[SPARK-7577] [ML] [DOC] add bucketizer doc

CC jkbradley

Author: Xusen Yin <yinxusen@gmail.com>

Closes #6451 from yinxusen/SPARK-7577 and squashes the following commits:

e2dc32e [Xusen Yin] rename colums
e350e49 [Xusen Yin] add all demos
006ddf1 [Xusen Yin] add java test
3238481 [Xusen Yin] add bucketizer

1 files changed, 80 insertions, 0 deletions

diff --git a/mllib/src/test/java/org/apache/spark/ml/feature/JavaBucketizerSuite.java b/mllib/src/test/java/org/apache/spark/ml/feature/JavaBucketizerSuite.java
new file mode 100644
index 0000000000..d5bd230a95
--- /dev/null
+++ b/mllib/src/test/java/org/apache/spark/ml/feature/JavaBucketizerSuite.java
@@ -0,0 +1,80 @@
+/*
+ * 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.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.DataTypes;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+
+public class JavaBucketizerSuite {
+  private transient JavaSparkContext jsc;
+  private transient SQLContext jsql;
+
+  @Before
+  public void setUp() {
+    jsc = new JavaSparkContext("local", "JavaBucketizerSuite");
+    jsql = new SQLContext(jsc);
+  }
+
+  @After
+  public void tearDown() {
+    jsc.stop();
+    jsc = null;
+  }
+
+  @Test
+  public void bucketizerTest() {
+    double[] splits = {-0.5, 0.0, 0.5};
+
+    JavaRDD<Row> data = jsc.parallelize(Lists.newArrayList(
+      RowFactory.create(-0.5),
+      RowFactory.create(-0.3),
+      RowFactory.create(0.0),
+      RowFactory.create(0.2)
+    ));
+    StructType schema = new StructType(new StructField[] {
+      new StructField("feature", DataTypes.DoubleType, false, Metadata.empty())
+    });
+    DataFrame dataset = jsql.createDataFrame(data, schema);
+
+    Bucketizer bucketizer = new Bucketizer()
+      .setInputCol("feature")
+      .setOutputCol("result")
+      .setSplits(splits);
+
+    Row[] result = bucketizer.transform(dataset).select("result").collect();
+
+    for (Row r : result) {
+      double index = r.getDouble(0);
+      Assert.assertTrue((index >= 0) && (index <= 1));
+    }
+  }
+}