Magic the Machine Learning

Posted: Monday, 2018-07-16 19:17 | Tags: MachineLearning, Programming, MTG
images/mtg/card_predict.jpg

In the previous post on this topic, we raised the question on how much particular abilities such as "flying" cost in the widely known trading card game Magic the Gathering. We found luckily there is a nice, usable free database out there that should be helpful to answer this and while trying to take a look into the data we learned about Prinicipal Component Analysis and how it can be helpful to visualize high-dimensional data.

Somewhat unsatisfactory we ended up without getting an answer to the "flying" question, lets try to come up with a model now that can help with that.

Shouldn't we just use deep convolutional neural networks or something?

Recently that seems to be the hammer that makes almost everything look like a nail, and I would be lying would I assure you that the recent advances in this area had not motivated this blog post. But, valued reader, keep in mind the question we are trying to answer: How much mana do abilities such as "flying" cost? How much does it cost to have a creature that has one unit more power or toughness? A (deep) neural network might be able to predict accurately the mana cost for any given card, but how would that answer our question? What we are actually after here is not approximating the mana cost of certain cards but understand how they are composed. While neural networks have recently proven to be useful function approximators for various tasks recently, they could not be farther away from something that provides a human-understandable model.

Wizards of the Coast, Magic: The Gathering, and their logos are trademarks of Wizards of the Coast LLC in the United States and other countries. © 2009 Wizards. All Rights Reserved. This web site is not affiliated with, endorsed, sponsored, or specifically approved by Wizards of the Coast LLC.

Read more...

Magic: The Data Gathering

Posted: Sunday, 2017-04-30 16:00 | Tags: MachineLearning, Programming, MTG
images/mtg/card_archivist.jpg

Magic: The Gathering is a trading card game I happen to like. It also so happens that there is a database of cards available online. Additionally I (like many programmers) kind-of got into Machine Learning recently. Lets see if we can combine these ingredients to come up with something interesting, shall we? Have you ever wondered whether cards got "cheaper" (in terms of Mana) in the past years or how much more a creature costs because it can fly? How much cheaper is a creature that has Defender? I'll be toying around with some card data and do some basic data analysis for practice, education and fun. There shall be some (somewhat hacky) Python code using Pandas, SciKit-Learn and Matplotlib in the end that you can use to reproduce (or extend) what I did (you'll have to wait for the second part for that though).

In this first part we will do some general analysis of the data and see what we can learn about the game with a simple Principal Component Analysis.

Wizards of the Coast, Magic: The Gathering, and their logos are trademarks of Wizards of the Coast LLC in the United States and other countries. © 2009 Wizards. All Rights Reserved. This web site is not affiliated with, endorsed, sponsored, or specifically approved by Wizards of the Coast LLC.

Read more...

Kakoune offers already various integrations for external tools such as git, ranger and various others. Recently there was also some nice integration of fzf made public (although afaik not (yet) included in the kakoune distribution).

I took all this, put it in my config, modified it to my needs and extended it a little.

images/screenshots/kakoune_external_thumb.png
Read more...

These days there are some damn cool things out there to build up your Unixoid (development) environment. This is a medium-sized elaboration on the stuff I like.

Spoilers: Including an editor that can be considered better than VIM in some regards and the single most awesome shell there is (no, not ZSH). I structured it a bit though so you can skip through the parts that are boring to you :-).

Read more...

Python notes

Posted: Sunday, 2017-01-22 11:02 | Tags: Programming, Python

I've been watching some PyCon talks online lately and stumbled across a few interesting things, these are mostly notes for myself but feel free to consider them useful ;-)

Read more...