Created
January 3, 2013 13:21
-
-
Save ichyo/4443429 to your computer and use it in GitHub Desktop.
マルコフ連鎖で文章作るねん
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 os | |
import sys | |
import re | |
from collections import defaultdict | |
import random | |
def split(sentence): | |
wakati = os.popen("echo '#{text}' | mecab -Owakati".format(text=sentence)).read() | |
return wakati.split()[1:] | |
count = defaultdict(list) | |
def learn(words, n): | |
words.append("$") | |
state = ("^", ) * n | |
for w in words: | |
count[state].append(w) | |
state = state[1:] + (w, ) | |
def create(n): | |
state = ("^", ) * n | |
res = "" | |
while True: | |
if len(count[state]) == 0: | |
break | |
w = random.choice(count[state]) | |
if w == "$": | |
break | |
state = state[1:] + (w, ) | |
if re.search("[a-zA-Z]", res[-1:]) != None and re.search("[a-zA-Z]", w[0:1]) != None: | |
res += " " | |
res += w | |
return res | |
if __name__ == '__main__': | |
N = 2 | |
text = sys.stdin.readlines() | |
for s in text: | |
if len(s) > 5: | |
learn(split(s), N) | |
for i in range(50): | |
print create(N) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment