diff options
Diffstat (limited to 'examples/src')
6 files changed, 203 insertions, 14 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaIsotonicRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaIsotonicRegressionExample.java new file mode 100644 index 0000000000..0ec17b0471 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaIsotonicRegressionExample.java @@ -0,0 +1,62 @@ +/* + * 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; + +// $example on$ + +import org.apache.spark.ml.regression.IsotonicRegression; +import org.apache.spark.ml.regression.IsotonicRegressionModel; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +// $example off$ +import org.apache.spark.sql.SparkSession; + +/** + * An example demonstrating IsotonicRegression. + * Run with + * <pre> + * bin/run-example ml.JavaIsotonicRegressionExample + * </pre> + */ +public class JavaIsotonicRegressionExample { + + public static void main(String[] args) { + // Create a SparkSession. + SparkSession spark = SparkSession + .builder() + .appName("JavaIsotonicRegressionExample") + .getOrCreate(); + + // $example on$ + // Loads data. + Dataset<Row> dataset = spark.read().format("libsvm") + .load("data/mllib/sample_isotonic_regression_libsvm_data.txt"); + + // Trains an isotonic regression model. + IsotonicRegression ir = new IsotonicRegression(); + IsotonicRegressionModel model = ir.fit(dataset); + + System.out.println("Boundaries in increasing order: " + model.boundaries()); + System.out.println("Predictions associated with the boundaries: " + model.predictions()); + + // Makes predictions. + model.transform(dataset).show(); + // $example off$ + + spark.stop(); + } +} diff --git a/examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java index c6361a3729..a30b5f1f73 100644 --- a/examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java +++ b/examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java @@ -17,6 +17,7 @@ package org.apache.spark.examples.mllib; // $example on$ + import scala.Tuple2; import scala.Tuple3; import org.apache.spark.api.java.function.Function; @@ -27,6 +28,8 @@ import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.JavaRDD; import org.apache.spark.mllib.regression.IsotonicRegression; import org.apache.spark.mllib.regression.IsotonicRegressionModel; +import org.apache.spark.mllib.regression.LabeledPoint; +import org.apache.spark.mllib.util.MLUtils; // $example off$ import org.apache.spark.SparkConf; @@ -35,27 +38,29 @@ public class JavaIsotonicRegressionExample { SparkConf sparkConf = new SparkConf().setAppName("JavaIsotonicRegressionExample"); JavaSparkContext jsc = new JavaSparkContext(sparkConf); // $example on$ - JavaRDD<String> data = jsc.textFile("data/mllib/sample_isotonic_regression_data.txt"); + JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile( + jsc.sc(), "data/mllib/sample_isotonic_regression_libsvm_data.txt").toJavaRDD(); // Create label, feature, weight tuples from input data with weight set to default value 1.0. JavaRDD<Tuple3<Double, Double, Double>> parsedData = data.map( - new Function<String, Tuple3<Double, Double, Double>>() { - public Tuple3<Double, Double, Double> call(String line) { - String[] parts = line.split(","); - return new Tuple3<>(new Double(parts[0]), new Double(parts[1]), 1.0); + new Function<LabeledPoint, Tuple3<Double, Double, Double>>() { + public Tuple3<Double, Double, Double> call(LabeledPoint point) { + return new Tuple3<>(new Double(point.label()), + new Double(point.features().apply(0)), 1.0); } } ); // Split data into training (60%) and test (40%) sets. JavaRDD<Tuple3<Double, Double, Double>>[] splits = - parsedData.randomSplit(new double[]{0.6, 0.4}, 11L); + parsedData.randomSplit(new double[]{0.6, 0.4}, 11L); JavaRDD<Tuple3<Double, Double, Double>> training = splits[0]; JavaRDD<Tuple3<Double, Double, Double>> test = splits[1]; // Create isotonic regression model from training data. // Isotonic parameter defaults to true so it is only shown for demonstration - final IsotonicRegressionModel model = new IsotonicRegression().setIsotonic(true).run(training); + final IsotonicRegressionModel model = + new IsotonicRegression().setIsotonic(true).run(training); // Create tuples of predicted and real labels. JavaPairRDD<Double, Double> predictionAndLabel = test.mapToPair( diff --git a/examples/src/main/python/ml/isotonic_regression_example.py b/examples/src/main/python/ml/isotonic_regression_example.py new file mode 100644 index 0000000000..1e61bd8eff --- /dev/null +++ b/examples/src/main/python/ml/isotonic_regression_example.py @@ -0,0 +1,54 @@ +# +# 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. +# + +""" +Isotonic Regression Example. +""" +from __future__ import print_function + +# $example on$ +from pyspark.ml.regression import IsotonicRegression, IsotonicRegressionModel +# $example off$ +from pyspark.sql import SparkSession + +""" +An example demonstrating isotonic regression. +Run with: + bin/spark-submit examples/src/main/python/ml/isotonic_regression_example.py +""" +if __name__ == "__main__": + + spark = SparkSession\ + .builder\ + .appName("PythonIsotonicRegressionExample")\ + .getOrCreate() + + # $example on$ + # Loads data. + dataset = spark.read.format("libsvm")\ + .load("data/mllib/sample_isotonic_regression_libsvm_data.txt") + + # Trains an isotonic regression model. + model = IsotonicRegression().fit(dataset) + print("Boundaries in increasing order: " + str(model.boundaries)) + print("Predictions associated with the boundaries: " + str(model.predictions)) + + # Makes predictions. + model.transform(dataset).show() + # $example off$ + + spark.stop() diff --git a/examples/src/main/python/mllib/isotonic_regression_example.py b/examples/src/main/python/mllib/isotonic_regression_example.py index 89dc9f4b66..33d618ab48 100644 --- a/examples/src/main/python/mllib/isotonic_regression_example.py +++ b/examples/src/main/python/mllib/isotonic_regression_example.py @@ -23,7 +23,8 @@ from __future__ import print_function from pyspark import SparkContext # $example on$ import math -from pyspark.mllib.regression import IsotonicRegression, IsotonicRegressionModel +from pyspark.mllib.regression import LabeledPoint, IsotonicRegression, IsotonicRegressionModel +from pyspark.mllib.util import MLUtils # $example off$ if __name__ == "__main__": @@ -31,10 +32,14 @@ if __name__ == "__main__": sc = SparkContext(appName="PythonIsotonicRegressionExample") # $example on$ - data = sc.textFile("data/mllib/sample_isotonic_regression_data.txt") + # Load and parse the data + def parsePoint(labeledData): + return (labeledData.label, labeledData.features[0], 1.0) + + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_isotonic_regression_libsvm_data.txt") # Create label, feature, weight tuples from input data with weight set to default value 1.0. - parsedData = data.map(lambda line: tuple([float(x) for x in line.split(',')]) + (1.0,)) + parsedData = data.map(parsePoint) # Split data into training (60%) and test (40%) sets. training, test = parsedData.randomSplit([0.6, 0.4], 11) diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/IsotonicRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/IsotonicRegressionExample.scala new file mode 100644 index 0000000000..7c5d3f2341 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/IsotonicRegressionExample.scala @@ -0,0 +1,62 @@ +/* + * 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.regression.IsotonicRegression +// $example off$ +import org.apache.spark.sql.SparkSession + +/** + * An example demonstrating Isotonic Regression. + * Run with + * {{{ + * bin/run-example ml.IsotonicRegressionExample + * }}} + */ +object IsotonicRegressionExample { + + def main(args: Array[String]): Unit = { + + // Creates a SparkSession. + val spark = SparkSession + .builder + .appName(s"${this.getClass.getSimpleName}") + .getOrCreate() + + // $example on$ + // Loads data. + val dataset = spark.read.format("libsvm") + .load("data/mllib/sample_isotonic_regression_libsvm_data.txt") + + // Trains an isotonic regression model. + val ir = new IsotonicRegression() + val model = ir.fit(dataset) + + println(s"Boundaries in increasing order: ${model.boundaries}") + println(s"Predictions associated with the boundaries: ${model.predictions}") + + // Makes predictions. + model.transform(dataset).show() + // $example off$ + + spark.stop() + } +} +// scalastyle:on println diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala index c4336639d7..e5dea129c1 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala @@ -21,6 +21,7 @@ package org.apache.spark.examples.mllib import org.apache.spark.{SparkConf, SparkContext} // $example on$ import org.apache.spark.mllib.regression.{IsotonicRegression, IsotonicRegressionModel} +import org.apache.spark.mllib.util.MLUtils // $example off$ object IsotonicRegressionExample { @@ -30,12 +31,12 @@ object IsotonicRegressionExample { val conf = new SparkConf().setAppName("IsotonicRegressionExample") val sc = new SparkContext(conf) // $example on$ - val data = sc.textFile("data/mllib/sample_isotonic_regression_data.txt") + val data = MLUtils.loadLibSVMFile(sc, + "data/mllib/sample_isotonic_regression_libsvm_data.txt").cache() // Create label, feature, weight tuples from input data with weight set to default value 1.0. - val parsedData = data.map { line => - val parts = line.split(',').map(_.toDouble) - (parts(0), parts(1), 1.0) + val parsedData = data.map { labeledPoint => + (labeledPoint.label, labeledPoint.features(0), 1.0) } // Split data into training (60%) and test (40%) sets. |