Topic: Cluster Analysis

[Mike]

Has anyone ever done this?  I have a feeling I should look at it for my current work project.  Wondering if anyone knew of any good sites/books that explain it (and maybe give some code samples)

[ober]

We have a cluster here where I work but I don't know enough to really give you a lot of information on it.  We only use one DB but we have 3 production application servers that handle all the traffic and requests.  We use a hardware device to do the load balancing though.

[webwhy]

Has anyone ever done this?  I have a feeling I should look at it for my current work project.  Wondering if anyone knew of any good sites/books that explain it (and maybe give some code samples)

assuming you're talking about data clustering through anaylsis/machine learning/data mining?

http://mahout.apache.org/

[ober]

Yeah, I could have been wrong as far as what you were driving at?

[Mike]

This type of cluster analysis: http://en.wikipedia.org/wiki/Cluster_analysis

Here is the problem:
Our school isn't seat based, instead the teachers go to the kids.  The project I'm working on is to automate the assigning of the students to various teachers.  One aspect is going to be physical location of the student.  So I'm thinking some type of cluster analysis to find clusters of students.

[webwhy]

sounds like mahout is what you're looking for

[Mike]

So mahout is out since it is Java and isn't really integratable.  I did look at the algorithms and k-means was actually very useful and got me some good information.