[SPARK-2511][MLLIB] add HashingTF and IDF

This is roughly the TF-IDF implementation used in the Databricks Cloud Demo: http://databricks.com/cloud/ .

Both `HashingTF` and `IDF` are implemented as transformers, similar to scikit-learn.

Author: Xiangrui Meng <meng@databricks.com>

Closes #1671 from mengxr/tfidf and squashes the following commits:

7d65888 [Xiangrui Meng] use JavaConverters._
5fe9ec4 [Xiangrui Meng] fix unit test
6e214ec [Xiangrui Meng] add apache header
cfd9aed [Xiangrui Meng] add Java-friendly methods move classes to mllib.feature
3814440 [Xiangrui Meng] add HashingTF and IDF

1 files changed, 66 insertions, 0 deletions

diff --git a/mllib/src/test/java/org/apache/spark/mllib/feature/JavaTfIdfSuite.java b/mllib/src/test/java/org/apache/spark/mllib/feature/JavaTfIdfSuite.java
new file mode 100644
index 0000000000..e8d99f4ae4
--- /dev/null
+++ b/mllib/src/test/java/org/apache/spark/mllib/feature/JavaTfIdfSuite.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.ArrayList;
+import java.util.List;
+
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+import com.google.common.collect.Lists;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.mllib.linalg.Vector;
+
+public class JavaTfIdfSuite implements Serializable {
+  private transient JavaSparkContext sc;
+
+  @Before
+  public void setUp() {
+    sc = new JavaSparkContext("local", "JavaTfIdfSuite");
+  }
+
+  @After
+  public void tearDown() {
+    sc.stop();
+    sc = null;
+  }
+
+  @Test
+  public void tfIdf() {
+    // The tests are to check Java compatibility.
+    HashingTF tf = new HashingTF();
+    JavaRDD<ArrayList<String>> documents = sc.parallelize(Lists.newArrayList(
+      Lists.newArrayList("this is a sentence".split(" ")),
+      Lists.newArrayList("this is another sentence".split(" ")),
+      Lists.newArrayList("this is still a sentence".split(" "))), 2);
+    JavaRDD<Vector> termFreqs = tf.transform(documents);
+    termFreqs.collect();
+    IDF idf = new IDF();
+    JavaRDD<Vector> tfIdfs = idf.fit(termFreqs).transform(termFreqs);
+    List<Vector> localTfIdfs = tfIdfs.collect();
+    int indexOfThis = tf.indexOf("this");
+    for (Vector v: localTfIdfs) {
+      Assert.assertEquals(0.0, v.apply(indexOfThis), 1e-15);
+    }
+  }
+}