keyphrase.py 文件源码

def keyphrases(self, N=20, fileids=None, categories=None):
        """
        Returns the top N keyphrases grouped by document id.
        TODO: this currently ignores fileids/categories.
        """
        if not self.tfidfs or not self.lexicon or not self.fileids:
            raise ValueError("Must call the score method first!")

        for idx, doc in enumerate(self.tfidfs):
            fileid = self.fileids[idx]

            # Get the top N terms by TF-IDF score
            scores = [
                (self.lexicon[wid], score)
                for wid, score in heapq.nlargest(N, doc, key=itemgetter(1))
            ]

            yield fileid, scores