LUCENE-6045 - fixed javadocs

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1677367 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Tommaso Teofili 2015-05-03 06:54:29 +00:00
parent 62b73edde1
commit 11c4a88e23
4 changed files with 44 additions and 4 deletions

View File

@ -64,6 +64,20 @@ public class BooleanPerceptronClassifier implements Classifier<Boolean> {
private final String textFieldName; private final String textFieldName;
private FST<Long> fst; private FST<Long> fst;
/**
* Creates a {@link BooleanPerceptronClassifier}
*
* @param leafReader the reader on the index to be used for classification
* @param textFieldName the name of the field used as input for the classifier
* @param classFieldName the name of the field used as the output for the classifier
* @param analyzer an {@link Analyzer} used to analyze unseen text
* @param query a {@link Query} to eventually filter the docs used for training the classifier, or {@code null}
* if all the indexed docs should be used
* @param batchSize the size of the batch of docs to use for updating the perceptron weights
* @param threshold the threshold used for class separation
* @throws IOException if the building of the underlying {@link FST} fails and / or {@link TermsEnum} for the text field
* cannot be found
*/
public BooleanPerceptronClassifier(LeafReader leafReader, String textFieldName, String classFieldName, Analyzer analyzer, public BooleanPerceptronClassifier(LeafReader leafReader, String textFieldName, String classFieldName, Analyzer analyzer,
Query query, Integer batchSize, Double threshold) throws IOException { Query query, Integer batchSize, Double threshold) throws IOException {
this.textTerms = MultiFields.getTerms(leafReader, textFieldName); this.textTerms = MultiFields.getTerms(leafReader, textFieldName);

View File

@ -59,8 +59,15 @@ public class CachingNaiveBayesClassifier extends SimpleNaiveBayesClassifier {
private int docsWithClassSize; private int docsWithClassSize;
/** /**
* Creates a new NaiveBayes classifier with inside caching. If you want less memory usage you could * Creates a new NaiveBayes classifier with inside caching. If you want less memory usage you could call
* call {@link #reInitCache(int, boolean) reInitCache()}. * {@link #reInitCache(int, boolean) reInitCache()}.
*
* @param leafReader the reader on the index to be used for classification
* @param analyzer an {@link Analyzer} used to analyze unseen text
* @param query a {@link Query} to eventually filter the docs used for training the classifier, or {@code null}
* if all the indexed docs should be used
* @param classFieldName the name of the field used as the output for the classifier
* @param textFieldNames the name of the fields used as the inputs for the classifier
*/ */
public CachingNaiveBayesClassifier(LeafReader leafReader, Analyzer analyzer, Query query, String classFieldName, String... textFieldNames) { public CachingNaiveBayesClassifier(LeafReader leafReader, Analyzer analyzer, Query query, String classFieldName, String... textFieldNames) {
super(leafReader, analyzer, query, classFieldName, textFieldNames); super(leafReader, analyzer, query, classFieldName, textFieldNames);

View File

@ -53,6 +53,19 @@ public class KNearestNeighborClassifier implements Classifier<BytesRef> {
private final int k; private final int k;
private final Query query; private final Query query;
/**
* Creates a {@link KNearestNeighborClassifier}.
*
* @param leafReader the reader on the index to be used for classification
* @param analyzer an {@link Analyzer} used to analyze unseen text
* @param query a {@link Query} to eventually filter the docs used for training the classifier, or {@code null}
* if all the indexed docs should be used
* @param k the no. of docs to select in the MLT results to find the nearest neighbor
* @param minDocsFreq {@link MoreLikeThis#minDocFreq} parameter
* @param minTermFreq {@link MoreLikeThis#minTermFreq} parameter
* @param classFieldName the name of the field used as the output for the classifier
* @param textFieldNames the name of the fields used as the inputs for the classifier
*/
public KNearestNeighborClassifier(LeafReader leafReader, Analyzer analyzer, Query query, int k, int minDocsFreq, public KNearestNeighborClassifier(LeafReader leafReader, Analyzer analyzer, Query query, int k, int minDocsFreq,
int minTermFreq, String classFieldName, String... textFieldNames) { int minTermFreq, String classFieldName, String... textFieldNames) {
this.textFieldNames = textFieldNames; this.textFieldNames = textFieldNames;

View File

@ -80,7 +80,13 @@ public class SimpleNaiveBayesClassifier implements Classifier<BytesRef> {
/** /**
* Creates a new NaiveBayes classifier. * Creates a new NaiveBayes classifier.
* classify any documents. *
* @param leafReader the reader on the index to be used for classification
* @param analyzer an {@link Analyzer} used to analyze unseen text
* @param query a {@link Query} to eventually filter the docs used for training the classifier, or {@code null}
* if all the indexed docs should be used
* @param classFieldName the name of the field used as the output for the classifier
* @param textFieldNames the name of the fields used as the inputs for the classifier
*/ */
public SimpleNaiveBayesClassifier(LeafReader leafReader, Analyzer analyzer, Query query, String classFieldName, String... textFieldNames) { public SimpleNaiveBayesClassifier(LeafReader leafReader, Analyzer analyzer, Query query, String classFieldName, String... textFieldNames) {
this.leafReader = leafReader; this.leafReader = leafReader;
@ -183,7 +189,7 @@ public class SimpleNaiveBayesClassifier implements Classifier<BytesRef> {
q.add(query, BooleanClause.Occur.MUST); q.add(query, BooleanClause.Occur.MUST);
} }
indexSearcher.search(q, indexSearcher.search(q,
totalHitCountCollector); totalHitCountCollector);
docCount = totalHitCountCollector.getTotalHits(); docCount = totalHitCountCollector.getTotalHits();
} }
return docCount; return docCount;