Relational Data Mining
Hi everbody ,
I'd like to know how to apply data mining algorithms implemented in rapidminer on relational data sets ! I mean the dataset that I have is not a simple flat file , they are number of files related to each other by primary and foreign keys !
Is there any way to handle this in rapidminer ?
Thanks ,
-Arian
I'd like to know how to apply data mining algorithms implemented in rapidminer on relational data sets ! I mean the dataset that I have is not a simple flat file , they are number of files related to each other by primary and foreign keys !
Is there any way to handle this in rapidminer ?
Thanks ,
-Arian
Tagged:
0
Answers
-
Hi!
That's not a problem at all. RapidMiner is a full-featured ETL tool.
Just read your files with the appropriate operators (e. g. CSV), mark the ID fields with the role ID, and use the Join operator to created joined datasets just like in a relational database.
The resulting dataset can be used with the data mining algorithms.
Regards
Balázs0