Merge pull request #927 from ajdapretnar/doc-links

Documentation converted from .md to .rst + internal links added.

doc/visual-programming/source/widgets/classify/classificationtree.rst

@@ -0,0 +1,76 @@
+Classification Tree
+===================
+
+.. figure:: icons/classification-tree.png
+
+Classification Tree
+
+Signals
+-------
+
+**Inputs**:
+
+-  **Data**
+
+Data set
+
+-  **Preprocessor**
+
+Preprocessed data.
+
+**Outputs**:
+
+-  **Learner**
+
+The classification tree learning algorithm with settings as specified in
+the dialog.
+
+-  **Classification Tree**
+
+Trained classifier (a subtype of Classifier). Signal *Classification
+Tree* sends data only if the learning data (signal **Classified Data**)
+is present.
+
+Description
+-----------
+
+.. figure:: images/ClassificationTree-stamped.png
+
+1. Learner can be given a name under which it will appear in other
+   widgets. The default name is “Classification Tree”.
+
+2. In *Feature selection* you can choose a measure for split selection:
+
+   -  `Entropy <http://www.saedsayad.com/decision_tree.htm>`__
+      (measure of homogeneity)
+   -  `Gini
+      index <https://en.wikipedia.org/wiki/Gini_coefficient>`__
+      (measure of dispersion)
+
+3. *Pruning* criteria:
+
+   -  **Minimal instances in leaves**; if checked, the algorithm will
+      never construct a split which would put less than the specified
+      number of training examples into any of the branches.
+   -  **Stop splitting nodes with less instances than** forbids the
+      algorithm to split the nodes with less than the given number of
+      instances.
+   -  **Limit the depth** of the classification tree.
+
+4. After changing the settings, you need to click *Apply*, which will
+   put the new learner in the output and, if the training examples are
+   given, construct a new classifier and output it as well.
+
+Examples
+--------
+
+There are two typical uses for this widget. First, you may want to
+induce the model and check what it looks like. You do it with the schema
+below; to learn more about it, see the documentation on
+:doc:`Classification Tree Viewer <\classificationtreeviewer>`.
+
+.. figure:: images/ClassificationTreeViewer-SimpleSchema.png
+
+The second schema checks the accuracy of the algorithm.
+
+.. figure:: images/ClassificationTreeViewer-Interaction.png

doc/visual-programming/source/widgets/classify/classificationtreeviewer.rst

@@ -0,0 +1,79 @@
+Classification Tree Viewer
+==========================
+
+.. figure:: icons/classification-tree-viewer.png
+
+Visualization of classification tree.
+
+Signals
+-------
+
+**Inputs**:
+
+-  **Classification Tree**
+
+Classification tree.
+
+**Outputs**:
+
+-  **Data**
+
+Data from the selected tree node.
+
+Description
+-----------
+
+This is a versatile widget with 2-D visualization of a `classification
+tree`_. The user can select a node, instructing the widget to output the
+data associated with the node thus enabling explorative data analysis.
+
+.. figure:: images/ClassificationTreeViewer-stamped.png
+
+1. Information on the input.
+
+2. Set the zoom and define the tree width. Nodes display information
+   bubble when hovering over them.
+
+3. Edges between nodes in the tree graph are drawn based on the selected
+   edge width.
+
+   -  All the edges will be of equal width if *Fixed* is chosen.
+   -  When *Relative to root* is selected, the width of the edge will
+      correspond to the proportion of instances in the corresponding
+      node with respect to all the instances in the training data. Under
+      this selection the edge will get thinner and thinner when
+      traversing toward the bottom of the tree.
+   -  *Relative to parent* makes the edge width correspond to proportion
+      of instances in the nodes with respect to the instances in their
+      parent node.
+
+4. Nodes box defines the target class, which you can change based on
+   classes in the data. You can also set the color scheme in *Set
+   Colors*.
+
+5. Press *Save Graph* to save the classification tree graph as a file.
+
+Examples
+--------
+
+Below is a simple schema where we have read the data, constructed the
+classification tree and viewed it in our tree viewer. If both the viewer
+and :doc:`Classification Tree<../classify/classificationtree>` are open, any run of tree induction
+algorithm will immediately affect the visualization. You can thus use
+this combination to explore how parameters of the induction algorithm
+influence the structure of the resulting tree.
+
+.. figure:: images/ClassificationTreeViewer-SimpleSchema.png
+
+Clicking on any node will output the related data instances. This is
+explored in the schema below that shows the subset in the data table and
+in the :doc:`Scatterplot<../visualize/scatterplot>`. Make sure that the tree data is
+passed as a data subset; this can be done by connecting the
+:doc:`Scatterplot<../visualize/scatterplot>` to the :doc:`File<../data/file>` widget first, and connecting it to the
+**Tree Viewer** widget next.
+
+.. figure:: images/ClassificationTreeViewer-Interaction.png
+
+
+.. _classification tree: https://en.wikipedia.org/wiki/Decision_tree_learning
+.. _scatterplot: /widgets/visualize/scatterplot.html