def convert_model(self, model: Snippet) -> BOW:
bags = [self._uasts2bow(uast) for uast in model.uasts]
data = list(zip(*[(bag_[x], i, x) for i, bag_ in enumerate(bags) for x in bag_]))
matrix = csr_matrix((data[0], (data[1], data[2])),
shape=(len(bags), len(self._uasts2bow.vocabulary)),
dtype=numpy.float32)
bow = BOW(log_level=logging.WARNING)
bow.construct(repos=model.names, matrix=matrix, tokens=self._tokens)
bow.meta["dependencies"] = [self._uasts2bow.docfreq]
return bow
def convert_model(self, model: UASTModel) -> BOW:
bag = self._uasts2bow(model.uasts)
data = numpy.array(list(bag.values()), dtype=numpy.float32)
indices = numpy.array(list(bag.keys()), dtype=numpy.int32)
matrix = csr_matrix((data, indices, [0, len(data)]),
shape=(1, len(self._uasts2bow.vocabulary)))
bow = BOW(log_level=logging.WARNING)
bow.construct(repos=[model.repository],
matrix=matrix,
tokens=self._tokens)
bow.meta["dependencies"] = [self._uasts2bow.docfreq]
return bow