keyword_extractor.py 文件源码

def extract(self, text, max_length=3, metric='avg', incl_scores=False):
        """Extract keywords and keyphrases from input text in descending order of score"""
        sentences = nltk.sent_tokenize(text)
        phrase_list = self._generate_candidate_keywords(sentences, max_length=max_length)
        word_scores = self._calculate_word_scores(phrase_list)
        phrase_scores = self._calculate_phrase_scores(phrase_list, word_scores, metric=metric)
        sorted_phrase_scores = sorted(phrase_scores.iteritems(), key=operator.itemgetter(1), reverse=True)
        n_phrases = len(sorted_phrase_scores)

        if incl_scores:
            return sorted_phrase_scores[0:int(n_phrases/self.top_fraction)]
        else:
            return map(lambda x: x[0], sorted_phrase_scores[0:int(n_phrases/self.top_fraction)])