KDD procedures – CF-Miner

 

CF-Miner procedure

Author(s):

Milan Šimůnek, Jan Rauch

Responsibility:

Jan Rauch (theory), Milan Šimůnek (software), Martin Kejkula (help)

Description:

Data mining procedure Cf-Miner mines for patterns of the form (~ R) / Cond. Here R is a categorial attribute with categories r1, , rK and Cond is a Boolean attribute.

The procedure deals with data matrices. The attribute R corresponds to a column of the analysed data matrix. Boolean attribute Cond is derived from the other columns of the data matrix.

The intuitive meaning of the pattern (~ R) / Cond is that the categories of the attribute R satisfy the condition given by the symbol ~ for the subset of rows of analysed data matrix defined by the Boolean attribute Cond.

The symbol ~ is called CF-quantifier. It corresponds to a condition imposed on the vector of frequencies of particular categories of the attribute R. The pattern (~ R) / Cond is verified on the data matrix M / Cond. Here M is the analysed data matrix and M / Cond is a data matrix consisting of all rows of M satisfying Cond.

Files to download:
LISp-Miner.Core.zip 33.41 MB July 22, 2014
Legacy LISp-Miner system core files separated into modules for each GUHA procedure. Contains also other legacy modules (LMAdmin, LMDataSource, LMTaskPooler, LMProcPooler, LMSwbImporter and LMSwbExporter)
History:

The procedure Cf-Miner was suggested by J. Rauch in 2002. Reason was the necessity to mine for patterns describing a distribution of frequencies of a categorial attribute. The second reason was the possibility to use the software tools for dealing with strings of bits developed for the 4ft-Miner procedure. The suggestion was published under name Pareto-Miner in [RS 02].

The first version of the procedure with set of simple CF-quantifiers was implemented by M. Šimůnek.

Print page

 
 

Send comments about this site to the webmaster