identify_df.py

import re
import sys
import pickle
import pandas as pd
import tensorflow as tf
from check_malware import check_malware


def get_data():
    '''
        Extracting data from dataset
    '''
    no_of_arg = len(sys.argv)-1
    arg = sys.argv[1:]

    for i in range(no_of_arg):
        if((arg[i][0]=="'") or (arg[i][0]=='"')):
            arg[i] = arg[i][1:-1]

    for k in arg:
        # reading csv file
        j = pd.read_csv(k)
        j.drop(columns=['TimeDateStamp'], inplace=True)
        classes, prob, pred = check_malware(j)

        print('\n', k)
        print('--------------------------------------')
        print('Application => Category => Probability')
        print('--------------------------------------')
        for i in range(j.shape[0]):
            # for ML model
            # print(app[i], ' => ', classes[i], ' => ', prob[i][pred[i]])

            # for DL model
            print(i, ' => ', classes[i], ' => ', prob[i][0])

        # tupled_data.extend(j.values.tolist())

    # test_df = pd.DataFrame(data=tupled_data, columns=j.columns)
    # check_malware(test_df)

if __name__ == "__main__":
    get_data()