stemmer = OrengoStemmer() # or PorterStemmer() or SavoyStemmer()
print stemmer.getWordStem("extremamente")
stemmer.enableCaching(1000) stemmer.ignore(PTStemmerUtilities.fileToSet("data/stopwords.txt")) stemmer.ignore(PTStemmerUtilities.fileToSet("data/namedEntities.txt")) stem = stemmer.getWordStem("ciências") print PTStemmerUtilities.removeDiacritics(stem)
There was an error while loading. Please reload this page.