X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=mgclustercommand.cpp;h=1861aa5b5d8c19f547ed90e3ec57866a3b53ecd2;hb=9b53f130ac9af5e95444ce2e817fce25ed19ff03;hp=4ca0cdfb9af8f71338be56a9649ec4c6f8a07a87;hpb=2ecee16fec29d4c525f740ec19b27962ca09c050;p=mothur.git diff --git a/mgclustercommand.cpp b/mgclustercommand.cpp index 4ca0cdf..1861aa5 100644 --- a/mgclustercommand.cpp +++ b/mgclustercommand.cpp @@ -13,8 +13,8 @@ vector MGClusterCommand::setParameters(){ try { CommandParameter pblast("blast", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pblast); - CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); - CommandParameter plarge("large", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(plarge); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName",false,false); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pcount); CommandParameter plength("length", "Number", "", "5", "", "", "",false,false); parameters.push_back(plength); CommandParameter ppenalty("penalty", "Number", "", "0.10", "", "", "",false,false); parameters.push_back(ppenalty); CommandParameter pcutoff("cutoff", "Number", "", "0.70", "", "", "",false,false); parameters.push_back(pcutoff); @@ -147,6 +147,14 @@ MGClusterCommand::MGClusterCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["name"] = inputDir + it->second; } } + + it = parameters.find("count"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["count"] = inputDir + it->second; } + } } @@ -165,15 +173,19 @@ MGClusterCommand::MGClusterCommand(string option) { if (namefile == "not open") { abort = true; } else if (namefile == "not found") { namefile = ""; } else { m->setNameFile(namefile); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if (countfile != "" && namefile != "") { m->mothurOut("[ERROR]: Cannot have both a name file and count file. Please use one or the other."); m->mothurOutEndLine(); abort = true; } if ((blastfile == "")) { m->mothurOut("When executing a mgcluster command you must provide a blastfile."); m->mothurOutEndLine(); abort = true; } //check for optional parameter and set defaults string temp; - temp = validParameter.validFile(parameters, "large", false); if (temp == "not found") { temp = "false"; } - large = m->isTrue(temp); - - temp = validParameter.validFile(parameters, "precision", false); if (temp == "not found") { temp = "100"; } + temp = validParameter.validFile(parameters, "precision", false); if (temp == "not found") { temp = "100"; } precisionLength = temp.length(); m->mothurConvert(temp, precision); @@ -237,10 +249,12 @@ int MGClusterCommand::execute(){ list = new ListVector(nameMap->getListVector()); RAbundVector* rabund = NULL; - if(large) { - map nameMapCounts = m->readNames(namefile); - createRabund(nameMapCounts); - rabund = &rav; + if(countfile != "") { + //map nameMapCounts = m->readNames(namefile); + ct = new CountTable(); + ct->readTable(countfile); + rabund = new RAbundVector(); + createRabund(ct, list, rabund); }else { rabund = new RAbundVector(list->getRAbundVector()); } @@ -262,15 +276,19 @@ int MGClusterCommand::execute(){ string sabundFileName = fileroot+ tag + "." + getOutputFileNameTag("sabund"); string rabundFileName = fileroot+ tag + "." + getOutputFileNameTag("rabund"); - string listFileName = fileroot+ tag + "." + getOutputFileNameTag("list"); + string listFileName = fileroot+ tag + "."; + if (countfile != "") { listFileName += "unique_"; } + listFileName += getOutputFileNameTag("list"); - m->openOutputFile(sabundFileName, sabundFile); - m->openOutputFile(rabundFileName, rabundFile); + if (countfile == "") { + m->openOutputFile(sabundFileName, sabundFile); + m->openOutputFile(rabundFileName, rabundFile); + } m->openOutputFile(listFileName, listFile); if (m->control_pressed) { delete nameMap; delete read; delete list; delete rabund; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -279,7 +297,7 @@ int MGClusterCommand::execute(){ if (!hclusterWanted) { //get distmatrix and overlap - SparseMatrix* distMatrix = read->getDistMatrix(); + SparseDistanceMatrix* distMatrix = read->getDistMatrix(); overlapMatrix = read->getOverlapMatrix(); //already sorted by read delete read; @@ -293,7 +311,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete distMatrix; delete list; delete rabund; delete cluster; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -305,7 +323,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete distMatrix; delete list; delete rabund; delete cluster; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -328,7 +346,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete distMatrix; delete list; delete rabund; delete cluster; delete temp; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -359,7 +377,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete distMatrix; delete list; delete rabund; delete cluster; delete temp; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -389,7 +407,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -406,7 +424,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; delete hcluster; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -422,7 +440,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; delete hcluster; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove(distFile); m->mothurRemove(overlapFile); outputTypes.clear(); @@ -437,7 +455,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; delete hcluster; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove(distFile); m->mothurRemove(overlapFile); outputTypes.clear(); @@ -461,7 +479,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; delete hcluster; delete temp; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove(distFile); m->mothurRemove(overlapFile); outputTypes.clear(); @@ -497,7 +515,7 @@ int MGClusterCommand::execute(){ if (m->control_pressed) { delete nameMap; delete list; delete rabund; delete hcluster; delete temp; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove(distFile); m->mothurRemove(overlapFile); outputTypes.clear(); @@ -519,14 +537,15 @@ int MGClusterCommand::execute(){ } delete list; - if (!large) {delete rabund;} + delete rabund; listFile.close(); - sabundFile.close(); - rabundFile.close(); - + if (countfile == "") { + sabundFile.close(); + rabundFile.close(); + } if (m->control_pressed) { delete nameMap; - listFile.close(); rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".list")); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); + listFile.close(); if (countfile == "") { rabundFile.close(); sabundFile.close(); m->mothurRemove((fileroot+ tag + ".rabund")); m->mothurRemove((fileroot+ tag + ".sabund")); } m->mothurRemove((fileroot+ tag + ".list")); outputTypes.clear(); return 0; } @@ -534,8 +553,10 @@ int MGClusterCommand::execute(){ m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); m->mothurOut(listFileName); m->mothurOutEndLine(); outputNames.push_back(listFileName); outputTypes["list"].push_back(listFileName); - m->mothurOut(rabundFileName); m->mothurOutEndLine(); outputNames.push_back(rabundFileName); outputTypes["rabund"].push_back(rabundFileName); - m->mothurOut(sabundFileName); m->mothurOutEndLine(); outputNames.push_back(sabundFileName); outputTypes["sabund"].push_back(sabundFileName); + if (countfile == "") { + m->mothurOut(rabundFileName); m->mothurOutEndLine(); outputNames.push_back(rabundFileName); outputTypes["rabund"].push_back(rabundFileName); + m->mothurOut(sabundFileName); m->mothurOutEndLine(); outputNames.push_back(sabundFileName); outputTypes["sabund"].push_back(sabundFileName); + } m->mothurOutEndLine(); if (saveCutoff != cutoff) { @@ -578,12 +599,14 @@ int MGClusterCommand::execute(){ void MGClusterCommand::printData(ListVector* mergedList){ try { mergedList->print(listFile); - mergedList->getRAbundVector().print(rabundFile); - - SAbundVector sabund = mergedList->getSAbundVector(); + SAbundVector sabund = mergedList->getSAbundVector(); + + if (countfile == "") { + mergedList->getRAbundVector().print(rabundFile); + sabund.print(sabundFile); + } sabund.print(cout); - sabund.print(sabundFile); } catch(exception& e) { m->errorOut(e, "MGClusterCommand", "printData"); @@ -714,14 +737,25 @@ void MGClusterCommand::sortHclusterFiles(string unsortedDist, string unsortedOve //********************************************************************************************************************** -void MGClusterCommand::createRabund(map nameMapCounts){ +void MGClusterCommand::createRabund(CountTable*& ct, ListVector*& list, RAbundVector*& rabund){ try { - //RAbundVector rav; - map::iterator it; - //it = nameMapCounts.begin(); - //for(int i = 0; i < list->getNumBins(); i++) { rav.push_back((*it).second); it++; } - for ( it=nameMapCounts.begin(); it!=nameMapCounts.end(); it++ ) { rav.push_back( it->second ); } + //vector names = ct.getNamesOfSeqs(); + + //for ( int i; i < ct.getNumGroups(); i++ ) { rav.push_back( ct.getNumSeqs(names[i]) ); } //return rav; + + for(int i = 0; i < list->getNumBins(); i++) { + vector binNames; + string bin = list->get(i); + m->splitAtComma(bin, binNames); + int total = 0; + for (int j = 0; j < binNames.size(); j++) { + total += ct->getNumSeqs(binNames[j]); + } + rabund->push_back(total); + } + + } catch(exception& e) { m->errorOut(e, "MGClusterCommand", "createRabund");