[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Clarification on the "rand-index" based external cluster evaluation
- To: Rao Kambhampati <rao@asu.edu>
- Subject: Clarification on the "rand-index" based external cluster evaluation
- From: Subbarao Kambhampati <rao@asu.edu>
- Date: Tue, 13 Apr 2010 16:00:39 -0700
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:sender:received:date :x-google-sender-auth:received:message-id:subject:from:to :content-type; bh=l05G4wQHDMrtm78wl8+kyyOr/5JE5kkMMROS9pZ5mLs=; b=XGuj4GRxzQcTq8h2KVlY1umKwcUje7WofOF31U9Iq59v9NxEr5rMgzI1jktaT0l/T2 8So1kq22mrrEMq++V6K4jeZgz4ingXEIBsQZd47TDXZfS0L4k9VRyWbP88HSPs7W+wyl y64L5IYsMXLl4o0XsHlb/iQafmfdq1ktN8uFE=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:date:x-google-sender-auth:message-id:subject :from:to:content-type; b=aW/wF92ShWmCbWF4H6w7ewAaR8phWQc/6MkbWw3LsX21/L8veBjCeEe71hDC0MnIiB 19f+nWws+Zq2+4IrrgWOrUTFRkwZl6Lxk81HYM3nqKd+f23nPI8bIs3g4KrXRzZi9H++ ikks+WCSnSpT424QheoqH/mnMKop1Im0GKfqk=
- Sender: subbarao2z2@gmail.com
Folks:
In talking to a student, I realized I didn't make something clear in describing the rand-index based external cluster evaluation method.
Rand-Index classifies every pair of entities e1,e2 into four categories
[in-the-same-ground-truth-cluster, in-the-same-generated-cluster] A
[in-the-same-ground-truth-cluster, in-different-generated-clusters] C
[in-different-ground-truth-clusters, in-the-same-generated-cluster] B
[in-different-ground-truth-clusters, in-different-generated-clusters] D
If A,B,C,D are the number in each class, then A+B+C+D will be n*(n-1)/2 (which is the number of pairs over n entities).
I modified the slide to make this point clear..
Rao