diff options
author | Xusen Yin <yinxusen@gmail.com> | 2015-12-07 13:16:47 -0800 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2015-12-07 13:16:47 -0800 |
commit | 871e85d9c14c6b19068cc732951a8ae8db61b411 (patch) | |
tree | 43dab0f6f405c465ce604ba1a95c0a26ca7efe5d /examples | |
parent | 3f4efb5c23b029496b112760fa062ff070c20334 (diff) | |
download | spark-871e85d9c14c6b19068cc732951a8ae8db61b411.tar.gz spark-871e85d9c14c6b19068cc732951a8ae8db61b411.tar.bz2 spark-871e85d9c14c6b19068cc732951a8ae8db61b411.zip |
[SPARK-11963][DOC] Add docs for QuantileDiscretizer
https://issues.apache.org/jira/browse/SPARK-11963
Author: Xusen Yin <yinxusen@gmail.com>
Closes #9962 from yinxusen/SPARK-11963.
Diffstat (limited to 'examples')
-rw-r--r-- | examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java | 71 | ||||
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala | 49 |
2 files changed, 120 insertions, 0 deletions
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 new file mode 100644 index 0000000000..251ae79d9a --- /dev/null +++ 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 new file mode 100644 index 0000000000..8f29b7eaa6 --- /dev/null +++ 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 |