ratio_gen.py

#!/usr/bin/env python3

import os
import sys
import pandas as pd
import zipfile
from multiprocessing import Pool


def data_collector(values):
	data = {}
	os.chdir(values[0])
	zipper = zipfile.ZipFile(f'{values[1].split(".")[0]}.zip',"w")
	zipper.write(values[1],compress_type=zipfile.ZIP_DEFLATED)
	zipper.close()
	data['name'] = values[1].split(".")[0]
	data['size'] = os.path.getsize(values[1])
	data['csize'] = os.path.getsize(f'{values[1].split(".")[0]}.zip')
	data['type'] = values[1].split(".")[1]
	os.remove(f'{values[1].split(".")[0]}.zip')
	return data


if __name__ == '__main__':

	o_path = os.getcwd()
	byt_path = os.path.join(o_path, "Dataset", "bytes")
	asm_path = os.path.join(o_path,"Dataset", "asm")	
	values = [[byt_path,i] for i in os.listdir(byt_path) if ".bytes" in i]
	values = values + [[asm_path,i] for i in os.listdir(asm_path) if ".asm" in i]			
	df = 0;struct_dat = []
	
	with Pool(4) as p:
		df = p.map(data_collector, values)
	bytes_data = [i for i in df if i['type']=="bytes"]
	asm_data = [i for i in df if i['type']=="asm"]
	for i in range(len(bytes_data)):
		ind_data = {}
		b =	bytes_data[i]
		a =	asm_data[i]
		if b['name'] != a['name']:
			print("Error")
			sys.exit(1)
		ind_data['name'] = b['name']
		ind_data["ratio(bytes/asm)"] = b['size']/a['size']
		ind_data["ratio(c_bytes/c_asm)"] = b['csize']/a['csize']
		ind_data["size(bytes)"] = b['size']
		ind_data["size(c_bytes)"] =	b['csize']
		ind_data["size(asm)"] = a['size']
		ind_data["size(c_asm)"] = a['csize']
		struct_dat.append(ind_data)
	os.chdir(o_path)
	frame = pd.DataFrame(struct_dat)
	frame = frame.set_index('name')
	print(frame)
	frame.to_csv(os.path.join("results",'ratio_data.csv'), sep = ',', encoding = 'utf-8', index = True)