Java NumericToNominal.setInputFormat方法代码示例

import weka.filters.unsupervised.attribute.NumericToNominal; //导入方法依赖的package包/类
public static String buildAssociate() throws Exception {
    InstanceQuery query = new InstanceQuery();
    query.setUsername("root");
    query.setPassword("cs6310");
    query.setDatabaseURL("jdbc:mysql://localhost/system?#characterEncoding=UTF-8");
    query.setQuery("select * from courses_sessions;");
    // You can declare that your data set is sparse
    // query.setSparseData(true);
    Instances data = query.retrieveInstances();
    data.setClassIndex(data.numAttributes() - 1);

    final NumericToNominal filter = new NumericToNominal();

    filter.setInputFormat(data);
    data = Filter.useFilter(data, filter);
    if (data.size() > 0) {
        // build associator
        Apriori apriori = new Apriori();
        apriori.setClassIndex(data.classIndex());
        apriori.buildAssociations(data);
        return String.valueOf(apriori);
    } else {
        return "Not enough data provided";
    }
}
 

import weka.filters.unsupervised.attribute.NumericToNominal; //导入方法依赖的package包/类
/**
 * 
 * @param data
 * @return
 */
protected Instances[] splitWorkload(Instances data) {
    int offset = 0;
    int all_cnt = data.numInstances();
    for (SplitType stype : SplitType.values()) {
        int idx = stype.ordinal();
        this.split_counts[idx] = (int)Math.round(all_cnt * stype.percentage);
        
        try {
            this.splits[idx] = new Instances(data, offset, this.split_counts[idx]);
        
            // Apply NumericToNominal filter!
            NumericToNominal filter = new NumericToNominal();
            filter.setInputFormat(this.splits[idx]);
            this.splits[idx] = Filter.useFilter(this.splits[idx], filter);
            
        } catch (Exception ex) {
            throw new RuntimeException("Failed to split " + stype + " workload", ex);
        }
        
        offset += this.split_counts[idx];
        if (debug.val) LOG.debug(String.format("%-12s%d", stype.toString()+":", this.split_counts[idx]));
    } // FOR
    return (this.splits);
}
 

import weka.filters.unsupervised.attribute.NumericToNominal; //导入方法依赖的package包/类
protected Classifier generateDecisionTree(AbstractClusterer clusterer, MarkovAttributeSet aset, Instances data) throws Exception {
    // We need to create a new Attribute that has the ClusterId
    Instances newData = data; // new Instances(data);
    newData.insertAttributeAt(new Attribute("ClusterId"), newData.numAttributes());
    Attribute cluster_attr = newData.attribute(newData.numAttributes()-1);
    assert(cluster_attr != null);
    assert(cluster_attr.index() > 0);
    newData.setClass(cluster_attr);
    
    // We will then tell the Classifier to predict that ClusterId based on the MarkovAttributeSet
    ObjectHistogram<Integer> cluster_h = new ObjectHistogram<Integer>();
    for (int i = 0, cnt = newData.numInstances(); i < cnt; i++) {
        // Grab the Instance and throw it at the the clusterer to get the target cluster
        Instance inst = newData.instance(i);
        int c = (int)clusterer.clusterInstance(inst);
        inst.setClassValue(c);
        cluster_h.put(c);
    } // FOR
    System.err.println("Number of Elements: " + cluster_h.getValueCount());
    System.err.println(cluster_h);

    NumericToNominal filter = new NumericToNominal();
    filter.setInputFormat(newData);
    newData = Filter.useFilter(newData, filter);
    
    String output = this.catalog_proc.getName() + "-labeled.arff";
    FileUtil.writeStringToFile(output, newData.toString());
    LOG.info("Wrote labeled data set to " + output);
    
    // Decision Tree
    J48 j48 = new J48();
    String options[] = {
        "-S", Integer.toString(this.rand.nextInt()),
        
    };
    j48.setOptions(options);

    // Make sure we add the ClusterId attribute to a new MarkovAttributeSet so that
    // we can tell the Classifier to classify that!
    FilteredClassifier fc = new FilteredClassifier();
    MarkovAttributeSet classifier_aset = new MarkovAttributeSet(aset);
    classifier_aset.add(cluster_attr);
    fc.setFilter(classifier_aset.createFilter(newData));
    fc.setClassifier(j48);
    
    // Bombs away!
    fc.buildClassifier(newData);
    
    return (fc);
}
 

import weka.filters.unsupervised.attribute.NumericToNominal; //导入方法依赖的package包/类
@Override
    protected void setUp() throws Exception {
        super.setUp(ProjectType.TPCC);
        this.addPartitions(NUM_PARTITIONS);
        
        HStoreConf.singleton().site.markov_path_caching = false;
        
        if (workload == null) {
            catalog_proc = this.getProcedure(TARGET_PROCEDURE);
            
            File file = this.getWorkloadFile(ProjectType.TPCC);
            workload = new Workload(catalog);

            // Check out this beauty:
            // (1) Filter by procedure name
            // (2) Filter on partitions that start on our BASE_PARTITION
            // (3) Filter to only include multi-partition txns
            // (4) Another limit to stop after allowing ### txns
            // Where is your god now???
            edu.brown.workload.filters.Filter filter = new ProcedureNameFilter(false)
                    .include(TARGET_PROCEDURE.getSimpleName())
//                    .attach(new ProcParameterValueFilter().include(1, new Long(5))) // D_ID
//                    .attach(new ProcParameterArraySizeFilter(CatalogUtil.getArrayProcParameters(catalog_proc).get(0), 10, ExpressionType.COMPARE_EQUAL))
//                    .attach(new BasePartitionTxnFilter(p_estimator, BASE_PARTITION))
//                    .attach(new MultiPartitionTxnFilter(p_estimator))
                    .attach(new ProcedureLimitFilter(WORKLOAD_XACT_LIMIT));
            workload.load(file, catalog_db, filter);
            assert(workload.getTransactionCount() > 0);
            
            // Now extract the FeatureSet that we will use in our tests
            Map<Procedure, FeatureSet> fsets = new FeatureExtractor(catalogContext, p_estimator).calculate(workload);
            FeatureSet fset = fsets.get(catalog_proc);
            assertNotNull(fset);
            data = fset.export(catalog_proc.getName(), false);
            
            NumericToNominal weka_filter = new NumericToNominal();
            weka_filter.setInputFormat(data);
            data = Filter.useFilter(data, weka_filter);
        }
        assertNotNull(data);
        
        fclusterer = new FeatureClusterer(catalogContext, catalog_proc, workload, catalogContext.getAllPartitionIds());
    }