[1/3] ignite git commit: IGNITE-8169: [ML] Adopt KMeans to the new Partitioned Dataset and cleanup old code
Repository: ignite Updated Branches: refs/heads/ignite-2.5 b3f252666 -> 7173b0c48 http://git-wip-us.apache.org/repos/asf/ignite/blob/7173b0c4/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java -- diff --git a/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java b/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java deleted file mode 100644 index 705db7a..000 --- a/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java +++ /dev/null @@ -1,198 +0,0 @@ -/* - * 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.ml.clustering; - -import java.io.IOException; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.Collections; -import java.util.Comparator; -import java.util.HashMap; -import java.util.List; -import java.util.Map; -import java.util.Random; -import java.util.stream.Collectors; -import java.util.stream.IntStream; -import org.apache.ignite.Ignite; -import org.apache.ignite.internal.util.IgniteUtils; -import org.apache.ignite.ml.math.StorageConstants; -import org.apache.ignite.ml.math.Vector; -import org.apache.ignite.ml.math.VectorUtils; -import org.apache.ignite.ml.math.distances.DistanceMeasure; -import org.apache.ignite.ml.math.distances.EuclideanDistance; -import org.apache.ignite.ml.math.functions.Functions; -import org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix; -import org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector; -import org.apache.ignite.testframework.junits.common.GridCommonAbstractTest; -import org.junit.Assert; - -import static org.apache.ignite.ml.clustering.KMeansUtil.checkIsInEpsilonNeighbourhood; - -/** - * This test checks logic of clustering (checks for clusters structures). - */ -public class KMeansDistributedClustererTestSingleNode extends GridCommonAbstractTest { -/** - * Number of nodes in grid. We should use 1 in this test because otherwise algorithm will be unstable - * (We cannot guarantee the order in which results are returned from each node). - */ -private static final int NODE_COUNT = 1; - -/** Grid instance. */ -private Ignite ignite; - -/** - * Default constructor. - */ -public KMeansDistributedClustererTestSingleNode() { -super(false); -} - -/** - * {@inheritDoc} - */ -@Override protected void beforeTest() throws Exception { -ignite = grid(NODE_COUNT); -} - -/** {@inheritDoc} */ -@Override protected void beforeTestsStarted() throws Exception { -for (int i = 1; i <= NODE_COUNT; i++) -startGrid(i); -} - -/** {@inheritDoc} */ -@Override protected void afterTestsStopped() throws Exception { -stopAllGrids(); -} - -/** */ -public void testPerformClusterAnalysisDegenerate() { - IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName()); - -KMeansDistributedClusterer clusterer = new KMeansDistributedClusterer(new EuclideanDistance(), 1, 1, 1L); - -double[] v1 = new double[] {1959, 325100}; -double[] v2 = new double[] {1960, 373200}; - -SparseDistributedMatrix points = new SparseDistributedMatrix(2, 2, StorageConstants.ROW_STORAGE_MODE, -StorageConstants.RANDOM_ACCESS_MODE); - -points.setRow(0, v1); -points.setRow(1, v2); - -KMeansModel mdl = clusterer.cluster(points, 1); - -Assert.assertEquals(1, mdl.centers().length); -Assert.assertEquals(2, mdl.centers()[0].size()); -} - -/** */ -public void testClusterizationOnDatasetWithObviousStructure() throws IOException { - IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName()); - -int ptsCnt = 1; -int squareSideLen = 1; - -Random rnd = new Random(123456L); - -// Let centers be in the vertices of square. -Map centers = new HashMap<>(); -centers.put(100, new DenseLocalOnHeapVector
[1/3] ignite git commit: IGNITE-8169: [ML] Adopt KMeans to the new Partitioned Dataset and cleanup old code
Repository: ignite Updated Branches: refs/heads/master 228254ae3 -> 9e21cec02 http://git-wip-us.apache.org/repos/asf/ignite/blob/9e21cec0/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java -- diff --git a/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java b/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java deleted file mode 100644 index 705db7a..000 --- a/modules/ml/src/test/java/org/apache/ignite/ml/clustering/KMeansDistributedClustererTestSingleNode.java +++ /dev/null @@ -1,198 +0,0 @@ -/* - * 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.ml.clustering; - -import java.io.IOException; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.Collections; -import java.util.Comparator; -import java.util.HashMap; -import java.util.List; -import java.util.Map; -import java.util.Random; -import java.util.stream.Collectors; -import java.util.stream.IntStream; -import org.apache.ignite.Ignite; -import org.apache.ignite.internal.util.IgniteUtils; -import org.apache.ignite.ml.math.StorageConstants; -import org.apache.ignite.ml.math.Vector; -import org.apache.ignite.ml.math.VectorUtils; -import org.apache.ignite.ml.math.distances.DistanceMeasure; -import org.apache.ignite.ml.math.distances.EuclideanDistance; -import org.apache.ignite.ml.math.functions.Functions; -import org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix; -import org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector; -import org.apache.ignite.testframework.junits.common.GridCommonAbstractTest; -import org.junit.Assert; - -import static org.apache.ignite.ml.clustering.KMeansUtil.checkIsInEpsilonNeighbourhood; - -/** - * This test checks logic of clustering (checks for clusters structures). - */ -public class KMeansDistributedClustererTestSingleNode extends GridCommonAbstractTest { -/** - * Number of nodes in grid. We should use 1 in this test because otherwise algorithm will be unstable - * (We cannot guarantee the order in which results are returned from each node). - */ -private static final int NODE_COUNT = 1; - -/** Grid instance. */ -private Ignite ignite; - -/** - * Default constructor. - */ -public KMeansDistributedClustererTestSingleNode() { -super(false); -} - -/** - * {@inheritDoc} - */ -@Override protected void beforeTest() throws Exception { -ignite = grid(NODE_COUNT); -} - -/** {@inheritDoc} */ -@Override protected void beforeTestsStarted() throws Exception { -for (int i = 1; i <= NODE_COUNT; i++) -startGrid(i); -} - -/** {@inheritDoc} */ -@Override protected void afterTestsStopped() throws Exception { -stopAllGrids(); -} - -/** */ -public void testPerformClusterAnalysisDegenerate() { - IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName()); - -KMeansDistributedClusterer clusterer = new KMeansDistributedClusterer(new EuclideanDistance(), 1, 1, 1L); - -double[] v1 = new double[] {1959, 325100}; -double[] v2 = new double[] {1960, 373200}; - -SparseDistributedMatrix points = new SparseDistributedMatrix(2, 2, StorageConstants.ROW_STORAGE_MODE, -StorageConstants.RANDOM_ACCESS_MODE); - -points.setRow(0, v1); -points.setRow(1, v2); - -KMeansModel mdl = clusterer.cluster(points, 1); - -Assert.assertEquals(1, mdl.centers().length); -Assert.assertEquals(2, mdl.centers()[0].size()); -} - -/** */ -public void testClusterizationOnDatasetWithObviousStructure() throws IOException { - IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName()); - -int ptsCnt = 1; -int squareSideLen = 1; - -Random rnd = new Random(123456L); - -// Let centers be in the vertices of square. -Map centers = new HashMap<>(); -centers.put(100, new DenseLocalOnHeapVector(new