ID3 modular interface setup+ID3 API example added

examples/undocumented/python_modular/multiclass_id3classifiertree_modular.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+from numpy import array
+
+# create data
+train_data = array([[1.0, 2.0, 1.0, 3.0, 1.0, 3.0, 2.0, 2.0, 3.0, 1.0, 2.0, 2.0, 3.0, 1.0, 2.0],
+[2.0, 1.0, 2.0, 1.0, 2.0, 1.0, 1.0, 2.0, 2.0, 2.0, 1.0, 2.0, 2.0, 2.0, 1.0],
+[3.0, 2.0, 3.0, 3.0, 3.0, 2.0, 2.0, 1.0, 3.0, 1.0, 2.0, 1.0, 3.0, 1.0, 2.0],
+[1.0, 2.0, 1.0, 2.0, 1.0, 2.0, 1.0, 2.0, 2.0, 1.0, 1.0, 2.0, 2.0, 1.0, 1.0]])
+
+train_labels = array([1.0, 2.0, 1.0, 3.0, 1.0, 2.0, 2.0, 1.0, 3.0, 1.0, 2.0, 1.0, 3.0, 1.0, 2.0])
+
+test_data = array([[2.0, 2.0, 1.0, 3.0, 3.0],
+[2.0, 1.0, 2.0, 1.0, 2.0],
+[3.0, 2.0, 1.0, 3.0, 2.0],
+[1.0, 2.0, 1.0, 2.0, 1.0]])
+
+parameter_list = [[train_data, train_labels, test_data]]
+
+def multiclass_id3classifiertree_modular(train=train_data,labels=train_labels,test=test_data):	
+	try:
+		from modshogun import RealFeatures, MulticlassLabels, ID3ClassifierTree
+	except ImportError:
+		return
+
+	# wrap features and labels into Shogun objects
+	feats_train=RealFeatures(train)
+	feats_test=RealFeatures(test)
+	feats_labels=MulticlassLabels(labels)
+
+	# ID3 Tree formation
+	id3=ID3ClassifierTree()
+	id3.set_labels(feats_labels)
+	id3.train(feats_train)
+
+	# Classify test data
+	output=id3.apply_multiclass(feats_test).get_labels()
+
+	return id3,output
+
+if __name__=='__main__':
+	print('ID3ClassifierTree')
+	multiclass_id3classifiertree_modular(*parameter_list[0])

src/interfaces/modular/Multiclass.i

@@ -16,6 +16,7 @@
 %rename(RelaxedTreeNodeData) CRelaxedTreeNodeData;
 %rename(TreeMachineNode) CTreeMachineNode;
 %rename(VwConditionalProbabilityTree) VwConditionalProbabilityTree;
+%rename(ID3ClassifierTree) CID3ClassifierTree;
 
 %rename(RejectionStrategy) CRejectionStrategy;
 %rename(ThresholdRejectionStrategy) CThresholdRejectionStrategy;
@@ -70,10 +71,12 @@
 %include <shogun/multiclass/tree/TreeMachine.h>
 %include <shogun/multiclass/tree/RelaxedTreeNodeData.h>
 %include <shogun/multiclass/tree/ConditionalProbabilityTreeNodeData.h>
+%include <shogun/multiclass/tree/ID3TreeNodeData.h>
 namespace shogun
 {
     %template(TreeMachineWithConditionalProbabilityTreeNodeData) CTreeMachine<ConditionalProbabilityTreeNodeData>;
     %template(TreeMachineWithRelaxedTreeNodeData) CTreeMachine<RelaxedTreeNodeData>;
+    %template(TreeMachineWithID3TreeNodeData) CTreeMachine<id3TreeNodeData>;
 }
 
 %include <shogun/multiclass/tree/ConditionalProbabilityTree.h>
@@ -82,6 +85,7 @@ namespace shogun
 %include <shogun/multiclass/tree/RelaxedTree.h>
 %include <shogun/multiclass/tree/TreeMachineNode.h>
 %include <shogun/multiclass/tree/VwConditionalProbabilityTree.h>
+%include <shogun/multiclass/tree/ID3ClassifierTree.h>
 
 %include <shogun/multiclass/RejectionStrategy.h>
 %include <shogun/multiclass/MulticlassStrategy.h>

src/interfaces/modular/Multiclass_includes.i

@@ -9,6 +9,8 @@
  #include <shogun/multiclass/tree/RelaxedTreeUtil.h>
  #include <shogun/multiclass/tree/TreeMachineNode.h>
  #include <shogun/multiclass/tree/VwConditionalProbabilityTree.h>
+ #include <shogun/multiclass/tree/ID3TreeNodeData.h>
+ #include <shogun/multiclass/tree/ID3ClassifierTree.h>
 
  #include <shogun/multiclass/RejectionStrategy.h>
  #include <shogun/multiclass/MulticlassStrategy.h>

src/shogun/multiclass/tree/ID3ClassifierTree.h

@@ -44,25 +44,45 @@ namespace shogun
  * values using the ID3 algorithm. The training algorithm implemented is as follows :
  *
  * function ID3 (R: a set of non-categorical attributes,
+ *
  *		 C: the categorical attribute,
+ *
  *		 S: a training set) returns a decision tree;
+ *
  * begin
+ *
  *	If S consists of records all with the same value for 
+ *
  *	   the categorical attribute, 
+ *
  *	   return a single node with that value;
+ *
  *	If R is empty, then return a single node with as value
+ *
  *	   the most frequent of the values of the categorical attribute
+ *
  *	   that are found in records of S; [note that then there
+ *
  *	   will be errors, that is, records that will be improperly
+ *
  *	   classified];
+ *
  *	Let D be the attribute with largest Gain(D,S) 
+ *
  *	   among attributes in R;
+ *
  *	Let \f${d_j| j=1,2, .., m}\f$ be the values of attribute D;
+ *
  *	Let \f${S_j| j=1,2, .., m}\f$ be the subsets of S consisting 
+ *
  *	   respectively of records with value dj for attribute D;
+ *
  *	Return a tree with root labeled D and arcs labeled 
+ *
  *	  \f$d_1, d_2, .., d_m\f$ going respectively to the trees 
+ *
  *	ID3(R-{D}, C, \f$S_1\f$), .., ID3(R-{D}, C, \f$S_m\f$);
+ *
  * end ID3;
  *
  */