File: abstractrandomforest.cpp

package info (click to toggle)
mothur 1.33.3%2Bdfsg-2
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 11,248 kB
  • ctags: 12,231
  • sloc: cpp: 152,046; fortran: 665; makefile: 74; sh: 34
file content (59 lines) | stat: -rw-r--r-- 2,288 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
//
//  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);
	} 
}

/***********************************************************************/