ma_cisco_malware/models/__init__.py
René Knaebel 595c2ea894 change argument interface
- add more properties for network specification
 - change names for consistency
2017-09-07 15:53:58 +02:00

92 lines
2.9 KiB
Python

import keras.backend as K
from . import pauls_networks
from . import renes_networks
def get_models_by_params(params: dict):
# decomposing param section
# mainly embedding model
network_type = params.get("type")
network_depth = params.get("depth")
embedding_size = params.get("embedding_size")
input_length = params.get("input_length")
filter_embedding = params.get("filter_embedding")
kernel_embedding = params.get("kernel_embedding")
hidden_embedding = params.get("dense_embedding")
dropout = params.get("dropout")
# mainly prediction model
flow_features = params.get("flow_features")
domain_features = params.get("domain_features")
window_size = params.get("window_size")
domain_length = params.get("domain_length")
filter_main = params.get("filter_main")
kernel_main = params.get("kernel_main")
dense_dim = params.get("dense_main")
model_output = params.get("model_output", "both")
# create models
if network_depth == "small":
networks = pauls_networks
elif network_depth == "medium":
networks = renes_networks
else:
raise Exception("network not found")
embedding_model = networks.get_embedding(embedding_size, input_length, filter_embedding, kernel_embedding,
hidden_embedding, 0.5)
old_model = networks.get_model(0.25, flow_features, domain_features, window_size, domain_length,
filter_main, kernel_main, dense_dim, embedding_model, model_output)
new_model = networks.get_new_model(0.25, flow_features, domain_features, window_size, domain_length,
filter_main, kernel_main, dense_dim, embedding_model, model_output)
return embedding_model, old_model, new_model
def get_metrics():
return dict([
("precision", precision),
("recall", recall),
("f1_score", f1_score),
])
def get_metric_functions():
return [precision, recall, f1_score]
def precision(y_true, y_pred):
# Count positive samples.
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
return true_positives / (predicted_positives + K.epsilon())
def recall(y_true, y_pred):
# Count positive samples.
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
return true_positives / (possible_positives + K.epsilon())
def f1_score(y_true, y_pred):
return f_score(1)(y_true, y_pred)
def f05_score(y_true, y_pred):
return f_score(0.5)(y_true, y_pred)
def f_score(beta):
def _f(y_true, y_pred):
p = precision(y_true, y_pred)
r = recall(y_true, y_pred)
bb = beta ** 2
fbeta_score = (1 + bb) * (p * r) / (bb * p + r + K.epsilon())
return fbeta_score
return _f