for j in clazz:
clazz_dict[list(j.keys())[0]] = clazz_index
for i in conf_rat_list:
conf_rat_dict[list(i.keys())[0]] = list(i.values())[0]
conf_rank()
dataset = open(sys.argv[1]).read().split("\n")[1:]
output = open(sys.argv[2], "a")
all_count = len(dataset)
bar = DownloadProgressBar(max=all_count - 1)
value = 0
output.write(get_features("", head=True))
print("正在生成全部特征 ...")
for i in bar.iter(range(all_count - 1)):
line = dataset[value]
author_name = line.split(",")[0]
if author_name != "":
feature = get_features(author_name)
output.write(feature)
value += 1
def check_dimension():
s = open(sys.argv[2], "r")
print("正在检查维数")
while True:
line = s.readline()
if line == "":
break
rs['year'] = int(info[2:])
elif info[:2] == '#c':
rs['conf'] = info[2:]
elif info[:2] == '#%':
rs['ref'].append(int(info[2:]))
if rs['year'] == None: print(s)
if rs['year'] > 2013: return False
return index, rs
paper_dict = dict()
all_count = len(papers)
bar_count = int(ceil(len(papers) / 1000))
bar = DownloadProgressBar(max=bar_count)
_i = 0
for i in bar.iter(range(bar_count)):
for j in range(_i * 1000, (_i + 1) * 1000):
if j == all_count:
break
paper = handlePaperInfo(papers[j])
if paper == False:
continue
paper_dict[paper[0]] = paper[1]
_i += 1
papers = paper_dict
print("正在构建被引用关系")
cnt = 0
for p_index in papers.keys():
paper = papers[p_index]
if "ref" in paper:
