weibozhao commented on a change in pull request #54: URL: https://github.com/apache/flink-ml/pull/54#discussion_r823401050
########## File path: flink-ml-lib/src/main/java/org/apache/flink/ml/feature/minmaxscaler/MinMaxScaler.java ########## @@ -0,0 +1,165 @@ +/* + * 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.feature.minmaxscaler; + +import org.apache.flink.api.common.functions.RichMapPartitionFunction; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.ml.api.Estimator; +import org.apache.flink.ml.common.datastream.DataStreamUtils; +import org.apache.flink.ml.linalg.DenseVector; +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.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +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.types.Row; +import org.apache.flink.util.Collector; +import org.apache.flink.util.Preconditions; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; + +/** An Estimator which implements the MinMaxScaler algorithm. */ +public class MinMaxScaler + implements Estimator<MinMaxScaler, MinMaxScalerModel>, MinMaxScalerParams<MinMaxScaler> { + private final Map<Param<?>, Object> paramMap = new HashMap<>(); + + public MinMaxScaler() { + ParamUtils.initializeMapWithDefaultValues(paramMap, this); + } + + @Override + public MinMaxScalerModel fit(Table... inputs) { + Preconditions.checkArgument(inputs.length == 1); + StreamTableEnvironment tEnv = + (StreamTableEnvironment) ((TableImpl) inputs[0]).getTableEnvironment(); + DataStream<Tuple2<DenseVector, DenseVector>> minMaxVectors = + computeMinMaxVectors(tEnv.toDataStream(inputs[0]), getFeaturesCol()); + DataStream<MinMaxScalerModelData> modelData = genModelData(minMaxVectors); + MinMaxScalerModel model = + new MinMaxScalerModel().setModelData(tEnv.fromDataStream(modelData)); + ReadWriteUtils.updateExistingParams(model, getParamMap()); + return model; + } + + @Override + public Map<Param<?>, Object> getParamMap() { + return paramMap; + } + + @Override + public void save(String path) throws IOException { + ReadWriteUtils.saveMetadata(this, path); + } + + public static MinMaxScaler load(StreamExecutionEnvironment env, String path) + throws IOException { + return ReadWriteUtils.loadStageParam(path); + } + + /** + * Generates minMax scaler model data. + * + * @param minMaxVectors Input distributed minMaxVectors. + * @return MinMax scaler model data. + */ + private static DataStream<MinMaxScalerModelData> genModelData( + DataStream<Tuple2<DenseVector, DenseVector>> minMaxVectors) { + DataStream<MinMaxScalerModelData> modelData = + DataStreamUtils.mapPartition( + minMaxVectors, + new RichMapPartitionFunction< + Tuple2<DenseVector, DenseVector>, MinMaxScalerModelData>() { + @Override + public void mapPartition( + Iterable<Tuple2<DenseVector, DenseVector>> dataPoints, + Collector<MinMaxScalerModelData> out) { + DenseVector minVector = null; + DenseVector maxVector = null; + int vecSize = 0; + for (Tuple2<DenseVector, DenseVector> dataPoint : dataPoints) { + if (maxVector == null) { + vecSize = dataPoint.f0.size(); + maxVector = dataPoint.f1; + minVector = dataPoint.f0; + } + for (int i = 0; i < vecSize; ++i) { + minVector.values[i] = + Math.min( + dataPoint.f0.values[i], + minVector.values[i]); + maxVector.values[i] = + Math.max( + dataPoint.f1.values[i], + maxVector.values[i]); + } + } + out.collect(new MinMaxScalerModelData(minVector, maxVector)); + } + }); + modelData.getTransformation().setParallelism(1); + return modelData; + } + + /** + * Computes max and min values of features. + * + * @param inputData Input data. + * @param featureCol Feature column name. + * @return Max and min values of features. + */ + private DataStream<Tuple2<DenseVector, DenseVector>> computeMinMaxVectors( Review comment: computeMinMaxVectors execute in parallel mode, genModelData reduce distributed minMax values to one. -- 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...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
