def create_random_sets():
print("Generating TRAINING set...")
training_set = onehot.generate_set(
set_size, malware_ratio) # generate random training set
print("Generating TRAINING input...")
data, labels = onehot.generate_input(
training_set, total_features) # perform one-hot encoding
print("Generating TESTING set...")
testing_set = onehot.generate_set(
testing_set_size, malware_ratio) # generate random testing set
print("Generating TESTING input...")
test_data, test_labels = onehot.generate_input(
testing_set, total_features) # perform one-hot encoding
return data, labels, test_data, test_labels # return train data - labels and test data - labels
def create_sets():
if os.path.isfile("training_set_8500.txt") is False:
set_size = 8500
malware_ratio = 0.3
print("Creating data-labels...")
print("Generating TESTING set...")
training_set = onehot.generate_set(
set_size, malware_ratio) # generate random testing set
with open("training_set_1500.txt", "w") as file:
for item in training_set:
file.write(str(item) + "\n")
if os.path.isfile("testing_set_8500.txt") is False:
set_size = 8500
malware_ratio = 0.3
print("Creating data-labels...")
print("Generating TESTING set...")
testing_set = onehot.generate_set(
set_size, malware_ratio) # generate random testing set
with open("testing_set_1500.txt", "w") as file:
for item in testing_set:
file.write(str(item) + "\n")
training_set = []
testing_set = []
with open(
"training_set_8500.txt", "r"
) as file: # read training set file and append applications to list
for line in file:
line.strip() # remove whitespace
line = line[:-1] # remove \n
training_set.append(line) # add item to list
with open(
"testing_set_8500.txt", "r"
) as file: # read testing set file and append applications to list
for line in file:
line.strip()
line = line[:-1]
testing_set.append(line)
print("Generating TRAINING input...")
data, labels = onehot.generate_input(
training_set, total_features) # perform one-hot encoding
print("Generating TESTING input...")
test_data, test_labels = onehot.generate_input(
testing_set, total_features) # perform one-hot encoding
return data, labels, test_data, test_labels
def create_random_sets(set_size=1500, malware_ratio=0.3):
print("Generating set...")
testing_set = onehot.generate_set(set_size, malware_ratio) # generate random set
print("Generating input...")
# shuffle the set randomly and perform one-hot encoding
test_data, test_labels = onehot.generate_input(testing_set, total_features)
return test_data, test_labels
def create_set():
if os.path.isfile("testing_set_200.txt") is False:
set_size = 200
malware_ratio = 0.5
print("Creating data-labels...")
print("Generating TESTING set...")
testing_set = onehot.generate_set(
set_size, malware_ratio) # generate random testing set
with open("testing_set_200.txt", "w") as file:
for item in testing_set:
file.write(str(item) + "\n")
testing_set = [] # the list of testing set
with open(
"testing_set_200.txt", "r"
) as file: # read testing set file and append applications to list
for line in file:
line.strip()
line = line[:-1]
testing_set.append(line)
print("Generating TESTING input...")
test_data, test_labels = onehot.generate_input(
testing_set, total_features) # perform one-hot encoding
return test_data, test_labels
if __name__ == "__main__":
total_features = 545333 # total unique features
set_size = 2000 # set site that will be used to create random training set
testing_set_size = 2000 # set site that will be used to create random test set
malware_ratio = 0.3 # malware ratio in the set size
onehot.create_list_of_apps() # function from set_one_encoding.py
# check if a predefined training
if os.path.isfile("training_set_2000.txt") is False and os.path.isfile(
"testing_set_2000.txt") is False:
print("Creating data-labels...")
print("Generating TRAINING set...")
training_set = onehot.generate_set(
set_size, malware_ratio) # generate random training set
with open("training_set_2000.txt", "w") as file:
for item in training_set:
file.write(str(item) + "\n")
print("Generating TESTING set...")
testing_set = onehot.generate_set(
testing_set_size, malware_ratio) # generate random testing set
with open("testing_set_2000.txt", "w") as file:
for item in testing_set:
file.write(str(item) + "\n")
training_set = [] # the list of training set
testing_set = [] # the list of testing set
with open(