KDD procedures – Data Preprocessing

 

Subsystem Data Preprocessing

Author(s):

Milan Šimůnek, Jan Rauch

Responsibility:

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

Description:

The Data Preprocessing subsystem consists of three parts – metabase, modul Admin and data transformation and exploration procedure DataSource.

Metabase is a central data store for all the definitions and results used by all KDD procedures of the LISp-Miner system.

The only function of the modul Admin is to ensure the connection between the analysed database and the corresponding metabase.

Data transformation and exploration procedure DataSource is a tool for preparation of data matrices for all KDD procedures. It has lot of possibilities of data tramsformations and efficient tools for both introductory and advanced data exploration.

Files to download:
LISp-Miner.Core.OldUI.zip 33.45 MB August 13, 2014
Legacy LISp-Miner system core files separated into modules for each GUHA procedure. Contains also other legacy modules LMAdmin and LMDataSource.
History:

The history of this subsystem started with implementation of the first version of the procedure 4ft-Miner. Several data transformation tools were embedded in this procedure. The data transformation tools were separated according to the new conception and independent transformation and exploration procedure DataSource was implemented. Procedure DataSource became the basis of the Data Preprocessing subsystem.

An important part of the LISp-Miner system became a metabase as a central data store for all the definitions and results used in all KDD procedures and the module Admin was implemented in 1999. This way the basis of the subsystem Elementary was completed.

Various data exploration tools inspired by particular data mining procedures were invented by M. Šim?nek in 2000–2004.

The whole Elementary subsystem was implemented by M. Šimůnek.

Print page

 
 

Send comments about this site to the webmaster