Comments on: Canabalt

By: Nathan

Nathan — Fri, 20 Nov 2009 15:07:09 +0000

What’s up with the ggplot fad?

By: Jeromy Anglim

Jeromy Anglim — Fri, 20 Nov 2009 04:13:55 +0000

I’d be interested to see the relationship between practice and performance for particular individuals. I imagine that date stamps could be used to indicate time (i.e., 1 , 2, 3, etc. ) and twitter User IDs could be used to identify individuals. You could then summarise properties of the individual-level learning curves. You could answer questions like: what is the shape of the learning curve? Do people differ in their rate of learning?

Of course, there are many questions about the way the data is sampled. It may be possible to find subsets of people in the data who seem to post every single game. These might be the most interesting individuals.

There may also be ways of detecting fraudulent posts. For example, an unusual sequence of scores may indicate problematic posting.

If scores do improve with practice, then it’s likely that skill is important.

By: Hadley

Hadley — Fri, 20 Nov 2009 02:54:40 +0000

You currently need to use the full scale_y_continuous call. I have some ideas on how to ylab work for a future release.

Neat use of ggplot2!

By: John Myles White

John Myles White — Mon, 16 Nov 2009 15:05:56 +0000

Hi all, I’m glad you enjoyed this post. My second pass at analyzing the scores is up now. I just revised it, since the first posted draft wasn’t as clear as it should have been.

@Tigershungry, your point about systematic bias in the scores posted to Twitter is well-taken. If you can think of a way to get all of the scores from a population similar to the people posting to Twitter, we can estimate the exact size of the bias.

As for the pixel art compliments, all of the credit goes to Hadley Wickham, who I think is really one of the true masters of modern data visualization. I just used the graphics code he wrote.

By: axcho

axcho — Fri, 13 Nov 2009 20:11:50 +0000

“I think the nice detail here is, that the graph is itself also pixel art.”

Haha, good point. :) You could make a meta-Canabalt game where the levels are generated from the scores of other players… :p

By: coollavagames

coollavagames — Fri, 13 Nov 2009 18:29:18 +0000

I think the nice detail here is, that the graph is itself also pixel art.

By: Tigershungry

Tigershungry — Fri, 13 Nov 2009 16:26:27 +0000

Really interesting work. I wonder if given that the score tweets aren’t completely automatic (players being more inclined to tweet their ‘better scores’), I wonder if a curve based on data from all players run attempts would look different.

By: danny B

danny B — Fri, 13 Nov 2009 15:38:22 +0000

this is really interesting! i look forward to seeing your analysis!! :)