import json # 读取数据,我们的数据为json格式的
data = []
with open("./data/arxiv-metadata-oai-snapshot.json", 'r') as f:
for idx, line in enumerate(f):
d = json.loads(line)
d = {'authors': d['authors'], 'categories': d['categories'], 'authors_parsed': d['authors_parsed']}
data.append(d)
data = pd.DataFrame(data)
03-16