Re: DM: Clustering and categorical attributes

[Murray Jorgensen]

At 23:31 11/01/98 -0500, Carol Romanowski wrote:
>Hello-
>
>I have a question about non-numeric data - what are good algorithms 
>to
>use when doing cluster analysis with attributes that have many
>categories?  For instance, I have a dataset in which several fields 
>are
>alpha-numeric codes, and there are at least 1000 possible codes.
>

Do you mean 1000 codes for a single attribute or 1000 different 
attribute
profiles? If the former I think that you will have to recode your
attributes to reduce the number of possible values for an attribute.

>I have read of a method that is based on k-means clustering.  Are 
>there
>others?

Surely k-means clustering requires numerical attributes?


>Thanks
>
>Carol
>
>
Murray Jorgensen,  Department of Statistics,  U of Waikato, Hamilton, 
NZ
-----[+64-7-838-4773]---------------------------[maj@waikato.ac.nz]-----
"Doubt everything or believe everything:these are two equally 
convenient
strategies. With either we dispense with the need to think."
http://www.cs.waikato.ac.nz/stats/Staff/maj.html       - Henri 
Poincare'