#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(); }
if (baseTName == "saved") { baseTName = rdb->getSavedTaxonomy(); }
/************calculate the probablity that each word will be in a specific taxonomy*************/
- string tfileroot = baseTName.substr(0,baseTName.find_last_of(".")+1);
+ string tfileroot = m->getFullPathName(baseTName.substr(0,baseTName.find_last_of(".")+1));
string tempfileroot = m->getRootName(m->getSimpleName(baseName));
string phyloTreeName = tfileroot + "tree.train";
string phyloTreeSumName = tfileroot + "tree.sum";
}
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(); }
//initialze probabilities
wordGenusProb.resize(numKmers);
WordPairDiffArr.resize(numKmers);
- //cout << numKmers << '\t' << genusNodes.size() << endl;
+
for (int j = 0; j < wordGenusProb.size(); j++) { wordGenusProb[j].resize(genusNodes.size()); }
- //cout << numKmers << '\t' << genusNodes.size() << endl;
- ofstream out;
+ ofstream out;
ofstream out2;
#ifdef USE_MPI
#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++) {
if (m->control_pressed) { break; }
if (pid == 0) {
#endif
- out << i << '\t';
+ if (shortcuts) { out << i << '\t'; }
#ifdef USE_MPI
}
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
}
//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
if (pid == 0) {
#endif
- out << k << '\t' << wordGenusProb[i][k] << '\t' ;
+ if (shortcuts) { out << k << '\t' << wordGenusProb[i][k] << '\t' ; }
#ifdef USE_MPI
}
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
}
if (pid == 0) {
#endif
- out.close();
- out2.close();
-
+ if (shortcuts) {
+ out.close();
+ out2.close();
+ }
#ifdef USE_MPI
}
#endif
delete phyloTree;
phyloTree = new PhyloTree(phyloTreeTest, phyloTreeName);
-
+
//save probabilities
if (rdb->save) { rdb->wordGenusProb = wordGenusProb; rdb->WordPairDiffArr = WordPairDiffArr; }
}
/**************************************************************************************************/
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");
exit(1);
}
}
-/**************************************************************************************************/
+**************************************************************************************************/
void Bayesian::readProbFile(ifstream& in, ifstream& inNum, string inName, string inNumName) {
try{
istringstream iss (tempBuf,istringstream::in);
float probTemp;
iss >> zeroCountProb[i] >> numbers[i] >> probTemp;
- WordPairDiffArr[i].prob = tempProb;
+ WordPairDiffArr[i].prob = probTemp;
}