source: orange/docs/widgets/rst/unsupervized/attributedistance.rst @ 11359:8d54e79aa135

Revision 11359:8d54e79aa135, 1.9 KB checked in by Ales Erjavec <ales.erjavec@…>, 14 months ago (diff)

Cleanup of 'Widget catalog' documentation.

Fixed rst text formating, replaced dead hardcoded reference links (now using
:ref:), etc.

Line 
1.. _Attribute Distance:
2
3Attribute Distance
4==================
5
6.. image:: ../icons/AttributeDistance.png
7
8Computes distances between examples in the data set
9
10Signals
11-------
12
13Inputs:
14   - Examples
15      A list of examples
16
17
18Outputs:
19   - Distance Matrix
20      A matrix of attribute distances
21
22
23Description
24-----------
25
26Widget Attribute Distances computes the distances between the attributes in
27the data sets. Don't confuse it with a similar widget for computing the
28distances between examples.
29
30.. image:: images/AttributeDistance.png
31   :alt: Association Rules Widget
32
33Since the widget cannot compute distances between discrete and continuous
34attributes, all attributes are first either discretized, by splitting the
35attribute into four quartiles, or "continuized" by treating any discrete
36attributes as ordinal with values equivalent to 0, 1, 2, 3... For other,
37possibly better methods of discretization/continuization, see widgets
38:ref:`Discretize` and :ref:`Continuize`.
39
40The two kinds of attributes then have different measures of distance.
41
42For discrete attributes, the distance can be computed as
43:obj:`Pearson's chi-square`, where the more the two attributes are dependent,
44the closer they are. The measure actually returns the p-value of the common
45chi-square test of independence. The other two measures are as defined by
46Aleks Jakulin in his work on `attribute interactions
47<http://stat.columbia.edu/~jakulin/Int/>`_: :obj:`2-way interaction` is
48defined as I(A;B)/H(A,B) and :obj:`3-way interaction` is I(A;B;C),
49respectively.
50
51
52Examples
53--------
54
55This widget is an intermediate widget: it shows no user readable results and
56its output needs to be fed to a widget that can do something useful with the
57computed distances, for instance the :ref:`Distance Map`,
58:ref:`Hierarchical Clustering` to cluster the attributes, or :ref:`MDS` to
59visualize the distances between them.
60
61.. image:: images/AttributeDistance-Schema.png
62   :alt: Association Rules
Note: See TracBrowser for help on using the repository browser.