X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rarefactcommand.cpp;h=ae28d230b419db28c36272e57fc38ac7e2feff65;hb=a537fefa3bd2c2eba7d532249375b6a11b295e25;hp=97d633278f4d43dc8b30a5e95298d2897bdabca7;hpb=315e38cf393c82be238da5b32574f225a020d25c;p=mothur.git diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index 97d6332..ae28d23 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -14,7 +14,12 @@ #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" @@ -22,20 +27,20 @@ //********************************************************************************************************************** -RareFactCommand::RareFactCommand(string option){ +RareFactCommand::RareFactCommand(string option) { try { globaldata = GlobalData::getInstance(); 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"}; + string Array[] = {"iters","freq","label","calc","abund","processors","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -51,18 +56,18 @@ RareFactCommand::RareFactCommand(string option){ //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 - 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; } + 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; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } @@ -77,7 +82,7 @@ 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"; } @@ -88,11 +93,14 @@ 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); } } catch(exception& e) { - errorOut(e, "RareFactCommand", "RareFactCommand"); + m->errorOut(e, "RareFactCommand", "RareFactCommand"); exit(1); } } @@ -100,19 +108,21 @@ RareFactCommand::RareFactCommand(string option){ void RareFactCommand::help(){ try { - 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"); + 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, 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"); + 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); - 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"); + 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) { - errorOut(e, "RareFactCommand", "help"); + m->errorOut(e, "RareFactCommand", "help"); exit(1); } } @@ -128,16 +138,23 @@ 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"); } + 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) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } return 0; } + if (inputFileNames.size() > 1) { - mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine(); + m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); } int i; validCalculator = new ValidCalculators(); @@ -147,33 +164,58 @@ 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"); }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] == "shannoneven") { + rDisplays.push_back(new RareDisplay(new ShannonEven(), new ThreeColumnFile(fileNameRoot+"r_shannoneven"))); + outputNames.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"); + }else if (Estimators[i] == "smithwilson") { + rDisplays.push_back(new RareDisplay(new SmithWilson(), new ThreeColumnFile(fileNameRoot+"r_smithwilson"))); + outputNames.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"); }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] == "simpsoneven") { + rDisplays.push_back(new RareDisplay(new SimpsonEven(), new ThreeColumnFile(fileNameRoot+"r_simpsoneven"))); + outputNames.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"); }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) { return 0; } + if (rDisplays.size() == 0) { for(int i=0;iinputFileName); read->read(&*globaldata); @@ -186,31 +228,36 @@ int RareFactCommand::execute(){ set processedLabels; set userLabels = labels; + 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) { 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){ - rCurve = new Rarefact(order, rDisplays); + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(order, rDisplays, processors); 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)) { + if ((m->anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = order->getLabel(); delete order; order = (input->getOrderVector(lastLabel)); - rCurve = new Rarefact(order, rDisplays); + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(order, rDisplays, processors); rCurve->getCurve(freq, nIters); delete rCurve; - mothurOut(order->getLabel()); mothurOutEndLine(); processedLabels.insert(order->getLabel()); userLabels.erase(order->getLabel()); @@ -224,29 +271,33 @@ int RareFactCommand::execute(){ order = (input->getOrderVector()); } + 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; bool needToRun = false; for (it = userLabels.begin(); it != userLabels.end(); it++) { - mothurOut("Your file does not include the label " + *it); + m->mothurOut("Your file does not include the label " + *it); if (processedLabels.count(lastLabel) != 1) { - mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } + 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) { if (order != NULL) { delete order; } order = (input->getOrderVector(lastLabel)); - rCurve = new Rarefact(order, rDisplays); + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(order, rDisplays, processors); rCurve->getCurve(freq, nIters); delete rCurve; - mothurOut(order->getLabel()); mothurOutEndLine(); delete order; } @@ -260,10 +311,19 @@ 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(); + 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) { - errorOut(e, "RareFactCommand", "execute"); + m->errorOut(e, "RareFactCommand", "execute"); exit(1); } } @@ -283,7 +343,7 @@ 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(); } @@ -322,7 +382,7 @@ vector RareFactCommand::parseSharedFile(string filename) { return filenames; } catch(exception& e) { - errorOut(e, "RareFactCommand", "parseSharedFile"); + m->errorOut(e, "RareFactCommand", "parseSharedFile"); exit(1); } }