Method transform

sklearn/feature_extraction/text.py:865–893

Transform a sequence of documents to a document-term matrix. Parameters ---------- X : iterable over raw text documents, length = n_samples Samples. Each sample must be a text document (either bytes or unicode strings, file name or file object dependi

(self, X)

        return self

    def transform(self, X):
        """Transform a sequence of documents to a document-term matrix.

        Parameters
        ----------
        X : iterable over raw text documents, length = n_samples
            Samples. Each sample must be a text document (either bytes or
            unicode strings, file name or file object depending on the
            constructor argument) which will be tokenized and hashed.

        Returns
        -------
        X : sparse matrix of shape (n_samples, n_features)
            Document-term matrix.
        """
        if isinstance(X, str):
            raise ValueError(
                "Iterable over raw text documents expected, string object received."
            )

        self._validate_ngram_range()

        analyzer = self.build_analyzer()
        X = self._get_hasher().transform(analyzer(doc) for doc in X)
        if self.binary:
            X.data.fill(1)
        if self.norm is not None:
            X = normalize(X, norm=self.norm, copy=False)
        return _align_api_if_sparse(X)

    def fit_transform(self, X, y=None):
        """Transform a sequence of documents to a document-term matrix.