Projet

Général

Profil

Documentation » Historique » Révision 36

Révision 35 (François Rioult, 06/12/2012 20:57) → Révision 36/37 (François Rioult, 19/10/2013 20:46)

h1. Documentation 

 KDAriane is a set of operators for data mining and machine learning, and a set of scenarios (supervised classification, missing values completion, strong emerging pattern mining, etc.). It uses Ariane as a graphical platform for designing the data streams. 

 h2. Demonstration 

 You can watch the [[short demonstration of KDAriane]]. 

 h2. Installation 

 * [[Prerequisite]] 
 * [[KDAriane]]  

 h2. Tutorial 

 You can read the document [[Data preparation]] for a first contact with @KDAriane@. 

 h2. Scenarios 

 In the @sample@ folder, @KDAriane@ provides some examples of KDD scenarios: 
 * [[Data preparation]]: a first scenario for the binarization of CSV data. 
 * [[Data mining complexity]]: pattern mining and complexity visualization 
 * [[CMAR]]: supervised classification with association rules [1] 

 h2. How is Ariane working? 

 Ariane is a graphical platform for designing image processing streams. Ariane works with graphical operators, and allows to build loops and while. 
 "Go to the Aiane dedicated site":http://www.greyc.ensicaen.fr/~regis/Ariane/ for a full documentation about Ariane. 

 KDAriane is provided with basic components for executing shell scripts. When an operator is executed, Ariane launches the script with giving the following arguments: 
 <pre> 
 script.sh parameter-1 ... parameter-p input-1 ... input-i output-1 ... output-o 
 </pre> 

 See [[Eval operators]] for shell scripting or calling binaries. 

 h2. Operators 

 The operator are divided in three categories:  

 * [[Eval operators]] that directly execute the commands entered by Ariane.  
 * [[KDD operators]] are special components for calling Weka components or RapidMiner processes. 
 * [[Shell operators]] that directly execute the commands entered by Ariane.  

 h2. Pattern mining prototypes 

 KDAriane uses some specific prototypes:  

 * [[music-dfs]] : mining patterns under various constraints 
 * [[mtminer]] : levelwise minimal transversals of hypergraph 
 * [[mvminer]] : mining delta-free patterns in presence of missing values 

 h2. Routines 

 Routines are complex streams that Ariane allows you to share. 
 * [[shell routines]] 
 * [[routines for missing values ]] 
 * [[KDD routines]] 

 h2. To-do 

 * sous-projet members 
 * unifier options mvminer 

 h2. Appendix 

 h3. Utilities 

 * [[gnuplot]]: plotting data with GNUplot 
 * [[score]] : computing validation values from a decision file 
 * [[complement]] : 
 * [[dictionary]] : 
 * [[segmentation]] : 

 h3. References