public class LanguageModels extends Object
| Constructor and Description |
|---|
LanguageModels(Locale language,
Map<Locale,LanguageModel> modelsMap) |
LanguageModels(Locale language,
Map<String,Double> idfDictionary,
Locale defaultLanguage) |
| Modifier and Type | Method and Description |
|---|---|
DocumentVector |
buildDocumentVector(Locale language,
String document,
de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher keywordMatcher) |
de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher |
buildMatcher(Locale lang,
Iterable<String> keywords,
int ngramSize) |
Locale |
getDefaultLanguage() |
double |
getSimilarity(Locale language,
String doc,
DocumentVector reference,
de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher matcher)
calculate the cosine-similarity of the doc to the specification
|
static Map<String,Double> |
readIdfDictionary(InputStream is) |
static LanguageModel |
readLanguageModel(Locale locale,
InputStream idfIs) |
public LanguageModels(Locale language, Map<String,Double> idfDictionary, Locale defaultLanguage)
public LanguageModels(Locale language, Map<Locale,LanguageModel> modelsMap)
public Locale getDefaultLanguage()
public double getSimilarity(Locale language, String doc, DocumentVector reference, de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher matcher)
language - the language of this documentdoc - the text of the documentpublic de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher buildMatcher(Locale lang, Iterable<String> keywords, int ngramSize)
public DocumentVector buildDocumentVector(Locale language, String document, de.l3s.icrawl.contentanalysis.LanguageModel.KeywordMatcher keywordMatcher)
public static Map<String,Double> readIdfDictionary(InputStream is) throws IOException
IOExceptionpublic static LanguageModel readLanguageModel(Locale locale, InputStream idfIs) throws IOException
IOExceptionCopyright © 2017. All rights reserved.