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 main(args):
count = 0
stime = time.time()
csv_list = read_csv(args.csv_file)
etime = time.time()
cdq = ClusterDB('/home/dnlab/DataHDD/dbv3cluster.db')
print("DEBUG:", csv_list[0], etime - stime)
print("START UNION FIND")
stime = time.time()
#u = uf.UnionFind(int(cdq.get_max_address())+1)
u = uf.UnionFind(int(200000000))
etime = time.time()
print(f"MAKE ADDRESS END, TOTAL TIME:{etime - stime}")
for first, second in csv_list:
u.union(first, second)
if count % 10000000 == 0:
etime = time.time()
print(f"COUNT {count} END, TOTAL TIME: {etime - stime}")
count += 1
etime = time.time()
print(f"UNION FIND END TOTAL TIME:{etime - stime}")
del u.rank
print("START CLUSTERING")
stime = time.time()
count = 0
addr_list = list()
for index, cluster in enumerate(u.par):
addr_list.append((str(index), u.find(cluster)))
del u.par
df = pd.DataFrame(
addr_list,
columns=['addr', 'number'],
)
df.to_csv('/home/dnlab/DataHDD/cluster_result/40man.csv', index=False)
etime = time.time()
print(f"CLUSTERING END:{etime - stime}")
def main(args):
count = 0
stime = time.time()
csv_list = read_csv(args.csv_file)
etime = time.time()
cdq = ClusterDB('/home/dnlab/DataHDD/database/multi-input25man.db')
cdq.create_cluster_table()
print("DEBUG:", csv_list[0], etime - stime)
print("START UNION FIND")
stime = time.time()
#u = uf.UnionFind(int(dq.get_max_address())+1)
u = uf.UnionFind(90000000)
etime = time.time()
print(f"MAKE ADDRESS END, TOTAL TIME:{etime - stime}")
for first, second in csv_list:
u.union(first, second)
if count % 10000000 == 0:
etime = time.time()
print(f"COUNT {count} END, TOTAL TIME: {etime - stime}")
count += 1
etime = time.time()
print(f"UNION FIND END TOTAL TIME:{etime - stime}")
del u.rank
print("START CLUSTERING")
stime = time.time()
count = 0
addr_list = list()
for index, cluster in enumerate(u.par):
addr_list.append((str(index), u.find(cluster)))
if count % 10000 == 0:
cdq.begin_transactions()
cdq.insert_cluster_many(addr_list)
cdq.commit_transactions()
etime = time.time()
print(
f"COUNT {count} END, TOTAL TIME: {etime - stime}, {addr_list[len(addr_list)-1]}"
)
del addr_list
addr_list = list()
count += 1
cdq.begin_transactions()
cdq.insert_cluster_many(addr_list)
cdq.commit_transactions()
del addr_list
etime = time.time()
del u.par
print(f"CLUSTERING END:{etime - stime}")
import sys
sys.path.append('/home/dnlab/Jupyter-Bitcoin/Heuristics/ExperimentSpeed/')
import pandas as pd
from test_cluster_db_query import ClusterDB
import test_db_query as dq
import csv
import time
cdq = ClusterDB('/home/dnlab/DataSSD/dbv3cluster.db')
df = pd.read_csv('/home/dnlab/DataHDD/tag_v2.csv')
df = df[df['len'] > 500]
clt_list = []
count = 0
for addr_group in df['group'].to_list():
s_time = time.time()
addr_list = cdq.find_addr_from_cluster_num(addr_group)
cluster_list = list(cdq.get_tag_from_addr(addr_list))
#if len(addr_list) > 10000:
count += 1
cls_list.append(",".join(cluster_list))
if count % 10 == 0:
print(count, cat_list[-1], time.time() - s_time)
cat_list = []
count = 0
for addr_group in df['group'].to_list():