From 68fb2a46edc95f867d4b28597d20da2597f008c1 Mon Sep 17 00:00:00 2001
From: Xusen Yin <yinxusen@gmail.com>
Date: Tue, 19 May 2015 13:43:48 -0700
Subject: [SPARK-7586] [ML] [DOC] Add docs of Word2Vec in ml package

CC jkbradley.

JIRA [issue](https://issues.apache.org/jira/browse/SPARK-7586).

Author: Xusen Yin <yinxusen@gmail.com>

Closes #6181 from yinxusen/SPARK-7586 and squashes the following commits:

77014c5 [Xusen Yin] comment fix
57a4c07 [Xusen Yin] small fix for docs
1178c8f [Xusen Yin] remove the correctness check in java suite
1c3f389 [Xusen Yin] delete sbt commit
1af152b [Xusen Yin] check python example code
1b5369e [Xusen Yin] add docs of word2vec
---
 .../apache/spark/ml/feature/JavaWord2VecSuite.java | 76 ++++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 mllib/src/test/java/org/apache/spark/ml/feature/JavaWord2VecSuite.java

(limited to 'mllib/src')

diff --git a/mllib/src/test/java/org/apache/spark/ml/feature/JavaWord2VecSuite.java b/mllib/src/test/java/org/apache/spark/ml/feature/JavaWord2VecSuite.java
new file mode 100644
index 0000000000..39c70157f8
--- /dev/null
+++ b/mllib/src/test/java/org/apache/spark/ml/feature/JavaWord2VecSuite.java
@@ -0,0 +1,76 @@
+/*
+ * 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 com.google.common.collect.Lists;
+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.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.*;
+
+public class JavaWord2VecSuite {
+  private transient JavaSparkContext jsc;
+  private transient SQLContext sqlContext;
+
+  @Before
+  public void setUp() {
+    jsc = new JavaSparkContext("local", "JavaWord2VecSuite");
+    sqlContext = new SQLContext(jsc);
+  }
+
+  @After
+  public void tearDown() {
+    jsc.stop();
+    jsc = null;
+  }
+
+  @Test
+  public void testJavaWord2Vec() {
+    JavaRDD<Row> jrdd = jsc.parallelize(Lists.newArrayList(
+      RowFactory.create(Lists.newArrayList("Hi I heard about Spark".split(" "))),
+      RowFactory.create(Lists.newArrayList("I wish Java could use case classes".split(" "))),
+      RowFactory.create(Lists.newArrayList("Logistic regression models are neat".split(" ")))
+    ));
+    StructType schema = new StructType(new StructField[]{
+      new StructField("text", new ArrayType(DataTypes.StringType, true), false, Metadata.empty())
+    });
+    DataFrame documentDF = sqlContext.createDataFrame(jrdd, schema);
+
+    Word2Vec word2Vec = new Word2Vec()
+      .setInputCol("text")
+      .setOutputCol("result")
+      .setVectorSize(3)
+      .setMinCount(0);
+    Word2VecModel model = word2Vec.fit(documentDF);
+    DataFrame result = model.transform(documentDF);
+
+    for (Row r: result.select("result").collect()) {
+      double[] polyFeatures = ((Vector)r.get(0)).toArray();
+      Assert.assertEquals(polyFeatures.length, 3);
+    }
+  }
+}
-- 
cgit v1.2.3