text.py 文件源码

def _count_vocab(self, raw_documents, fixed_vocab):
        """Create sparse feature matrix, and vocabulary where fixed_vocab=False
        """
        if fixed_vocab:
            vocabulary = self.vocabulary_
        else:
            # Add a new value when a new vocabulary item is seen
            vocabulary = defaultdict()
            vocabulary.default_factory = vocabulary.__len__

        analyze = self.build_analyzer()
        j_indices = _make_int_array()
        indptr = _make_int_array()
        indptr.append(0)
        for doc in raw_documents:
            for feature in analyze(doc):
                try:
                    j_indices.append(vocabulary[feature])
                except KeyError:
                    # Ignore out-of-vocabulary items for fixed_vocab=True
                    continue
            indptr.append(len(j_indices))

        if not fixed_vocab:
            # disable defaultdict behaviour
            vocabulary = dict(vocabulary)
            if not vocabulary:
                raise ValueError("empty vocabulary; perhaps the documents only"
                                 " contain stop words")

        j_indices = frombuffer_empty(j_indices, dtype=np.intc)
        indptr = np.frombuffer(indptr, dtype=np.intc)
        values = np.ones(len(j_indices))

        X = sp.csr_matrix((values, j_indices, indptr),
                          shape=(len(indptr) - 1, len(vocabulary)),
                          dtype=self.dtype)
        X.sum_duplicates()
        return vocabulary, X