def cmp_algorithm_cv(base_dir, normal_dir, data_path, output_dir, model_name='', dataset=''):
char_wb = False
if 'tf' in model_name:
tf = True
else:
tf = False
if 'ngram' in model_name:
ngram = (2, 15)
# char_wb = True
else:
ngram = None
classifier_dir = base_dir + dataset
outfile = os.path.join(classifier_dir, model_name + 'cv_res_sel.json')
if os.path.exists(outfile):
return
if os.path.exists(os.path.join(output_dir, model_name + "vec_sel.pkl")):
X = Learner.obj_from_file(os.path.join(output_dir, model_name + "X_sel.pkl"))
y = Learner.obj_from_file(os.path.join(output_dir, model_name + "y_sel.pkl"))
else:
instances, y = Learner.gen_instances(os.path.join(normal_dir, 'March'),
data_path, char_wb=char_wb, simulate=False)
X, feature_names, vec = Learner.gen_X_matrix(instances, tf=tf, ngrams_range=ngram)
Learner.save2file(X, os.path.join(output_dir, model_name + "X.pkl"))
Learner.save2file(y, os.path.join(output_dir, model_name + "y.pkl"))
Learner.save2file(vec, os.path.join(output_dir, model_name + "vec.pkl"))
Learner.save2file(feature_names, os.path.join(output_dir, model_name + "feature_names.pkl"))
X, feature_names, vec = Learner.feature_selection(X, y, 500, vec, instances, tf=tf, ngram_range=ngram)
Learner.save2file(X, os.path.join(output_dir, model_name + "X_sel.pkl"))
Learner.save2file(y, os.path.join(output_dir, model_name + "y_sel.pkl"))
Learner.save2file(vec, os.path.join(output_dir, model_name + "vec_sel.pkl"))
Learner.save2file(feature_names, os.path.join(output_dir, model_name + "feature_names_sel.pkl"))
CtuCCAnalyzer.train_and_save(X, y, model_name, classifier_dir)
def feature_tab(base_dir):
# Open X and output the attribute amount
for model_name in ['bag', 'bag-ngram', 'tf', 'tf-ngram']:
if model_name == 'bag':
model_n = 'Bag-of-word'
elif model_name == 'tf':
model_n = 'Tf-idf'
elif model_name == 'bag-ngram':
model_n = 'Bag-of-word-NGram'
else:
model_n = 'Tf-idf-NGram'
model_name = model_name + '_'
for dataset in ['Neris', 'Murlo', 'Virut', 'Sogou']:
if dataset != 'Neris':
model_n = ''
line = model_n + ' & ' + dataset + '& '
output_dir = base_dir + dataset
X = Learner.obj_from_file(os.path.join(output_dir, model_name + "X.pkl"))
line += str(X.shape[1]) + ' & 500 & '
# print X.shape[1]
feature_names = Learner.obj_from_file(os.path.join(output_dir, model_name + "feature_names_sel.pkl"))
for i in range(1, 5):
feature_name = feature_names[i]
if len(feature_name) > 8:
feature_name = str(feature_name)[0:8]
line += feature_name + ', '
line += ' ...\\\\ '
print line
def zero_day_helper(base_dir, src_name, model_name, algorithm, target_name, normal_dir=None):
vec_dir = os.path.join(base_dir, src_name)
model_path = os.path.join(vec_dir, model_name + algorithm + '_sel.pkl')
target_path = os.path.join(base_dir, target_name)
if normal_dir is None:
data, labels = Learner.gen_instances('', target_path)
else:
data, labels = Learner.gen_instances(os.path.join(normal_dir, target_name), '')
vec = Learner.obj_from_file(os.path.join(vec_dir, model_name + 'vec.pkl'))
vec_sel = Learner.obj_from_file(os.path.join(vec_dir, model_name + 'vec_sel.pkl'))
data, vocab, vec = Learner.gen_X_matrix(data, vec=vec)
return Learner.predict(Learner.obj_from_file(model_path),
vec_sel, data, labels=labels,
src_name=src_name, model_name=model_name)
