Blaz Zupan avatar Blaz Zupan committed 7d7ee77

Updated documentation for Rank widget.

Comments (0)

Files changed (10)

Add a comment to this file

docs/widgets/rst/data/images/Rank-ITree.png

Removed
Old image
Add a comment to this file

docs/widgets/rst/data/images/Rank-Select-Schema.png

Added
New image
Add a comment to this file

docs/widgets/rst/data/images/Rank-Select-Widgets.png

Added
New image
Add a comment to this file

docs/widgets/rst/data/images/Rank-Tree.png

Removed
Old image
Add a comment to this file

docs/widgets/rst/data/images/Rank-after-file-Schema.png

Removed
Old image
Add a comment to this file

docs/widgets/rst/data/images/Rank-and-Test.png

Added
New image
Add a comment to this file

docs/widgets/rst/data/images/Rank-stamped.png

Added
New image

docs/widgets/rst/data/images/Rank-tags.txt

+0	430	388
+1	229	109
+2	229	275
+3	117	363
+4	117	419
+5	117	523
+6	229	655
Add a comment to this file

docs/widgets/rst/data/images/Rank.png

Old
Old image
New
New image

docs/widgets/rst/data/rank.rst

 
 .. image:: ../../../../Orange/OrangeWidgets/Data/icons/Rank.svg
 
-A widget for ranking the attributes and selecting attribute subsets.
+Ranking of attributes in classification or regression data sets.
 
 Signals
 -------
 
 Inputs:
 
-
-   - Examples (ExampleTable)
+   - Data
       Input data set.
 
-
 Outputs:
 
-
-   - Reduced Example Table (ExampleTable)
-      Data set which include described by selected attributes.
-
-   - ExampleTable Attributes (ExampleTable)
-      Data set in where each example corresponds to an attribute from the
-      original set, and the attributes correspond one of the selected
-      attribute evaluation measures.
-
+   - Reduced Data
+      Data set which selected attributes.
 
 Description
 -----------
 
-This widget computes a set of measures for evaluating the quality/usefulness
-of attributes: ReliefF, information gain, gain ratio and gini index.
-Besides providing this information, it also allows user to select a subset
-of attributes or it can automatically select the specified number of
-best-ranked attributes.
+Rank widget considers class-labeled data sets (classification or regression)
+and scores the attributes according to their correlation with the
+class.
 
-.. image:: images/Rank.png
+.. image:: images/Rank-stamped.png
 
-The right-hand side of the widget presents the computed quality of the
-attributes. The first line shows the attribute name and the second the
-number of its values (or a "C", if the attribute is continuous. Remaining
-columns show different measures of quality.
+1. Attributes (rows) and their scores by different scoring methods
+   (columns).
+#. Scoring techniques and their (optional) parameters.
+#. For scoring techniques that require discrete attributes this is the number
+   of intervals to which continues attributes will be discretized to.
+#. Number of decimals used in reporting the score.
+#. Toggles the bar-based visualisation of the feature scores.
+#. Adds a score table to the current report.
 
-The user is able to select the measures (s)he wants computed and presented.
-:obj:`ReliefF` requires setting two arguments: the number of :obj:`Neighbours`
-taken into account and the number of randomly chosen reference :obj:`Examples`.
-The former should be higher if there is a lot of noise; the latter generally
-makes the computation less reliable if set too low, while higher values
-make it slow.
+Example: Attribute Ranking and Selection
+----------------------------------------
 
-The order in which the attributes are presented can be set either in the
-list below the measures or by clicking the table's column headers. Attributes
-can also be sorted by a measure not printed in the table.
+Below we have used immediately after the :ref:`File`
+widget to reduce the set of data attribute and include only the most
+informative one:
 
-Measures that cannot handle continuous attributes (impurity
-measures - information gain, gain ratio and gini index) are run on
-discretized attributes. For sake of simplicity we always split the
-continuous attributes in intervals with (approximately) equal number of
-examples, but the user can set the number of :obj:`Intervals`.
+.. image:: images/Rank-Select-Schema.png
 
-It is also possible to set the number of decimals
-(:obj:`No. of decimals`) in the print out. Using a number to high may
-exaggerate the accuracy of the computation; many decimals may only be
-useful when the computed numbers are really small.
+Notice how the widget outputs a data set that includes only the best-scored
+attributes:
 
-The widget outputs two example tables. The one, whose corresponding signal
-is named :obj:`ExampleTable Attributes` looks pretty much like the one
-shown in the Rank widget, except that the second column is split into two
-columns, one giving the attribute type (D for discrete and C for continuous),
-and the other giving the number of distinct values if the attribute is
-discrete and undefined if it's continuous.
+.. image:: images/Rank-Select-Widgets.png
 
-The second, more interesting table has the same examples as the original,
-but with a subset of the attributes. To select/unselect attributes, click
-the corresponding rows in the table. This way, the widget can be used for
-manual selection of attributes. Something similar can also be done with
-a :ref:`Select Attributes` widget, except that the Rank widget can be used
-for selecting the attributes according to their quality, while Select
-Attributes offers more in terms of changing the order of attributes,
-picking another class attribute and similar.
+Example: Feature Subset Selection for Machine Learning
+------------------------------------------------------
 
-The widget can also be used to automatically select a feature subset.
-If :obj:`Best ranked` is selected in box :obj:`Select Attributes`, the
-widget will output a data set where examples are described by the
-specified number of best ranked attributes. The data set is changed
-whenever the order of attributes is changed for any reason (different
-measure is selected for sorting, ReliefF or discretization settings are
-changed...)
+Following is a bit more complicated example. In the workflow below we
+first split the data into training and test set. In the upper branch
+the training data passes through the Rank widget to select the most
+informative attributes, while in the lower branch there is no feature
+selection. Both feature selected and original data sets are passed to
+its own :ref:`Test Learners` widget, which develops a
+:ref:`Naive Bayes <Naive Bayes>` classifier and scores it on a test set.
 
-The first two options in :obj:`Select Attributes` box can be used to
-clear the selection (:obj:`None`) or to select all attributes (:obj:`All`).
+.. image:: images/Rank-and-Test.png
 
-Button :obj:`Commit` sends the data set with the selected attributes.
-If :obj:`Commit automatically` is set, the data set is committed on any change.
-
-
-Examples
---------
-
-On typical use of the widget is to put it immediately after the :ref:`File`
-widget to reduce the attribute set. The snapshot below shows this as a part of
-a bit more complicated schema.
-
-.. image:: images/Rank-after-file-Schema.png
-
-The examples in the file are put through ref:`Data Sampler` which split the
-data set into two subsets: one, containing 70% of examples (signal
-:obj:`Classified Examples`) will be used for training a
-:ref:`Naive Bayes <Naive Bayes>` classifier, and the other 30% (signal
-:obj:`Remaining Classified Examples`) for testing. Attribute subset selection
-based on information gain was performed on the training set only, and five most
-informative attributes were selected for learning. A data set with all other
-attributes removed (signal :obj:`Reduced Example Table`) is fed into
-:ref:`Test Learners`. Test Learners widgets also gets the
-:obj:`Remaining Classified Examples` to use them as test examples (don't
-forget to set :obj:`Test on Test Data` in that widget!).
-
-To verify how the subset selection affects the classifier's performance, we
-added another :ref:`Test Learners`, but connected it to the
-:ref:`Data Sampler` so that the two subsets emitted by the latter are used
-for training and testing without any feature subset selection.
-
-Running this schema on the heart disease data set shows quite a considerable
-improvements in all respects on the reduced attribute subset.
-
-In another, way simpler example, we connected a
-:ref:`Classification Tree Viewer` to the Rank widget to observe different
-attribute quality measures at different nodes. This can give us some picture
-about how important is the selection of measure in tree construction: the more
-the measures agree about attribute ranking, the less crucial is the measure
-selection.
-
-.. image:: images/Rank-Tree.png
-
-A variation of the above is using the Rank widget after the
-:ref:`Interactive Tree Builder`: the sorted attributes may help us in deciding
-the attribute to use at a certain node.
-
-.. image:: images/Rank-ITree.png
+For data sets with many features and naive Bayesian classifier feature
+selection, as shown above, would often yield a better predictive accuracy.
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.