markov-hacker-news
所属分类:数学计算
开发工具:Python
文件大小:0KB
下载次数:0
上传日期:2013-03-11 19:45:37
上 传 者:
sh-1993
说明: 黑客新闻模仿机器人
(Hacker News parody bot)
文件列表:
bigrams.py (2677, 2013-03-11)
headlines.json (9178, 2013-03-11)
requirements.txt (1925, 2013-03-11)
sample.py (1821, 2013-03-11)
sample.txt (366, 2013-03-11)
temp.py (568, 2013-03-11)
trigrams.py (3469, 2013-03-11)
Hacker News Markov chain generator
==================
Generates new-to-world Hacker News headlines, trained on several years of previous headlines. It uses a [Markov chain generator](https://github.com/sursh/markov-hacker-news/blob/master/) and trigrams to produce mostly human-sounding headlines. Old bigrams version also included for comparison.
Follow the Twitter bot [here](https://github.com/sursh/markov-hacker-news/blob/master/https://twitter.com/HackerNewsOrNot)!
By [Sasha Laundy](https://github.com/sursh/markov-hacker-news/blob/master/http://github.com/sursh) and [David Lundgren](https://github.com/sursh/markov-hacker-news/blob/master/http://github.com/maxlikely) at [Hacker School](https://github.com/sursh/markov-hacker-news/blob/master/http://hackerschool.com).
TODO:
- [x] Fix regex to not split on apostrophes & fix title casing
- Set it to pick a common starting word for the first seed
- [x] Recapitalize sentences before output
- [x] Use pickle to only generate the matrix once
- [x] Turn into Twitter bot with heroku
- [x] fix length of tweets
- [x] add seed function
TODO SOMEDAY:
- [ ] cut off long tail of sentence seeds as they're less likely to lead to a new headline
- [ ] Implement real HN headlines so Twitter bot is a "is this real or not?" stream
- [ ] Implement check to make sure generated lines aren't coincidentally real ones
- [ ] Toward the end of a sentence, transition into bigrams instead of trigrams
近期下载者:
相关文件:
收藏者: