[SPARK-11963][DOC] Add docs for QuantileDiscretizer

https://issues.apache.org/jira/browse/SPARK-11963 Author: Xusen Yin <[email protected]> Closes apache#9962 from yinxusen/SPARK-11963.
markhamstra · Dec 7, 2015 · 871e85d · 871e85d
1 parent 3f4efb5
commit 871e85d
Show file tree

Hide file tree

Showing 3 changed files with 185 additions and 0 deletions.
diff --git a/docs/ml-features.md b/docs/ml-features.md
@@ -1705,6 +1705,71 @@ print(output.select("features", "clicked").first())
 </div>
 </div>
 
+## QuantileDiscretizer
+
+`QuantileDiscretizer` takes a column with continuous features and outputs a column with binned
+categorical features.
+The bin ranges are chosen by taking a sample of the data and dividing it into roughly equal parts.
+The lower and upper bin bounds will be `-Infinity` and `+Infinity`, covering all real values.
+This attempts to find `numBuckets` partitions based on a sample of the given input data, but it may
+find fewer depending on the data sample values.
+
+Note that the result may be different every time you run it, since the sample strategy behind it is
+non-deterministic.
+
+**Examples**
+
+Assume that we have a DataFrame with the columns `id`, `hour`:
+
+~~~
+ id | hour
+----|------
+ 0  | 18.0
+----|------
+ 1  | 19.0
+----|------
+ 2  | 8.0
+----|------
+ 3  | 5.0
+----|------
+ 4  | 2.2
+~~~
+
+`hour` is a continuous feature with `Double` type. We want to turn the continuous feature into
+categorical one. Given `numBuckets = 3`, we should get the following DataFrame:
+
+~~~
+ id | hour | result
+----|------|------
+ 0  | 18.0 | 2.0
+----|------|------
+ 1  | 19.0 | 2.0
+----|------|------
+ 2  | 8.0  | 1.0
+----|------|------
+ 3  | 5.0  | 1.0
+----|------|------
+ 4  | 2.2  | 0.0
+~~~
+
+<div class="codetabs">
+<div data-lang="scala" markdown="1">
+
+Refer to the [QuantileDiscretizer Scala docs](api/scala/index.html#org.apache.spark.ml.feature.QuantileDiscretizer)
+for more details on the API.
+
+{% include_example scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala %}
+</div>
+
+<div data-lang="java" markdown="1">
+
+Refer to the [QuantileDiscretizer Java docs](api/java/org/apache/spark/ml/feature/QuantileDiscretizer.html)
+for more details on the API.
+
+{% include_example java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java %}
+</div>
+</div>
+
 # Feature Selectors
 
 ## VectorSlicer

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java
@@ -0,0 +1,71 @@
+/*
+ * 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.examples.ml;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.SQLContext;
+// $example on$
+import java.util.Arrays;
+
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.ml.feature.QuantileDiscretizer;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.RowFactory;
+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;
+// $example off$
+
+public class JavaQuantileDiscretizerExample {
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaQuantileDiscretizerExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext sqlContext = new SQLContext(jsc);
+
+    // $example on$
+    JavaRDD<Row> jrdd = jsc.parallelize(
+      Arrays.asList(
+        RowFactory.create(0, 18.0),
+        RowFactory.create(1, 19.0),
+        RowFactory.create(2, 8.0),
+        RowFactory.create(3, 5.0),
+        RowFactory.create(4, 2.2)
+      )
+    );
+
+    StructType schema = new StructType(new StructField[]{
+      new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
+      new StructField("hour", DataTypes.DoubleType, false, Metadata.empty())
+    });
+
+    DataFrame df = sqlContext.createDataFrame(jrdd, schema);
+
+    QuantileDiscretizer discretizer = new QuantileDiscretizer()
+      .setInputCol("hour")
+      .setOutputCol("result")
+      .setNumBuckets(3);
+
+    DataFrame result = discretizer.fit(df).transform(df);
+    result.show();
+    // $example off$
+    jsc.stop();
+  }
+}
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala
@@ -0,0 +1,49 @@
+/*
+ * 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.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.ml
+
+// $example on$
+import org.apache.spark.ml.feature.QuantileDiscretizer
+// $example off$
+import org.apache.spark.sql.SQLContext
+import org.apache.spark.{SparkConf, SparkContext}
+
+object QuantileDiscretizerExample {
+  def main(args: Array[String]) {
+    val conf = new SparkConf().setAppName("QuantileDiscretizerExample")
+    val sc = new SparkContext(conf)
+    val sqlContext = new SQLContext(sc)
+    import sqlContext.implicits._
+
+    // $example on$
+    val data = Array((0, 18.0), (1, 19.0), (2, 8.0), (3, 5.0), (4, 2.2))
+    val df = sc.parallelize(data).toDF("id", "hour")
+
+    val discretizer = new QuantileDiscretizer()
+      .setInputCol("hour")
+      .setOutputCol("result")
+      .setNumBuckets(3)
+
+    val result = discretizer.fit(df).transform(df)
+    result.show()
+    // $example off$
+    sc.stop()
+  }
+}
+// scalastyle:on println