X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=summarycommand.cpp;h=afb4758a29b3831cd7958583344aa223fec3e223;hb=92f998cc7debc4bf3e8594848586b8153d96db16;hp=5adf44ff8621e5ea6e5231abc9417cdb3ff93e80;hpb=9ca2caadbeac83bb84b3330d9204b1b659d62941;p=mothur.git diff --git a/summarycommand.cpp b/summarycommand.cpp index 5adf44f..afb4758 100644 --- a/summarycommand.cpp +++ b/summarycommand.cpp @@ -17,97 +17,272 @@ #include "npshannon.h" #include "shannon.h" #include "jackknife.h" +#include "geom.h" +#include "logsd.h" +#include "qstat.h" +#include "bergerparker.h" +#include "bstick.h" +#include "goodscoverage.h" +#include "coverage.h" +#include "efron.h" +#include "boneh.h" +#include "solow.h" +#include "shen.h" //********************************************************************************************************************** -SummaryCommand::SummaryCommand(){ +SummaryCommand::SummaryCommand(string option){ try { globaldata = GlobalData::getInstance(); - validCalculator = new ValidCalculators(); - int i; + abort = false; + allLines = 1; + labels.clear(); + Estimators.clear(); - for (i=0; iEstimators.size(); i++) { - if (validCalculator->isValidCalculator("summary", globaldata->Estimators[i]) == true) { - if(globaldata->Estimators[i] == "sobs"){ - sumCalculators.push_back(new Sobs()); - }else if(globaldata->Estimators[i] == "chao"){ - sumCalculators.push_back(new Chao1()); - }else if(globaldata->Estimators[i] == "ace"){ - convert(globaldata->getAbund(), abund); - if(abund < 5) - abund = 10; - sumCalculators.push_back(new Ace(abund)); - }else if(globaldata->Estimators[i] == "jack"){ - sumCalculators.push_back(new Jackknife()); - }else if(globaldata->Estimators[i] == "shannon"){ - sumCalculators.push_back(new Shannon()); - }else if(globaldata->Estimators[i] == "npshannon"){ - sumCalculators.push_back(new NPShannon()); - }else if(globaldata->Estimators[i] == "simpson"){ - sumCalculators.push_back(new Simpson()); - }else if(globaldata->Estimators[i] == "bootstrap"){ - sumCalculators.push_back(new Bootstrap()); - }else if (globaldata->Estimators[i] == "nseqs") { - sumCalculators.push_back(new NSeqs()); - } - } - } + //allow user to run help + if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; } - //reset calc for next command - globaldata->setCalc(""); + else { + //valid paramters for this command + string Array[] = {"label","calc","abund","size"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + + //check to make sure all parameters are valid for command + for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + //make sure the user has already run the read.otu command + if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { mothurOut("You must read a list, sabund, rabund or shared file before you can use the summary.single command."); mothurOutEndLine(); abort = true; } + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + //if the user has not specified any labels use the ones from read.otu + if(label == "") { + allLines = globaldata->allLines; + labels = globaldata->labels; + } + + calc = validParameter.validFile(parameters, "calc", false); + if (calc == "not found") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; } + else { + if (calc == "default") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; } + } + splitAtDash(calc, Estimators); + string temp; + temp = validParameter.validFile(parameters, "abund", false); if (temp == "not found") { temp = "10"; } + convert(temp, abund); + + temp = validParameter.validFile(parameters, "size", false); if (temp == "not found") { temp = "0"; } + convert(temp, size); + + } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SummaryCommand class Function SummaryCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "SummaryCommand", "SummaryCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the SummaryCommand class function SummaryCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** -SummaryCommand::~SummaryCommand(){ - delete sabund; - delete input; - delete read; +void SummaryCommand::help(){ + try { + mothurOut("The summary.single command can only be executed after a successful read.otu WTIH ONE EXECEPTION.\n"); + mothurOut("The summary.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n"); + mothurOut("The summary.single command parameters are label, calc, abund. No parameters are required.\n"); + mothurOut("The summary.single command should be in the following format: \n"); + mothurOut("summary.single(label=yourLabel, calc=yourEstimators).\n"); + mothurOut("Example summary.single(label=unique-.01-.03, calc=sobs-chao-ace-jack-bootstrap-shannon-npshannon-simpson).\n"); + validCalculator->printCalc("summary", cout); + mothurOut("The default value calc is sobs-chao-ace-jack-shannon-npshannon-simpson\n"); + mothurOut("The label parameter is used to analyze specific labels in your input.\n"); + mothurOut("Note: No spaces between parameter labels (i.e. label), '=' and parameters (i.e.yourLabels).\n\n"); + } + catch(exception& e) { + errorOut(e, "SummaryCommand", "help"); + exit(1); + } } //********************************************************************************************************************** +SummaryCommand::~SummaryCommand(){} + +//********************************************************************************************************************** + int SummaryCommand::execute(){ try { - //if the users entered no valid calculators don't execute command - if (sumCalculators.size() == 0) { return 0; } - - outputFileName = ((getRootName(globaldata->inputFileName)) + "summary"); - openOutputFile(outputFileName, outputFileHandle); - outputFileHandle << "label"; - - read = new ReadPhilFile(globaldata->inputFileName); - read->read(&*globaldata); - - for(int i=0;igetCols() == 1){ - outputFileHandle << '\t' << sumCalculators[i]->getName(); - } - else{ - outputFileHandle << '\t' << sumCalculators[i]->getName() << "\t" << sumCalculators[i]->getName() << "_lci\t" << sumCalculators[i]->getName() << "_hci"; - } - } - outputFileHandle << endl; + if (abort == true) { return 0; } - sabund = globaldata->sabund; - input = globaldata->ginput; - int count = 1; - while(sabund != NULL){ + if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } + else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(sabund->getLabel()) == 1){ - - cout << sabund->getLabel() << '\t' << count << endl; + for (int p = 0; p < inputFileNames.size(); p++) { + + string fileNameRoot = getRootName(inputFileNames[p]) + "summary"; + globaldata->inputFileName = inputFileNames[p]; + + if (inputFileNames.size() > 1) { + mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine(); + } + + + validCalculator = new ValidCalculators(); + + for (int i=0; iisValidCalculator("summary", Estimators[i]) == true) { + if(Estimators[i] == "sobs"){ + sumCalculators.push_back(new Sobs()); + }else if(Estimators[i] == "chao"){ + sumCalculators.push_back(new Chao1()); + }else if(Estimators[i] == "coverage"){ + sumCalculators.push_back(new Coverage()); + }else if(Estimators[i] == "geometric"){ + sumCalculators.push_back(new Geom()); + }else if(Estimators[i] == "logseries"){ + sumCalculators.push_back(new LogSD()); + }else if(Estimators[i] == "qstat"){ + sumCalculators.push_back(new QStat()); + }else if(Estimators[i] == "bergerparker"){ + sumCalculators.push_back(new BergerParker()); + }else if(Estimators[i] == "bstick"){ + sumCalculators.push_back(new BStick()); + }else if(Estimators[i] == "ace"){ + if(abund < 5) + abund = 10; + sumCalculators.push_back(new Ace(abund)); + }else if(Estimators[i] == "jack"){ + sumCalculators.push_back(new Jackknife()); + }else if(Estimators[i] == "shannon"){ + sumCalculators.push_back(new Shannon()); + }else if(Estimators[i] == "npshannon"){ + sumCalculators.push_back(new NPShannon()); + }else if(Estimators[i] == "simpson"){ + sumCalculators.push_back(new Simpson()); + }else if(Estimators[i] == "bootstrap"){ + sumCalculators.push_back(new Bootstrap()); + }else if (Estimators[i] == "nseqs") { + sumCalculators.push_back(new NSeqs()); + }else if (Estimators[i] == "goodscoverage") { + sumCalculators.push_back(new GoodsCoverage()); + }else if (Estimators[i] == "efron") { + sumCalculators.push_back(new Efron(size)); + }else if (Estimators[i] == "boneh") { + sumCalculators.push_back(new Boneh(size)); + }else if (Estimators[i] == "solow") { + sumCalculators.push_back(new Solow(size)); + }else if (Estimators[i] == "shen") { + sumCalculators.push_back(new Shen(size, abund)); + } + } + } + + //if the users entered no valid calculators don't execute command + if (sumCalculators.size() == 0) { return 0; } + + ofstream outputFileHandle; + openOutputFile(fileNameRoot, outputFileHandle); + outputFileHandle << "label"; + read = new ReadOTUFile(globaldata->inputFileName); + read->read(&*globaldata); + + sabund = globaldata->sabund; + string lastLabel = sabund->getLabel(); + input = globaldata->ginput; + + for(int i=0;igetCols() == 1){ + outputFileHandle << '\t' << sumCalculators[i]->getName(); + } + else{ + outputFileHandle << '\t' << sumCalculators[i]->getName() << "\t" << sumCalculators[i]->getName() << "_lci\t" << sumCalculators[i]->getName() << "_hci"; + } + } + outputFileHandle << endl; + + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. + set processedLabels; + set userLabels = labels; + + while((sabund != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if(allLines == 1 || labels.count(sabund->getLabel()) == 1){ + + mothurOut(sabund->getLabel()); mothurOutEndLine(); + processedLabels.insert(sabund->getLabel()); + userLabels.erase(sabund->getLabel()); + + outputFileHandle << sabund->getLabel(); + for(int i=0;i data = sumCalculators[i]->getValues(sabund); + outputFileHandle << '\t'; + sumCalculators[i]->print(outputFileHandle); + } + outputFileHandle << endl; + } + + if ((anyLabelsToProcess(sabund->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = sabund->getLabel(); + + delete sabund; + sabund = input->getSAbundVector(lastLabel); + + mothurOut(sabund->getLabel()); mothurOutEndLine(); + processedLabels.insert(sabund->getLabel()); + userLabels.erase(sabund->getLabel()); + + outputFileHandle << sabund->getLabel(); + for(int i=0;i data = sumCalculators[i]->getValues(sabund); + outputFileHandle << '\t'; + sumCalculators[i]->print(outputFileHandle); + } + outputFileHandle << endl; + + //restore real lastlabel to save below + sabund->setLabel(saveLabel); + } + + lastLabel = sabund->getLabel(); + + delete sabund; + sabund = input->getSAbundVector(); + } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + needToRun = true; + }else { + mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + if (sabund != NULL) { delete sabund; } + sabund = input->getSAbundVector(lastLabel); + + mothurOut(sabund->getLabel()); mothurOutEndLine(); outputFileHandle << sabund->getLabel(); for(int i=0;i data = sumCalculators[i]->getValues(sabund); @@ -115,22 +290,81 @@ int SummaryCommand::execute(){ sumCalculators[i]->print(outputFileHandle); } outputFileHandle << endl; + delete sabund; } - - sabund = input->getSAbundVector(); - count++; + + outputFileHandle.close(); + + delete input; globaldata->ginput = NULL; + delete read; + delete validCalculator; + globaldata->sabund = NULL; } - + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SummaryCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "SummaryCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the SummaryCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } +//********************************************************************************************************************** +vector SummaryCommand::parseSharedFile(string filename) { + try { + vector filenames; + + map filehandles; + map::iterator it3; + + + //read first line + read = new ReadOTUFile(filename); + read->read(&*globaldata); + + input = globaldata->ginput; + vector lookup = input->getSharedRAbundVectors(); + + string sharedFileRoot = getRootName(filename); + + //clears file before we start to write to it below + for (int i=0; igetGroup() + ".rabund").c_str()); + filenames.push_back((sharedFileRoot + lookup[i]->getGroup() + ".rabund")); + } + + ofstream* temp; + for (int i=0; igetGroup()] = temp; + groups.push_back(lookup[i]->getGroup()); + } + while(lookup[0] != NULL) { + + for (int i = 0; i < lookup.size(); i++) { + RAbundVector rav = lookup[i]->getRAbundVector(); + openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()])); + rav.print(*(filehandles[lookup[i]->getGroup()])); + (*(filehandles[lookup[i]->getGroup()])).close(); + } + + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input->getSharedRAbundVectors(); + } + + //free memory + for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { + delete it3->second; + } + delete read; + delete input; + globaldata->ginput = NULL; + + return filenames; + } + catch(exception& e) { + errorOut(e, "SummaryCommand", "parseSharedFile"); + exit(1); + } +} //**********************************************************************************************************************