Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/3022#discussion_r21655817
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/GMMExpectationMaximization.scala
---
@@ -0,0 +1,283 @@
+/*
+ * 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.clustering
+
+import breeze.linalg.{DenseVector => BreezeVector, DenseMatrix =>
BreezeMatrix}
+import breeze.linalg.{Transpose, det, inv}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.mllib.linalg.{Matrices, Vector, Vectors}
+import org.apache.spark.{Accumulator, AccumulatorParam, SparkContext}
+import org.apache.spark.SparkContext.DoubleAccumulatorParam
+
+/**
+ * Expectation-Maximization for multivariate Gaussian Mixture Models.
+ *
+ */
+object GMMExpectationMaximization {
+ /**
+ * Trains a GMM using the given parameters
+ *
+ * @param data training points stored as RDD[Vector]
+ * @param k the number of Gaussians in the mixture
+ * @param maxIterations the maximum number of iterations to perform
+ * @param delta change in log-likelihood at which convergence is
considered achieved
+ */
+ def train(data: RDD[Vector], k: Int, maxIterations: Int, delta: Double):
GaussianMixtureModel = {
+ new GMMExpectationMaximization().setK(k)
+ .setMaxIterations(maxIterations)
+ .setDelta(delta)
+ .run(data)
+ }
+
+ /**
+ * Trains a GMM using the given parameters
+ *
+ * @param data training points stored as RDD[Vector]
+ * @param k the number of Gaussians in the mixture
+ * @param maxIterations the maximum number of iterations to perform
+ */
+ def train(data: RDD[Vector], k: Int, maxIterations: Int):
GaussianMixtureModel = {
+ new
GMMExpectationMaximization().setK(k).setMaxIterations(maxIterations).run(data)
+ }
+
+ /**
+ * Trains a GMM using the given parameters
+ *
+ * @param data training points stored as RDD[Vector]
+ * @param k the number of Gaussians in the mixture
+ * @param delta change in log-likelihood at which convergence is
considered achieved
+ */
+ def train(data: RDD[Vector], k: Int, delta: Double):
GaussianMixtureModel = {
+ new GMMExpectationMaximization().setK(k).setDelta(delta).run(data)
+ }
+
+ /**
+ * Trains a GMM using the given parameters
+ *
+ * @param data training points stored as RDD[Vector]
+ * @param k the number of Gaussians in the mixture
+ */
+ def train(data: RDD[Vector], k: Int): GaussianMixtureModel = {
+ new GMMExpectationMaximization().setK(k).run(data)
+ }
+}
+
+/**
+ * This class performs multivariate Gaussian expectation maximization. It
will
+ * maximize the log-likelihood for a mixture of k Gaussians, iterating
until
+ * the log-likelihood changes by less than delta, or until it has reached
+ * the max number of iterations.
+ */
+class GMMExpectationMaximization private (
+ private var k: Int,
+ private var delta: Double,
+ private var maxIterations: Int) extends Serializable {
+
+ // Type aliases for convenience
+ private type DenseDoubleVector = BreezeVector[Double]
+ private type DenseDoubleMatrix = BreezeMatrix[Double]
+
+ // number of samples per cluster to use when initializing Gaussians
+ private val nSamples = 5;
+
+ // A default instance, 2 Gaussians, 100 iterations, 0.01 log-likelihood
threshold
--- End diff --
Use "/** ... */" for comment so it is part of the generated documentation.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
