7b881943c322c1a98eaab359b3ee9b148c9c3268,magpie/base/global_index.py,GlobalFrequencyIndex,__init__,#GlobalFrequencyIndex#Any#,11

Before Change

        self.X = self.vectorizer.fit_transform(contents)

        self.transformer = TfidfTransformer()
        self.tfidf = self.transformer.fit_transform(self.X)

    def get_term_occurrences(self, term):
        words = term.split()
        scores = [self._get_word_occurrences(w) for w in words]

After Change

                    for d in documents]

        // Build the index
        for doc_id, words in contents:
            for w in words:
                self.index[stem(w)].add(doc_id)

    // def get_term_occurrences(self, term):
    //     words = term.split()
    //     scores = [self._get_word_occurrences(w) for w in words]
    //
    //     // TODO another function could do here
    //     return sum(scores)
    //
    // def _get_word_occurrences(self, word):
    //     stemmed = stem(word)
    //     word_id = self.vectorizer.vocabulary_.get(stemmed)
    //     if word_id:
    //         return self.X[:, word_id].sum()
    //     else:
    //         return 0

    def get_term_idf(self, term):
        words = term.split()
        scores = [self._get_word_idf(w) for w in words]

Instances