hetero_feature_union.py 文件源码

def transform(self, posts):
        features = np.recarray(shape=(len(posts),),
                               dtype=[('subject', object), ('body', object)])
        for i, text in enumerate(posts):
            headers, _, bod = text.partition('\n\n')
            bod = strip_newsgroup_footer(bod)
            bod = strip_newsgroup_quoting(bod)
            features['body'][i] = bod

            prefix = 'Subject:'
            sub = ''
            for line in headers.split('\n'):
                if line.startswith(prefix):
                    sub = line[len(prefix):]
                    break
            features['subject'][i] = sub

        return features