[SPARK-7584] [MLLIB] User guide for VectorAssembler

This PR adds a section in the user guide for `VectorAssembler` with code examples in Python/Java/Scala. It also adds a unit test in Java.

jkbradley

Author: Xiangrui Meng <meng@databricks.com>

Closes #6556 from mengxr/SPARK-7584 and squashes the following commits:

11313f6 [Xiangrui Meng] simplify Java example
0cd47f3 [Xiangrui Meng] update user guide
fd36292 [Xiangrui Meng] update Java unit test
ce61ca0 [Xiangrui Meng] add Java unit test for VectorAssembler
e399942 [Xiangrui Meng] scala/python example code

1 files changed, 78 insertions, 0 deletions

diff --git a/mllib/src/test/java/org/apache/spark/ml/feature/JavaVectorAssemblerSuite.java b/mllib/src/test/java/org/apache/spark/ml/feature/JavaVectorAssemblerSuite.java
new file mode 100644
index 0000000000..b7c564caad
--- /dev/null
+++ b/mllib/src/test/java/org/apache/spark/ml/feature/JavaVectorAssemblerSuite.java
@@ -0,0 +1,78 @@
+/*
+ * 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.ml.feature;
+
+import java.util.Arrays;
+
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+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.RowFactory;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.types.*;
+import static org.apache.spark.sql.types.DataTypes.*;
+
+public class JavaVectorAssemblerSuite {
+  private transient JavaSparkContext jsc;
+  private transient SQLContext sqlContext;
+
+  @Before
+  public void setUp() {
+    jsc = new JavaSparkContext("local", "JavaVectorAssemblerSuite");
+    sqlContext = new SQLContext(jsc);
+  }
+
+  @After
+  public void tearDown() {
+    jsc.stop();
+    jsc = null;
+  }
+
+  @Test
+  public void testVectorAssembler() {
+    StructType schema = createStructType(new StructField[] {
+      createStructField("id", IntegerType, false),
+      createStructField("x", DoubleType, false),
+      createStructField("y", new VectorUDT(), false),
+      createStructField("name", StringType, false),
+      createStructField("z", new VectorUDT(), false),
+      createStructField("n", LongType, false)
+    });
+    Row row = RowFactory.create(
+      0, 0.0, Vectors.dense(1.0, 2.0), "a",
+      Vectors.sparse(2, new int[] {1}, new double[] {3.0}), 10L);
+    JavaRDD<Row> rdd = jsc.parallelize(Arrays.asList(row));
+    DataFrame dataset = sqlContext.createDataFrame(rdd, schema);
+    VectorAssembler assembler = new VectorAssembler()
+      .setInputCols(new String[] {"x", "y", "z", "n"})
+      .setOutputCol("features");
+    DataFrame output = assembler.transform(dataset);
+    Assert.assertEquals(
+      Vectors.sparse(6, new int[] {1, 2, 4, 5}, new double[] {1.0, 2.0, 3.0, 10.0}),
+      output.select("features").first().<Vector>getAs(0));
+  }
+}