X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rarefactcommand.cpp;h=f62cea1e5253ce0d1a970491d8eb25b0a73e6bb1;hb=5a86e9e5a5a9e061e17b3ae64fb8881f14e53b8a;hp=981f077969b1e734b2dc39fb05b372daa2a5f455;hpb=599af78a6ea4916919d460a131e2d0dffa28d35e;p=mothur.git diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index 981f077..f62cea1 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -22,113 +22,344 @@ //********************************************************************************************************************** -RareFactCommand::RareFactCommand(){ +RareFactCommand::RareFactCommand(string option) { try { globaldata = GlobalData::getInstance(); - string fileNameRoot; - fileNameRoot = getRootName(globaldata->inputFileName); - validCalculator = new ValidCalculators(); - - int i; - for (i=0; iEstimators.size(); i++) { - if (validCalculator->isValidCalculator("rarefaction", globaldata->Estimators[i]) == true) { - if (globaldata->Estimators[i] == "sobs") { - rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+"rarefaction"))); - }else if (globaldata->Estimators[i] == "chao") { - rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"r_chao"))); - }else if (globaldata->Estimators[i] == "ace") { - convert(globaldata->getAbund(), abund); - if(abund < 5) - abund = 10; - rDisplays.push_back(new RareDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"r_ace"))); - }else if (globaldata->Estimators[i] == "jack") { - rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"r_jack"))); - }else if (globaldata->Estimators[i] == "shannon") { - rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"r_shannon"))); - }else if (globaldata->Estimators[i] == "npshannon") { - rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon"))); - }else if (globaldata->Estimators[i] == "simpson") { - rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"r_simpson"))); - }else if (globaldata->Estimators[i] == "bootstrap") { - rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap"))); - }else if (globaldata->Estimators[i] == "coverage") { - rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+"r_coverage"))); - }else if (globaldata->Estimators[i] == "nseqs") { - rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+"r_nseqs"))); - } + abort = false; + allLines = 1; + labels.clear(); + Estimators.clear(); + + //allow user to run help + if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; } + + else { + //valid paramters for this command + string Array[] = {"iters","freq","label","calc","abund","outputdir","inputdir"}; + 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; } + } + + //if the user changes the output directory command factory will send this info to us in the output parameter + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ + outputDir = ""; + outputDir += hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it + } + + //make sure the user has already run the read.otu command + if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { m->mothurOut("You must read a list, sabund, rabund or shared file before you can use the rarefact.single command."); m->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"; } + else { + if (calc == "default") { calc = "sobs"; } + } + splitAtDash(calc, Estimators); + + string temp; + temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "0.10"; } + convert(temp, freq); + + temp = validParameter.validFile(parameters, "abund", false); if (temp == "not found") { temp = "10"; } + convert(temp, abund); + + temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } + convert(temp, nIters); } - //reset calc for next command - globaldata->setCalc(""); - } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactCommand class Function RareFactCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "RareFactCommand", "RareFactCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the RareFactCommand class function RareFactCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +//********************************************************************************************************************** + +void RareFactCommand::help(){ + try { + m->mothurOut("The rarefaction.single command can only be executed after a successful read.otu WTIH ONE EXECEPTION.\n"); + m->mothurOut("The rarefaction.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n"); + m->mothurOut("The rarefaction.single command parameters are label, iters, freq, calc and abund. No parameters are required. \n"); + m->mothurOut("The freq parameter is used indicate when to output your data. It is a percentage of the number of sequences. By default it is set to 0.10, meaning 10%. \n"); + m->mothurOut("The rarefaction.single command should be in the following format: \n"); + m->mothurOut("rarefaction.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"); + m->mothurOut("Example rarefaction.single(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-rchao-race-rjack-rbootstrap-rshannon-rnpshannon-rsimpson).\n"); + m->mothurOut("The default values for iters is 1000, freq is 100, and calc is rarefaction which calculates the rarefaction curve for the observed richness.\n"); + validCalculator->printCalc("rarefaction", cout); + m->mothurOut("The label parameter is used to analyze specific labels in your input.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "help"); exit(1); - } - + } } //********************************************************************************************************************** -RareFactCommand::~RareFactCommand(){ - delete order; - delete input; - delete rCurve; - delete read; -} +RareFactCommand::~RareFactCommand(){} //********************************************************************************************************************** int RareFactCommand::execute(){ try { - int count = 1; + + if (abort == true) { return 0; } + + vector outputNames; + + if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } + else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } + + if (m->control_pressed) { return 0; } - //if the users entered no valid calculators don't execute command - if (rDisplays.size() == 0) { return 0; } + for (int p = 0; p < inputFileNames.size(); p++) { + + string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p])); + globaldata->inputFileName = inputFileNames[p]; + + if (m->control_pressed) { return 0; } + + if (inputFileNames.size() > 1) { + m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); + } + int i; + validCalculator = new ValidCalculators(); + + + for (i=0; iisValidCalculator("rarefaction", Estimators[i]) == true) { + if (Estimators[i] == "sobs") { + rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+"rarefaction"))); + outputNames.push_back(fileNameRoot+"rarefaction"); + }else if (Estimators[i] == "chao") { + rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"r_chao"))); + outputNames.push_back(fileNameRoot+"r_chao"); + }else if (Estimators[i] == "ace") { + if(abund < 5) + abund = 10; + rDisplays.push_back(new RareDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"r_ace"))); + outputNames.push_back(fileNameRoot+"r_ace"); + }else if (Estimators[i] == "jack") { + rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"r_jack"))); + outputNames.push_back(fileNameRoot+"r_jack"); + }else if (Estimators[i] == "shannon") { + rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"r_shannon"))); + outputNames.push_back(fileNameRoot+"r_shannon"); + }else if (Estimators[i] == "npshannon") { + rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon"))); + outputNames.push_back(fileNameRoot+"r_npshannon"); + }else if (Estimators[i] == "simpson") { + rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"r_simpson"))); + outputNames.push_back(fileNameRoot+"r_simpson"); + }else if (Estimators[i] == "bootstrap") { + rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap"))); + outputNames.push_back(fileNameRoot+"r_bootstrap"); + }else if (Estimators[i] == "coverage") { + rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+"r_coverage"))); + outputNames.push_back(fileNameRoot+"r_coverage"); + }else if (Estimators[i] == "nseqs") { + rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+"r_nseqs"))); + outputNames.push_back(fileNameRoot+"r_nseqs"); + } + } + } + + + //if the users entered no valid calculators don't execute command + if (rDisplays.size() == 0) { for(int i=0;iinputFileName); + read->read(&*globaldata); + + order = globaldata->gorder; + string lastLabel = order->getLabel(); + input = globaldata->ginput; + + //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; + + if (m->control_pressed) { for(int i=0;iginput = NULL; delete order; globaldata->gorder = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + //as long as you are not at the end of the file or done wih the lines you want + while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if (m->control_pressed) { for(int i=0;iginput = NULL; delete order; globaldata->gorder = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); + + if(allLines == 1 || labels.count(order->getLabel()) == 1){ + + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(order, rDisplays); + rCurve->getCurve(freq, nIters); + delete rCurve; + + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); + } + + if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = order->getLabel(); + + delete order; + order = (input->getOrderVector(lastLabel)); + + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(order, rDisplays); + rCurve->getCurve(freq, nIters); + delete rCurve; + + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); + + //restore real lastlabel to save below + order->setLabel(saveLabel); + } + + lastLabel = order->getLabel(); + + delete order; + order = (input->getOrderVector()); + } + + if (m->control_pressed) { for(int i=0;iginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - order = globaldata->gorder; - input = globaldata->ginput; - - while(order != NULL){ - - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){ + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + if (m->control_pressed) { for(int i=0;iginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + //run last label if you need to + if (needToRun == true) { + if (order != NULL) { delete order; } + order = (input->getOrderVector(lastLabel)); + + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); rCurve = new Rarefact(order, rDisplays); - convert(globaldata->getFreq(), freq); - convert(globaldata->getIters(), nIters); rCurve->getCurve(freq, nIters); - delete rCurve; - - cout << order->getLabel() << '\t' << count << endl; + + delete order; } - delete order; - order = (input->getOrderVector()); - count++; - + + for(int i=0;igorder = NULL; + delete input; globaldata->ginput = NULL; + delete read; + delete validCalculator; + } - - for(int i=0;icontrol_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "RareFactCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the RareFactCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } +//********************************************************************************************************************** +vector RareFactCommand::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) { + m->errorOut(e, "RareFactCommand", "parseSharedFile"); + exit(1); + } +} //********************************************************************************************************************** + + +