search

tommeagher / heroku_ebooks

An archive of a script to generate Markov chains and to post to an _ebooks account on Twitter using Heroku. No longer actively supported.
264 stars 163 forks source link

Configuration for Markov Chain #70

Closed actualguy closed 4 years ago

actualguy commented 4 years ago

A lot of my generated tweets are coming out quite short. Are there any variables within the Markov.py that can be tweaked to produce different outcomes or is it pretty set in stone?

tommeagher commented 4 years ago

You can try tinkering with the ORDER variable in the settings: https://github.com/tommeagher/heroku_ebooks#configuring Do your source tweets tend to be short as well?

actualguy commented 4 years ago

One of my source accounts does tweet somewhat short tweets, so I think I will take that out of the rotation. Switching between 2-4 didn't seem to have too much effect, but I will keep experimenting.

Thanks!

tommeagher commented 4 years ago

Cool. I'm guessing it's a matter of using short tweets as the source. Longer tweets, closer to the 280 limit, should return longer strings. Will close this for now, but feel free to reopen it if you want to discuss further as you experiment.