add @experimental to Word2VecModel

add a Java-friendly method to Word2Vec.fit with tests

mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala

@@ -17,6 +17,9 @@
 
 package org.apache.spark.mllib.feature
 
+import java.lang.{Iterable => JavaIterable}
+
+import scala.collection.JavaConverters._
 import scala.collection.mutable
 import scala.collection.mutable.ArrayBuffer
 
@@ -25,6 +28,7 @@ import com.github.fommil.netlib.BLAS.{getInstance => blas}
 import org.apache.spark.Logging
 import org.apache.spark.SparkContext._
 import org.apache.spark.annotation.Experimental
+import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg.{Vector, Vectors}
 import org.apache.spark.mllib.rdd.RDDFunctions._
 import org.apache.spark.rdd._
@@ -239,7 +243,7 @@ class Word2Vec extends Serializable with Logging {
       a += 1
     }
   }
-  
+
   /**
    * Computes the vector representation of each word in vocabulary.
    * @param dataset an RDD of words
@@ -369,11 +373,22 @@ class Word2Vec extends Serializable with Logging {
 
     new Word2VecModel(word2VecMap.toMap)
   }
+
+  /**
+   * Computes the vector representation of each word in vocabulary (Java version).
+   * @param dataset a JavaRDD of words
+   * @return a Word2VecModel
+   */
+  def fit[S <: JavaIterable[String]](dataset: JavaRDD[S]): Word2VecModel = {
+    fit(dataset.rdd.map(_.asScala))
+  }
 }
 
 /**
-* Word2Vec model
+ * :: Experimental ::
+ * Word2Vec model
  */
+@Experimental
 class Word2VecModel private[mllib] (
     private val model: Map[String, Array[Float]]) extends Serializable {
 

mllib/src/test/java/org/apache/spark/mllib/feature/JavaWord2VecSuite.java

@@ -0,0 +1,66 @@
+/*
+ * 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.feature;
+
+import java.io.Serializable;
+import java.util.List;
+
+import scala.Tuple2;
+
+import com.google.common.collect.Lists;
+import com.google.common.base.Strings;
+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;
+
+public class JavaWord2VecSuite implements Serializable {
+  private transient JavaSparkContext sc;
+
+  @Before
+  public void setUp() {
+    sc = new JavaSparkContext("local", "JavaWord2VecSuite");
+  }
+
+  @After
+  public void tearDown() {
+    sc.stop();
+    sc = null;
+  }
+
+  @Test
+  @SuppressWarnings("unchecked")
+  public void word2Vec() {
+    // The tests are to check Java compatibility.
+    String sentence = Strings.repeat("a b ", 100) + Strings.repeat("a c ", 10);
+    List<String> words = Lists.newArrayList(sentence.split(" "));
+    List<List<String>> localDoc = Lists.newArrayList(words, words);
+    JavaRDD<List<String>> doc = sc.parallelize(localDoc);
+    Word2Vec word2vec = new Word2Vec()
+      .setVectorSize(10)
+      .setSeed(42L);
+    Word2VecModel model = word2vec.fit(doc);
+    Tuple2<String, Object>[] syms = model.findSynonyms("a", 2);
+    Assert.assertEquals(2, syms.length);
+    Assert.assertEquals("b", syms[0]._1());
+    Assert.assertEquals("c", syms[1]._1());
+  }
+}