def predict(data_path, model_path, config ):
image_size = config.image_size
model = keras.models.load_model(model_path)
for image_name in os.listdir(data_path):
image_path = get_path(data_path, image_name)
image = cv2.imread(image_path)
image = cv2.resize(image, (image_size, image_size))
predictions = model.predict([image.reshape(-1, image_size, image_size, 3)])
class_id = np.argmax(predictions)
class_name = get_category(config, class_id)
print(image_name + ': Prediction ' + class_name)
plt.imshow(image, cmap=plt.cm.binary)
plt.xlabel(class_name)
if config.display_plot:
plt.show()
db = client.test
@functools.lru_cache(maxsize=1000000)
def get_ad_info(aid):
ad_info = db.ad_info.find_one({"AdID": aid})
return trans_ad_info(ad_info)
uid_cnt_dict = read_dump("data/uid_cnt.dump")
adid_cnt_dict = read_dump("data/adid_cnt.dump")
ipid_cnt_dict = read_dump("data/ipid_cnt.dump")
query_cnt_dict = read_dump("data/query_cnt.dump")
title_cnt_dict = read_dump("data/title_cnt.dump")
query_param_cnt_dict = read_dump("data/query_param_cnt.dump")
ad_param_cnt_dict = read_dump("data/ad_param_cnt.dump")
user_info_map = get_user_info()
category_map = get_category()
user_cnt_iter = read_tsv("data/user_cnt.csv", delimiter=",")
user_aid_cnt_iter = next_row(read_tsv("data/user_aid_cnt.csv", delimiter=","))
main()
parser = argparse.ArgumentParser(description='Process some integers.')
parser.add_argument('--test', type=int, default=0)
parser.add_argument('--mongo', type=int, default=0)
parser.add_argument('--sz', type=int, default=None)
parser.add_argument('--maxl', type=int, default=1e6)
parser.add_argument('--type', type=str, default="ins")
parser.add_argument('--sr', type=float, default=0.1)
parser.add_argument('--seed', type=int, default=9)
parser.add_argument('--date', type=int, default=0)
parser.add_argument('--log', type=int, default=1)
args = parser.parse_args()
if args.mongo:
from pymongo import MongoClient
import functools32 as functools
client = MongoClient('localhost', 27017)
db = client.test
@functools.lru_cache(maxsize=1000000)
def get_ad_info(aid):
ad_info = db.ad_info.find_one({"AdID": aid})
return trans_ad_info(ad_info)
user_info_map = get_user_info()
category_map = get_category()
user_cnt_iter = read_tsv("data/user_cnt_%s.csv_sorted" % args.sz,
delimiter=",")
user_aid_cnt_iter = next_row(
read_tsv("data/user_aid_cnt_%s.csv_sorted" % args.sz, delimiter=","))
main()
def main():
if args.dir == None:
timestr = time.strftime("%Y%m%d-%H%M%S")
directory = os.path.join('experiment/', timestr)
else:
directory = args.dir
if not os.path.exists(directory):
os.mkdir(directory)
if args.sport:
sport = args.sport
else:
sport = random.randint(1024, 10000)
reps = 5
mss = args.mss
max_workers = 20
category_filename = os.path.join(directory, 'categories')
result_filename = os.path.join(directory, 'results.csv')
categories = {1:[], 2:[], 3:[], 4:[], 5:[]}
if args.ip:
ips = args.ip.split(',')
outputs = U.repeat_iw_query(ips=ips, sport=sport, reps=reps, mss=mss)
for j, output in enumerate(zip(*outputs)):
results, errors, use_error_req = output
category, result = U.get_category(results)
categories[category].append((ips[j], result))
result_str = ','.join([str(res) for res in results])
error_str = ','.join([str(error) for error in errors])
print('IP Address: {},Initial Windows: {}, Error Number: {}\n'.format(ips[j], result_str, error_str))
else:
if args.low == None or args.high == None:
raise Exception('Missing arguments to both IP and Low/High range. At least one must be supplied')
if args.low >= args.high:
raise Exception('Passed in low parameter is greater than or equal to high parameter. --low must be lower than --high')
num_ips = args.high - args.low
ip_list = U.get_ip_list(amount=num_ips, offset=args.low)
result_file = open(result_filename, 'w')
result_file.write('IP,Used_error,Results,Errors\n')
itr = math.ceil(len(ip_list) / max_workers)
pbar = tqdm(total=itr)
for i in range(itr):
end = min((i + 1) * max_workers, len(ip_list))
ips = ip_list[(i*max_workers):end]
outputs = U.repeat_iw_query(ips=ips, sport=sport, reps=reps, mss=mss)
for j, output in enumerate(zip(*outputs)):
results, errors, use_error_req = output
category, result = U.get_category(results)
categories[category].append((ips[j], result))
result_str = ','.join([str(res) for res in results])
error_str = ','.join([str(error) for error in errors])
result_file.write('{},{},{},{}\n'.format(ips[j], use_error_req, result_str, error_str))
pbar.update(1)
print('Number of IPs: {}'.format(len(ip_list)))
print('---------------')
category_total = 0
for i in range(1, 6):
category_len = len(categories[i])
category_total += category_len
print('Category {}: {}'.format(i, category_len))
print('Total: {}'.format(category_total))
results = [result for (ip, result) in categories[1] if result > 0]
result_total = 0
print('---------------')
for i in range(1, 11):
count = results.count(i)
result_total += count
print('ICW {}: {}'.format(i, count))
print('ICW 11+: {}'.format(len(results) - result_total))
print('Total: {}'.format(len(results)))
with open(category_filename, 'wb') as category_file:
pickle.dump(categories, category_file)
print('Saved categories pickle to "{}"'.format(category_filename))