mayya-sharipova commented on code in PR #13604: URL: https://github.com/apache/lucene/pull/13604#discussion_r1691405067
########## lucene/sandbox/src/test/org/apache/lucene/sandbox/codecs/quantization/TestKMeans.java: ########## @@ -0,0 +1,92 @@ +/* + * 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.lucene.sandbox.codecs.quantization; + +import java.io.IOException; +import java.util.Arrays; +import org.apache.lucene.index.VectorSimilarityFunction; +import org.apache.lucene.tests.util.LuceneTestCase; +import org.apache.lucene.util.hnsw.RandomAccessVectorValues; + +public class TestKMeans extends LuceneTestCase { + + public void testKMeansAPI() throws IOException { + int nVectors = random().nextInt(50, 1000); + int nClusters = random().nextInt(1, nVectors / 20); + int dims = random().nextInt(2, 20); + int randIdx = random().nextInt(VectorSimilarityFunction.values().length); + VectorSimilarityFunction similarityFunction = VectorSimilarityFunction.values()[randIdx]; + float[][] vectors = generateData(nVectors, dims, nClusters); + RandomAccessVectorValues.Floats vectorValues = + RandomAccessVectorValues.fromFloats(Arrays.asList(vectors), dims); + + // default case + { + KMeans.Results results = KMeans.cluster(vectorValues, similarityFunction, nClusters); + assertEquals(nClusters, results.centroids().length); + assertEquals(nVectors, results.vectorCentroids().length); + } + // expert case + { + boolean assignCentroidsToVectors = random().nextBoolean(); + int randIdx2 = random().nextInt(KMeans.KmeansInitializationMethod.values().length); + KMeans.KmeansInitializationMethod initializationMethod = + KMeans.KmeansInitializationMethod.values()[randIdx2]; Review Comment: @john-wagster I was thinking since initialization method is chose at random, it will be exercised in other tests as well. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
