vectorizer.py 文件源码

def vect_(self):
        if not hasattr(self, '_vect') or self._vect is None:
            mid = self.dsid
            mid_dir = self.cache_dir / mid
            if not mid_dir.exists():
                raise ValueError(('Vectorizer model id {} ({}) '
                                  'not found in the cache {}!')
                                 .format(mid, mid_dir))
            fname = mid_dir / 'vectorizer'
            if self.pars_['use_hashing']:
                self._vect = joblib.load(str(fname))
            else:
                # this is much faster in python 3 as cpickle is used
                # (only works if no numpy arrays are used)
                with fname.open('rb') as fh:
                    self._vect = pickle.load(fh)
        return self._vect