rene/ma_cisco_malware
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add simple flow feature extraction function

Browse Source
This commit is contained in:
René Knaebel 2017-07-11 13:46:25 +02:00
parent 522854ee0d
commit a196daa895
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
dataset.py
View File

@ -92,11 +92,18 @@ def get_flow_features(flow):
return features return features
def get_all_flow_features(features):
flows = np.stack(list(
map(lambda f: f[["duration", "bytes_up", "bytes_down"]], features))
)
return np.log1p(flows)
def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10, use_cisco_features=False): def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10, use_cisco_features=False):
domains = [] domains = []
features = [] features = []
print("get chunks from user data frames") print("get chunks from user data frames")
for i, user_flow in tqdm(list(enumerate(get_flow_per_user(user_flow_df)))[:50]): for i, user_flow in tqdm(list(enumerate(get_flow_per_user(user_flow_df)))):
(domain_windows, feature_windows) = get_user_chunks(user_flow, (domain_windows, feature_windows) = get_user_chunks(user_flow,
windowSize=window_size, windowSize=window_size,
overlapping=False, overlapping=False,