在Java中运行MALLET

我正在尝试在Java中运行Mallet并且收到以下错误.

Couldn't open cc.mallet.util.MalletLogger resources/logging.properties file.
Perhaps the 'resources' directories weren't copied into the 'class' directory.
Continuing.

我正试图从Mallet的网站(http://mallet.cs.umass.edu/topics-devel.php)运行这个例子.以下是我的代码.任何帮助表示赞赏.

package scriptAnalyzer;

import cc.mallet.util.*;
import cc.mallet.types.*;
import cc.mallet.pipe.*;
import cc.mallet.pipe.iterator.*;
import cc.mallet.topics.*;

import java.util.*;
import java.util.regex.*;
import java.io.*;

public class Mallet {

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

        String filePath = "C:/mallet/ap.txt";
        // Begin by importing documents from text to feature sequences
        ArrayList pipeList = new ArrayList();

        // Pipes: lowercase, tokenize, remove stopwords, map to features
        pipeList.add( new CharSequenceLowercase() );
        pipeList.add( new CharSequence2TokenSequence(Pattern.compile("\\p{L}[\\p{L}\\p{P}]+\\p{L}")) );
        pipeList.add( new TokenSequenceRemoveStopwords(new File("stoplists/en.txt"), "UTF-8", false, false, false) );
        pipeList.add( new TokenSequence2FeatureSequence() );

        InstanceList instances = new InstanceList (new SerialPipes(pipeList));

        Reader fileReader = new InputStreamReader(new FileInputStream(new File(filePath)), "UTF-8");
        instances.addThruPipe(new CsvIterator (fileReader, Pattern.compile("^(\\S*)[\\s,]*(\\S*)[\\s,]*(.*)$"),
                                               3, 2, 1)); // data, label, name fields

        // Create a model with 100 topics, alpha_t = 0.01, beta_w = 0.01
        //  Note that the first parameter is passed as the sum over topics, while
        //  the second is the parameter for a single dimension of the Dirichlet prior.
        int numTopics = 5;
        ParallelTopicModel model = new ParallelTopicModel(numTopics, 1.0, 0.01);

        model.addInstances(instances);

        // Use two parallel samplers, which each look at one half the corpus and combine
        //  statistics after every iteration.
        model.setNumThreads(2);

        // Run the model for 50 iterations and stop (this is for testing only, 
        //  for real applications, use 1000 to 2000 iterations)
        model.setNumIterations(50);
        model.estimate();

        // Show the words and topics in the first instance

        // The data alphabet maps word IDs to strings
        Alphabet dataAlphabet = instances.getDataAlphabet();

        FeatureSequence tokens = (FeatureSequence) model.getData().get(0).instance.getData();
        LabelSequence topics = model.getData().get(0).topicSequence;

        Formatter out = new Formatter(new StringBuilder(), Locale.US);
        for (int position = 0; position < tokens.getLength(); position++) {
            out.format("%s-%d ", dataAlphabet.lookupObject(tokens.getIndexAtPosition(position)), topics.getIndexAtPosition(position));
        }
        System.out.println(out);

        // Estimate the topic distribution of the first instance, 
        //  given the current Gibbs state.
        double[] topicDistribution = model.getTopicProbabilities(0);

        // Get an array of sorted sets of word ID/count pairs
        ArrayList> topicSortedWords = model.getSortedWords();

        // Show top 5 words in topics with proportions for the first document
        for (int topic = 0; topic < numTopics; topic++) {
            Iterator iterator = topicSortedWords.get(topic).iterator();

            out = new Formatter(new StringBuilder(), Locale.US);
            out.format("%d\t%.3f\t", topic, topicDistribution[topic]);
            int rank = 0;
            while (iterator.hasNext() && rank < 5) {
                IDSorter idCountPair = iterator.next();
                out.format("%s (%.0f) ", dataAlphabet.lookupObject(idCountPair.getID()), idCountPair.getWeight());
                rank++;
            }
            System.out.println(out);
        }

        // Create a new instance with high probability of topic 0
        StringBuilder topicZeroText = new StringBuilder();
        Iterator iterator = topicSortedWords.get(0).iterator();

        int rank = 0;
        while (iterator.hasNext() && rank < 5) {
            IDSorter idCountPair = iterator.next();
            topicZeroText.append(dataAlphabet.lookupObject(idCountPair.getID()) + " ");
            rank++;
        }

        // Create a new instance named "test instance" with empty target and source fields.
        InstanceList testing = new InstanceList(instances.getPipe());
        testing.addThruPipe(new Instance(topicZeroText.toString(), null, "test instance", null));

        TopicInferencer inferencer = model.getInferencer();
        double[] testProbabilities = inferencer.getSampledDistribution(testing.get(0), 10, 1, 5);
        System.out.println("0\t" + testProbabilities[0]);
    }

}

小智.. 10

如果未在"系统"属性中指定日志文件,则Mallet会查找日志文件.如果您使用Maven,最简单的解决方法是将文件放入

src/main/resources/cc/mallet/util/resources/logging.properties 

这将自动复制它的部分标准Maven构建过程:

target/classes/cc/mallet/util/resources/logging.properties 

所以你不需要任何特殊配置.该文件可以为空,但逻辑故意将其遗漏,因此您可以配置自己的日志记录.