features_analyzer.py

from os import listdir
from os.path import isfile, join
import operator
mypath = '../drebin/feature_vectors'
onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]


# Print iterations progress
def printProgressBar (iteration, total, prefix = '', suffix = '', decimals = 1, length = 50, fill = '█'):
    percent = ("{0:." + str(decimals) + "f}").format(100 * (iteration / float(total)))
    filledLength = int(length * iteration // total)
    bar = fill * filledLength + '-' * (length - filledLength)
    print('\r%s |%s| %s%% %s' % (prefix, bar, percent, suffix), end = '\r')
    # Print New Line on Complete
    if iteration == total: 
        print()


features = dict()

def load_malwares():
    with open('../drebin/sha256_family.csv', 'r') as f:
        raw_data = f.read()
        f.close()
    raw_data = raw_data.strip()
    lista_data = raw_data.split('\n')
    for i in range(len(lista_data)):
        if i != 0:
            lista_malware.append((lista_data[i].split(','))[0])
    return lista_malware

def analyzer(lista_file):
    printProgressBar(0,len(lista_file),'Progress:','Complete')
    lista_top_features = list()
    for a in range(len(lista_file)):
        printProgressBar(a+1,len(lista_file),'Progress:','Complete')
        path = '../drebin/feature_vectors/'+lista_file[a]
        with open(path, 'r') as f:
            raw_data = f.read()
            f.close()
        raw_data = raw_data.strip()
        #data.append(raw_data.split('\n'))
        data = raw_data.split('\n')
        for e in range(len(data)):
            if data[e] not in features.keys():
                features[data[e]] = 1
            else:
                features[data[e]] += 1
    for elem in range(0,8):
        most_used_feature = max(features.items(), key=operator.itemgetter(1))[0]
        lista_top_features.append(most_used_feature)
        features.pop(most_used_feature)
    return lista_top_features

if __name__ == "__main__":
    lista_malware = list()
    lista_malware = load_malwares()
    data = list()
    dic = list()
    analyzer(lista_malware)