Revert "[SPARK-25764][ML][EXAMPLES] Update BisectingKMeans example to…

… use ClusteringEvaluator" This reverts commit d0ecff2.
kimutansk · Oct 20, 2018 · 4acbda4 · 4acbda4
1 parent ec96d34
commit 4acbda4
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 27 deletions.
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java
@@ -20,7 +20,6 @@
 // $example on$
 import org.apache.spark.ml.clustering.BisectingKMeans;
 import org.apache.spark.ml.clustering.BisectingKMeansModel;
-import org.apache.spark.ml.evaluation.ClusteringEvaluator;
 import org.apache.spark.ml.linalg.Vector;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Row;
@@ -51,14 +50,9 @@ public static void main(String[] args) {
     BisectingKMeans bkm = new BisectingKMeans().setK(2).setSeed(1);
     BisectingKMeansModel model = bkm.fit(dataset);
 
-    // Make predictions
-    Dataset<Row> predictions = model.transform(dataset);
-
-    // Evaluate clustering by computing Silhouette score
-    ClusteringEvaluator evaluator = new ClusteringEvaluator();
-
-    double silhouette = evaluator.evaluate(predictions);
-    System.out.println("Silhouette with squared euclidean distance = " + silhouette);
+    // Evaluate clustering.
+    double cost = model.computeCost(dataset);
+    System.out.println("Within Set Sum of Squared Errors = " + cost);
 
     // Shows the result.
     System.out.println("Cluster Centers: ");

diff --git a/examples/src/main/python/ml/bisecting_k_means_example.py b/examples/src/main/python/ml/bisecting_k_means_example.py
@@ -24,7 +24,6 @@
 
 # $example on$
 from pyspark.ml.clustering import BisectingKMeans
-from pyspark.ml.evaluation import ClusteringEvaluator
 # $example off$
 from pyspark.sql import SparkSession
 
@@ -42,14 +41,9 @@
     bkm = BisectingKMeans().setK(2).setSeed(1)
     model = bkm.fit(dataset)
 
-    # Make predictions
-    predictions = model.transform(dataset)
-
-    # Evaluate clustering by computing Silhouette score
-    evaluator = ClusteringEvaluator()
-
-    silhouette = evaluator.evaluate(predictions)
-    print("Silhouette with squared euclidean distance = " + str(silhouette))
+    # Evaluate clustering.
+    cost = model.computeCost(dataset)
+    print("Within Set Sum of Squared Errors = " + str(cost))
 
     # Shows the result.
     print("Cluster Centers: ")

diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala
@@ -21,7 +21,6 @@ package org.apache.spark.examples.ml
 
 // $example on$
 import org.apache.spark.ml.clustering.BisectingKMeans
-import org.apache.spark.ml.evaluation.ClusteringEvaluator
 // $example off$
 import org.apache.spark.sql.SparkSession
 
@@ -49,14 +48,9 @@ object BisectingKMeansExample {
     val bkm = new BisectingKMeans().setK(2).setSeed(1)
     val model = bkm.fit(dataset)
 
-    // Make predictions
-    val predictions = model.transform(dataset)
-
-    // Evaluate clustering by computing Silhouette score
-    val evaluator = new ClusteringEvaluator()
-
-    val silhouette = evaluator.evaluate(predictions)
-    println(s"Silhouette with squared euclidean distance = $silhouette")
+    // Evaluate clustering.
+    val cost = model.computeCost(dataset)
+    println(s"Within Set Sum of Squared Errors = $cost")
 
     // Shows the result.
     println("Cluster Centers: ")