def shard_generator(): # TODO Enable sharding with shard size parameter
for input_file in input_files:
if self.legacy:
X = encode_bio_sequence(input_file)
else:
sequences = _read_file(input_file)
X = self.featurizer(sequences)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids
def shard_generator():
for input_file in input_files:
X = encode_bio_sequence(input_file)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids