Dependencies
Declarations
-
org
-
apache
-
lucene
-
classification
-
BM25NBClassifier
- indexReader: IndexReader
- textFieldNames: String[]
- classFieldName: String
- analyzer: Analyzer
- indexSearcher: IndexSearcher
- query: Query
- BM25NBClassifier(IndexReader, Analyzer, Query, String, String[]): void
- assignClass(String): ClassificationResult<BytesRef>
- getClasses(String): List<ClassificationResult<BytesRef>>
- getClasses(String, int): List<ClassificationResult<BytesRef>>
- assignClassNormalizedList(String): List<ClassificationResult<BytesRef>>
- normClassificationResults(List<ClassificationResult<BytesRef>>): ArrayList<ClassificationResult<BytesRef>>
- tokenize(String): String[]
- calculateLogLikelihood(String[], Term): double
- getTermProbForClass(Term, String[]): double
- calculateLogPrior(Term): double
-
BooleanPerceptronClassifier
- bias: Double
- textTerms: Terms
- analyzer: Analyzer
- textFieldName: String
- fst: FST<Long>
- BooleanPerceptronClassifier(IndexReader, Analyzer, Query, Integer, Double, String, String): void
- updateWeights(IndexReader, int, Boolean, SortedMap<String, Double>, double, boolean): void
- updateFST(SortedMap<String, Double>): void
- assignClass(String): ClassificationResult<Boolean>
- getClasses(String): List<ClassificationResult<Boolean>>
- getClasses(String, int): List<ClassificationResult<Boolean>>
-
CachingNaiveBayesClassifier
- cclasses: ArrayList<BytesRef>
- termCClassHitCache: Map<String, Map<BytesRef, Integer>>
- classTermFreq: Map<BytesRef, Double>
- justCachedTerms: boolean
- docsWithClassSize: int
- CachingNaiveBayesClassifier(IndexReader, Analyzer, Query, String, String[]): void
- assignClassNormalizedList(String): List<ClassificationResult<BytesRef>>
- calculateLogLikelihood(String[]): List<ClassificationResult<BytesRef>>
- getWordFreqForClassess(String): Map<BytesRef, Integer>
- reInitCache(int, boolean): void
- ClassificationResult
- Classifier
-
KNearestFuzzyClassifier
- k: int
- assignClass(String): ClassificationResult<BytesRef>
- textFieldNames: String[]
- classFieldName: String
- indexSearcher: IndexSearcher
- query: Query
- analyzer: Analyzer
- KNearestFuzzyClassifier(IndexReader, Similarity, Analyzer, Query, int, String, String[]): void
- getClasses(String): List<ClassificationResult<BytesRef>>
- getClasses(String, int): List<ClassificationResult<BytesRef>>
- knnSearch(String): TopDocs
- buildListFromTopDocs(TopDocs): List<ClassificationResult<BytesRef>>
- toString(): String
-
KNearestNeighborClassifier
- mlt: MoreLikeThis
- textFieldNames: String[]
- classFieldName: String
- indexSearcher: IndexSearcher
- k: int
- query: Query
- KNearestNeighborClassifier(IndexReader, Similarity, Analyzer, Query, int, int, int, String, String[]): void
- assignClass(String): ClassificationResult<BytesRef>
- classifyFromTopDocs(TopDocs): ClassificationResult<BytesRef>
- getClasses(String): List<ClassificationResult<BytesRef>>
- getClasses(String, int): List<ClassificationResult<BytesRef>>
- knnSearch(String): TopDocs
- buildListFromTopDocs(TopDocs): List<ClassificationResult<BytesRef>>
- toString(): String
-
SimpleNaiveBayesClassifier
- indexReader: IndexReader
- textFieldNames: String[]
- classFieldName: String
- analyzer: Analyzer
- indexSearcher: IndexSearcher
- query: Query
- SimpleNaiveBayesClassifier(IndexReader, Analyzer, Query, String, String[]): void
- assignClass(String): ClassificationResult<BytesRef>
- getClasses(String): List<ClassificationResult<BytesRef>>
- getClasses(String, int): List<ClassificationResult<BytesRef>>
- assignClassNormalizedList(String): List<ClassificationResult<BytesRef>>
- countDocsWithClass(): int
- tokenize(String): String[]
- calculateLogLikelihood(String[], Term, int): double
- getTextTermFreqForClass(Term): double
- getWordFreqForClass(String, Term): int
- calculateLogPrior(Term, int): double
- docCount(Term): int
- normClassificationResults(List<ClassificationResult<BytesRef>>): ArrayList<ClassificationResult<BytesRef>>
-
document
- DocumentClassifier
-
KNearestNeighborDocumentClassifier
- field2analyzer: Map<String, Analyzer>
- KNearestNeighborDocumentClassifier(IndexReader, Similarity, Query, int, int, int, String, Map<String, Analyzer>, String[]): void
- assignClass(Document): ClassificationResult<BytesRef>
- getClasses(Document): List<ClassificationResult<BytesRef>>
- getClasses(Document, int): List<ClassificationResult<BytesRef>>
- knnSearch(Document): TopDocs
-
SimpleNaiveBayesDocumentClassifier
- field2analyzer: Map<String, Analyzer>
- SimpleNaiveBayesDocumentClassifier(IndexReader, Query, String, Map<String, Analyzer>, String[]): void
- assignClass(Document): ClassificationResult<BytesRef>
- getClasses(Document): List<ClassificationResult<BytesRef>>
- getClasses(Document, int): List<ClassificationResult<BytesRef>>
- assignNormClasses(Document): List<ClassificationResult<BytesRef>>
- analyzeSeedDocument(Document, Map<String, List<String[]>>, Map<String, Float>): void
- getTokenArray(TokenStream): String[]
- calculateLogLikelihood(String[], String, Term, int): double
- getTextTermFreqForClass(Term, String): double
- getWordFreqForClass(String, String, Term): int
- calculateLogPrior(Term, int): double
- docCount(Term): int
-
utils
-
ConfusionMatrixGenerator
- ConfusionMatrixGenerator(): void
- getConfusionMatrix(IndexReader, Classifier<Object>, String, String, long): ConfusionMatrix
-
ConfusionMatrix
- linearizedMatrix: Map<String, Map<String, Long>>
- avgClassificationTime: double
- numberOfEvaluatedDocs: int
- accuracy: double
- ConfusionMatrix(Map<String, Map<String, Long>>, double, int): void
- getLinearizedMatrix(): Map<String, Map<String, Long>>
- getPrecision(String): double
- getRecall(String): double
- getF1Measure(String): double
- getF1Measure(): double
- getAccuracy(): double
- getPrecision(): double
- getRecall(): double
- toString(): String
- getAvgClassificationTime(): double
- getNumberOfEvaluatedDocs(): int
- DatasetSplitter
- DocToDoubleVectorUtils
-
NearestFuzzyQuery
- fieldVals: ArrayList<FieldVals>
- analyzer: Analyzer
- MAX_VARIANTS_PER_TERM: int
- MIN_SIMILARITY: float
- PREFIX_LENGTH: int
- MAX_NUM_TERMS: int
- NearestFuzzyQuery(Analyzer): void
- FieldVals
- addTerms(String, String): void
- addTerms(IndexReader, FieldVals, ScoreTermQueue): void
- idf(int, int): float
- newTermQuery(IndexReader, Term): Query
- rewrite(IndexReader): Query
- ScoreTerm
- ScoreTermQueue
- toString(String): String
- hashCode(): int
- equals(Object): boolean
- equalsTo(NearestFuzzyQuery): boolean
- visit(QueryVisitor): void
-
ConfusionMatrixGenerator
-
BM25NBClassifier
-
classification
-
lucene
-
apache