Getting Attribute Statistics In Plug-in Algorithm

Hello,

for an internship i am writing a data mining plug-in algorithm in SSAS in C#. My algorithm is a subgroup discovery algorithm and for determining the quality of the the discoverd rules/ patterns, i need to know what the support is of the rules.

The rules are of the form (a = x AND b < y THEN c = z). I managed to obtain some statistics by calling MarginalStatistics.getCasesCount(..,..). But I would like more functionality.

For example the data mining structure:

id | column1 | column2 | column3 | column4
1 1 1 1.0 1
2 1 2 2.3 1
3 1 2 1.1 2

I want to evaluate the rule (column1 = 1 AND column2 = 2 THEN column3 > 0). The result should be 2. Now is my question, how do i get the support of my rule in my in C# written algorithm?

Thanks in advance,
Joris Valkonet
jorisv@avanade.com