imdb.py 文件源码

def __init__(self, path, text_field, label_field, **kwargs):
        """Create an IMDB dataset instance given a path and fields.

        Arguments:
            path: Path to the dataset's highest level directory
            text_field: The field that will be used for text data.
            label_field: The field that will be used for label data.
            Remaining keyword arguments: Passed to the constructor of
                data.Dataset.
        """
        fields = [('text', text_field), ('label', label_field)]
        examples = []

        for label in ['pos', 'neg']:
            for fname in glob.iglob(os.path.join(path, label, '*.txt')):
                with open(fname, 'r') as f:
                    text = f.readline()
                examples.append(data.Example.fromlist([text, label], fields))

        super(IMDB, self).__init__(examples, fields, **kwargs)