Created
February 4, 2013 01:39
-
-
Save RWJMurphy/4704585 to your computer and use it in GitHub Desktop.
Markov chain text generator in python
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 | |
from __future__ import print_function | |
import argparse | |
from collections import defaultdict | |
import os | |
import random | |
import sys | |
def main(args): | |
result = os.EX_OK | |
markov_data = defaultdict(list) | |
for inputfilename in args.FILE: | |
key = ("\n",)*args.sequence_length | |
if inputfilename == '-': | |
inputfile = sys.stdin | |
else: | |
inputfile = open(inputfilename, 'r') | |
for line in inputfile: | |
words = line.split(args.delimiter) + ["\n"] | |
if len(words): | |
for word in words: | |
markov_data[key].append(word) | |
key = key[1:] + (word,) | |
key = ("\n",)*args.sequence_length | |
for x in range(args.output_words): | |
word = random.choice(markov_data.get(key, ("\n",)*args.sequence_length)) | |
key = key[1:] + (word,) | |
print(word, end=" ") | |
return result | |
if __name__ == "__main__": | |
exit_code = os.EX_OK | |
parser = argparse.ArgumentParser() | |
parser.add_argument('--delimiter', '-d', default=None) | |
parser.add_argument('--sequence-length', '-l', type=int, default=2) | |
parser.add_argument('--output-words', '-o', type=int, default=1000) | |
parser.add_argument("FILE", nargs="*", default=['-']) | |
parsed_args = parser.parse_args() | |
try: | |
exit_code = main(parsed_args) | |
except KeyboardInterrupt: | |
pass | |
sys.exit(exit_code) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment