drawtr.py

# copied from kaggle microsoft malware classification problem discussion forum

import sys
import os
from math import log, pow
import numpy as np
import scipy as sp
from PIL import Image
import matplotlib.pyplot as plt
def saveimg(array,name):
    print( name)
    if array.shape[1]!=16:
        assert(False)
    b_=int((array.shape[0]*16)**(0.5))
    b_=int(pow(2, (int(log(b_)/log(2))+1)))
    a_=int(array.shape[0]*16/b_)
    print (a_,b_,int(a_*b_/16),array.shape)
    array=array[:int(a_*b_/16),:]

    array=np.reshape(array,(a_,b_))
    #print array.shape
    im = Image.fromarray(np.uint8(array))
    im.save('dataSample/'+name+'.jpg', "JPEG")
files=os.listdir('dataSample')
c=0
for cc,x in enumerate(files):
    if '.bytes' != x[-6:]:
        continue
    print (cc)
    f=open('dataSample/'+x)
    array=[]
    c+=1
    for line in f:
        xx=line.split()
        if len(xx)!=17:
            continue
        #if xx[1]=='??':
        #    break
        array.append([int(i,16) if i!='??' else 0 for i in xx[1:] ])
    saveimg(np.array(array),x)
    del array
    f.close()
print (c)