def main():
testbase = 'ub'
dataset_name = "u1m.data"
f = open('../testres.txt', 'a+')
k_val = [5]
per = [30]
#per = [1.4]
#metric = 'pr'
metric = 'mae'
#k_val = [5 9, 13, 17, 21]
test_name = "New User-based Test on: " + dataset_name + ' '
if item_based:
testbase = 'ib'
test_name = "New Item-based test on: " + dataset_name + ' '
iterate = product(per, k_val)
for per, k in iterate:
f.write('\n')
timestamp = strftime("%Y-%m-%d %H:%M:%S", gmtime())
f.write(test_name + timestamp + ' --> ')
e = Evaluater(dataset_name, rec_type=testbase, k=k, test_percentage=per,
eval_metric=metric)
f.write(str([per, k, e.eval_metric, e.sim_method.func_name]) + ' Error: ')
f.write(str(e.evaluate()))
f.close()
def main():
testbase = 'ub'
dataset_name = "u1m.data"
f = open('../testres.txt', 'a+')
k_val = [5]
per = [30]
#per = [1.4]
#metric = 'pr'
metric = 'mae'
#k_val = [5 9, 13, 17, 21]
test_name = "New User-based Test on: " + dataset_name + ' '
if item_based:
testbase = 'ib'
test_name = "New Item-based test on: " + dataset_name + ' '
iterate = product(per, k_val)
for per, k in iterate:
f.write('\n')
timestamp = strftime("%Y-%m-%d %H:%M:%S", gmtime())
f.write(test_name + timestamp + ' --> ')
e = Evaluater(dataset_name,
rec_type=testbase,
k=k,
test_percentage=per,
eval_metric=metric)
f.write(
str([per, k, e.eval_metric, e.sim_method.func_name]) + ' Error: ')
f.write(str(e.evaluate()))
f.close()
def cal_loss_redundancy(resource, availability, replication, lease):
replication_count = 0
data_loss = 0
data_count = 100
data_iterated = 0
lease_period = int(lease)
desired_availability = float(availability)
iteration = 0
bad_iteration = 0
if replication == 'random1copy' or replication == 'min1copy':
copy_number = 1
elif replication == 'random2copy' or replication == 'min2copy':
copy_number = 2
elif replication == 'random3copy' or replication == 'min3copy':
copy_number = 3
while iteration < 30:
quantile = int(range_minute * 0.05)
time_point = random.randint(start_minute + quantile,
end_minute - quantile)
job_count = len(interval_tree[time_point])
# evaluate sizes of data set and job set
if job_count < data_count * 3 * copy_number:
# print "Error : job set is less than 3 times of data set"
bad_iteration += 1
continue
availability_dict = dict()
for data_index in range(data_count):
data_name = "data" + str(data_index)
availability_dict[data_name] = desired_availability
match_job_dict = scheduler.schedule(time_point, lease_period,
availability_dict)
if not match_job_dict:
# print "Error : match_job_dict is none"
bad_iteration += 1
continue
for job in match_job_dict:
replication_count += len(match_job_dict[job])
evaluater = Evaluater(interval_tree, job_dict)
data_iterated = data_iterated + data_count
data_loss += evaluater.evaluate(time_point + lease_period,
match_job_dict)
iteration += 1
data_loss_rate = float(data_loss) / float(data_iterated)
redundancy_rate = float(replication_count) / float(data_iterated)
print "data loss rate : ", data_loss_rate
print "redundancy : ", redundancy_rate
print "bad iteration : ", bad_iteration
return (data_loss_rate, redundancy_rate)
def main(p):
start = time.time()
# 选择文件名以'json.gz'结尾的记录
file_name_list = filter(lambda x: x.endswith('json.gz'), os.listdir(p))
# TODO 添加文件是否是24个的判断(glob模块)
for file_name in file_name_list:
with open(os.path.join(p, file_name), 'r') as f:
raw_json_file = gzip.GzipFile(fileobj=f)
record_cleaner = Cleaner()
record_grouper = Grouper(db)
record_normalizer = Normalizer(db)
mongo_helper = MongoHelper(db)
counter = ActorCounter()
evaluater = Evaluater()
# 数据清洗
record_cleaner.set_dirty_data(raw_json_file)
record_cleaner.clean()
clean_record = record_cleaner.get_clean_data()
log.log('clean record %s' % len(clean_record))
# 数据处理
# 分组
record_grouper.set_records(clean_record)
record_grouper.group()
record_actor_exist = record_grouper.get_group_1()
record_actor_new= record_grouper.get_group_2()
log.log('record_actor_exist: %s' % len(record_actor_exist))
log.log('record_actor_new: %s' % len(record_actor_new))
# 处理记录的actor已存在的记录
log.log('Begin processing actor-exist records...')
# 只需要删掉记录的actor_attrs即可
for record in record_actor_exist:
del record['actor_attributes']
log.log('Finished.')
# 处理记录的actor不存在的记录
record_normalizer.set_records(record_actor_new)
record_normalizer.normalize()
record_actor_new = record_normalizer.get_record_actor_new()
new_actors = record_normalizer.get_new_actors()
# 把本地的今日新增的Actor更新到数据库
actors = new_actors.values()
mongo_helper.insert_new_actors(actors)
# 对新增的Actor, 改变Redis中相应的计数
counter.count_actor_list(actors)
# 计算每条记录的val
evaluater.set_records(record_actor_exist)
evaluater.evaluate()
val_actor_exist = evaluater.get_val_cache()
evaluater.set_records(record_actor_new)
evaluater.evaluate()
val_actor_new = evaluater.get_val_cache()
# 将记录插入数据库
mongo_helper.insert_new_reocrds(record_actor_new)
mongo_helper.insert_new_reocrds(record_actor_exist)
# 将今日用户新增的val更新到数据库
mongo_helper.update_val(val_actor_new)
mongo_helper.update_val(val_actor_exist)
record_cleaner.free_mem()
del record_cleaner
del record_grouper
del record_normalizer
del mongo_helper
del counter
del evaluater
# 生成CSV文件
util.grcount2csv()
end = time.time()
log.log('total: %s s' % (end - start))
def main(p):
start = time.time()
# 选择文件名以'json.gz'结尾的记录
file_name_list = filter(lambda x: x.endswith('json.gz'), os.listdir(p))
# TODO 添加文件是否是24个的判断(glob模块)
for file_name in file_name_list:
with open(os.path.join(p, file_name), 'r') as f:
raw_json_file = gzip.GzipFile(fileobj=f)
record_cleaner = Cleaner()
record_grouper = Grouper(db)
record_normalizer = Normalizer(db)
mongo_helper = MongoHelper(db)
counter = ActorCounter()
evaluater = Evaluater()
# 数据清洗
record_cleaner.set_dirty_data(raw_json_file)
record_cleaner.clean()
clean_record = record_cleaner.get_clean_data()
log.log('clean record %s' % len(clean_record))
# 数据处理
# 分组
record_grouper.set_records(clean_record)
record_grouper.group()
record_actor_exist = record_grouper.get_group_1()
record_actor_new = record_grouper.get_group_2()
log.log('record_actor_exist: %s' % len(record_actor_exist))
log.log('record_actor_new: %s' % len(record_actor_new))
# 处理记录的actor已存在的记录
log.log('Begin processing actor-exist records...')
# 只需要删掉记录的actor_attrs即可
for record in record_actor_exist:
del record['actor_attributes']
log.log('Finished.')
# 处理记录的actor不存在的记录
record_normalizer.set_records(record_actor_new)
record_normalizer.normalize()
record_actor_new = record_normalizer.get_record_actor_new()
new_actors = record_normalizer.get_new_actors()
# 把本地的今日新增的Actor更新到数据库
actors = new_actors.values()
mongo_helper.insert_new_actors(actors)
# 对新增的Actor, 改变Redis中相应的计数
counter.count_actor_list(actors)
# 计算每条记录的val
evaluater.set_records(record_actor_exist)
evaluater.evaluate()
val_actor_exist = evaluater.get_val_cache()
evaluater.set_records(record_actor_new)
evaluater.evaluate()
val_actor_new = evaluater.get_val_cache()
# 将记录插入数据库
mongo_helper.insert_new_reocrds(record_actor_new)
mongo_helper.insert_new_reocrds(record_actor_exist)
# 将今日用户新增的val更新到数据库
mongo_helper.update_val(val_actor_new)
mongo_helper.update_val(val_actor_exist)
record_cleaner.free_mem()
del record_cleaner
del record_grouper
del record_normalizer
del mongo_helper
del counter
del evaluater
# 生成CSV文件
util.grcount2csv()
end = time.time()
log.log('total: %s s' % (end - start))
#k = [5]
#percentage = [10]
prod = product(datafiles, k, metrics, r_method, n)
for filename, k, metric, r_m, n in prod:
if filename == 'datahouse':
X, y = getXy(filename)
else:
X, y = getXy(filename, delimiter=',')
if n:
normalize(X)
print 'data is normalized'
else:
print 'data is not normalized'
reg = KNeighborClassifier(X, y, k, metric, r_method=r_m)
e = Evaluater(reg, test_percentage = 30)
print '\t', e.evaluate()
print '\n'
#reg = KNeighborClassifier(X, y, m, sim_cosine, r_method="uniform")
#e = Evaluater(reg, test_percentage = l)
#print 'Test: k=%s, test/all_data=%s' % (m, l)
#print "\t", e.evaluate()
#del reg, e
availability_dict = dict()
for data_index in range(data_count):
data_name = "data" + str(data_index)
availability_dict[data_name] = desired_availability
# print availability_dict
match_job_dict = scheduler.schedule(time_point, lease_period,
availability_dict)
if not match_job_dict:
print "Error : match_job_dict is none"
bad_iteration += 1
continue
# for job in match_job_dict:
# print job, match_job_dict[job]
evaluater = Evaluater(interval_tree, job_dict)
data_iterated = data_iterated + data_count
data_loss += evaluater.evaluate(time_point + lease_period,
match_job_dict)
iteration += 1
print "data_loss : ", data_loss
print "data_iterated : ", data_iterated
print "iteration, bad_iteration : ", iteration, bad_iteration
loss_rate_list.append(float(data_loss) / float(data_iterated))
print loss_rate_list
print loss_rate_list
resource_dict = {'SU-OG-CE': 'suogce', 'GLOW': 'glow', 'MWT2': 'mwt2'}
avail_dict = {'0.99': '099', '0.90': '090', '0.80': '080'}
file_name = resource_dict[sys.argv[1]] + '_avail_' + avail_dict[sys.argv[
2]] + '_replication_' + sys.argv[3] + '_lease_' + sys.argv[4] + '.txt'
print file_name
with open(file_name, 'wb') as fp:
pickle.dump(loss_rate_list, fp)
