def run_linear_open_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a open-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
self.randomize_dataset_open_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
classes = clf.best_estimator_.classes_
for scores in out:
m = np.max(scores)
if (abs(m / scores[:][:]) < 0.5).any():
self.predictions = np.append(self.predictions, 99)
else:
p = classes[np.where(scores == m)]
self.predictions = np.append(self.predictions, p)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
pz.save(self.predictions, "mca_predictions_open.pz")
pz.save(self.true_labels, "mca_true_labels_open.pz")
def run_linear_closed_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a closed-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
print "[*] Iteration {0}".format(i)
print "[*] Randomizing dataset..."
self.randomize_dataset_closed_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
print "[*] Training..."
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.predict(self.X_test)
print "[*] Testing..."
self.predictions = np.append(self.predictions, out)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
print "[*] Predictions saved."
pz.save(self.predictions, "mca_predictions_closed.pz")
pz.save(self.true_labels, "mca_true_labels_closed.pz")
def run_linear_experiment(self, rocs_filename, iterations=10):
"""
Run a classification experiment by running several iterations.
In each iteration data is randomized, a linear svm classifier
is trained and evaluated using cross-validation over a the
cost parameter in the range np.logspace(-3, 3, 7). The best
classifier is used for testing and a ROC curve is computed
and saved as property and locally.
:param rocs_filename: the file to save all rocs computed
:param iterations: number of runs (training/testing)
"""
for i in xrange(iterations):
print "[*] Iteration {0}".format(i)
print "[*] Randomizing dataset..."
self.randomize_dataset()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
print "[*] Training..."
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
print "[*] Testing..."
roc = ev.compute_roc(np.float32(out.flatten()),
np.float32(self.Y_test))
self.rocs.append(roc)
print "[*] ROC saved."
pz.save(self.rocs, rocs_filename)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-d', '--directory', help='directory of the apk')
args = parser.parse_args()
if args.directory:
# progressbar
file_count = count_file(args.directory, '.apk')
pbar = use_progressbar('networkxifying call graph...', file_count)
pbar.start()
progress = 0
for parent, dirnames, filenames in os.walk(args.directory):
for filename in filenames:
if filename.endswith('.apk'):
# print(os.path.join(parent, filename))
cg, graphdir = generate(os.path.join(parent, filename))
fcg = networkxify(cg)
h = os.path.splitext(filename)[0]
fnx = os.path.join(graphdir, "{}.pz".format(h))
pz.save(fcg, os.path.join(graphdir, fnx))
# progressbar
progress += 1
pbar.update(progress)
# progressbar
pbar.finish()
else:
parser.print_help()
def save_data(X, m, Y, filenames):
'''Store pz objects for the data matrix, the labels and
the name of the original samples so that they can be used
in a new experiment without the need to extract all
features again'''
print '[SC] Saving labels, data matrix and file names...'
pz.save(X, 'X.pz')
pz.save(m, 'maximum.pz')
pz.save(Y, 'Y.pz')
pz.save(filenames, 'filenames.pz')
def save_data(self):
""" Store pz objects for the data matrix, the labels and
the name of the original samples so that they can be used
in a new experiment without the need to extract all
features again
"""
print "[*] Saving labels, data matrix and file names..."
pz.save(self.X, "X.pz")
pz.save(self.Y, "Y.pz")
pz.save(self.fnames, "fnames.pz")