X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=sharedrabundvector.cpp;h=3901650cef965dc7a3c0126ecb54a8fb425e434d;hp=94a65191eabe4a286481c3829f31a1ba0ed02c00;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=74c78f9abd9e733f0c2f812efec97a76632fcbf8 diff --git a/sharedrabundvector.cpp b/sharedrabundvector.cpp index 94a6519..3901650 100644 --- a/sharedrabundvector.cpp +++ b/sharedrabundvector.cpp @@ -14,8 +14,13 @@ /***********************************************************************/ +SharedRAbundVector::SharedRAbundVector() : DataVector(), maxRank(0), numBins(0), numSeqs(0) {} +/***********************************************************************/ + +SharedRAbundVector::~SharedRAbundVector() { + //for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } -SharedRAbundVector::SharedRAbundVector() : DataVector(), maxRank(0), numBins(0), numSeqs(0) {} +} /***********************************************************************/ @@ -44,34 +49,82 @@ SharedRAbundVector::SharedRAbundVector(string id, vector rav) : Data } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function SharedRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function SharedRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "SharedRAbundVector"); exit(1); } } -/***********************************************************************/ +***********************************************************************/ //reads a shared file SharedRAbundVector::SharedRAbundVector(ifstream& f) : DataVector(), maxRank(0), numBins(0), numSeqs(0) { try { - globaldata = GlobalData::getInstance(); - - if (globaldata->gGroupmap == NULL) { groupmap = new GroupMap(); } + m->clearAllGroups(); + vector allGroups; - int num, inputData, pos, count; + int num, inputData, count; count = 0; string holdLabel, nextLabel, groupN; individual newguy; - for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } - lookup.clear(); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; } lookup.clear(); + + //are we at the beginning of the file?? + if (m->saveNextLabel == "") { + f >> label; + + //is this a shared file that has headers + if (label == "label") { + //gets "group" + f >> label; m->gobble(f); + + //gets "numOtus" + f >> label; m->gobble(f); + + //eat rest of line + label = m->getline(f); m->gobble(f); + + //parse labels to save + istringstream iStringStream(label); + m->binLabelsInFile.clear(); + while(!iStringStream.eof()){ + if (m->control_pressed) { break; } + string temp; + iStringStream >> temp; m->gobble(iStringStream); + + m->binLabelsInFile.push_back(temp); + } + + f >> label >> groupN >> num; + }else { + //read in first row since you know there is at least 1 group. + f >> groupN >> num; + + //make binlabels because we don't have any + string snumBins = toString(num); + m->binLabelsInFile.clear(); + for (int i = 0; i < num; i++) { + //if there is a bin label use it otherwise make one + string binLabel = "Otu"; + string sbinNumber = toString(i+1); + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + m->binLabelsInFile.push_back(binLabel); + } + } + }else { + label = m->saveNextLabel; + + //read in first row since you know there is at least 1 group. + f >> groupN >> num; + } + + //reset labels, currentLabels may have gotten changed as otus were eliminated because of group choices or sampling + m->currentBinLabels = m->binLabelsInFile; - //read in first row since you know there is at least 1 group. - f >> label >> groupN >> num; holdLabel = label; //add new vector to lookup @@ -80,39 +133,28 @@ SharedRAbundVector::SharedRAbundVector(ifstream& f) : DataVector(), maxRank(0), lookup[0]->setLabel(label); lookup[0]->setGroup(groupN); - if (globaldata->gGroupmap == NULL) { - //save group in groupmap - groupmap->namesOfGroups.push_back(groupN); - groupmap->groupIndex[groupN] = 0; - } + allGroups.push_back(groupN); //fill vector. data = first sharedrabund in file for(int i=0;i> inputData; - lookup[0]->push_back(inputData, i, groupN); //abundance, bin, group - push_back(inputData, i, groupN); - numSeqs += inputData; - numBins++; - if (inputData > maxRank) { maxRank = inputData; } + lookup[0]->push_back(inputData, groupN); //abundance, bin, group + push_back(inputData, groupN); + if (inputData > maxRank) { maxRank = inputData; } } - //save position in file in case next line is a new label. - pos = f.tellg(); - - if (f.eof() != true) { f >> nextLabel; } + m->gobble(f); + if (!(f.eof())) { f >> nextLabel; } + //read the rest of the groups info in while ((nextLabel == holdLabel) && (f.eof() != true)) { f >> groupN >> num; count++; - if (globaldata->gGroupmap == NULL) { - //save group in groupmap - groupmap->namesOfGroups.push_back(groupN); - groupmap->groupIndex[groupN] = count; - } + allGroups.push_back(groupN); //add new vector to lookup temp = new SharedRAbundVector(); @@ -123,27 +165,19 @@ SharedRAbundVector::SharedRAbundVector(ifstream& f) : DataVector(), maxRank(0), //fill vector. for(int i=0;i> inputData; - lookup[count]->push_back(inputData, i, groupN); //abundance, bin, group + + lookup[count]->push_back(inputData, groupN); //abundance, bin, group } - //save position in file in case next line is a new label. - pos = f.tellg(); - + m->gobble(f); + if (f.eof() != true) { f >> nextLabel; } } - - //put file pointer back since you are now at a new distance label - f.seekg(pos, ios::beg); - - if (globaldata->gGroupmap == NULL) { globaldata->gGroupmap = groupmap; } - + m->saveNextLabel = nextLabel; + m->setAllGroups(allGroups); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function SharedRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function SharedRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "SharedRAbundVector"); exit(1); } } @@ -161,11 +195,7 @@ void SharedRAbundVector::set(int binNumber, int newBinSize, string groupname){ numSeqs += (newBinSize - oldBinSize); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function set. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function set. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "set"); exit(1); } } @@ -209,12 +239,22 @@ vector SharedRAbundVector::getData(){ } /***********************************************************************/ -void SharedRAbundVector::push_back(int binSize, int otu, string groupName){ +void SharedRAbundVector::clear(){ + numBins = 0; + maxRank = 0; + numSeqs = 0; + data.clear(); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; } + lookup.clear(); +} +/***********************************************************************/ + +void SharedRAbundVector::push_back(int binSize, string groupName){ try { individual newGuy; newGuy.abundance = binSize; newGuy.group = groupName; - newGuy.bin = otu; + newGuy.bin = data.size(); data.push_back(newGuy); numBins++; @@ -226,11 +266,7 @@ void SharedRAbundVector::push_back(int binSize, int otu, string groupName){ numSeqs += binSize; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function push_back. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function push_back. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "push_back"); exit(1); } } @@ -254,11 +290,7 @@ void SharedRAbundVector::insert(int binSize, int otu, string groupName){ numSeqs += binSize; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function insert. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function insert. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "insert"); exit(1); } } @@ -282,11 +314,7 @@ void SharedRAbundVector::push_front(int binSize, int otu, string groupName){ numSeqs += binSize; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function push_front. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function push_front. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "push_front"); exit(1); } } @@ -323,8 +351,54 @@ int SharedRAbundVector::size(){ return data.size(); } + /***********************************************************************/ -void SharedRAbundVector::print(ostream& output){ +void SharedRAbundVector::printHeaders(ostream& output){ + try { + string snumBins = toString(numBins); + output << "label\tGroup\tnumOtus\t"; + if (m->sharedHeaderMode == "tax") { + for (int i = 0; i < numBins; i++) { + + //if there is a bin label use it otherwise make one + string binLabel = "PhyloType"; + string sbinNumber = toString(i+1); + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + if (i < m->currentBinLabels.size()) { binLabel = m->currentBinLabels[i]; } + + output << binLabel << '\t'; + } + output << endl; + }else { + for (int i = 0; i < numBins; i++) { + //if there is a bin label use it otherwise make one + string binLabel = "Otu"; + string sbinNumber = toString(i+1); + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + if (i < m->currentBinLabels.size()) { binLabel = m->currentBinLabels[i]; } + + output << binLabel << '\t'; + } + + output << endl; + } + m->printedHeaders = true; + } + catch(exception& e) { + m->errorOut(e, "SharedRAbundVector", "printHeaders"); + exit(1); + } +} +/***********************************************************************/ +void SharedRAbundVector::print(ostream& output) { try { output << numBins << '\t'; @@ -332,11 +406,7 @@ void SharedRAbundVector::print(ostream& output){ output << endl; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function print. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function print. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "print"); exit(1); } } @@ -356,7 +426,7 @@ int SharedRAbundVector::getGroupIndex() { return index; } void SharedRAbundVector::setGroupIndex(int vIndex) { index = vIndex; } /***********************************************************************/ int SharedRAbundVector::getNumBins(){ - return numBins; + return numBins; } /***********************************************************************/ @@ -381,25 +451,120 @@ vector SharedRAbundVector::getSharedRAbundVectors(){ SharedUtil* util; util = new SharedUtil(); - util->setGroups(globaldata->Groups, globaldata->gGroupmap->namesOfGroups); - + vector Groups = m->getGroups(); + vector allGroups = m->getAllGroups(); + util->setGroups(Groups, allGroups); + m->setGroups(Groups); + + bool remove = false; for (int i = 0; i < lookup.size(); i++) { //if this sharedrabund is not from a group the user wants then delete it. - if (util->isValidGroup(lookup[i]->getGroup(), globaldata->Groups) == false) { - delete lookup[i]; + if (util->isValidGroup(lookup[i]->getGroup(), m->getGroups()) == false) { + remove = true; + delete lookup[i]; lookup[i] = NULL; lookup.erase(lookup.begin()+i); i--; } } - + + delete util; + + if (remove) { eliminateZeroOTUS(lookup); } + return lookup; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getSharedRAbundVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getSharedRAbundVectors"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getSharedRAbundVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +//********************************************************************************************************************** +int SharedRAbundVector::eliminateZeroOTUS(vector& thislookup) { + try { + + vector newLookup; + for (int i = 0; i < thislookup.size(); i++) { + SharedRAbundVector* temp = new SharedRAbundVector(); + temp->setLabel(thislookup[i]->getLabel()); + temp->setGroup(thislookup[i]->getGroup()); + newLookup.push_back(temp); + } + + //for each bin + vector newBinLabels; + string snumBins = toString(thislookup[0]->getNumBins()); + for (int i = 0; i < thislookup[0]->getNumBins(); i++) { + if (m->control_pressed) { for (int j = 0; j < newLookup.size(); j++) { delete newLookup[j]; } return 0; } + + //look at each sharedRabund and make sure they are not all zero + bool allZero = true; + for (int j = 0; j < thislookup.size(); j++) { + if (thislookup[j]->getAbundance(i) != 0) { allZero = false; break; } + } + + //if they are not all zero add this bin + if (!allZero) { + for (int j = 0; j < thislookup.size(); j++) { + newLookup[j]->push_back(thislookup[j]->getAbundance(i), thislookup[j]->getGroup()); + } + + //if there is a bin label use it otherwise make one + string binLabel = "Otu"; + string sbinNumber = toString(i+1); + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + if (i < m->currentBinLabels.size()) { binLabel = m->currentBinLabels[i]; } + + newBinLabels.push_back(binLabel); + } + } + + for (int j = 0; j < thislookup.size(); j++) { delete thislookup[j]; } + + thislookup = newLookup; + m->currentBinLabels = newBinLabels; + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "SharedRAbundVector", "eliminateZeroOTUS"); + exit(1); + } + } + +/***********************************************************************/ +vector SharedRAbundVector::getSharedRAbundFloatVectors(vector thislookup){ + try { + vector newLookupFloat; + for (int i = 0; i < lookup.size(); i++) { + SharedRAbundFloatVector* temp = new SharedRAbundFloatVector(); + temp->setLabel(thislookup[i]->getLabel()); + temp->setGroup(thislookup[i]->getGroup()); + newLookupFloat.push_back(temp); + } + + for (int i = 0; i < thislookup.size(); i++) { + + for (int j = 0; j < thislookup[i]->getNumBins(); j++) { + + if (m->control_pressed) { return newLookupFloat; } + + int abund = thislookup[i]->getAbundance(j); + + float relabund = abund / (float) thislookup[i]->getNumSeqs(); + + newLookupFloat[i]->push_back(relabund, thislookup[i]->getGroup()); + } + } + + return newLookupFloat; + } + catch(exception& e) { + m->errorOut(e, "SharedRAbundVector", "getSharedRAbundVectors"); exit(1); } } @@ -407,20 +572,19 @@ vector SharedRAbundVector::getSharedRAbundVectors(){ RAbundVector SharedRAbundVector::getRAbundVector() { try { - RAbundVector rav(data.size()); + RAbundVector rav; for (int i = 0; i < data.size(); i++) { - rav.set(i, data[i].abundance); + if(data[i].abundance != 0) { + rav.push_back(data[i].abundance); + } } - + + rav.setLabel(label); return rav; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getRAbundVector"); exit(1); } } @@ -435,11 +599,7 @@ RAbundVector SharedRAbundVector::getRAbundVector2() { return rav; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getRAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getRAbundVector2"); exit(1); } } @@ -461,11 +621,7 @@ SharedSAbundVector SharedRAbundVector::getSharedSAbundVector(){ return sav; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getSharedSAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getSharedSAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getSharedSAbundVector"); exit(1); } } @@ -484,11 +640,7 @@ SAbundVector SharedRAbundVector::getSAbundVector() { return sav; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getSAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getSAbundVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getSAbundVector"); exit(1); } } @@ -512,11 +664,7 @@ SharedOrderVector SharedRAbundVector::getSharedOrderVector() { return ov; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SharedRAbundVector class Function getOrderVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SharedRAbundVector class function getOrderVector. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "SharedRAbundVector", "getSharedOrderVector"); exit(1); } } @@ -525,23 +673,19 @@ SharedOrderVector SharedRAbundVector::getSharedOrderVector() { OrderVector SharedRAbundVector::getOrderVector(map* nameMap = NULL) { try { OrderVector ov; - - for(int i=0;ierrorOut(e, "SharedRAbundVector", "getOrderVector"); exit(1); } }