X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=abstractrandomforest.cpp;fp=abstractrandomforest.cpp;h=ae60b773742c25e0af85f811167003641e4646a4;hb=035f86272c776e1cccaa47021e26782e49cd41e7;hp=0000000000000000000000000000000000000000;hpb=96dbe925073caefaed6e6db85659c144a806aeb1;p=mothur.git

diff --git a/abstractrandomforest.cpp b/abstractrandomforest.cpp
new file mode 100644
index 0000000..ae60b77
--- /dev/null
+++ b/abstractrandomforest.cpp
@@ -0,0 +1,58 @@
+//
+//  abstractrandomforest.cpp
+//  Mothur
+//
+//  Created by Sarah Westcott on 10/1/12.
+//  Copyright (c) 2012 Schloss Lab. All rights reserved.
+//
+
+#include "abstractrandomforest.hpp"
+
+/***********************************************************************/
+AbstractRandomForest::AbstractRandomForest(const std::vector < std::vector<int> > dataSet, 
+                     const int numDecisionTrees, 
+                     const string treeSplitCriterion = "informationGain")
+: dataSet(dataSet), 
+numDecisionTrees(numDecisionTrees),
+numSamples((int)dataSet.size()),
+numFeatures((int)(dataSet[0].size() - 1)),
+globalDiscardedFeatureIndices(getGlobalDiscardedFeatureIndices()),
+globalVariableImportanceList(numFeatures, 0),
+treeSplitCriterion(treeSplitCriterion) {
+    m = MothurOut::getInstance();
+    // TODO: double check if the implemenatation of 'globalOutOfBagEstimates' is correct
+}
+
+/***********************************************************************/
+
+vector<int> AbstractRandomForest::getGlobalDiscardedFeatureIndices() {
+    try {
+        vector<int> globalDiscardedFeatureIndices;
+        
+        // calculate feature vectors
+        vector< vector<int> > featureVectors(numFeatures, vector<int>(numSamples, 0));
+        for (int i = 0; i < numSamples; i++) {
+            if (m->control_pressed) { return globalDiscardedFeatureIndices; }
+            for (int j = 0; j < numFeatures; j++) { featureVectors[j][i] = dataSet[i][j]; }
+        }
+        
+        for (int i = 0; i < featureVectors.size(); i++) {
+            if (m->control_pressed) { return globalDiscardedFeatureIndices; }
+            double standardDeviation = m->getStandardDeviation(featureVectors[i]);
+            if (standardDeviation <= 0){ globalDiscardedFeatureIndices.push_back(i); }
+        }
+        
+        if (m->debug) {
+            m->mothurOut("number of global discarded features:  " + toString(globalDiscardedFeatureIndices.size())+ "\n");
+            m->mothurOut("total features: " + toString(featureVectors.size())+ "\n");
+        }
+        
+        return globalDiscardedFeatureIndices;
+    }
+	catch(exception& e) {
+		m->errorOut(e, "AbstractRandomForest", "getGlobalDiscardedFeatureIndices");
+		exit(1);
+	} 
+}
+
+/***********************************************************************/
\ No newline at end of file