def getCategoryProbabilityFromDocument(self, document):
if self._nltkClassifier == None:
raise ClassifierException("The classifier must first be loaded by the loadClassifier() method")
docwords = [word for word in document_as_words(document) if word not in nltk.corpus.stopwords.words('english')]
bigrams = bigram_feats(docwords,200)
words = word_feats(docwords,2000)
featureset = dict(bigrams.items() + words.items())
probdist = self._nltkClassifier.prob_classify(featureset)
results = []
samples = probdist.samples()
for i in samples:
prob = probdist.prob(i)
if (prob >= 0.001):
results.append((probdist.prob(i),i))
results = sorted(results, reverse=True)
return results
def getCategoryFromDocument(self, document):
if self._nltkClassifier == None:
raise ClassifierException("The classifier must first be loaded by the loadClassifier() method")
docwords = document_as_words(document)
topic = self._nltkClassifier.classify(docwords)
return topic
