changes while testing

[mothur.git] / bayesian.cpp

diff --git a/bayesian.cpp b/bayesian.cpp
index 1dc38337aef1bcc3b695ff56e86061cdab58c13d..8278afb32e1d2c028a83ffdece17ed9910a78e20 100644 (file)
--- a/bayesian.cpp
+++ b/bayesian.cpp
@@ -12,13 +12,14 @@
 #include "phylosummary.h"
 #include "referencedb.h"
 /**************************************************************************************************/
-Bayesian::Bayesian(string tfile, string tempFile, string method, int ksize, int cutoff, int i, int tid, bool f) : 
+Bayesian::Bayesian(string tfile, string tempFile, string method, int ksize, int cutoff, int i, int tid, bool f, bool sh) : 
 Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
        try {
                ReferenceDB* rdb = ReferenceDB::getInstance();
                
                threadID = tid;
                flip = f;
+        shortcuts = sh;
                string baseName = tempFile;
                        
                if (baseName == "saved") { baseName = rdb->getSavedReference(); }
@@ -63,7 +64,7 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                        }
                        saveIn.close();                 
                }
-               
+
                if(probFileTest && probFileTest2 && phyloTreeTest && probFileTest3 && FilesGood){       
                        if (tempFile == "saved") { m->mothurOutEndLine();  m->mothurOut("Using sequences from " + rdb->getSavedReference() + " that are saved in memory.");     m->mothurOutEndLine(); }
                        
@@ -113,7 +114,7 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                WordPairDiffArr.resize(numKmers);
                        
                                for (int j = 0; j < wordGenusProb.size(); j++) {        wordGenusProb[j].resize(genusNodes.size());             }
-                    ofstream out;
+                ofstream out;
                                ofstream out2;
                                
                                #ifdef USE_MPI
@@ -124,25 +125,28 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                #endif
 
                                
-                               m->openOutputFile(probFileName, out);
+                if (shortcuts) { 
+                    m->openOutputFile(probFileName, out); 
                                
-                               //output mothur version
-                               out << "#" << m->getVersion() << endl;
+                    //output mothur version
+                    out << "#" << m->getVersion() << endl;
                                
-                               out << numKmers << endl;
+                    out << numKmers << endl;
                                
-                               m->openOutputFile(probFileName2, out2);
+                    m->openOutputFile(probFileName2, out2);
                                
-                               //output mothur version
-                               out2 << "#" << m->getVersion() << endl;
+                    //output mothur version
+                    out2 << "#" << m->getVersion() << endl;
+                }
                                
                                #ifdef USE_MPI
                                        }
                                #endif
 
-                               
                                //for each word
                                for (int i = 0; i < numKmers; i++) {
+                    //m->mothurOut("[DEBUG]: kmer = " + toString(i) + "\n");
+                    
                                        if (m->control_pressed) {  break; }
                                        
                                        #ifdef USE_MPI
@@ -151,7 +155,7 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                                if (pid == 0) {  
                                        #endif
 
-                                       out << i << '\t';
+                    if (shortcuts) {  out << i << '\t'; }
                                        
                                        #ifdef USE_MPI
                                                }
@@ -159,12 +163,10 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                        
                                        vector<int> seqsWithWordi = database->getSequencesWithKmer(i);
                                        
-                                       map<int, int> count;
-                                       for (int k = 0; k < genusNodes.size(); k++) {  count[genusNodes[k]] = 0;  }                     
-                                                       
                                        //for each sequence with that word
+                    vector<int> count; count.resize(genusNodes.size(), 0);
                                        for (int j = 0; j < seqsWithWordi.size(); j++) {
-                                               int temp = phyloTree->getIndex(names[seqsWithWordi[j]]);
+                                               int temp = phyloTree->getGenusIndex(names[seqsWithWordi[j]]);
                                                count[temp]++;  //increment count of seq in this genus who have this word
                                        }
                                        
@@ -178,9 +180,9 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                                //probabilityInThisTaxonomy = (# of seqs with that word in this taxonomy + probabilityInTemplate) / (total number of seqs in this taxonomy + 1);
                                                
                                                
-                                               wordGenusProb[i][k] = log((count[genusNodes[k]] + probabilityInTemplate) / (float) (genusTotals[k] + 1));  
+                                               wordGenusProb[i][k] = log((count[k] + probabilityInTemplate) / (float) (genusTotals[k] + 1));  
                                                                        
-                                               if (count[genusNodes[k]] != 0) { 
+                                               if (count[k] != 0) { 
                                                        #ifdef USE_MPI
                                                                int pid;
                                                                MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
@@ -188,7 +190,7 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                                                if (pid == 0) {  
                                                        #endif
 
-                                                       out << k << '\t' << wordGenusProb[i][k] << '\t' ; 
+                            if (shortcuts) { out << k << '\t' << wordGenusProb[i][k] << '\t' ; }
                                                        
                                                        #ifdef USE_MPI
                                                                }
@@ -204,8 +206,10 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                                if (pid == 0) {  
                                        #endif
                                        
-                                       out << endl;
-                                       out2 << probabilityInTemplate << '\t' << numNotZero << '\t' << log(probabilityInTemplate) << endl;
+                            if (shortcuts) { 
+                                out << endl;
+                                out2 << probabilityInTemplate << '\t' << numNotZero << '\t' << log(probabilityInTemplate) << endl;
+                            }
                                        
                                        #ifdef USE_MPI
                                                }
@@ -218,9 +222,10 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                                        if (pid == 0) {  
                                #endif
                                
-                               out.close();
-                               out2.close();
-                               
+                        if (shortcuts) { 
+                            out.close();
+                            out2.close();
+                        }
                                #ifdef USE_MPI
                                        }
                                #endif
@@ -236,7 +241,9 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
                        }
                }
                
+        if (m->debug) { m->mothurOut("[DEBUG]: about to generateWordPairDiffArr\n"); }
                generateWordPairDiffArr();
+        if (m->debug) { m->mothurOut("[DEBUG]: done generateWordPairDiffArr\n"); }
                
                //save probabilities
                if (rdb->save) { rdb->wordGenusProb = wordGenusProb; rdb->WordPairDiffArr = WordPairDiffArr; }
@@ -252,9 +259,8 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
 /**************************************************************************************************/
 Bayesian::~Bayesian() {
        try {
-               
-                delete phyloTree; 
-                if (database != NULL) {  delete database; }
+        if (phyloTree != NULL) { delete phyloTree; }
+        if (database != NULL) {  delete database; }
        }
        catch(exception& e) {
                m->errorOut(e, "Bayesian", "~Bayesian");
@@ -296,7 +302,7 @@ string Bayesian::getTaxonomy(Sequence* seq) {
                        }  
                }
                
-               if (queryKmers.size() == 0) {  m->mothurOut(seq->getName() + "is bad."); m->mothurOutEndLine(); simpleTax = "unknown;";  return "unknown;"; }
+               if (queryKmers.size() == 0) {  m->mothurOut(seq->getName() + " is bad. It has no kmers of length " + toString(kmerSize) + "."); m->mothurOutEndLine(); simpleTax = "unknown;";  return "unknown;"; }
                
                
                int index = getMostProbableTaxonomy(queryKmers);
@@ -306,7 +312,11 @@ string Bayesian::getTaxonomy(Sequence* seq) {
                //bootstrap - to set confidenceScore
                int numToSelect = queryKmers.size() / 8;
        
+        if (m->debug) {  m->mothurOut(seq->getName() + "\t"); }
+        
                tax = bootstrapResults(queryKmers, index, numToSelect);
+        
+        if (m->debug) {  m->mothurOut("\n"); }
                
                return tax;     
        }
@@ -372,6 +382,7 @@ string Bayesian::bootstrapResults(vector<int> kmers, int tax, int numToSelect) {
                int seqTaxIndex = tax;
                TaxNode seqTax = phyloTree->get(tax);
                
+        
                while (seqTax.level != 0) { //while you are not at the root
                                        
                                itBoot2 = confidenceScores.find(seqTaxIndex); //is this a classification we already have a count on
@@ -381,11 +392,13 @@ string Bayesian::bootstrapResults(vector<int> kmers, int tax, int numToSelect) {
                                        confidence = itBoot2->second;
                                }
                                
+                if (m->debug) { m->mothurOut(seqTax.name + "(" + toString(((confidence/(float)iters) * 100)) + ");"); }
+            
                                if (((confidence/(float)iters) * 100) >= confidenceThreshold) {
                                        confidenceTax = seqTax.name + "(" + toString(((confidence/(float)iters) * 100)) + ");" + confidenceTax;
                                        simpleTax = seqTax.name + ";" + simpleTax;
                                }
-                               
+            
                                seqTaxIndex = seqTax.parent;
                                seqTax = phyloTree->get(seqTax.parent);
                }