Changeset 9928:9dddd16dbc01 in orange


Ignore:
Timestamp:
02/07/12 16:43:32 (2 years ago)
Author:
Matija Polajnar <matija.polajnar@…>
Branch:
default
Message:

Improve multilabel and multitarget documentation introduction.

Location:
docs/reference/rst
Files:
3 edited

Legend:

Unmodified
Added
Removed
  • docs/reference/rst/Orange.data.formats.rst

    r9927 r9928  
    44Loading and saving data 
    55======================= 
     6 
     7.. _tab-delimited: 
    68 
    79Tab-delimited format 
  • docs/reference/rst/Orange.multilabel.rst

    r9505 r9928  
    22Multi-label classification (``multilabel``) 
    33########################################### 
     4 
     5`Multi-label classification <http://en.wikipedia 
     6.org/wiki/Multi-label_classification>`_ is a machine learning prediction 
     7problem in which multiple binary variables (i.e. labels) are being predicted. 
     8Orange supports such a task, although the set of available methods is 
     9currently rather limited. 
     10 
     11Multi-label data is represented as :ref:`multi-target data <multiple-classes>` 
     12with discrete binary classes with values '0' and '1'. Multi-target data is 
     13also supported by Orange's tab file format 
     14using :ref:`multiclass directive <tab-delimited>`. 
    415 
    516.. automodule:: Orange.multilabel 
  • docs/reference/rst/Orange.multitarget.rst

    r9553 r9928  
    33########################################### 
    44 
    5 This module contains methods for working with 
    6 :ref:`multi-target data <multiple-classes>`. 
     5Multi-target prediction tries to achieve better prediction accuracy or speed 
     6through prediction of multiple dependent variable at once. It works on 
     7:ref:`multi-target data <multiple-classes>`, which is also supported by 
     8Orange's tab file format using :ref:`multiclass directive <tab-delimited>`. 
    79 
    810.. toctree:: 
Note: See TracChangeset for help on using the changeset viewer.