Clustering and storing clustered data

myid_tuhin123

Hi All,

I am new to RapidMiner and data mining. Just yesterday got it downloaded and started exploring.

I need to use it to create some clusters (lets say 4 clusters) from an existing data.
now using these data, I need to prepare 4-5 clusters and store them in the db.(I will be using these clusters' data in future for creating some analytics, that is the later part)
clusters should be containing mean, standard deviation and range (on which they were calculated)
and once the cluster is created I will be saving it to my mysql db.

I also would appreciate if any one can give me some suggestions how should I use clustering through my application (I am working on  java based web application which uses hibernate as ORM with mysql database).

Looking forward to get a positive reply.

Thanks,
tuhin

MariusHelf

Hi Tuhin,

I would suggest that first of all you get accustomed to RapidMiner. You can find a link to video tutorials in the post linked in my signature.
Then you can use one of the Cluster Performance operators to evaluate the clustering.
To work with databases, we have the Read/Write/Update Database operators and Execute SQL.

When you managed to do that in the GUI, you can start to integrate the process into your own java application.

Happy Mining!
~Marius