@@ -53,7 +53,8 @@ private[feature] trait PCAParams extends Params with HasInputCol with HasOutputC
 
 /**
  * :: Experimental ::
- * PCA trains a model to project vectors to a low-dimensional space using PCA.
+ * PCA trains a model to project vectors to a lower dimensional space of the top [[PCA!.k]]
+ * principal components.
  */
 @Experimental
 class PCA (override val uid: String) extends Estimator[PCAModel] with PCAParams
@@ -106,7 +107,7 @@ object PCA extends DefaultParamsReadable[PCA] {
 
 /**
  * :: Experimental ::
- * Model fitted by [[PCA]].
+ * Model fitted by [[PCA]].  Transforms vectors to a lower dimensional space.
  *
  * @param pc A principal components Matrix. Each column is one principal component.
  * @param explainedVariance A vector of proportions of variance explained by

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

@@ -194,7 +194,9 @@ object RFormula extends DefaultParamsReadable[RFormula] {
 
 /**
  * :: Experimental ::
- * A fitted RFormula. Fitting is required to determine the factor levels of formula terms.
+ * Model fitted by [[RFormula]]. Fitting is required to determine the factor levels of
+ * formula terms.
+ *
  * @param resolvedFormula the fitted R formula.
  * @param pipelineModel the fitted feature model, including factor to index mappings.
  */

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

@@ -240,7 +240,8 @@ object VectorIndexer extends DefaultParamsReadable[VectorIndexer] {
 
 /**
  * :: Experimental ::
- * Transform categorical features to use 0-based indices instead of their original values.
+ * Model fitted by [[VectorIndexer]].  Transform categorical features to use 0-based indices
+ * instead of their original values.
  *  - Categorical features are mapped to indices.
  *  - Continuous features (columns) are left unchanged.
  * This also appends metadata to the output column, marking features as Numeric (continuous),

python/pyspark/ml/feature.py

@@ -609,7 +609,7 @@ class IDF(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWritab
     """
 
     minDocFreq = Param(Params._dummy(), "minDocFreq",
-                       "minimum of documents in which a term should appear for filtering",
+                       "minimum number of documents in which a term should appear for filtering",
                        typeConverter=TypeConverters.toInt)
 
     @keyword_only
@@ -1302,7 +1302,8 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable,
 
     minTokenLength = Param(Params._dummy(), "minTokenLength", "minimum token length (>= 0)",
                            typeConverter=TypeConverters.toInt)
-    gaps = Param(Params._dummy(), "gaps", "whether regex splits on gaps (True) or matches tokens")
+    gaps = Param(Params._dummy(), "gaps", "whether regex splits on gaps (True) or matches tokens " +
+                 "(False)")
     pattern = Param(Params._dummy(), "pattern", "regex pattern (Java dialect) used for tokenizing",
                     typeConverter=TypeConverters.toString)
     toLowercase = Param(Params._dummy(), "toLowercase", "whether to convert all characters to " +
@@ -1907,7 +1908,7 @@ class VectorIndexer(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, Ja
     """
     .. note:: Experimental
 
-    Class for indexing categorical feature columns in a dataset of [[Vector]].
+    Class for indexing categorical feature columns in a dataset of `Vector`.
 
     This has 2 usage modes:
       - Automatically identify categorical features (default behavior)
@@ -2025,6 +2026,16 @@ class VectorIndexerModel(JavaModel, JavaMLReadable, JavaMLWritable):
 
     Model fitted by VectorIndexer.
 
+    Transform categorical features to use 0-based indices instead of their original values.
+      - Categorical features are mapped to indices.
+      - Continuous features (columns) are left unchanged.
+
+    This also appends metadata to the output column, marking features as Numeric (continuous),
+    Nominal (categorical), or Binary (either continuous or categorical).
+    Non-ML metadata is not carried over from the input to the output column.
+
+    This maintains vector sparsity.
+
     .. versionadded:: 1.4.0
     """
 
@@ -2327,7 +2338,8 @@ class PCA(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, JavaMLWritab
     """
     .. note:: Experimental
 
-    PCA trains a model to project vectors to a low-dimensional space using PCA.
+    PCA trains a model to project vectors to a lower dimensional space of the
+    top :py:attr:`k` principal components.
 
     >>> from pyspark.ml.linalg import Vectors
     >>> data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),),
@@ -2401,7 +2413,7 @@ class PCAModel(JavaModel, JavaMLReadable, JavaMLWritable):
     """
     .. note:: Experimental
 
-    Model fitted by PCA.
+    Model fitted by PCA.  Transforms vectors to a lower dimensional space.
 
     .. versionadded:: 1.5.0
     """
@@ -2532,7 +2544,8 @@ class RFormulaModel(JavaModel, JavaMLReadable, JavaMLWritable):
     """
     .. note:: Experimental
 
-    Model fitted by :py:class:`RFormula`.
+    Model fitted by :py:class:`RFormula`. Fitting is required to determine the
+    factor levels of formula terms.
 
     .. versionadded:: 1.5.0
     """