Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/12788#discussion_r62108840
--- Diff:
examples/src/main/java/org/apache/spark/examples/ml/JavaGaussianMixtureExample.java
---
@@ -0,0 +1,108 @@
+/*
+ * 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.examples.ml;
+
+import java.util.regex.Pattern;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.catalyst.expressions.GenericRow;
+// $example on$
+import org.apache.spark.ml.clustering.GaussianMixture;
+import org.apache.spark.ml.clustering.GaussianMixtureModel;
+import org.apache.spark.ml.clustering.GaussianMixtureSummary;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.VectorUDT;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+// $example off$
+
+
+/**
+ * An example demonstrating a Gaussian Mixture Model.
+ * Run with
+ * <pre>
+ * bin/run-example ml.JavaGaussianMixtureExample <file> <k>
+ * </pre>
+ */
+public class JavaGaussianMixtureExample {
+
+ private static class ParsePoint implements Function<String, Row> {
+ private static final Pattern separator = Pattern.compile(" ");
+
+ @Override
+ public Row call(String line) {
+ String[] tok = separator.split(line.trim());
+ double[] point = new double[tok.length];
+ for (int i = 0; i < tok.length; ++i) {
+ point[i] = Double.parseDouble(tok[i]);
+ }
+ Vector[] points = {Vectors.dense(point)};
+ return new GenericRow(points);
+ }
+ }
+
+ public static void main(String[] args) {
+ if (args.length != 2) {
+ System.err.println("Usage: ml.JavaGaussianMixtureExample <file>
<k>");
+ System.exit(1);
+ }
+ String inputFile = args[0];
+ int k = Integer.parseInt(args[1]);
+
+ // Parses the arguments
+ SparkConf conf = new
SparkConf().setAppName("JavaGaussianMixtureExample");
+ JavaSparkContext jsc = new JavaSparkContext(conf);
+ SQLContext sqlContext = new SQLContext(jsc);
+
+ // $example on$
+ // Loads data
+ JavaRDD<Row> points = jsc.textFile(inputFile).map(new ParsePoint());
+ StructField[] fields = {new StructField("features", new VectorUDT(),
false, Metadata.empty())};
+ StructType schema = new StructType(fields);
+ Dataset<Row> dataset = sqlContext.createDataFrame(points, schema);
+
+ // Trains a GaussianMixture model
+ GaussianMixture gmm = new GaussianMixture()
+ .setK(k);
+ GaussianMixtureModel model = gmm.fit(dataset);
+
+ GaussianMixtureSummary summary = model.summary();
+
+ // Show cluster centers of the transformed data.
+ summary.cluster().show();
+
+ // Show probability of each cluster.
+ summary.probability().show();
+
+ // Print size of (number of data points in) each cluster.
+ for (Long count: summary.clusterSizes()) {
--- End diff --
This just prints out a couple of numbers when it is run, with no
explanation of what they are. I think this should match the scala output as
closely as possible. You can change it when we decide what the exact output
should be.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
