Libsvm java工程实践

/**
     * 对传入的文本特征根据训练好的分类模型进行分类
     * @param model 已经训练好的模型
     * @param contentFeature    传入的计算好的文本分词后的特征
     * @return
     */
    public static int libSvmPredict(svm_model model, String contentFeature){
        //默认分类类别为-1
        int label = -1;
        //判断传入的文本特征是否为空
        if (contentFeature == null) return label;
        //对传入的特征进行切分
        StringTokenizer st = new StringTokenizer(contentFeature," \t\n\r\f:");
        //这里target用不到，测试中会用到，即我们测试语料的类别标签
//        double target = atof(st.nextToken());
        int m = st.countTokens()/2;
        svm_node[] x = new svm_node[m];
        for(int j=0;j<m;j++)
        {
            x[j] = new svm_node();
            x[j].index = atoi(st.nextToken());
            x[j].value = atof(st.nextToken());
        }

        double v = svm.svm_predict(model,x);
        label = (int) v;
        return label;
    }

/**
     * 获取模型分词用的term词表
     * @param termsPath
     * @return
     */
    public static Map<String, Integer> getModelTerms(String termsPath){
        Map<String, Integer> termsMap = new HashMap<String, Integer>(  );
        try {
            String termsStr = FileOptionUtil.readFile( termsPath, "UTF-8" );
            if (termsStr != null){
                String[] terms = termsStr.split( "\r\n" );
                if (terms!=null && terms.length>0){
                    for (int i=0; i<terms.length; i++){
                        String term = terms[i];
                        String[] termM = term.split( "\t" );
                        if (termM!=null && termM.length==2){
                            termsMap.put( termM[0], Integer.parseInt(termM[1]) );
                        }
                    }
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return termsMap;
    }

    public static String getContentFeature(String content, Map<String, Integer> terms){
        String contentFature = "";
        //对传入的文本进行分词
        Map<String, Integer> contentTermsMap = HanLPAnalyser.segString( content );
        Map<Integer, Double> contentTfIdf = new TreeMap<Integer, Double>( new Comparator<Integer>() {
            @Override
            public int compare(Integer o1, Integer o2) {
                return o1.compareTo( o2 );
            }
        } );
        //计算tf-idf，这里我们就用单存的tf代替tf-idf，idf值均为1
        for (String word : contentTermsMap.keySet()){
            if (terms.containsKey( word )){
                contentTfIdf.put( terms.get( word ), getWordTF( word, contentTermsMap ) );
            }
        }

        for (Integer key : contentTfIdf.keySet()){
            contentFature += key + ":" + contentTfIdf.get( key ) + " ";
        }

        return contentFature.trim();
    }

public static void main(String[] args){
        String s = "&nbsp&nbsp&nbsp&nbsp依照上海证券交易所发布的《关于证券公司创设白云机场权证有关事项的\n" +
                "通知》,光大证券股份有限公司向上海证券交易所申请注销白云机场认沽权证并\n" +
                "已获核准,中国证券登记结算有限责任公司上海分公司已办理相应登记手续。本\n" +
                "公司此次获准注销的白云机场认沽权证数量为1,500万份,该权证的条款与原白\n" +
                "云机场认沽权证(交易简称机场JTP1、交易代码580998、行权代码582998)的条\n" +
                "款完全相同。\n" +
                "&nbsp&nbsp&nbsp&nbsp\n";
        Map<String, Integer> terms = LibSvmDataProcess.getModelTerms( "/Users/zhouyh/work/yanfa/xunlianji/UTF8/heji/terms.txt" );
        String contentFeature = LibSvmDataProcess.getContentFeature( s, terms);
        svm_model model = GetSvmModel.getSvmModelInstance().getModel( "/Users/zhouyh/work/yanfa/xunlianji/UTF8/heji/model.txt" );
        int label = libSvmPredict(model, contentFeature);
        System.out.println(label);
    }