source: orange/docs/widgets/rst/regression/regressiontree.rst @ 11404:1a7b773d7c7b

Revision 11404:1a7b773d7c7b, 2.0 KB checked in by Ales Erjavec <ales.erjavec@…>, 13 months ago (diff)

Replaced the use of :code: role with :obj:

RevLine 
[11050]1.. _Regression Tree:
2
3Regression Tree Learner
4=======================
5
6.. image:: ../icons/RegressionTree.png
7
8Regression Tree Learner
9
10Signals
11-------
12
13Inputs:
14   - Examples (ExampleTable)
15      A table with training examples
16
17
18Outputs:
19   - Learner
[11359]20      The classification tree learning algorithm with settings as specified in
21      the dialog.
[11050]22   - Regression Tree
23      Trained classifier (a subtype of Classifier)
24
25
[11404]26Signal :obj:`Regression Tree` sends data only if the learning data (signal
27:obj:`Examples`) is present.
[11050]28
29Description
30-----------
31
[11359]32This widget constructs a regression tree learning algorithm. As all widgets
33for classification and regression, this widget provides a learner and
34classifier/regressor on the output. Learner is a learning algorithm with
35settings as specified by the user. It can be fed into widgets for testing
36learners, for instance :ref:`Test Learners`.
[11050]37
38.. image:: images/RegressionTree.png
39   :alt: Regression Tree Widget
40
[11359]41Learner can be given a name under which it will appear in, say,
42:ref:`Test Learners`. The default name is "Regression Tree".
[11050]43
[11404]44If :obj:`Binarization` is checked, the values of multivalued attributes
[11359]45are split into two groups (based on the statistics in the particular node)
46to yield a binary tree. Binarization gets rid of the usual measures' bias
47towards attributes with more values and is generally recommended.
[11050]48
[11359]49The widget can be instructed to prune the tree during induction by setting
50:obj:`Do not split nodes with less instances than`. For pruning after
51induction, there is pruning with m-estimate of error.
[11050]52
[11359]53After changing one or more settings, you need to push :obj:`Apply`, which will
54put the new learner on the output and, if the training examples are given,
55construct a new classifier and output it as well.
[11050]56
57Examples
58--------
59
[11359]60There are two typical uses of this widget. First, you may want to induce
61the model and check what it looks like with the schema below.
[11050]62
63.. image:: images/RegressionTree-Schema.png
64
65The second schema checks the accuracy of the algorithm.
66
67.. image:: images/RegressionTree-Schema2.png
Note: See TracBrowser for help on using the repository browser.