Read files in a folder and measure speed

createfile.py

#!/usr/bin/env python

"""Create text files of different sizes with random content."""

import random
import string
import logging
import sys

logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s',
                    level=logging.DEBUG,
                    stream=sys.stdout)


def create_file(filename, size):
    """
    Create files of a given size with random strings in them.
    Use values over 10,000,0000 with caution as it might render your PC useless
    for a couple of minutes.

    @param filename: The path to the filename
    @param size: Size in bytes
    """
    with open(filename, 'w') as f:
        symbols = string.letters + string.whitespace
        random_string = ''.join(random.choice(symbols) for _ in range(size))
        f.write(random_string)


def main():
    for el in [10, 100, 1024, 10*1024, 100*1024]:
        size = el*1024
        logging.info("Start creation of %i Byte file.", size)
        create_file("%i.txt" % size, size)


if __name__ == '__main__':
    main()

reading.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
Read all files in current directory 100 times and measure the time it takes.
"""

from os import listdir
from os.path import isfile, join
import logging
import sys
import time
import random
import natsort
from numpy import average, median

logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s',
                    level=logging.DEBUG,
                    stream=sys.stdout)


def read_file(path):
    content = ""
    with open(path) as f:
        content = f.read()
    return content


def print_results(times):
    """
    :param times: A dictionary which maps file paths to lists of execution
        times
    """
    filenames = times.keys()
    times = natsort.natsorted(times.items())
    maxlen = str(max([len(f) for f in filenames]) + 2)
    fformatter = "{0:<" + maxlen + "}"
    fheader = u"" + fformatter + u"{1:>6}{2:>10}{3:>10}{4:>10}"
    header = fheader.format('file_name', 'min', 'max', 'median', 'average')
    print(header)
    print("-"*len(header))
    for filename, t in times:
        min_str = "%0.4f" % min(t)
        max_str = "%0.4f" % max(t)
        med_str = "%0.4f" % median(t)
        avg_str = "%0.4f" % average(t)
        print(fheader.format(filename, min_str, max_str, med_str, avg_str))


def main():
    mypath = '.'
    onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
    times = {}
    for filename in onlyfiles:
        times[filename] = []

    # Make every filename occur 100 times in list
    readlist = []
    for el in onlyfiles:
        for _ in range(100):
            readlist.append(el)
    onlyfiles = readlist

    random.shuffle(onlyfiles)

    # Execute the test
    for file_path in onlyfiles:
        start_time = time.time()
        content = read_file(file_path)
        read_time = time.time() - start_time
        print(content[:4] + content[-4:])
        logging.info("%s needed %0.2f seconds to read.", file_path, read_time)
        times[file_path].append(read_time)

    # Print the results
    print_results(times)


if __name__ == '__main__':
    main()