Changeset 3669:aaf3a7c84948 in orange


Ignore:
Timestamp:
05/18/07 11:02:01 (7 years ago)
Author:
ales_erjavec <ales.erjavec@…>
Branch:
default
Convert:
d23e8b8b7b10545028b9a9de5037578abd18a4d4
Message:

Added SVMLearnerSparse (/Easy)

File:
1 edited

Legend:

Unmodified
Added
Removed
  • orange/doc/modules/orngSVM.htm

    r3522 r3669  
    4242  <dd>Determines if a probability model should be build (default False)</dd> 
    4343</dl> 
     44<h2>SVMLearnerSparse</h2> 
     45<p><INDEX name="classes/SVMLearnerSparse (in orngSVM)">Same as <code>SVMLearner</code> except that it learns from the examples mata attributes.  Note that meta attributes dont need to be registerd with the dataset domain, or present in all the examples. 
     46Use this if you are using large sparse datasets. </p> 
    4447 
    4548<h2>SVMLearnerEasy</h2> 
    4649<p><INDEX name="classes/SVMLearner (in orngSVM)">Same as above except that it will automaticaly scale the data and perform parameter optimization using the <code>parameter_selection</code> similar to the easy.py script  
    4750in libSVM package. Use this if the <code>SVMLearner</code> performs badly. </p>  
     51 
     52<h2>SVMLearnerSparseEasy</h2> 
     53<p><INDEX name="classes/SVMLearnerSparseEasy (in orngSVM)">Same as <code>SVMLearnerEasy</code> except that it learns from the examples mata attributes.  Note that meta attributes dont need to be registerd with the dataset domain, or present in all the examples. 
     54Use this if you are using large sparse datasets (and have absolutely no respect for the fourth dimension commonly named as time). </p> 
    4855 
    4956<h2>parameterSelection</h2> 
Note: See TracChangeset for help on using the changeset viewer.