X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rarefactcommand.cpp;h=cb377273ebf711d1c7ef41363178a30a4add2e31;hb=fd5f17bcbe5fadab2c525f3d1fcfd1d79a60ae72;hp=566561e9e695c3f74f7ffb1ce0b1d56ee0e3bc20;hpb=aa9238c0a9e6e7aa0ed8b8b606b08ad4fd7dcfe3;p=mothur.git diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index 566561e..cb37727 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -14,14 +14,79 @@ #include "chao1.h" #include "bootstrap.h" #include "simpson.h" +#include "simpsoneven.h" +#include "heip.h" +#include "smithwilson.h" +#include "invsimpson.h" #include "npshannon.h" +#include "shannoneven.h" #include "shannon.h" #include "jackknife.h" #include "coverage.h" //********************************************************************************************************************** - - +vector RareFactCommand::getValidParameters(){ + try { + string Array[] = {"iters","freq","label","calc","abund","processors","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector RareFactCommand::getRequiredParameters(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector RareFactCommand::getRequiredFiles(){ + try { + string AlignArray[] = {"shared","list","rabund","sabund","or"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** +RareFactCommand::RareFactCommand(){ + try { + abort = true; + //initialize outputTypes + vector tempOutNames; + outputTypes["rarefaction"] = tempOutNames; + outputTypes["r_chao"] = tempOutNames; + outputTypes["r_ace"] = tempOutNames; + outputTypes["r_jack"] = tempOutNames; + outputTypes["r_shannon"] = tempOutNames; + outputTypes["r_shannoneven"] = tempOutNames; + outputTypes["r_heip"] = tempOutNames; + outputTypes["r_smithwilson"] = tempOutNames; + outputTypes["r_npshannon"] = tempOutNames; + outputTypes["r_simpson"] = tempOutNames; + outputTypes["r_simpsoneven"] = tempOutNames; + outputTypes["r_invsimpson"] = tempOutNames; + outputTypes["r_bootstrap"] = tempOutNames; + outputTypes["r_coverage"] = tempOutNames; + outputTypes["r_nseqs"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "RareFactCommand"); + exit(1); + } +} +//********************************************************************************************************************** RareFactCommand::RareFactCommand(string option) { try { globaldata = GlobalData::getInstance(); @@ -35,7 +100,7 @@ RareFactCommand::RareFactCommand(string option) { else { //valid paramters for this command - string Array[] = {"iters","freq","label","calc","abund","outputdir","inputdir"}; + string Array[] = {"iters","freq","label","calc","abund","processors","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -48,10 +113,28 @@ RareFactCommand::RareFactCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["rarefaction"] = tempOutNames; + outputTypes["r_chao"] = tempOutNames; + outputTypes["r_ace"] = tempOutNames; + outputTypes["r_jack"] = tempOutNames; + outputTypes["r_shannon"] = tempOutNames; + outputTypes["r_shannoneven"] = tempOutNames; + outputTypes["r_heip"] = tempOutNames; + outputTypes["r_smithwilson"] = tempOutNames; + outputTypes["r_npshannon"] = tempOutNames; + outputTypes["r_simpson"] = tempOutNames; + outputTypes["r_simpsoneven"] = tempOutNames; + outputTypes["r_invsimpson"] = tempOutNames; + outputTypes["r_bootstrap"] = tempOutNames; + outputTypes["r_coverage"] = tempOutNames; + outputTypes["r_nseqs"] = tempOutNames; + //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 + outputDir += m->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 @@ -62,7 +145,7 @@ RareFactCommand::RareFactCommand(string option) { label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } else { - if(label != "all") { splitAtDash(label, labels); allLines = 0; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } @@ -77,7 +160,7 @@ RareFactCommand::RareFactCommand(string option) { else { if (calc == "default") { calc = "sobs"; } } - splitAtDash(calc, Estimators); + m->splitAtDash(calc, Estimators); string temp; temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } @@ -88,6 +171,9 @@ RareFactCommand::RareFactCommand(string option) { temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } convert(temp, nIters); + + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } + convert(temp, processors); } } @@ -102,7 +188,9 @@ 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 rarefaction.single command parameters are label, iters, freq, calc, processors and abund. No parameters are required. \n"); + m->mothurOut("The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n"); + m->mothurOut("The processors parameter allows you to specify the number of processors to use. The default is 1.\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"); @@ -128,19 +216,18 @@ int RareFactCommand::execute(){ if (abort == true) { return 0; } - vector outputNames; - + string hadShared = ""; if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } - else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } - - if (m->control_pressed) { return 0; } + else { hadShared = globaldata->getSharedFile(); inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } + + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } return 0; } for (int p = 0; p < inputFileNames.size(); p++) { - string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p])); + string fileNameRoot = outputDir + m->getRootName(m->getSimpleName(inputFileNames[p])); globaldata->inputFileName = inputFileNames[p]; - if (m->control_pressed) { return 0; } + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } return 0; } if (inputFileNames.size() > 1) { m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); @@ -153,36 +240,51 @@ int RareFactCommand::execute(){ if (validCalculator->isValidCalculator("rarefaction", Estimators[i]) == true) { if (Estimators[i] == "sobs") { rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+"rarefaction"))); - outputNames.push_back(fileNameRoot+"rarefaction"); + outputNames.push_back(fileNameRoot+"rarefaction"); outputTypes["rarefaction"].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"); + outputNames.push_back(fileNameRoot+"r_chao"); outputTypes["r_chao"].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"); + outputNames.push_back(fileNameRoot+"r_ace"); outputTypes["r_ace"].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"); + outputNames.push_back(fileNameRoot+"r_jack"); outputTypes["r_jack"].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"); + outputNames.push_back(fileNameRoot+"r_shannon"); outputTypes["r_shannon"].push_back(fileNameRoot+"r_shannon"); + }else if (Estimators[i] == "shannoneven") { + rDisplays.push_back(new RareDisplay(new ShannonEven(), new ThreeColumnFile(fileNameRoot+"r_shannoneven"))); + outputNames.push_back(fileNameRoot+"r_shannoneven"); outputTypes["r_shannoneven"].push_back(fileNameRoot+"r_shannoneven"); + }else if (Estimators[i] == "heip") { + rDisplays.push_back(new RareDisplay(new Heip(), new ThreeColumnFile(fileNameRoot+"r_heip"))); + outputNames.push_back(fileNameRoot+"r_heip"); outputTypes["r_heip"].push_back(fileNameRoot+"r_heip"); + }else if (Estimators[i] == "smithwilson") { + rDisplays.push_back(new RareDisplay(new SmithWilson(), new ThreeColumnFile(fileNameRoot+"r_smithwilson"))); + outputNames.push_back(fileNameRoot+"r_smithwilson"); outputTypes["r_smithwilson"].push_back(fileNameRoot+"r_smithwilson"); }else if (Estimators[i] == "npshannon") { rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon"))); - outputNames.push_back(fileNameRoot+"r_npshannon"); + outputNames.push_back(fileNameRoot+"r_npshannon"); outputTypes["r_npshannon"].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"); + outputNames.push_back(fileNameRoot+"r_simpson"); outputTypes["r_simpson"].push_back(fileNameRoot+"r_simpson"); + }else if (Estimators[i] == "simpsoneven") { + rDisplays.push_back(new RareDisplay(new SimpsonEven(), new ThreeColumnFile(fileNameRoot+"r_simpsoneven"))); + outputNames.push_back(fileNameRoot+"r_simpsoneven"); outputTypes["r_simpsoneven"].push_back(fileNameRoot+"r_simpsoneven"); + }else if (Estimators[i] == "invsimpson") { + rDisplays.push_back(new RareDisplay(new InvSimpson(), new ThreeColumnFile(fileNameRoot+"r_invsimpson"))); + outputNames.push_back(fileNameRoot+"r_invsimpson"); outputTypes["r_invsimpson"].push_back(fileNameRoot+"r_invsimpson"); }else if (Estimators[i] == "bootstrap") { rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap"))); - outputNames.push_back(fileNameRoot+"r_bootstrap"); + outputNames.push_back(fileNameRoot+"r_bootstrap"); outputTypes["r_bootstrap"].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"); + outputNames.push_back(fileNameRoot+"r_coverage"); outputTypes["r_coverage"].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"); + outputNames.push_back(fileNameRoot+"r_nseqs"); outputTypes["r_nseqs"].push_back(fileNameRoot+"r_nseqs"); } } } @@ -202,18 +304,18 @@ int RareFactCommand::execute(){ 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; } + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } 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; } + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } 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; } if(allLines == 1 || labels.count(order->getLabel()) == 1){ m->mothurOut(order->getLabel()); m->mothurOutEndLine(); - rCurve = new Rarefact(order, rDisplays); + rCurve = new Rarefact(order, rDisplays, processors); rCurve->getCurve(freq, nIters); delete rCurve; @@ -221,14 +323,14 @@ int RareFactCommand::execute(){ userLabels.erase(order->getLabel()); } - if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->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 = new Rarefact(order, rDisplays, processors); rCurve->getCurve(freq, nIters); delete rCurve; @@ -245,7 +347,7 @@ int RareFactCommand::execute(){ 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; } + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } for(int i=0;iginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } //output error messages about any remaining user labels set::iterator it; @@ -260,7 +362,7 @@ int RareFactCommand::execute(){ } } - 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; } + if (m->control_pressed) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } 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) { @@ -268,7 +370,7 @@ int RareFactCommand::execute(){ order = (input->getOrderVector(lastLabel)); m->mothurOut(order->getLabel()); m->mothurOutEndLine(); - rCurve = new Rarefact(order, rDisplays); + rCurve = new Rarefact(order, rDisplays, processors); rCurve->getCurve(freq, nIters); delete rCurve; @@ -285,6 +387,8 @@ int RareFactCommand::execute(){ } + if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } m->mothurOutEndLine(); @@ -315,7 +419,7 @@ vector RareFactCommand::parseSharedFile(string filename) { input = globaldata->ginput; vector lookup = input->getSharedRAbundVectors(); - string sharedFileRoot = getRootName(filename); + string sharedFileRoot = m->getRootName(filename); //clears file before we start to write to it below for (int i=0; i RareFactCommand::parseSharedFile(string filename) { for (int i = 0; i < lookup.size(); i++) { RAbundVector rav = lookup[i]->getRAbundVector(); - openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()])); + m->openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()])); rav.print(*(filehandles[lookup[i]->getGroup()])); (*(filehandles[lookup[i]->getGroup()])).close(); }