Carrot2对文章进行聚类代码示例

沙漠中的鱼 — Tue, 08 Jan 2013 07:08:00 GMT

public class ClusteringFlyStoneDocument {

    public static void main(String[] args) {

        final Controller controller = ControllerFactory.createCachingPooling(IDocumentSource.class);
        //创建需要处理的属性对象
        final Map attributes = Maps.newHashMap();

        //需要处理的文档集合
        List documents = SampleDocumentData.DOCUMENTS_DATA_MINING;

        //将文档添加到聚类属性中
        CommonAttributesDescriptor.attributeBuilder(attributes).documents(documents);

        //设置处理的语言（）
        MultilingualClusteringDescriptor.attributeBuilder(attributes).defaultLanguage(LanguageCode.CHINESE_SIMPLIFIED);

        //设置需要处理的对象，以及聚类的算法
        final ProcessingResult englishResult = controller.process(attributes, LingoClusteringAlgorithm.class);

        //获取结果，打印聚类主题及关联信息
        final List clustersByTopic = englishResult.getClusters();
        System.out.println("=======聚类主题=====");
        for(Cluster cluster : clustersByTopic){
            System.out.println("【主题】" +cluster.getLabel());
            List cDocLst = cluster.getAllDocuments();
            for(Document doc : cDocLst){
                System.out.println("--------" + doc.getTitle());
            }
        }

        //通过URL进行聚类
        final ProcessingResult byDomainClusters = controller.process(documents, null,ByUrlClusteringAlgorithm.class);
        final List clustersByDomain = byDomainClusters.getClusters();
        System.out.println("=======URL聚类=======");
        for(Cluster cluster : clustersByDomain){
            System.out.println("【URL】" +cluster.getLabel());
            List cDocLst = cluster.getAllDocuments();
            for(Document doc : cDocLst){
                System.out.println("----" + doc.getTitle());
            }
        }
    }

}

沙漠中的鱼 2013-01-08 15:08 发表评论

BlogJava-沙漠中的鱼-文章分类-数据挖掘

Carrot2对文章进行聚类代码示例