jiangxin369 commented on code in PR #162: URL: https://github.com/apache/flink-ml/pull/162#discussion_r996440219
########## flink-ml-core/src/main/java/org/apache/flink/ml/util/QuantileSummary.java: ########## @@ -0,0 +1,359 @@ +/* + * 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.util; + +import org.apache.flink.util.Preconditions; + +import java.io.Serializable; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.LinkedList; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; + +import static org.apache.flink.util.Preconditions.checkState; + +/** + * Helper class to compute an approximate quantile summary. This implementation is based on the + * algorithm proposed in the paper: "Space-efficient Online Computation of Quantile Summaries" by + * Greenwald, Michael and Khanna, Sanjeev. (https://doi.org/10.1145/375663.375670) + */ +public class QuantileSummary { + + private static final int BUFFER_SIZE = 10000; + private static final int COMPRESS_THRESHOLD = 10000; + + private double relativeError; + private long count; + private List<StatsTuple> sampled; + private List<Double> headBuffer = new ArrayList<>(BUFFER_SIZE); + + /** + * * QuantileSummaries Constructor. + * + * @param relativeError The target relative error. + */ + public QuantileSummary(double relativeError) { Review Comment: I will add another public constructor with both `relativeError` and `compressThreshold` but also keep the construct with only `relativeError` meanwhile, because in most cases users do not need to worry about the `compressThreshold`, so do LSH and RobustScaler. -- 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
