X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=abstractrandomforest.hpp;fp=abstractrandomforest.hpp;h=3be91b9b9b47a8f04ffbb30ff31d4448549f3d50;hb=035f86272c776e1cccaa47021e26782e49cd41e7;hp=0000000000000000000000000000000000000000;hpb=96dbe925073caefaed6e6db85659c144a806aeb1;p=mothur.git

diff --git a/abstractrandomforest.hpp b/abstractrandomforest.hpp
new file mode 100755
index 0000000..3be91b9
--- /dev/null
+++ b/abstractrandomforest.hpp
@@ -0,0 +1,67 @@
+//
+//  abstractrandomforest.hpp
+//  rrf-fs-prototype
+//
+//  Created by Abu Zaher Faridee on 7/20/12.
+//  Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+#ifndef rrf_fs_prototype_abstractrandomforest_hpp
+#define rrf_fs_prototype_abstractrandomforest_hpp
+
+#include "mothurout.h"
+#include "macros.h"
+#include "abstractdecisiontree.hpp"
+
+#define DEBUG_MODE
+
+/***********************************************************************/
+
+class AbstractRandomForest{
+public:
+    // intialization with vectors
+    AbstractRandomForest(const std::vector < std::vector<int> > dataSet, 
+                       const int numDecisionTrees, 
+                       const string);
+    virtual ~AbstractRandomForest(){ }
+    virtual int populateDecisionTrees() = 0;
+    virtual int calcForrestErrorRate() = 0;
+    virtual int calcForrestVariableImportance(string) = 0;
+ 
+/***********************************************************************/
+  
+protected:
+  
+    // TODO: create a better way of discarding feature
+    // currently we just set FEATURE_DISCARD_SD_THRESHOLD to 0 to solved this
+    // it can be tuned for better selection
+    // also, there might be other factors like Mean or other stuffs
+    // same would apply for createLocalDiscardedFeatureList in the TreeNode class
+  
+    // TODO: Another idea is getting an aggregated discarded feature indices after the run, from combining
+    // the local discarded feature indices
+    // this would penalize a feature, even if in global space the feature looks quite good
+    // the penalization would be averaged, so this woould unlikely to create a local optmina
+    
+    vector<int> getGlobalDiscardedFeatureIndices();
+    
+    int numDecisionTrees;
+    int numSamples;
+    int numFeatures;
+    vector< vector<int> > dataSet;
+    vector<int> globalDiscardedFeatureIndices;
+    vector<double> globalVariableImportanceList;
+    string treeSplitCriterion;
+    // This is a map of each feature to outcome count of each classes
+    // e.g. 1 => [2 7] means feature 1 has 2 outcome of 0 and 7 outcome of 1
+    map<int, vector<int> > globalOutOfBagEstimates;
+    
+    // TODO: fix this, do we use pointers?
+    vector<AbstractDecisionTree*> decisionTrees;
+    
+    MothurOut* m;
+  
+private:
+
+};
+#endif