All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.apache.flink.ml.feature.lsh.MinHashLSH Maven / Gradle / Ivy

/*
 * 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.lsh;

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.table.api.bridge.java.StreamTableEnvironment;

import java.io.IOException;

/**
 * An Estimator that implements the MinHash LSH algorithm, which supports LSH for Jaccard distance.
 *
 * 

The input could be dense or sparse vectors. Each input vector must have at least one non-zero * index and all non-zero values are treated as binary "1" values. The sizes of input vectors should * be same and not larger than a predefined prime (i.e., 2038074743). * *

See: MinHash. */ public class MinHashLSH extends LSH implements MinHashLSHParams { @Override protected MinHashLSHModel createModel( DataStream inputDim, StreamTableEnvironment tEnv) { DataStream modelData = inputDim.map( dim -> MinHashLSHModelData.generateModelData( getNumHashTables(), getNumHashFunctionsPerTable(), dim, getSeed())); MinHashLSHModel model = new MinHashLSHModel().setModelData(tEnv.fromDataStream(modelData)); ParamUtils.updateExistingParams(model, getParamMap()); return model; } public static MinHashLSH load(StreamTableEnvironment tEnv, String path) throws IOException { return ReadWriteUtils.loadStageParam(path); } }





© 2015 - 2025 Weber Informatics LLC | Privacy Policy