[SPARK-23163][DOC][PYTHON] Sync ML Python API with Scala

python/pyspark/ml/evaluation.py

@@ -334,7 +334,13 @@ class ClusteringEvaluator(JavaEvaluator, HasPredictionCol, HasFeaturesCol,
     .. note:: Experimental
 
     Evaluator for Clustering results, which expects two input
-    columns: prediction and features.
+    columns: prediction and features. The metric computes the Silhouette
+    measure using the squared Euclidean distance.
+
+    The Silhouette is a measure for the validation of the consistency
+    within clusters. It ranges between 1 and -1, where a value close to
+    1 means that the points in a cluster are close to the other points
+    in the same cluster and far from the points of the other clusters.
 
     >>> from pyspark.ml.linalg import Vectors
     >>> featureAndPredictions = map(lambda x: (Vectors.dense(x[0]), x[1]),

python/pyspark/ml/feature.py

@@ -3440,7 +3440,7 @@ class ChiSqSelector(JavaEstimator, HasFeaturesCol, HasOutputCol, HasLabelCol, Ja
 
     selectorType = Param(Params._dummy(), "selectorType",
                          "The selector type of the ChisqSelector. " +
-                         "Supported options: numTopFeatures (default), percentile and fpr.",
+                         "Supported options: numTopFeatures (default), percentile, fpr, fdr, fwe.",
                          typeConverter=TypeConverters.toString)
 
     numTopFeatures = \

python/pyspark/ml/fpm.py

@@ -144,7 +144,7 @@ def freqItemsets(self):
     @since("2.2.0")
     def associationRules(self):
         """
-        Data with three columns:
+        DataFrame with three columns:
         * `antecedent`  - Array of the same type as the input column.
         * `consequent`  - Array of the same type as the input column.
         * `confidence`  - Confidence for the rule (`DoubleType`).