lindong28 commented on a change in pull request #27: URL: https://github.com/apache/flink-ml/pull/27#discussion_r750017538
########## File path: flink-ml-lib/src/main/java/org/apache/flink/ml/clustering/kmeans/KMeans.java ########## @@ -0,0 +1,337 @@ +/* + * 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.flink.ml.clustering.kmeans; + +import org.apache.flink.api.common.functions.MapFunction; +import org.apache.flink.api.common.functions.MapPartitionFunction; +import org.apache.flink.api.common.functions.ReduceFunction; +import org.apache.flink.api.common.state.ListState; +import org.apache.flink.api.common.state.ListStateDescriptor; +import org.apache.flink.api.common.typeinfo.BasicTypeInfo; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.api.java.tuple.Tuple3; +import org.apache.flink.api.java.typeutils.ObjectArrayTypeInfo; +import org.apache.flink.api.java.typeutils.TupleTypeInfo; +import org.apache.flink.iteration.DataStreamList; +import org.apache.flink.iteration.IterationBody; +import org.apache.flink.iteration.IterationBodyResult; +import org.apache.flink.iteration.IterationConfig; +import org.apache.flink.iteration.IterationListener; +import org.apache.flink.iteration.Iterations; +import org.apache.flink.iteration.ReplayableDataStreamList; +import org.apache.flink.ml.api.core.Estimator; +import org.apache.flink.ml.common.datastream.EndOfStreamWindows; +import org.apache.flink.ml.common.datastream.MapPartitionFunctionWrapper; +import org.apache.flink.ml.common.iteration.ForwardInputsOfLastRound; +import org.apache.flink.ml.common.iteration.TerminateOnMaxIterationNum; +import org.apache.flink.ml.distance.DistanceMeasure; +import org.apache.flink.ml.linalg.DenseVector; +import org.apache.flink.ml.linalg.typeinfo.DenseVectorTypeInfo; +import org.apache.flink.ml.param.Param; +import org.apache.flink.ml.util.ParamUtils; +import org.apache.flink.ml.util.ReadWriteUtils; +import org.apache.flink.runtime.state.StateInitializationContext; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.streaming.api.functions.windowing.AllWindowFunction; +import org.apache.flink.streaming.api.operators.AbstractStreamOperator; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.api.operators.TwoInputStreamOperator; +import org.apache.flink.streaming.api.windowing.windows.TimeWindow; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableImpl; +import org.apache.flink.util.Collector; + +import org.apache.commons.collections.IteratorUtils; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Random; + +/** + * An Estimator which implements the k-means clustering algorithm. + * + * <p>See https://en.wikipedia.org/wiki/K-means_clustering. + */ +public class KMeans implements Estimator<KMeans, KMeansModel>, KMeansParams<KMeans> { + private final Map<Param<?>, Object> paramMap = new HashMap<>(); + + public KMeans() { + ParamUtils.initializeMapWithDefaultValues(paramMap, this); + } + + @Override + public KMeansModel fit(Table... inputs) { + StreamTableEnvironment tEnv = + (StreamTableEnvironment) ((TableImpl) inputs[0]).getTableEnvironment(); + DataStream<DenseVector> points = Review comment: Simply making this change will break compilation. Maybe we can make this work by also changing many other places. But I am not sure it is useful to make this change given that we don't support SparseVector yet. Maybe we can make this change after `SparseVector` is supported. Then we can write unit tests to validate that KMeans (as well as other algorithms) can support both SparseVector and DenseVector as inputs. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
