X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rarefactcommand.cpp;h=97d633278f4d43dc8b30a5e95298d2897bdabca7;hb=a218321731df14d231bbc08e79906f757cf1540d;hp=680f68c1e6694557edac00e259449d0d53169400;hpb=0470f6d037aacb3563c3f7010708120a4a67d4e6;p=mothur.git diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index 680f68c..97d6332 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -27,57 +27,52 @@ RareFactCommand::RareFactCommand(string option){ globaldata = GlobalData::getInstance(); abort = false; allLines = 1; - lines.clear(); labels.clear(); Estimators.clear(); //allow user to run help - if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; } + if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; } else { //valid paramters for this command - string Array[] = {"iters","freq","line","label","calc","abund"}; + string Array[] = {"iters","freq","label","calc","abund","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - parser = new OptionParser(); - parser->parse(option, parameters); delete parser; + OptionParser parser(option); + map parameters = parser.getParameters(); - ValidParameters* validParameter = new ValidParameters(); + ValidParameters validParameter; //check to make sure all parameters are valid for command - for (it = parameters.begin(); it != parameters.end(); it++) { - if (validParameter->isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + 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->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { cout << "You must read a list, sabund or rabund before you can use the rarefaction.single command." << endl; abort = true; } + 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 rarefact.single command."); mothurOutEndLine(); abort = true; } //check for optional parameter and set defaults // ...at some point should added some additional type checking... - line = validParameter->validFile(parameters, "line", false); - if (line == "not found") { line = ""; } - else { - if(line != "all") { splitAtDash(line, lines); allLines = 0; } - else { allLines = 1; } - } - - label = validParameter->validFile(parameters, "label", false); + label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } else { if(label != "all") { splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } - //make sure user did not use both the line and label parameters - if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; } - //if the user has not specified any line or labels use the ones from read.otu - else if((line == "") && (label == "")) { + //if the user has not specified any labels use the ones from read.otu + if(label == "") { allLines = globaldata->allLines; labels = globaldata->labels; - lines = globaldata->lines; } - calc = validParameter->validFile(parameters, "calc", false); + calc = validParameter.validFile(parameters, "calc", false); if (calc == "not found") { calc = "sobs"; } else { if (calc == "default") { calc = "sobs"; } @@ -85,100 +80,46 @@ RareFactCommand::RareFactCommand(string option){ splitAtDash(calc, Estimators); string temp; - temp = validParameter->validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } + temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } convert(temp, freq); - temp = validParameter->validFile(parameters, "abund", false); if (temp == "not found") { temp = "10"; } + 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"; } + temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } convert(temp, nIters); - - delete validParameter; - - if (abort == false) { - - string fileNameRoot = getRootName(globaldata->inputFileName); - 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"))); - }else if (Estimators[i] == "chao") { - rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(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"))); - }else if (Estimators[i] == "jack") { - rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"r_jack"))); - }else if (Estimators[i] == "shannon") { - rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"r_shannon"))); - }else if (Estimators[i] == "npshannon") { - rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon"))); - }else if (Estimators[i] == "simpson") { - rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"r_simpson"))); - }else if (Estimators[i] == "bootstrap") { - rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap"))); - }else if (Estimators[i] == "coverage") { - rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+"r_coverage"))); - }else if (Estimators[i] == "nseqs") { - rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+"r_nseqs"))); - } - } - } - } - } } 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"; + 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"; - exit(1); - } - } //********************************************************************************************************************** void RareFactCommand::help(){ try { - cout << "The rarefaction.single command can only be executed after a successful read.otu WTIH ONE EXECEPTION." << "\n"; - cout << "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"; - cout << "The rarefaction.single command parameters are label, line, iters, freq, calc and abund. No parameters are required, but you may not use " << "\n"; - cout << "both the line and label parameters at the same time. The rarefaction.single command should be in the following format: " << "\n"; - cout << "rarefaction.single(label=yourLabel, line=yourLines, iters=yourIters, freq=yourFreq, calc=yourEstimators)." << "\n"; - cout << "Example rarefaction.single(label=unique-.01-.03, line=0-5-10, iters=10000, freq=10, calc=sobs-rchao-race-rjack-rbootstrap-rshannon-rnpshannon-rsimpson)." << "\n"; - cout << "The default values for iters is 1000, freq is 100, and calc is rarefaction which calculates the rarefaction curve for the observed richness." << "\n"; + mothurOut("The rarefaction.single command can only be executed after a successful read.otu WTIH ONE EXECEPTION.\n"); + 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"); + mothurOut("The rarefaction.single command parameters are label, iters, freq, calc and abund. No parameters are required. \n"); + mothurOut("The rarefaction.single command should be in the following format: \n"); + mothurOut("rarefaction.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"); + mothurOut("Example rarefaction.single(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-rchao-race-rjack-rbootstrap-rshannon-rnpshannon-rsimpson).\n"); + 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); - cout << "The label and line parameters are used to analyze specific lines in your input." << "\n"; - cout << "Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq)." << "\n" << "\n"; + mothurOut("The label parameter is used to analyze specific labels in your input.\n"); + mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "RareFactCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the RareFactCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** -RareFactCommand::~RareFactCommand(){ - delete order; - delete input; - delete rCurve; - delete read; - delete validCalculator; -} +RareFactCommand::~RareFactCommand(){} //********************************************************************************************************************** @@ -187,90 +128,205 @@ int RareFactCommand::execute(){ if (abort == true) { return 0; } - int count = 1; + if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } + else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } - //if the users entered no valid calculators don't execute command - if (rDisplays.size() == 0) { return 0; } - - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); - - order = globaldata->gorder; - OrderVector* lastOrder = order; - 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; - set userLines = lines; - - //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) || (userLines.size() != 0))) { + for (int p = 0; p < inputFileNames.size(); p++) { - if(allLines == 1 || lines.count(count) == 1 || labels.count(order->getLabel()) == 1){ + string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p])); + globaldata->inputFileName = inputFileNames[p]; + + if (inputFileNames.size() > 1) { + mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine(); + } + int i; + validCalculator = new ValidCalculators(); - rCurve = new Rarefact(order, rDisplays); - rCurve->getCurve(freq, nIters); - delete rCurve; - cout << order->getLabel() << '\t' << count << endl; - processedLabels.insert(order->getLabel()); - userLabels.erase(order->getLabel()); - userLines.erase(count); + for (i=0; iisValidCalculator("rarefaction", Estimators[i]) == true) { + if (Estimators[i] == "sobs") { + rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+"rarefaction"))); + }else if (Estimators[i] == "chao") { + rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(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"))); + }else if (Estimators[i] == "jack") { + rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"r_jack"))); + }else if (Estimators[i] == "shannon") { + rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"r_shannon"))); + }else if (Estimators[i] == "npshannon") { + rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon"))); + }else if (Estimators[i] == "simpson") { + rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"r_simpson"))); + }else if (Estimators[i] == "bootstrap") { + rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap"))); + }else if (Estimators[i] == "coverage") { + rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+"r_coverage"))); + }else if (Estimators[i] == "nseqs") { + rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+"r_nseqs"))); + } + } } - if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastOrder->getLabel()) != 1)) { - rCurve = new Rarefact(lastOrder, rDisplays); + + //if the users entered no valid calculators don't execute command + if (rDisplays.size() == 0) { return 0; } + + read = new ReadOTUFile(globaldata->inputFileName); + 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; + + //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(allLines == 1 || labels.count(order->getLabel()) == 1){ + + rCurve = new Rarefact(order, rDisplays); + rCurve->getCurve(freq, nIters); + delete rCurve; + + mothurOut(order->getLabel()); mothurOutEndLine(); + 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)); + + rCurve = new Rarefact(order, rDisplays); + rCurve->getCurve(freq, nIters); + delete rCurve; + + mothurOut(order->getLabel()); mothurOutEndLine(); + 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()); + } + + //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 (order != NULL) { delete order; } + order = (input->getOrderVector(lastLabel)); + + rCurve = new Rarefact(order, rDisplays); rCurve->getCurve(freq, nIters); delete rCurve; - - cout << lastOrder->getLabel() << '\t' << count << endl; - processedLabels.insert(lastOrder->getLabel()); - userLabels.erase(lastOrder->getLabel()); + + mothurOut(order->getLabel()); mothurOutEndLine(); + delete order; } - if (count != 1) { delete lastOrder; } - lastOrder = order; - - order = (input->getOrderVector()); - count++; + + for(int i=0;igorder = NULL; + delete input; globaldata->ginput = NULL; + delete read; + delete validCalculator; + } - //output error messages about any remaining user labels - set::iterator it; - bool needToRun = false; - for (it = userLabels.begin(); it != userLabels.end(); it++) { - cout << "Your file does not include the label "<< *it; - if (processedLabels.count(lastOrder->getLabel()) != 1) { - cout << ". I will use " << lastOrder->getLabel() << "." << endl; - needToRun = true; - }else { - cout << ". Please refer to " << lastOrder->getLabel() << "." << endl; - } - } + return 0; + } + catch(exception& e) { + errorOut(e, "RareFactCommand", "execute"); + exit(1); + } +} +//********************************************************************************************************************** +vector RareFactCommand::parseSharedFile(string filename) { + try { + vector filenames; + + map filehandles; + map::iterator it3; - //run last line if you need to - if (needToRun == true) { - rCurve = new Rarefact(lastOrder, rDisplays); - rCurve->getCurve(freq, nIters); - delete rCurve; + + //read first line + read = new ReadOTUFile(filename); + read->read(&*globaldata); - cout << lastOrder->getLabel() << '\t' << count << endl; + 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")); } - delete lastOrder; + ofstream* temp; + for (int i=0; igetGroup()] = temp; + groups.push_back(lookup[i]->getGroup()); + } - for(int i=0;igetRAbundVector(); + 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) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "RareFactCommand", "parseSharedFile"); 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); - } } - //********************************************************************************************************************** + + +