java - 将 Lucene 索引转换为 Mahout vector

Question

我有一个 Spring Web 应用程序。它通过 Hibernate Search 将模型 Education 映射到 lucene 索引:

@Entity
@Table(name="educations")
@Indexed
public class Education {

    @Id
    @GeneratedValue(strategy = GenerationType.AUTO)
    @Field(termVector = TermVector.WITH_POSITION_OFFSETS)
    private long id;

    @Column(name = "name")
    @Field(termVector = TermVector.WITH_POSITION_OFFSETS)
    @Boost(value = 1.5f)
    private String name;

    @Column(name = "local_name")
    private String localName;

    @Column(name = "description", columnDefinition="TEXT")
    @Field(termVector = TermVector.WITH_POSITION_OFFSETS)
    private String description;

这太棒了!

现在我正在尝试通过 Mahout 0.9 集群我的 Lucene 索引。我进行了基本的 K 均值聚类，但我不知道如何将 Lucene 索引转换为 Mahout vector 。

这是我的基本 K-Means 聚类类，它适用于一些测试数据点，如下所示:

package com.courseportal.project.utils.lsh.util;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.classify.WeightedPropertyVectorWritable;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.clustering.kmeans.Kluster;
import org.apache.mahout.common.distance.EuclideanDistanceMeasure;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class SimpleKMeansClustering {

    public static final double[][] points = {
            {1, 1}, {2, 1}, {1, 2},
            {2, 2}, {3, 3}, {8, 8},
            {9, 8}, {8, 9}, {9, 9}};

    public static void writePointsToFile(List<Vector> points,
                                         String fileName,
                                         FileSystem fs,
                                         Configuration conf) throws IOException {
        Path path = new Path(fileName);
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
                path, LongWritable.class, VectorWritable.class);
        long recNum = 0;
        VectorWritable vec = new VectorWritable();
        for (Vector point : points) {
            vec.set(point);
            writer.append(new LongWritable(recNum++), vec);
        }
        writer.close();
    }

    public static List<Vector> getPoints(double[][] raw) {
        List<Vector> points = new ArrayList<Vector>();
        for (int i = 0; i < raw.length; i++) {
            double[] fr = raw[i];
            Vector vec = new RandomAccessSparseVector(fr.length);
            vec.assign(fr);
            points.add(vec);

        }
        return points;
    }

    public static void main(String args[]) throws Exception {

        int k = 2;

        List<Vector> vectors = getPoints(points);

        File testData = new File("clustering/testdata");
        if (!testData.exists()) {
            testData.mkdir();
        }
        testData = new File("clustering/testdata/points");
        if (!testData.exists()) {
            testData.mkdir();
        }

        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);
        writePointsToFile(vectors, "clustering/testdata/points/file1", fs, conf);

        Path path = new Path("clustering/testdata/clusters/part-00000");
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf, path, Text.class, Kluster.class);

        for (int i = 0; i < k; i++) {
            Vector vec = vectors.get(i);
            Kluster cluster = new Kluster(vec, i, new EuclideanDistanceMeasure());
            writer.append(new Text(cluster.getIdentifier()), cluster);
        }
        writer.close();

        KMeansDriver.run(conf,
                new Path("clustering/testdata/points"),
                new Path("clustering/testdata/clusters"),
                new Path("clustering/output"),
                0.001,
                10,
                true,
                0,
                true);

        SequenceFile.Reader reader = new SequenceFile.Reader(fs,
                new Path("clustering/output/" + Cluster.CLUSTERED_POINTS_DIR + "/part-m-0"), conf);

        IntWritable key = new IntWritable();
        WeightedPropertyVectorWritable value = new WeightedPropertyVectorWritable();
        while (reader.next(key, value)) {
            System.out.println(value.toString() + " belongs to cluster " + key.toString());
        }
        reader.close();
    }
}

我读到( here )我应该使用 LuceneIndexToSequenceFiles 来执行此操作，但我在 Mahout 0.9 中找不到该类。这是我必须手动拉入的东西吗？

如何转换索引以与 K-means 聚类类一起使用？

Answer 1

您可以使用package org.apache.mahout.text;和类SequenceFilesFromLuceneStorageMRJob(用于分布式转换)或SequenceFilesFromLuceneStorageDriver。

有关其用法的更多信息，您可以在 mahout-0.9 测试中找到。例如这里:

mahout-0.9/integration/src/test/java/org/apache/mahout/text/SequenceFilesFromLuceneStorageDriverTest.java
mahout-0.9/integration/src/test/java/org/apache/mahout/text/SequenceFilesFromLuceneStorageMRJob.java

这里https://mahout.apache.org/users/basics/creating-vectors-from-text.html

重要提示:您的 Lucene 索引必须使用 Mahout 中使用的相同版本的 Lucene 创建。