feature_extractors.py 文件源码

def __init__(self, language='en', window_width=2, collapse_fes=True, target_size=None):
        """ Initializes the extractor.

            :param language: The language of the sentences that will be used
            :param window_width: how many tokens to look before and after a each
             token when building its features.
            :param collapse_fes: Whether to collapse FEs to a single token
             or to keep them split.
        """
        self.language = language
        self.tagger = TTPosTagger(language)
        self.window_width = window_width
        self.collapse_fes = collapse_fes
        self.unk_feature = 'UNK'
        self.vectorizer = DictVectorizer()
        self.target_size = target_size
        self.reducer = TruncatedSVD(target_size) if target_size else None
        self.vocabulary = set()
        self.label_index = {}
        self.lu_index = {}
        self.stopwords = set(w.lower() for w in StopWords().words(language))
        self.start()