examples/src/main/java/org/apache/ignite/examples/ml/clustering/KMeansClusterizationExample.java

/*
 * 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.clustering;

import java.io.IOException;
import javax.cache.Cache;
import org.apache.ignite.Ignite;
import org.apache.ignite.IgniteCache;
import org.apache.ignite.Ignition;
import org.apache.ignite.cache.query.QueryCursor;
import org.apache.ignite.cache.query.ScanQuery;
import org.apache.ignite.examples.ml.util.MLSandboxDatasets;
import org.apache.ignite.examples.ml.util.SandboxMLCache;
import org.apache.ignite.ml.clustering.kmeans.KMeansModel;
import org.apache.ignite.ml.clustering.kmeans.KMeansTrainer;
import org.apache.ignite.ml.dataset.feature.extractor.Vectorizer;
import org.apache.ignite.ml.dataset.feature.extractor.impl.DummyVectorizer;
import org.apache.ignite.ml.math.Tracer;
import org.apache.ignite.ml.math.primitives.vector.Vector;

/**
 * Run KMeans clustering algorithm ({@link KMeansTrainer}) over distributed dataset.
 * <p>
 * Code in this example launches Ignite grid and fills the cache with test data points (based on the
 * <a href="https://en.wikipedia.org/wiki/Iris_flower_data_set"></a>Iris dataset</a>).</p>
 * <p>
 * After that it trains the model based on the specified data using
 * <a href="https://en.wikipedia.org/wiki/K-means_clustering">KMeans</a> algorithm.</p>
 * <p>
 * Finally, this example loops over the test set of data points, applies the trained model to predict what cluster does
 * this point belong to, and compares prediction to expected outcome (ground truth).</p>
 * <p>
 * You can change the test data used in this example and re-run it to explore this algorithm further.</p>
 */
public class KMeansClusterizationExample {
    /**
     * Run example.
     */
    public static void main(String[] args) throws IOException {
        System.out.println();
        System.out.println(">>> KMeans clustering algorithm over cached 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, Vector> dataCache = null;
            try {
                dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.TWO_CLASSED_IRIS);

                Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);

                KMeansTrainer trainer = new KMeansTrainer();

                KMeansModel mdl = trainer.fit(
                    ignite,
                    dataCache,
                    vectorizer
                );

                System.out.println(">>> KMeans centroids");
                Tracer.showAscii(mdl.getCenters()[0]);
                Tracer.showAscii(mdl.getCenters()[1]);
                System.out.println(">>>");

                System.out.println(">>> --------------------------------------------");
                System.out.println(">>> | Predicted cluster\t| Erased class label\t|");
                System.out.println(">>> --------------------------------------------");

                try (QueryCursor<Cache.Entry<Integer, Vector>> observations = dataCache.query(new ScanQuery<>())) {
                    for (Cache.Entry<Integer, Vector> observation : observations) {
                        Vector val = observation.getValue();
                        Vector inputs = val.copyOfRange(1, val.size());
                        double groundTruth = val.get(0);

                        double prediction = mdl.predict(inputs);

                        System.out.printf(">>> | %.4f\t\t\t| %.4f\t\t|\n", prediction, groundTruth);
                    }

                    System.out.println(">>> ---------------------------------");
                    System.out.println(">>> KMeans clustering algorithm over cached dataset usage example completed.");
                }
            }
            finally {
                if (dataCache != null)
                    dataCache.destroy();
            }
        }
        finally {
            System.out.flush();
        }
    }
}