def read_data(data_dir, duration=None, labels=None):
'''
Reads all the data in the specified directory and parses it into
a feature array and a label array.
Args:
data_dir: path to the directory that contains the training data
duration: Time window to compute feature information
labels: List containing labels to use
Returns:
X: numpy 2D array that contains the (high dimensional) features
y: numpy 1D array that contains the labels for the features in X
new_labels: Reordered labels used in training
'''
X = []
y = []
assigned_labels = []
# Get all the files in the directory
files = []
with open(os.path.join(data_dir,'label_assignments.json')) as handle:
label_assignments = json.load(handle)
for dirpath, dirnames, filenames in os.walk(data_dir):
for file in filenames:
files.append(os.path.join(dirpath,file))
# Go through all the files in the directory
for filename in files:
# Extract the label from the filename
name = os.path.split(filename)[1]
name = name.split('-')[0]
if name in label_assignments:
label = label_assignments[name]
if label not in labels: label = 'Unknown'
else:
label = 'Unknown'
if label not in assigned_labels:
assigned_labels.append(label)
print("Reading", filename,"as",label)
# Bin the sessions with the specified time window
binned_sessions = sessionizer(
filename,
duration=duration
)
# For each of the session bins, compute the full feature vectors
for session_dict in binned_sessions:
features, _, _ = extract_features(session_dict)
# Store the feature vector and the labels
X.append(features)
y.append(assigned_labels.index(label))
# Update the labels to reflect the new assignments
new_labels = assigned_labels + \
[l for l in labels if l not in assigned_labels]
return np.stack(X), np.stack(y), new_labels
def get_features(self, filepath, source_ip=None):
'''
Reads a pcap specified by the file path and returns an array of the
computed model inputs
Args:
filepath: Path to pcap to compute features for
Returns:
features: Numpy 2D array containing features for each time bin
timestamp: datetime of the last observed packet
'''
# Read the capture into a feature array
X = []
timestamps = []
binned_sessions = sessionizer(filepath, duration=self.duration)
self.sessions = binned_sessions
if len(binned_sessions) is 0:
return None, None, None, None
for session_dict in binned_sessions:
if len(session_dict) > 0:
if source_ip is None:
feature_list, source_ip, other_ips = extract_features(
session_dict
)
else:
feature_list, _, other_ips = extract_features(
session_dict,
capture_source=source_ip
)
X.append(feature_list)
last_packet = list(session_dict.items())[-1]
timestamps.append(last_packet[1][0][0])
if len(X) == 0:
return None, None, None, None
full_features = np.stack(X)
# Mean normalize the features
full_features -= np.expand_dims(self.means, 0)
full_features /= np.expand_dims(self.stds, 0)
features = full_features[:, self.feature_list]
return features, source_ip, timestamps, other_ips
def read_data(data_dir, duration=None, labels=None):
'''
Reads all the data in the specified directory and parses it into
a feature array and a label array.
Args:
data_dir: path to the directory that contains the training data
duration: Time window to compute feature information
labels: List containing labels to use
Returns:
X: numpy 2D array that contains the (high dimensional) features
y: numpy 1D array that contains the labels for the features in X
new_labels: Reordered labels used in training
'''
logger = logging.getLogger(__name__)
try:
if 'LOG_LEVEL' in os.environ and os.environ['LOG_LEVEL'] != '':
logger.setLevel(os.environ['LOG_LEVEL'])
except Exception as e:
logger.error(
'Unable to set logging level because: {0} defaulting to INFO.'.
format(str(e)))
X = []
y = []
assigned_labels = []
# Get all the files in the directory
files = []
with open('opts/label_assignments.json') as handle:
label_assignments = json.load(handle)
for dirpath, _, filenames in os.walk(data_dir):
for file in filenames:
_, ext = os.path.splitext(file)
if ext == '.pcap':
files.append(os.path.join(dirpath, file))
# Go through all the files in the directory
logger.info('Found {0} pcap files to read.'.format(len(files)))
count = 0
for filename in files:
count += 1
# Extract the label from the filename
name = os.path.split(filename)[1]
name = name.split('-')[0]
if name in label_assignments:
label = label_assignments[name]
if label not in labels:
label = 'Unknown'
else:
label = 'Unknown'
if label not in assigned_labels:
assigned_labels.append(label)
logger.info('Reading {0} ({1} bytes) as {2} ({3}/{4})'.format(
filename, os.path.getsize(filename), label, count, len(files)))
# Bin the sessions with the specified time window
binned_sessions = sessionizer(filename, duration=duration)
# Get the capture source from the binned sessions
capture_source = get_source(binned_sessions)
# For each of the session bins, compute the full feature vectors
for session_dict in binned_sessions:
features, _, _ = extract_features(session_dict,
capture_source=capture_source)
# Store the feature vector and the labels
X.append(features)
y.append(assigned_labels.index(label))
# Update the labels to reflect the new assignments
new_labels = assigned_labels + \
[l for l in labels if l not in assigned_labels]
return np.stack(X), np.stack(y), new_labels
