X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=bayesian.cpp;h=8278afb32e1d2c028a83ffdece17ed9910a78e20;hp=bccf0ce0dda18501c129b7604546f4e9fc43382b;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=5b72d1cf3fa48730e5bb70d59cced1e43e1fe424

diff --git a/bayesian.cpp b/bayesian.cpp
index bccf0ce..8278afb 100644
--- a/bayesian.cpp
+++ b/bayesian.cpp
@@ -64,7 +64,7 @@ Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
 			}
 			saveIn.close();			
 		}
-FilesGood = false;
+
 		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(); }
 			
@@ -143,9 +143,10 @@ FilesGood = false;
 					}
 				#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
@@ -162,12 +163,10 @@ FilesGood = false;
 					
 					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
 					}
 					
@@ -181,9 +180,9 @@ FilesGood = false;
 						//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
@@ -242,7 +241,9 @@ FilesGood = false;
 			}
 		}
 		
+        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; }
@@ -258,9 +259,8 @@ FilesGood = false;
 /**************************************************************************************************/
 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");
@@ -302,7 +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);
@@ -312,7 +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;	
 	}
@@ -378,6 +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
@@ -387,11 +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);
 		}