dmitrievanthony commented on a change in pull request #5851: IGNITE-10968: [ML] Create new ignite module SparkMLModelImport and add LogRegression converter URL: https://github.com/apache/ignite/pull/5851#discussion_r248732884
########## File path: examples/src/main/java/org/apache/ignite/examples/ml/inference/spark/LogRegFromSparkViaSparkModelParserExample.java ########## @@ -0,0 +1,83 @@ +/* + * 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.ignite.examples.ml.inference.spark; + +import java.io.FileNotFoundException; +import org.apache.hadoop.fs.Path; +import org.apache.ignite.Ignite; +import org.apache.ignite.IgniteCache; +import org.apache.ignite.Ignition; +import org.apache.ignite.examples.ml.tutorial.TitanicUtils; +import org.apache.ignite.ml.math.functions.IgniteBiFunction; +import org.apache.ignite.ml.math.primitives.vector.Vector; +import org.apache.ignite.ml.math.primitives.vector.VectorUtils; +import org.apache.ignite.ml.regressions.logistic.LogisticRegressionModel; +import org.apache.ignite.ml.selection.scoring.evaluator.BinaryClassificationEvaluator; +import org.apache.ignite.ml.selection.scoring.metric.Accuracy; +import org.apache.ignite.ml.sparkmodelparser.SparkModelParser; +import org.apache.ignite.ml.sparkmodelparser.SupportedSparkModels; + +/** + * Run logistic regression model loaded from snappy.parquet file. + * The snappy.parquet file was generated by Spark MLLib model.write.overwrite().save(..) operator. + * <p> + * You can change the test data used in this example and re-run it to explore this algorithm further.</p> + */ +public class LogRegFromSparkViaSparkModelParserExample { + /** Run example. */ + public static void main(String[] args) throws FileNotFoundException { + System.out.println(); + System.out.println(">>> Logistic regression model loaded from Spark through serialization over partitioned dataset usage example started."); + // Start ignite grid. + try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) { + System.out.println(">>> Ignite grid started."); + + IgniteCache<Integer, Object[]> dataCache = TitanicUtils.readPassengers(ignite); + + IgniteBiFunction<Integer, Object[], Vector> featureExtractor = (k, v) -> { + double[] data = new double[] {(double)v[0], (double)v[5], (double)v[6]}; + data[0] = Double.isNaN(data[0]) ? 0 : data[0]; + data[1] = Double.isNaN(data[1]) ? 0 : data[1]; + data[2] = Double.isNaN(data[2]) ? 0 : data[2]; + + return VectorUtils.of(data); + }; + + IgniteBiFunction<Integer, Object[], Double> lbExtractor = (k, v) -> (double)v[1]; + + LogisticRegressionModel mdl = (LogisticRegressionModel) SparkModelParser.parse( + new Path("examples/src/main/resources/models/spark/serialized/data" + Review comment: I think it would be better to use `IgniteUtils.resolveIgnitePath`. It works on TeamCity and local run 100%, not sure about your code. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
