Example usage for org.apache.lucene.classification.document SimpleNaiveBayesDocumentClassifier SimpleNaiveBayesDocumentClassifier

Introduction

In this page you can find the example usage for org.apache.lucene.classification.document SimpleNaiveBayesDocumentClassifier SimpleNaiveBayesDocumentClassifier.

Prototype

public SimpleNaiveBayesDocumentClassifier(IndexReader indexReader, Query query, String classFieldName,
        Map<String, Analyzer> field2analyzer, String... textFieldNames) 

Source Link

Document

Creates a new NaiveBayes classifier.

Usage

From source file:org.apache.solr.update.processor.ClassificationUpdateProcessor.java

License:Apache License

/**
 * Sole constructor/*from w  w  w  .  j  av a  2 s . c o  m*/
 *
 * @param classificationParams classification advanced params
 * @param next            next update processor in the chain
 * @param indexReader     index reader
 * @param schema          schema
 */
public ClassificationUpdateProcessor(ClassificationUpdateProcessorParams classificationParams,
        UpdateRequestProcessor next, IndexReader indexReader, IndexSchema schema) {
    super(next);
    this.trainingClassField = classificationParams.getTrainingClassField();
    this.predictedClassField = classificationParams.getPredictedClassField();
    this.maxOutputClasses = classificationParams.getMaxPredictedClasses();
    String[] inputFieldNamesWithBoost = classificationParams.getInputFieldNames();
    Algorithm classificationAlgorithm = classificationParams.getAlgorithm();

    Map<String, Analyzer> field2analyzer = new HashMap<>();
    String[] inputFieldNames = this.removeBoost(inputFieldNamesWithBoost);
    for (String fieldName : inputFieldNames) {
        SchemaField fieldFromSolrSchema = schema.getField(fieldName);
        Analyzer indexAnalyzer = fieldFromSolrSchema.getType().getQueryAnalyzer();
        field2analyzer.put(fieldName, indexAnalyzer);
    }
    switch (classificationAlgorithm) {
    case KNN:
        classifier = new KNearestNeighborDocumentClassifier(indexReader, null,
                classificationParams.getTrainingFilterQuery(), classificationParams.getK(),
                classificationParams.getMinDf(), classificationParams.getMinTf(), trainingClassField,
                field2analyzer, inputFieldNamesWithBoost);
        break;
    case BAYES:
        classifier = new SimpleNaiveBayesDocumentClassifier(indexReader, null, trainingClassField,
                field2analyzer, inputFieldNamesWithBoost);
        break;
    }
}

---