Association Rule Mining on Relational DataBase

Question

I am working on a project "Association Rule Mining on Relational Data Base". I have completed my implementation but the problem is I don't have any other tool to compare (check) my results

Can any one suggest me the tool for association rule mining on Relational data base.

Example input in my implementation is:

A   B   C
0   0   0
0   0   1
0   1   1
1   1   1
1   1   1

Output :

A:1 --> B:1 C:1    100.0%
B:1 --> A:1 C:1    66.66667%
A:1 B:1 --> C:1    100.0%
C:1 --> A:1 B:1    50.0%
A:1 C:1 --> B:1    100.0%
B:1 C:1 --> A:1    66.66667%

in the output A:1 means column A and value 1.

Answer 1

You might consider the Analysis Services of MS SQL Server. Analysis Services have the Microsoft Association rule mining algorithm implementation for the relational database(Of course, MS SQL Server). http://technet.microsoft.com/en-us/library/ms174916.aspx

Answer 2

Check my software SPMF : http://www.philippe-fournier-viger.com/spmf/

It offers more than 50 algorithms for itemset mining, association rule mining, etc.

You could compare the result with the FPGrowth and Apriori implementation for mining association rules in my software to see if the result is the same.

Answer 3

Export the data, and then analyse it in Weka/KNIME/Whatever.

There is no benefit of keeping the data in a database, and the results should be the same after all.

Answer 4

KNIME is a great tool for data mining in general, you can modell your case in there and test to see if you get the same results. But you may have to read a bit on how to connect your db etc, or maybe just start feeding it with text files.