Last active
August 29, 2015 14:01
-
-
Save msharp/72586a8d94be108b8b7c to your computer and use it in GitHub Desktop.
File Sampler - sample every n rows from a file
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import sys | |
import os | |
class FileSampler: | |
def __init__(self): | |
self.parse_args(sys.argv) | |
@staticmethod | |
def run(): | |
sampler = FileSampler() | |
sampler.split() | |
def split(self): | |
file_number = 1 | |
line_number = 1 | |
for line in self.in_file: | |
if line_number % self.sample_rate == 0: | |
print(line.strip()) | |
line_number += 1 | |
def parse_args(self,argv): | |
"""parse args and set up instance variables""" | |
try: | |
self.sample_rate = 10 | |
if len(argv) > 2: | |
self.sample_rate = int(argv[2]) | |
self.file_name = argv[1] | |
self.in_file = open(self.file_name, "r") | |
except: | |
print self.usage() | |
sys.exit(1) | |
def usage(self): | |
return """ | |
Sample every n rows from a file. | |
Usage: | |
$ python file_sampler.py <file_name> [sample_rate] | |
sample_rate is optional (default is 10) | |
""" | |
if __name__ == "__main__": | |
FileSampler.run() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment