SPARK-2149. [MLLIB] Univariate kernel density estimation

Author: Sandy Ryza <sandy@cloudera.com>

Closes #1093 from sryza/sandy-spark-2149 and squashes the following commits:

5f06b33 [Sandy Ryza] More review comments
0f73060 [Sandy Ryza] Respond to Sean's review comments
0dfa005 [Sandy Ryza] SPARK-2149. Univariate kernel density estimation

1 files changed, 47 insertions, 0 deletions

diff --git a/mllib/src/test/scala/org/apache/spark/mllib/stat/KernelDensitySuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/stat/KernelDensitySuite.scala
new file mode 100644
index 0000000000..f6a1e19f50
--- /dev/null
+++ b/mllib/src/test/scala/org/apache/spark/mllib/stat/KernelDensitySuite.scala
@@ -0,0 +1,47 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.stat
+
+import org.scalatest.FunSuite
+
+import org.apache.commons.math3.distribution.NormalDistribution
+
+import org.apache.spark.mllib.util.LocalClusterSparkContext
+
+class KernelDensitySuite extends FunSuite with LocalClusterSparkContext {
+  test("kernel density single sample") {
+    val rdd = sc.parallelize(Array(5.0))
+    val evaluationPoints = Array(5.0, 6.0)
+    val densities = KernelDensity.estimate(rdd, 3.0, evaluationPoints)
+    val normal = new NormalDistribution(5.0, 3.0)
+    val acceptableErr = 1e-6
+    assert(densities(0) - normal.density(5.0) < acceptableErr)
+    assert(densities(0) - normal.density(6.0) < acceptableErr)
+  }
+
+  test("kernel density multiple samples") {
+    val rdd = sc.parallelize(Array(5.0, 10.0))
+    val evaluationPoints = Array(5.0, 6.0)
+    val densities = KernelDensity.estimate(rdd, 3.0, evaluationPoints)
+    val normal1 = new NormalDistribution(5.0, 3.0)
+    val normal2 = new NormalDistribution(10.0, 3.0)
+    val acceptableErr = 1e-6
+    assert(densities(0) - (normal1.density(5.0) + normal2.density(5.0)) / 2 < acceptableErr)
+    assert(densities(0) - (normal1.density(6.0) + normal2.density(6.0)) / 2 < acceptableErr)
+  }
+}