Just another site

Thought this was cool: What is the optimal way to encode a feature which consists a list of categories?

leave a comment »

In Machine Learning: Cosmin Negruseri voted up an answer.

Separate Booleans would be a good way to go, and some algorithms perform best on all Boolean features.  The only thing you would lose is if there are genres which are strictly mutually exclusive; better to represent these with a categorical variable.

See question on Quora

from Cosmin Negruseri on Quora:


Written by cwyalpha

十二月 24, 2012 在 4:53 上午

发表在 Uncategorized


Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / 更改 )

Twitter picture

You are commenting using your Twitter account. Log Out / 更改 )

Facebook photo

You are commenting using your Facebook account. Log Out / 更改 )

Google+ photo

You are commenting using your Google+ account. Log Out / 更改 )

Connecting to %s

%d 博主赞过: