Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/9353#discussion_r43474242
--- Diff:
examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java
---
@@ -0,0 +1,89 @@
+/*
+ * 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.mllib;
+
+// $example on$
+import scala.Tuple2;
+import scala.Tuple3;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.api.java.function.PairFunction;
+import org.apache.spark.api.java.JavaDoubleRDD;
+import org.apache.spark.api.java.JavaPairRDD;
+// $example off$
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.mllib.regression.IsotonicRegression;
+import org.apache.spark.mllib.regression.IsotonicRegressionModel;
+// $example off$
+import org.apache.spark.SparkConf;
+
+public class JavaIsotonicRegressionExample {
+ public static void main(String[] args) {
+ SparkConf sparkConf = new
SparkConf().setAppName("JavaIsotonicRegressionExample");
+ JavaSparkContext sc = new JavaSparkContext(sparkConf);
+ JavaSparkContext jsc = new JavaSparkContext(sparkConf);
+ // $example on$
+ JavaRDD<String> data =
sc.textFile("data/mllib/sample_isotonic_regression_data.txt");
+
+ // 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);
+ }
+ }
+ );
+
+ // Split data into training (60%) and test (40%) sets.
+ JavaRDD<Tuple3<Double, Double, Double>>[] splits =
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);
+
+ // Create tuples of predicted and real labels.
+ JavaPairRDD<Double, Double> predictionAndLabel = test.mapToPair(
+ new PairFunction<Tuple3<Double, Double, Double>, Double, Double>() {
+ @Override
+ public Tuple2<Double, Double> call(Tuple3<Double, Double, Double>
point) {
+ Double predictedLabel = model.predict(point._2());
+ return new Tuple2<Double, Double>(predictedLabel, point._1());
+ }
+ }
+ );
+
+ // Calculate mean squared error between predicted and real labels.
+ Double meanSquaredError = new JavaDoubleRDD(predictionAndLabel.map(
+ new Function<Tuple2<Double, Double>, Object>() {
+ @Override
+ public Object call(Tuple2<Double, Double> pl) {
+ return Math.pow(pl._1() - pl._2(), 2);
+ }
+ }
+ ).rdd()).mean();
+ System.out.println("Mean Squared Error = " + meanSquaredError);
+
+ // Save and load model
+ model.save(sc.sc(), "myModelPath");
--- End diff --
See my comments on the Scala example about model path.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
