def main(args):
term = 10000
start_height = 1
end_height = dq.get_max_height()
pool_num = multiprocessing.cpu_count() // 2
cdq = ClusterDB(args.dbpath)
stime = time.time()
u = uf.UnionFind(int(dq.get_max_address()) + 1)
try:
for sheight, eheight in zip(range(start_height, end_height, term), \
range(start_height+term, end_height+term, term)):
if eheight >= end_height:
eheight = end_height + 1
with multiprocessing.Pool(pool_num) as p:
result = p.imap(one_time_change, range(sheight, eheight))
for addr_list in result:
for addr_set in addr_list:
addr_1 = addr_set[0]
addr_2 = addr_set[1]
print(addr_1, ',', addr_2)
u.union(int(addr_1), int(addr_2))
etime = time.time()
#print('height: {}, time:{}'.format(eheight, etime-stime))
del u.rank
db_write(stime, cdq, u)
except KeyboardInterrupt:
print('Keyboard Interrupt Detected! Commit transactions...')
cdq.commit_transactions()
def main():
start_addr = 0
end_addr = dq.get_max_address()
print("max_addr:", end_addr)
cdq = ClusterDB('/home/dnlab/DataHDD/dbv3cluster.db')
cdq.create_cluster_table()
stime = time.time()
for i in range(start_addr, end_addr, 10000):
cdq.begin_transactions()
addr_list = dq.get_addr_many(i, i + 10000)
cdq.insert_cluster_many(addr_list)
etime = time.time()
print('addr index: {}, time:{}'.format(i, etime-stime))
cdq.commit_transactions()
def is_resume():
cur_address = cdq.get_max_address()
max_address = dq.get_max_address()
if cur_address == max_address:
return False
return True
def resume():
if is_resume():
term = 10000
start_height = cdq.get_max_height()
end_height = dq.gext_max_height()
pool_num = multiprocessing.cpu_count()//2
s_index = cdq.get_max_address()
u = uf.UnionFind(dq.get_max_address() - s_index + 1)
try:
for sheight, eheight in zip(range(start_height, end_height, term), \
range(start_height+term, end_height+term, term)):
if eheight >= end_height:
eheight = end_height + 1
with multiprocessing.Pool(pool_num) as p:
result = p.imap(multi_input, range(sheight, eheight))
for addr_list in result:
for addr_set in addr_list:
addr_1 = addr_set[0]
addr_2 = addr_set[1]
u.union(int(addr_1) - s_index, int(addr_2) - s_index)
etime = time.time()
print('height: {}, time:{}'.format(eheight, etime-stime))
del u.rank
except KeyboardInterrupt:
print('Keyboard Interrupt Detected! Commit transactions...')
cdq.commit_transactions()
addr_list = []
count = 0
for index, cluster in enumerate(u.par):
addr_list.append((str(index + s_index), u.find(cluster) + s_index))
count += 1
df = pd.DataFrame(addr_list, columns =['Address', 'ClusterNum'])
mi_group = mi_df.groupby('ClusterNum')
for cluster_number, addr_group in mi_group:
if cluster_number != -1:
addr_list = list(addr_group.Address)
cluster_num_list = list(cdq.get_cluster_number(addr_list))
if len(cluster_num_list) <= 1:
if cluster_num == -1:
insert_cluster_many(list(zip(addr_list, [cluster_number] * len(addr_list))))
else:
insert_cluster_many(list(zip(addr_list, [cluster_num] * len(addr_list))))
else:
cluster_num_list.sort()
cluster_num = cluster_num_list.pop(0)
if cluster_num == -1:
cluster_num = cluster_num_list.pop(0)
#TODO 만약 같은 주소가 존재한다면 update 그렇지 않다면 insert
update_cluster_many(list(zip([cluster_num] * len(addr_list), addr_list)))
'''
지속적인 비트코인 주소를 업데이트하는 함수
1. 현재주소와, 최대주소 비교 (Meta Table 만드는것 추천)
2. 현재주소와 최대주소가 다르다면, Clustering 시작
3. start_height = Metatable.blk.+1
end_height = dq.get_max_height()
4. index = cur_addr
5. uf.UnionFind(max_addr - cur_addr + 1)
6. 아래와 유사
** u.union(int(addr_1) - index, int(addr_2) - index) ** ==> 함수 1 union
addr_list.append((str(index) + index, u.find(cluster)+index)) ==> 함수 2 Clustering
df = pd.DataFrame(addr_list)
for cluster_list groupby 해서 주소리스트를 가져옴: ==> dbwrite
- 주소들이 포함된 모든 클러스터 번호를 가져옴
만약 클러스터 번호가 없다면 그대로 add
- 클러스터 번호가 1개라면 그 번호로 클러스터 add
- 만약 클러스터 번호가 여러개라면 가장 작은것으로 add후
다른 클러스터가 있는것은 update
'''
def main(args):
term = 10000
start_height = 1
end_height = dq.get_max_height()
pool_num = multiprocessing.cpu_count()//2
cdq = ClusterDB(args.dbpath)
stime = time.time()
u = uf.UnionFind(int(dq.get_max_address())+1)
try:
for sheight, eheight in zip(range(start_height, end_height, term), \
range(start_height+term, end_height+term, term)):
if eheight >= end_height:
eheight = end_height + 1
with multiprocessing.Pool(pool_num) as p:
result = p.imap(multi_input, range(sheight, eheight))
for addr_list in result:
for addr_set in addr_list:
addr_1 = addr_set[0]
addr_2 = addr_set[1]
u.union(int(addr_1), int(addr_2))
etime = time.time()
print('height: {}, time:{}'.format(eheight, etime-stime))
del u.rank
db_write(stime, cdq, u)
except KeyboardInterrupt:
print('Keyboard Interrupt Detected! Commit transactions...')
cdq.commit_transactions()
if __name__=="__main__":
import argparse
parser = argparse.ArgumentParser(description='Heuristics Clusterings')
parser.add_argument('--dbpath', '-d', type=str,
required=True,
help='insert make dbpath')
parser.add_argument('--resume', '-r', type=bool,
default=False,
help='execute resume')
args = parser.parse_args()
main(args)