-
Notifications
You must be signed in to change notification settings - Fork 28.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-12159][ML] Add user guide section for IndexToString transformer
Documentation regarding the `IndexToString` label transformer with code snippets in Scala/Java/Python. Author: BenFradet <[email protected]> Closes #10166 from BenFradet/SPARK-12159. (cherry picked from commit 06746b3) Signed-off-by: Joseph K. Bradley <[email protected]>
- Loading branch information
Showing
4 changed files
with
268 additions
and
16 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
75 changes: 75 additions & 0 deletions
75
examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| /* | ||
| * 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.JavaRDD; | ||
| import org.apache.spark.api.java.JavaSparkContext; | ||
| import org.apache.spark.sql.SQLContext; | ||
|
|
||
| // $example on$ | ||
| import java.util.Arrays; | ||
|
|
||
| import org.apache.spark.ml.feature.IndexToString; | ||
| import org.apache.spark.ml.feature.StringIndexer; | ||
| import org.apache.spark.ml.feature.StringIndexerModel; | ||
| 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 JavaIndexToStringExample { | ||
| public static void main(String[] args) { | ||
| SparkConf conf = new SparkConf().setAppName("JavaIndexToStringExample"); | ||
| JavaSparkContext jsc = new JavaSparkContext(conf); | ||
| SQLContext sqlContext = new SQLContext(jsc); | ||
|
|
||
| // $example on$ | ||
| JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList( | ||
| RowFactory.create(0, "a"), | ||
| RowFactory.create(1, "b"), | ||
| RowFactory.create(2, "c"), | ||
| RowFactory.create(3, "a"), | ||
| RowFactory.create(4, "a"), | ||
| RowFactory.create(5, "c") | ||
| )); | ||
| StructType schema = new StructType(new StructField[]{ | ||
| new StructField("id", DataTypes.IntegerType, false, Metadata.empty()), | ||
| new StructField("category", DataTypes.StringType, false, Metadata.empty()) | ||
| }); | ||
| DataFrame df = sqlContext.createDataFrame(jrdd, schema); | ||
|
|
||
| StringIndexerModel indexer = new StringIndexer() | ||
| .setInputCol("category") | ||
| .setOutputCol("categoryIndex") | ||
| .fit(df); | ||
| DataFrame indexed = indexer.transform(df); | ||
|
|
||
| IndexToString converter = new IndexToString() | ||
| .setInputCol("categoryIndex") | ||
| .setOutputCol("originalCategory"); | ||
| DataFrame converted = converter.transform(indexed); | ||
| converted.select("id", "originalCategory").show(); | ||
| // $example off$ | ||
| jsc.stop(); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,45 @@ | ||
| # | ||
| # 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. | ||
| # | ||
|
|
||
| from __future__ import print_function | ||
|
|
||
| from pyspark import SparkContext | ||
| # $example on$ | ||
| from pyspark.ml.feature import IndexToString, StringIndexer | ||
| # $example off$ | ||
| from pyspark.sql import SQLContext | ||
|
|
||
| if __name__ == "__main__": | ||
| sc = SparkContext(appName="IndexToStringExample") | ||
| sqlContext = SQLContext(sc) | ||
|
|
||
| # $example on$ | ||
| df = sqlContext.createDataFrame( | ||
| [(0, "a"), (1, "b"), (2, "c"), (3, "a"), (4, "a"), (5, "c")], | ||
| ["id", "category"]) | ||
|
|
||
| stringIndexer = StringIndexer(inputCol="category", outputCol="categoryIndex") | ||
| model = stringIndexer.fit(df) | ||
| indexed = model.transform(df) | ||
|
|
||
| converter = IndexToString(inputCol="categoryIndex", outputCol="originalCategory") | ||
| converted = converter.transform(indexed) | ||
|
|
||
| converted.select("id", "originalCategory").show() | ||
| # $example off$ | ||
|
|
||
| sc.stop() |
60 changes: 60 additions & 0 deletions
60
examples/src/main/scala/org/apache/spark/examples/ml/IndexToStringExample.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| /* | ||
| * 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 | ||
|
|
||
| import org.apache.spark.sql.SQLContext | ||
| import org.apache.spark.{SparkConf, SparkContext} | ||
| // $example on$ | ||
| import org.apache.spark.ml.feature.{StringIndexer, IndexToString} | ||
| // $example off$ | ||
|
|
||
| object IndexToStringExample { | ||
| def main(args: Array[String]) { | ||
| val conf = new SparkConf().setAppName("IndexToStringExample") | ||
| val sc = new SparkContext(conf) | ||
|
|
||
| val sqlContext = SQLContext.getOrCreate(sc) | ||
|
|
||
| // $example on$ | ||
| val df = sqlContext.createDataFrame(Seq( | ||
| (0, "a"), | ||
| (1, "b"), | ||
| (2, "c"), | ||
| (3, "a"), | ||
| (4, "a"), | ||
| (5, "c") | ||
| )).toDF("id", "category") | ||
|
|
||
| val indexer = new StringIndexer() | ||
| .setInputCol("category") | ||
| .setOutputCol("categoryIndex") | ||
| .fit(df) | ||
| val indexed = indexer.transform(df) | ||
|
|
||
| val converter = new IndexToString() | ||
| .setInputCol("categoryIndex") | ||
| .setOutputCol("originalCategory") | ||
|
|
||
| val converted = converter.transform(indexed) | ||
| converted.select("id", "originalCategory").show() | ||
| // $example off$ | ||
| sc.stop() | ||
| } | ||
| } | ||
| // scalastyle:on println |