model.py 文件源码

def get_supervised_data(self, preprocessed, bin_sites,
                            active_learning=False, random_state=1234,
                            n_jobs=-1):
        """Compute the feature matrix and the regression values."""
        preprocessed, preprocessed_ = tee(preprocessed)
        if self.mode == 'sequence':
            dists = [attr['dist'] for attr, _ in preprocessed_]
        else:
            dists = [g.graph['id']['dist'] for g in preprocessed_]
        vals = np.array([common.dist_to_val(d, self.max_dist) for d in dists])
        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, vals