Package org.apache.lucene.classification
Class KNearestNeighborClassifier
- java.lang.Object
-
- org.apache.lucene.classification.KNearestNeighborClassifier
-
- All Implemented Interfaces:
Classifier<BytesRef>
- Direct Known Subclasses:
KNearestNeighborDocumentClassifier
public class KNearestNeighborClassifier extends Object implements Classifier<BytesRef>
A k-Nearest Neighbor classifier (seehttp://en.wikipedia.org/wiki/K-nearest_neighbors
) based onMoreLikeThis
- WARNING: This API is experimental and might change in incompatible ways in the next release.
-
-
Field Summary
Fields Modifier and Type Field Description protected String
classFieldName
the name of the field used as the output textprotected IndexSearcher
indexSearcher
anIndexSearcher
used to perform queriesprotected int
k
the no.protected MoreLikeThis
mlt
aMoreLikeThis
instance used to perform MLT queriesprotected Query
query
aQuery
used to filter the documents that should be used from this classifier's underlyingLeafReader
protected String[]
textFieldNames
the name of the fields used as the input text
-
Constructor Summary
Constructors Constructor Description KNearestNeighborClassifier(IndexReader indexReader, Similarity similarity, Analyzer analyzer, Query query, int k, int minDocsFreq, int minTermFreq, String classFieldName, String... textFieldNames)
Creates aKNearestNeighborClassifier
.
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description ClassificationResult<BytesRef>
assignClass(String text)
Assign a class (with score) to the given text Stringprotected List<ClassificationResult<BytesRef>>
buildListFromTopDocs(TopDocs topDocs)
build a list of classification results from search resultsprotected ClassificationResult<BytesRef>
classifyFromTopDocs(TopDocs knnResults)
TODOList<ClassificationResult<BytesRef>>
getClasses(String text)
Get all the classes (sorted by score, descending) assigned to the given text String.List<ClassificationResult<BytesRef>>
getClasses(String text, int max)
Get the firstmax
classes (sorted by score, descending) assigned to the given text String.String
toString()
-
-
-
Field Detail
-
mlt
protected final MoreLikeThis mlt
aMoreLikeThis
instance used to perform MLT queries
-
textFieldNames
protected final String[] textFieldNames
the name of the fields used as the input text
-
classFieldName
protected final String classFieldName
the name of the field used as the output text
-
indexSearcher
protected final IndexSearcher indexSearcher
anIndexSearcher
used to perform queries
-
k
protected final int k
the no. of docs to compare in order to find the nearest neighbor to the input text
-
query
protected final Query query
aQuery
used to filter the documents that should be used from this classifier's underlyingLeafReader
-
-
Constructor Detail
-
KNearestNeighborClassifier
public KNearestNeighborClassifier(IndexReader indexReader, Similarity similarity, Analyzer analyzer, Query query, int k, int minDocsFreq, int minTermFreq, String classFieldName, String... textFieldNames)
Creates aKNearestNeighborClassifier
.- Parameters:
indexReader
- the reader on the index to be used for classificationanalyzer
- anAnalyzer
used to analyze unseen textsimilarity
- theSimilarity
to be used by the underlyingIndexSearcher
ornull
(defaults toBM25Similarity
)query
- aQuery
to eventually filter the docs used for training the classifier, ornull
if all the indexed docs should be usedk
- the no. of docs to select in the MLT results to find the nearest neighborminDocsFreq
-MoreLikeThis.minDocFreq
parameterminTermFreq
-MoreLikeThis.minTermFreq
parameterclassFieldName
- the name of the field used as the output for the classifiertextFieldNames
- the name of the fields used as the inputs for the classifier, they can contain boosting indication e.g. title^10
-
-
Method Detail
-
assignClass
public ClassificationResult<BytesRef> assignClass(String text) throws IOException
Description copied from interface:Classifier
Assign a class (with score) to the given text String- Specified by:
assignClass
in interfaceClassifier<BytesRef>
- Parameters:
text
- a String containing text to be classified- Returns:
- a
ClassificationResult
holding assigned class of typeT
and score - Throws:
IOException
- If there is a low-level I/O error.
-
classifyFromTopDocs
protected ClassificationResult<BytesRef> classifyFromTopDocs(TopDocs knnResults) throws IOException
TODO- Throws:
IOException
-
getClasses
public List<ClassificationResult<BytesRef>> getClasses(String text) throws IOException
Description copied from interface:Classifier
Get all the classes (sorted by score, descending) assigned to the given text String.- Specified by:
getClasses
in interfaceClassifier<BytesRef>
- Parameters:
text
- a String containing text to be classified- Returns:
- the whole list of
ClassificationResult
, the classes and scores. Returnsnull
if the classifier can't make lists. - Throws:
IOException
- If there is a low-level I/O error.
-
getClasses
public List<ClassificationResult<BytesRef>> getClasses(String text, int max) throws IOException
Description copied from interface:Classifier
Get the firstmax
classes (sorted by score, descending) assigned to the given text String.- Specified by:
getClasses
in interfaceClassifier<BytesRef>
- Parameters:
text
- a String containing text to be classifiedmax
- the number of return list elements- Returns:
- the whole list of
ClassificationResult
, the classes and scores. Cut for "max" number of elements. Returnsnull
if the classifier can't make lists. - Throws:
IOException
- If there is a low-level I/O error.
-
buildListFromTopDocs
protected List<ClassificationResult<BytesRef>> buildListFromTopDocs(TopDocs topDocs) throws IOException
build a list of classification results from search results- Parameters:
topDocs
- the search results as aTopDocs
object- Returns:
- a
List
ofClassificationResult
, one for each existing class - Throws:
IOException
- if it's not possible to get the stored value of class field
-
-