model.py 文件源码

def get_predict_data(self, preprocessed, n_jobs=-1):
        """Compute the feature matrix and extract the subseq info."""
        def _subdict(dic):
            subdict = dict((k, dic[k]) for k in [
                           'tr_name', 'center', 'tr_len'] if k in dic)
            return subdict

        preprocessed, preprocessed_ = tee(preprocessed)
        if self.mode == 'sequence':
            info = [_subdict(attr) for attr, _ in preprocessed_]
        else:
            info = [_subdict(g.graph['id']) for g in preprocessed_]

        if self.mode == 'sequence':
            self.vectorizer = SeqVectorizer(auto_weights=True,
                                            **self.vectorizer_args)
        else:
            self.vectorizer = GraphVectorizer(auto_weights=True,
                                              **self.vectorizer_args)
        matrix = vectorize(preprocessed, vectorizer=self.vectorizer,
                           block_size=400, n_jobs=n_jobs)
        return matrix, info