Welcome to this site for the book of Feature Selection for Knowledge Discovery and Ddata Mining

From this web site you will get the links to different programs and data sets used in the book titled FEATURE SELECTION. To get and build the programs successfully it is recomended to read the README files in different subdirectories. You will get all the datasets and programs related to the feature selection and discretization mentioned in the book in the following file hierarchy.

 All the datasets used in the different experiments of this book have been downloaded or generated by the programs from  UCI Machine Learningrepository. The feture selection algorithms have been collected from respective literatures. Neither the authors of the book nor the developer of the programs shall be liable for any direct, incidental or consequential damages resultiong from use of the software or documentation, regardless of the theory of the liability.

For easy reference of the machine learning (ML), data mining and knowledge discovery (KD) resources, the book FETURE SELECTION  FOR KNOWLEDGE DISCOVERY maintains an extensive appendix,  Appendix A . Any suggestions for maintaing this link will be appreciated.

 If you publish material based on programs obtained from this site, then, in your acknowledgments, please note the assistance you received by using this site. This will help others to obtain the same programs and replicate your experiments.

 If you have suggestions concerning the site send email to hliu@asu.edu

File hierarchy for relevant programs and data files

/FSBOOK
   |
   |-----DATA (Contains some data files)
   |              |
   |              |------corral.data
   |              |------iris.data
   |              |------credit.data
   |              |------led17.data
   |              |------monk1.data
   |              |------monk2.data
   |              |------monk3.data
   |              |------parity5+5.data
   |              |------parity5+2.data
   |
   |-----CODE (Contains feature selection programs)
   |              |
   |              |------ZIP (zipped source code of all applications)
   |              |------ABB (Source code for ABB)
   |              |------B+B (Source code for B+B)
   |              |------LVF (Source code for LVF)
   |              |------LVW (Source code for LVW)
   |              |                |------C4.5 (Code for LVW using C4.5)
   |              |                |------NBC (Code for LVW using NBC)
   |              |
   |              |------QBB (Source code for QBB)
   |              |------LVI (Source code for LVI)
   |              |------FOCUS (Source code for FOCUS)
   |              |------RELIEF (Source code for RELIEF)
   |              |------SFG (Source code for sequential forward
   |              |                        feature generation using information gain)
   |              |------WSBG (Source code for sequential backward
   |              |                |                feature generation using classifier accuracy (NBC &
   |              |                |                C4.5) )
   |              |                |
   |              |                |-------C4.5 (Code for WSBG using C4.5)
   |              |                |-------NBC (Code for WSBG using NBC)
   |              |
   |              |------WSFG (Source code for sequential forward
   |              |                |                feature generation using classifier accuracy (NBC &
   |              |                |                C4.5) )
   |              |                |
   |              |                |------C4.5 (Code for WSFG using C4.5)
   |              |                |------NBC (Code for WSFG using NBC)
   |              |
   |              |------APPL (Source code to run all the above
   |                                       &nb sp;  applications using option menu interface)
   |
   |-----DOC (Contains some documents for system  understanding)
   |
   |-----TOOLS (Contains some classifier and discretizers )
                  |
                  |------CLASSIFIER
                  |                |
                  |                |
                  |                |-------NBC (Code for NBC)
                  |
                  |------DISCRETIZER
                  |                |
                  |                |
                  |                |------Chi-merge (Code for Chi-merge)
                  |                |------Chi2 (Code for Chi2)
                  |
                  |------ENTROPY
                  |                |
                  |                |
                  |                |------entropyc (Code to measure entropy for cont. attrib)
                  |                |------entropyd (Code to measure entropy for disc. attrib)
                  |
                  |------MISC (Programs to generate names file and shuffle data)
                                   |
                                   |------NAMES (Code to generate names file)
                                   |------SHUFFLE (Code to shuffle data)
 


Authors' Home

[Dr. Huan Liu]

[Dr. Hiroshi Motoda]

This page was maintained by

[Md. Farhad Hussain]


This page has been accessed : [an error occurred while processing this directive] times



Current Time: Wednesday, 17-Apr-2024 19:41:10 MST

Last Upadted: Wednesday, 19-Dec-2001 09:03:08 MST