<P>
An implementation of the well known Apriori algorithm for the data mining step. It works on a sample read from the database. The sample size is given by the parameter <I>SampleSize</I>.

<P>
The input format is fixed. There is one input concept (<I>TheInputConcept</I>) having a BaseAttribute for the customer ID (parameter: <I>CustID</I>), one for the transaction ID (<I>TransID</I>), and one for an item part of this customer/transaction's itemset (<I>Item</I>). The algorithm expects all entries of these <TT>BaseAttribute</TT>s to be integers. No null values are allowed.

<P>
It then finds all frequent (parameter: <I>MinSupport</I>) rules with at least the specified confidence (parameter: <I>MinConfidence</I>). Please keep in mind that these settings (especially the minimal support) are applied to a sample!

<P> The output is specified by three parameters. <I>TheOutputConcept</I> is the 
  concept the output table is attached to. It has two <TT>BaseAttribute</TT>s, 
  <I>PremiseBA</I> for the premises of rules and <I>ConclusionBA</I> for the conclusions. 
  Each entry for one of these attributes contains a set of whitespace-separated 
  item IDs (integers).<BR>
  <BR>
<P>
PARAMETERDESCRIPTION
TheInputConcept:inherited
CustID:customer id (integer, not NULL)
TransID:transaction id (integer, not NULL)
Item:item id (integer, not NULL)
MinSupport:minimal support (integer)
MinConfidence:minimal confidence (in [0,1])
SampleSize:the size of the sample to be used
PremiseBA:premises of rules
ConclusionBA:conclusions of rules
TheOutputConcept:inherited
