Created
November 11, 2023 15:45
-
-
Save benhoyt/619cf3113866450aa31d8a2c1f8e01dc to your computer and use it in GitHub Desktop.
Generate text from an input using a simple Markov chain generator
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
import collections, random, sys, textwrap | |
# Build possibles table indexed by pair of prefix words (w1, w2) | |
w1 = w2 = '' | |
possibles = collections.defaultdict(list) | |
for line in sys.stdin: | |
for word in line.split(): | |
possibles[w1, w2].append(word) | |
w1, w2 = w2, word | |
# Avoid empty possibles lists at end of input | |
possibles[w1, w2].append('') | |
possibles[w2, ''].append('') | |
# Generate randomized output (start with a random capitalized prefix) | |
w1, w2 = random.choice([k for k in possibles if k[0][:1].isupper()]) | |
output = [w1, w2] | |
for _ in range(int(sys.argv[1])): | |
word = random.choice(possibles[w1, w2]) | |
output.append(word) | |
w1, w2 = w2, word | |
# Print output wrapped to 70 columns | |
print(textwrap.fill(' '.join(output))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment