def read(self, file_path):
instances = []
with open(file_path, "r") as data_file:
logger.info("Reading instances from lines in file at: %s", file_path)
for line_num, line in enumerate(tqdm.tqdm(data_file)):
line = line.strip("\n")
if not line:
continue
line_parts = line.split('\t')
if len(line_parts) != 2:
raise ConfigurationError("Invalid line format: %s (line number %d)" % (line, line_num + 1))
source_sequence, target_sequence = line_parts
instances.append(self.text_to_instance(source_sequence, target_sequence))
if not instances:
raise ConfigurationError("No instances read!")
return Dataset(instances)
评论列表
文章目录