[SPARK-9149] [ML] [EXAMPLES] Add an example of spark.ml KMeans

[SPARK-9149] Add an example of spark.ml KMeans - ASF JIRA https://issues.apache.org/jira/browse/SPARK-9149

jkbradley Should we support other data formats, such as TSV or CSV. I have implemented these examples which support only space separated file which is same as the example for `spark.mllib`'s `KMeans`.

Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>

Closes #7697 from yu-iskw/SPARK-9149 and squashes the following commits:

7137bad [Yu ISHIKAWA] Fix the typo
56b9da2 [Yu ISHIKAWA] Fix the place of the wrong import statment
554e574 [Yu ISHIKAWA] Change the way to format input data in KMeansExample
e7a948a [Yu ISHIKAWA] Import spark.ml.clustering.KMeans
1901e0c [Yu ISHIKAWA] Change how to initialize an array for a DataFrame schema
d8043f5 [Yu ISHIKAWA] Return a value directly
d81bf55 [Yu ISHIKAWA] Fix a typo and its access specifiers
3e0862d [Yu ISHIKAWA] Make KMeansExample more simple
51ce9c1 [Yu ISHIKAWA] Make JavaKMeansExample more simple
a5a01e0 [Yu ISHIKAWA] Fix a Javadoc about the command to execute the example
b09ec13 [Yu ISHIKAWA] [SPARK-9149][ML][Examples] Add an example of spark.ml KMeans

3 files changed, 241 insertions, 0 deletions

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java
new file mode 100644
index 0000000000..be2bf0c7b4
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java
@@ -0,0 +1,97 @@
+/*
+ * 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.ml.clustering.KMeansModel;
+import org.apache.spark.ml.clustering.KMeans;
+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.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.catalyst.expressions.GenericRow;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+
+
+/**
+ * An example demonstrating a k-means clustering.
+ * Run with
+ * <pre>
+ * bin/run-example ml.JavaSimpleParamsExample <file> <k>
+ * </pre>
+ */
+public class JavaKMeansExample {
+
+  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);
+      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.JavaKMeansExample <file> <k>");
+      System.exit(1);
+    }
+    String inputFile = args[0];
+    int k = Integer.parseInt(args[1]);
+
+    // Parses the arguments
+    SparkConf conf = new SparkConf().setAppName("JavaKMeansExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext sqlContext = new SQLContext(jsc);
+
+    // 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);
+    DataFrame dataset = sqlContext.createDataFrame(points, schema);
+
+    // Trains a k-means model
+    KMeans kmeans = new KMeans()
+      .setK(k);
+    KMeansModel model = kmeans.fit(dataset);
+
+    // Shows the result
+    Vector[] centers = model.clusterCenters();
+    System.out.println("Cluster Centers: ");
+    for (Vector center: centers) {
+      System.out.println(center);
+    }
+
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/python/ml/kmeans_example.py b/examples/src/main/python/ml/kmeans_example.py
new file mode 100644
index 0000000000..150dadd42f
--- /dev/null
+++ b/examples/src/main/python/ml/kmeans_example.py
@@ -0,0 +1,71 @@
+#
+# 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.
+#
+
+from __future__ import print_function
+
+import sys
+import re
+
+import numpy as np
+from pyspark import SparkContext
+from pyspark.ml.clustering import KMeans, KMeansModel
+from pyspark.mllib.linalg import VectorUDT, _convert_to_vector
+from pyspark.sql import SQLContext
+from pyspark.sql.types import Row, StructField, StructType
+
+"""
+A simple example demonstrating a k-means clustering.
+Run with:
+  bin/spark-submit examples/src/main/python/ml/kmeans_example.py <input> <k>
+
+This example requires NumPy (http://www.numpy.org/).
+"""
+
+
+def parseVector(line):
+    array = np.array([float(x) for x in line.split(' ')])
+    return _convert_to_vector(array)
+
+
+if __name__ == "__main__":
+
+    FEATURES_COL = "features"
+
+    if len(sys.argv) != 3:
+        print("Usage: kmeans_example.py <file> <k>", file=sys.stderr)
+        exit(-1)
+    path = sys.argv[1]
+    k = sys.argv[2]
+
+    sc = SparkContext(appName="PythonKMeansExample")
+    sqlContext = SQLContext(sc)
+
+    lines = sc.textFile(path)
+    data = lines.map(parseVector)
+    row_rdd = data.map(lambda x: Row(x))
+    schema = StructType([StructField(FEATURES_COL, VectorUDT(), False)])
+    df = sqlContext.createDataFrame(row_rdd, schema)
+
+    kmeans = KMeans().setK(2).setSeed(1).setFeaturesCol(FEATURES_COL)
+    model = kmeans.fit(df)
+    centers = model.clusterCenters()
+
+    print("Cluster Centers: ")
+    for center in centers:
+        print(center)
+
+    sc.stop()
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala
new file mode 100644
index 0000000000..5ce38462d1
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/KMeansExample.scala
@@ -0,0 +1,73 @@
+/*
+ * 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 org.apache.spark.{SparkContext, SparkConf}
+import org.apache.spark.mllib.linalg.{VectorUDT, Vectors}
+import org.apache.spark.ml.clustering.KMeans
+import org.apache.spark.sql.{Row, SQLContext}
+import org.apache.spark.sql.types.{StructField, StructType}
+
+
+/**
+ * An example demonstrating a k-means clustering.
+ * Run with
+ * {{{
+ * bin/run-example ml.KMeansExample <file> <k>
+ * }}}
+ */
+object KMeansExample {
+
+  final val FEATURES_COL = "features"
+
+  def main(args: Array[String]): Unit = {
+    if (args.length != 2) {
+      // scalastyle:off println
+      System.err.println("Usage: ml.KMeansExample <file> <k>")
+      // scalastyle:on println
+      System.exit(1)
+    }
+    val input = args(0)
+    val k = args(1).toInt
+
+    // Creates a Spark context and a SQL context
+    val conf = new SparkConf().setAppName(s"${this.getClass.getSimpleName}")
+    val sc = new SparkContext(conf)
+    val sqlContext = new SQLContext(sc)
+
+    // Loads data
+    val rowRDD = sc.textFile(input).filter(_.nonEmpty)
+      .map(_.split(" ").map(_.toDouble)).map(Vectors.dense).map(Row(_))
+    val schema = StructType(Array(StructField(FEATURES_COL, new VectorUDT, false)))
+    val dataset = sqlContext.createDataFrame(rowRDD, schema)
+
+    // Trains a k-means model
+    val kmeans = new KMeans()
+      .setK(k)
+      .setFeaturesCol(FEATURES_COL)
+    val model = kmeans.fit(dataset)
+
+    // Shows the result
+    // scalastyle:off println
+    println("Final Centers: ")
+    model.clusterCenters.foreach(println)
+    // scalastyle:on println
+
+    sc.stop()
+  }
+}