add javadoc

Author: Peng, Meng

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

@@ -90,6 +90,9 @@ private[feature] trait ChiSqSelectorParams extends Params
 /**
  * Chi-Squared feature selection, which selects categorical features to use for predicting a
  * categorical label.
+ * The selector supports three selection methods: KBest, Percentile and FPR.
+ * By default, the selection method is KBest, the default number of top features is 50.
+ * User can use setNumTopFeatures, setPercentile and setAlpha to set different selection methods.
  */
 @Since("1.6.0")
 final class ChiSqSelector @Since("1.6.0") (@Since("1.6.0") override val uid: String)
@@ -99,7 +102,7 @@ final class ChiSqSelector @Since("1.6.0") (@Since("1.6.0") override val uid: Str
   def this() = this(Identifiable.randomUID("chiSqSelector"))
 
   /** @group setParam */
-  @Since("2.1.0")
+  @Since("1.6.0")
   def setNumTopFeatures(value: Int): this.type = {
     set(selectorType, ChiSqSelectorType.KBest.toString)
     set(numTopFeatures, value)

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

@@ -166,21 +166,27 @@ object ChiSqSelectorModel extends Loader[ChiSqSelectorModel] {
 
 /**
  * Creates a ChiSquared feature selector.
+ * The selector supports three selection methods: KBest, Percentile and FPR.
+ * By default, the selection method is KBest, the default number of top features is 50.
+ * User can use setNumTopFeatures, setPercentile and setAlpha to set different selection methods.
  */
-@Since("2.1.0")
+@Since("1.3.0")
 class ChiSqSelector @Since("2.1.0") () extends Serializable {
   var numTopFeatures: Int = 50
   var percentile: Double = 0.1
   var alpha: Double = 0.05
   var selectorType = ChiSqSelectorType.KBest
 
+  /**
+   * The is the same to call this() and setNumTopFeatures(numTopFeatures)
+   */
   @Since("1.3.0")
   def this(numTopFeatures: Int) {
     this()
     this.numTopFeatures = numTopFeatures
   }
 
-  @Since("2.1.0")
+  @Since("1.6.0")
   def setNumTopFeatures(value: Int): this.type = {
     numTopFeatures = value
     selectorType = ChiSqSelectorType.KBest

python/pyspark/mllib/feature.py

@@ -310,8 +310,8 @@ class ChiSqSelector(object):
 
     .. versionadded:: 1.4.0
     """
-    def __init__(self):
-        self.numTopFeatures = 50
+    def __init__(self, numTopFeatures=50):
+        self.numTopFeatures = numTopFeatures
         self.selectorType = ChiSqSelectorType.KBest
 
     @since('2.1.0')