def mainVisualize(params={}):
withhold = 0
#default value for params
params = test.defParams(params)
train_dir = "train"
test_dir = "test"
# TODO put the names of the feature functions you've defined above in this list
ffs = [system_call_2gram_feats] #[system_call_count_feats]
#ffs = [first_last_system_call_feats, system_call_count_feats]
# extract features
print "extracting training features..."
time1 = time.clock()
X_train, t_train, train_ids, X_test, t_test, test_ids = test.loadData(
params, withhold, ffs)
time2 = time.clock()
print "done extracting %d training features, time: %.4f s" % (
X_train.shape[1], time2 - time1)
print
import matplotlib.pyplot as plt
import matplotlib.cm as cm
plt.matshow(X_train.T.toarray(), cmap=cm.get_cmap('Reds'))
plt.colorbar()
plt.show()
def mainTest(withhold=0, params={}):
#default value for params
params = test.defParams(params)
train_dir = "train"
test_dir = "test"
# TODO put the names of the feature functions you've defined above in this list
ffs = [system_call_count_feats, system_call_2gram_feats]
#ffs = [first_last_system_call_feats, system_call_count_feats]
# extract features
print "extracting training features..."
time1 = time.clock()
X_train, t_train, train_ids, X_test, y_test, test_ids = test.loadData(
params, withhold, ffs)
time2 = time.clock()
print "done extracting %d training features, time: %.4f s" % (
X_train.shape[1], time2 - time1)
print
#preds = methods.logRegress(X_train,t_train,X_test)
#preds = methods.decisionTree(X_train,t_train,X_test)
#preds = methods.randomForest(X_train,t_train,X_test)
preds = methods.extraTrees(X_train, t_train, X_test)
if withhold != 0:
print testCatAcc(preds, y_test)
if params['writePredict'] == True:
print "writing predictions..."
util.write_predictions(preds, test_ids, params['outputFile'])
print "done!"
def mainVisualizeFeatures(params={}):
withhold = 0
#default value for params
params = test.defParams(params)
train_dir = "train"
test_dir = "test"
# TODO put the names of the feature functions you've defined above in this list
ffs = [system_call_2gram_feats] #[system_call_count_feats]
#ffs = [first_last_system_call_feats, system_call_count_feats]
# extract features
print "extracting training features..."
time1 = time.clock()
X_train, global_feat_dict, t_train, train_ids = extract_feats(
ffs, train_dir)
time2 = time.clock()
print "done extracting %d training features, time: %.4f s" % (
X_train.shape[1], time2 - time1)
print
feature_data = np.zeros((len(global_feat_dict), 2))
feature_names = []
for (feature, index) in global_feat_dict.iteritems():
feature_data[index][0] = X_train[:, index].mean()
feature_data[index][1] = X_train[:, index].toarray().std()
feature_names.append(feature)
import matplotlib.pyplot as plt
import matplotlib.cm as cm
ind = np.arange(len(global_feat_dict))
feature_data.sort(axis=0)
plt.bar(ind, feature_data[:, 0], yerr=feature_data[:, 1])
plt.xticks(ind, feature_names, rotation='vertical')
plt.show()
