def generate_raw_data(input_file, embed_map, gen_type='gold'):
print('loading data from %s' % input_file)
data_reader = jsonlines.open(input_file)
raw_data = []
for doc_data in data_reader.iter():
doc = Document(doc_data, embed_map)
if gen_type == 'gold':
raw_data += doc.generate_gold_anaphor_data()
else:
raw_data += doc.generate_candidate_anaphor_data()
print("---> total number of training pairs: %s" % len(raw_data))
return raw_data
