def record_detect(flow_address, host_stored_address):
with open(host_stored_address, 'rb') as host_collector_file:
host_collector = cpickle.load(host_collector_file)
flow_feature_list = []
start_time = datetime.datetime.now()
record_num = 0
with open(flow_address, 'rb') as infile:
for line in infile:
record = line.strip(' \n').split('\t')
if len(record) == 13 and record[_host] != '':
current_record = FlowRecord(record)
current_model = host_collector.get_host_model(
current_record['host'])
rfF.calculate(current_record, current_model)
flow_feature = [
current_record['path_prop'],
current_record['specialSymbol_prop'],
current_record['enumeration'],
current_record['variable_composition'],
current_record['variable_order'],
current_record['value_length_prop'],
current_record['value_distribution1'],
current_record['value_distribution2']
]
flow_feature_list.append(flow_feature)
record_num += 1
if record_num % 10000 == 0:
print 'Record completed: %s' % record_num
end_time = datetime.datetime.now()
print 'Calculate Records: %s' % record_num
print 'Record Calculated Consuming: %s' % (end_time - start_time)
return flow_feature_list
def record_detect(flow_address, host_stored_address):
with open(host_stored_address, 'rb') as host_collector_file:
host_collector = cpickle.load(host_collector_file)
flow_feature_list = []
start_time = datetime.datetime.now()
record_num = 0
with open(flow_address, 'rb') as infile:
for line in infile:
record = line.strip(' \n').split('\t')
if len(record) == 13 and record[_host] != '':
current_record = FlowRecord(record)
current_model = host_collector.get_host_model(current_record['host'])
rfF.calculate(current_record, current_model)
flow_feature = [
current_record['path_prop'],
current_record['specialSymbol_prop'],
current_record['enumeration'],
current_record['variable_composition'],
current_record['variable_order'],
current_record['value_length_prop'],
current_record['value_distribution1'],
current_record['value_distribution2']
]
flow_feature_list.append(flow_feature)
record_num += 1
if record_num % 10000 == 0:
print 'Record completed: %s' % record_num
end_time = datetime.datetime.now()
print 'Calculate Records: %s' % record_num
print 'Record Calculated Consuming: %s' % (end_time - start_time)
return flow_feature_list
def cal_feature(record, host_collector):
current_record = FlowRecord(record)
current_model = host_collector.get_host_model(current_record['host'])
rfF.calculate(current_record, current_model)
flow_feature = [
current_record['path_prop'], current_record['specialSymbol_prop'],
current_record['enumeration'], current_record['variable_composition'],
current_record['variable_order'], current_record['value_length_prop'],
current_record['value_distribution1'],
current_record['value_distribution2']
]
flow_feature = [str(feature) for feature in flow_feature]
return flow_feature
def cal_feature(record, host_collector):
current_record = FlowRecord(record)
current_model = host_collector.get_host_model(current_record['host'])
rfF.calculate(current_record, current_model)
flow_feature = [
current_record['path_prop'],
current_record['specialSymbol_prop'],
current_record['enumeration'],
current_record['variable_composition'],
current_record['variable_order'],
current_record['value_length_prop'],
current_record['value_distribution1'],
current_record['value_distribution2']
]
flow_feature = [str(feature) for feature in flow_feature]
return flow_feature
