read_ascii_csv_performance.py

import numpy as np
import time
import sys
import csv
import mmap

ret = []
current_time = time.time()

with open(sys.argv[1], 'r') as f:
    for line in f:
        floats = map(float, line.split(' '))
        ret.append(floats)

x = np.asarray(ret)
convert_time = time.time() - current_time
print('customized function convertion time: {} secs'.format(convert_time))


ret = []
current_time = time.time()
with open(sys.argv[1], 'r+b') as f:
    mm = mmap.mmap(f.fileno(), 0)
    line = mm.readline()
    while line != '':
        ret.append(map(float, line.split(' ')))
        line = mm.readline()

y = np.asarray(ret)
convert_time = time.time() - current_time

print('mmap convertion time: {} secs'.format(convert_time))

ret = []
current_time = time.time()
with open(sys.argv[1], 'r') as f:
    reader = csv.reader(f, delimiter=' ')
    for row in reader:
        floats = map(float, row)
        ret.append(floats)

z = np.asarray(ret)
convert_time = time.time() - current_time

A = np.load(sys.argv[2])

print('CSV convertion time: {} secs'.format(convert_time))
print('Customized Function Correctness: {}'.format(np.array_equal(x, A)))
print('mmap Function Correctness: {}'.format(np.array_equal(y, A)))
print('CSV Function Correctness: {}'.format(np.array_equal(z, A)))