SHOGUN  4.2.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
ID3ClassifierTree.h
Go to the documentation of this file.
1 /*
2  * Copyright (c) The Shogun Machine Learning Toolbox
3  * Written (w) 2014 Parijat Mazumdar
4  * All rights reserved.
5  *
6  * Redistribution and use in source and binary forms, with or without
7  * modification, are permitted provided that the following conditions are met:
8  *
9  * 1. Redistributions of source code must retain the above copyright notice, this
10  * list of conditions and the following disclaimer.
11  * 2. Redistributions in binary form must reproduce the above copyright notice,
12  * this list of conditions and the following disclaimer in the documentation
13  * and/or other materials provided with the distribution.
14  *
15  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
16  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
17  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
18  * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
19  * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
21  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
22  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25  *
26  * The views and conclusions contained in the software and documentation are those
27  * of the authors and should not be interpreted as representing official policies,
28  * either expressed or implied, of the Shogun Development Team.
29  */
30 
31 
32 #ifndef _ID3CLASSIFIERTREE_H__
33 #define _ID3CLASSIFIERTREE_H__
34 
35 #include <shogun/lib/config.h>
36 
41 
42 namespace shogun
43 {
44 
74 class CID3ClassifierTree : public CTreeMachine<id3TreeNodeData>
75 {
76 public:
79 
81  virtual ~CID3ClassifierTree();
82 
86  virtual const char* get_name() const { return "ID3ClassifierTree"; }
87 
91  virtual CMulticlassLabels* apply_multiclass(CFeatures* data=NULL);
92 
113  bool prune_tree(CDenseFeatures<float64_t>* validation_data, CMulticlassLabels* validation_labels, float64_t epsilon=0.f);
114 
115 protected:
116 
120  virtual bool train_machine(CFeatures* data=NULL);
121 
122 private:
123 
132  node_t* id3train(CFeatures* data, CMulticlassLabels* class_labels, SGVector<int32_t> values, int level = 0);
133 
141  float64_t informational_gain_attribute(int32_t attr_no, CFeatures* data, CMulticlassLabels* class_labels);
142 
148  float64_t entropy(CMulticlassLabels* labels);
149 
157  void prune_tree_machine(CDenseFeatures<float64_t>* feats, CMulticlassLabels* gnd_truth, node_t* current, float64_t epsilon);
158 
165  CMulticlassLabels* apply_multiclass_from_current_node(CDenseFeatures<float64_t>* feats, node_t* current);
166 };
167 } /* namespace shogun */
168 
169 #endif /* _ID3CLASSIFIERTREE_H__ */
CTreeMachineNode< id3TreeNodeData > node_t
Definition: TreeMachine.h:52
virtual const char * get_name() const
Multiclass Labels for multi-class classification.
double float64_t
Definition: common.h:50
all of classes and functions are contained in the shogun namespace
Definition: class_list.h:18
class ID3ClassifierTree, implements classifier tree for discrete feature values using the ID3 algorit...
virtual bool train_machine(CFeatures *data=NULL)
The class Features is the base class of all feature objects.
Definition: Features.h:68
class TreeMachine, a base class for tree based multiclass classifiers. This class is derived from CBa...
Definition: TreeMachine.h:48
bool prune_tree(CDenseFeatures< float64_t > *validation_data, CMulticlassLabels *validation_labels, float64_t epsilon=0.f)
virtual CMulticlassLabels * apply_multiclass(CFeatures *data=NULL)

SHOGUN Machine Learning Toolbox - Documentation