The program below is about finding the values below the percentage and splitting them into five different output files. This works great for small input data files. But when I am trying to run it for a big data it takes ages to compute. Any suggestions on optimizing the program so that I can get fast computation?

#seperate by col 5
import numpy as np
import os
import re
import math
import csv
import sys
import time
import multiprocessing
from scipy import stats

curdir = 'Tools/'
inputdir = 'input/'
filename = 'input'
outputdir = 'output/'

def seperate(filename):
    print "Begin seperating File: %s" % filename
    dtype = np.dtype([('id1',str,12),('id2',str,12),('c1',int),('c2',int),('c3',float)])
    data = np.loadtxt(curdir + inputdir + filename,dtype=dtype)
    col = 'c3'
    col_data = np.array(data[:][col])
    cache = {}
    def get_per(per):
            if(cache.has_key(per)):
                return cache.get(per)
            else:
                r = 100 - stats.percentileofscore(col_data,per)
                cache[per] = r
                return r
    o1 = file(curdir + outputdir+ filename + '_0_20','w')
    o2 = file(curdir + outputdir+ filename + '_20_40','w')
    o3 = file(curdir + outputdir+ filename + '_40_60','w')
    o4 = file(curdir + outputdir+ filename + '_60_80','w')
    o5 = file(curdir + outputdir+ filename + '_80_100','w')
    for line in data:
        per = get_per(line[col])
        output_format = "%s %s %d %d %.1f\n"
        output_data = (line['id1'],line['id2'],line['c1'],line['c2'],line['c3'])
        if per>=0 and per < 20:
            o1.write(output_format % output_data)
        elif per>=20 and per<40:
            o2.write(output_format % output_data)
            pass
        elif per>=40 and per<60:
            o3.write(output_format % output_data)
            pass
        elif per>=60 and per<80:
            o4.write(output_format % output_data)
            pass
        elif per>=80 and per<=100:
            o5.write(output_format % output_data)
            pass
    o1.close()
    o2.close()
    o3.close()
    o4.close()
    o5.close()

    print "Finish seperating File: %s" % filename

 
ps = []
print "Reading Files"
for parent,dirNames,fileNames in os.walk(curdir+inputdir):
    if fileNames:
        #multi_process
        print fileNames
        for fileName in fileNames:
            m = re.match(r'^(?!\.)',fileName)
            if m:
                ps.append(multiprocessing.Process(target=seperate,args=(fileName,)))

#runing by multiple processes
for p in ps:
    p.start()
for p in ps:
    p.join()