X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=summarycommand.cpp;h=032282411f60905990f59dc0275259266e86d7e7;hb=315e38cf393c82be238da5b32574f225a020d25c;hp=731a4101eaff0b6b5712caf15bf7a0ad6feb6e62;hpb=e911fa88572a16ef40e0b51fb132ab6e02370797;p=mothur.git diff --git a/summarycommand.cpp b/summarycommand.cpp index 731a410..0322824 100644 --- a/summarycommand.cpp +++ b/summarycommand.cpp @@ -36,16 +36,15 @@ SummaryCommand::SummaryCommand(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[] = {"line","label","calc","abund","size"}; + string Array[] = {"label","calc","abund","size","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -59,17 +58,16 @@ SummaryCommand::SummaryCommand(string option){ } //make sure the user has already run the read.otu command - if ((globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { mothurOut("You must read a list, sabund or rabund before you can use the summary.single command."); mothurOutEndLine(); 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 summary.single command."); mothurOutEndLine(); 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 + } + //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); if (label == "not found") { label = ""; } else { @@ -77,13 +75,10 @@ SummaryCommand::SummaryCommand(string option){ else { allLines = 1; } } - //make sure user did not use both the line and label parameters - if ((line != "") && (label != "")) { mothurOut("You cannot use both the line and label parameters at the same time. "); mothurOutEndLine(); 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); @@ -100,62 +95,7 @@ SummaryCommand::SummaryCommand(string option){ temp = validParameter.validFile(parameters, "size", false); if (temp == "not found") { temp = "0"; } convert(temp, size); - if (abort == false) { - - validCalculator = new ValidCalculators(); - int i; - - for (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)); - } - } - } - } } - - } catch(exception& e) { errorOut(e, "SummaryCommand", "SummaryCommand"); @@ -168,14 +108,14 @@ 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, line, calc, abund. No parameters are required, but you may not use \n"); - mothurOut("both the line and label parameters at the same time. The summary.single command should be in the following format: \n"); - mothurOut("summary.single(label=yourLabel, line=yourLines, calc=yourEstimators).\n"); - mothurOut("Example summary.single(label=unique-.01-.03, line=0,5,10, calc=sobs-chao-ace-jack-bootstrap-shannon-npshannon-simpson).\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 and line parameters are used to analyze specific lines in your input.\n"); - mothurOut("Note: No spaces between parameter labels (i.e. line), '=' and parameters (i.e.yourLines).\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. label), '=' and parameters (i.e.yourLabels).\n\n"); } catch(exception& e) { errorOut(e, "SummaryCommand", "help"); @@ -185,14 +125,7 @@ void SummaryCommand::help(){ //********************************************************************************************************************** -SummaryCommand::~SummaryCommand(){ - if (abort == false) { - delete input; globaldata->ginput = NULL; - delete read; - delete validCalculator; - globaldata->sabund = NULL; - } -} +SummaryCommand::~SummaryCommand(){} //********************************************************************************************************************** @@ -201,64 +134,162 @@ int SummaryCommand::execute(){ if (abort == true) { return 0; } - int count = 1; - - //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 ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); - - sabund = globaldata->sabund; - string lastLabel = sabund->getLabel(); - input = globaldata->ginput; + if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } + else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } - for(int i=0;igetCols() == 1){ - outputFileHandle << '\t' << sumCalculators[i]->getName(); + for (int p = 0; p < inputFileNames.size(); p++) { + + string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p])) + "summary"; + globaldata->inputFileName = inputFileNames[p]; + + if (inputFileNames.size() > 1) { + mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine(); } - else{ - outputFileHandle << '\t' << sumCalculators[i]->getName() << "\t" << sumCalculators[i]->getName() << "_lci\t" << sumCalculators[i]->getName() << "_hci"; + + sumCalculators.clear(); + + 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)); + } + } } - } - 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; - set userLines = lines; - - while((sabund != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) { - if(allLines == 1 || lines.count(count) == 1 || labels.count(sabund->getLabel()) == 1){ - - mothurOut(sabund->getLabel()); mothurOutEndLine(); - processedLabels.insert(sabund->getLabel()); - userLabels.erase(sabund->getLabel()); - userLines.erase(count); - - - outputFileHandle << sabund->getLabel(); - for(int i=0;i data = sumCalculators[i]->getValues(sabund); - outputFileHandle << '\t'; - sumCalculators[i]->print(outputFileHandle); + //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; } + 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; - if ((anyLabelsToProcess(sabund->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + 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(); - processedLabels.insert(sabund->getLabel()); - userLabels.erase(sabund->getLabel()); - outputFileHandle << sabund->getLabel(); for(int i=0;i data = sumCalculators[i]->getValues(sabund); @@ -266,52 +297,81 @@ int SummaryCommand::execute(){ sumCalculators[i]->print(outputFileHandle); } outputFileHandle << endl; - } - - lastLabel = sabund->getLabel(); + delete sabund; + } - delete sabund; - sabund = input->getSAbundVector(); - count++; + outputFileHandle.close(); + + delete input; globaldata->ginput = NULL; + delete read; + delete validCalculator; + globaldata->sabund = NULL; } - //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(); - } - } + return 0; + } + catch(exception& e) { + errorOut(e, "SummaryCommand", "execute"); + exit(1); + } +} +//********************************************************************************************************************** +vector SummaryCommand::parseSharedFile(string filename) { + try { + vector filenames; - //run last line if you need to - if (needToRun == true) { - if (sabund != NULL) { delete sabund; } - sabund = input->getSAbundVector(lastLabel); + map filehandles; + map::iterator it3; + + + //read first line + read = new ReadOTUFile(filename); + read->read(&*globaldata); - mothurOut(sabund->getLabel()); mothurOutEndLine(); - outputFileHandle << sabund->getLabel(); - for(int i=0;i data = sumCalculators[i]->getValues(sabund); - outputFileHandle << '\t'; - sumCalculators[i]->print(outputFileHandle); - } - outputFileHandle << endl; - delete sabund; + 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")); } - outputFileHandle.close(); + ofstream* temp; + for (int i=0; igetGroup()] = temp; + groups.push_back(lookup[i]->getGroup()); + } + + while(lookup[0] != NULL) { - return 0; + 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", "execute"); + errorOut(e, "SummaryCommand", "parseSharedFile"); exit(1); } } - //**********************************************************************************************************************