X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removerarecommand.cpp;h=923ca72eccbd2f88bad0b36b0c15fba58f1b829c;hb=f687723a8357916e86a05116978e6869b039ce36;hp=bcb9af60d096a82b13c13efa35f4b74d54b0897b;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677;p=mothur.git diff --git a/removerarecommand.cpp b/removerarecommand.cpp index bcb9af6..923ca72 100644 --- a/removerarecommand.cpp +++ b/removerarecommand.cpp @@ -14,70 +14,104 @@ #include "inputdata.h" //********************************************************************************************************************** -vector RemoveRareCommand::getValidParameters(){ +vector RemoveRareCommand::setParameters(){ try { - string Array[] = {"rabund","sabund", "group", "list", "shared","bygroup","nseqs","groups","label","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(plist); + CommandParameter prabund("rabund", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(prabund); + CommandParameter psabund("sabund", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(psabund); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pshared); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pgroup); + CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter pnseqs("nseqs", "Number", "", "0", "", "", "",false,true); parameters.push_back(pnseqs); + CommandParameter pbygroup("bygroup", "Boolean", "", "f", "", "", "",false,true); parameters.push_back(pbygroup); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "RemoveRareCommand", "getValidParameters"); + m->errorOut(e, "RemoveRareCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -RemoveRareCommand::RemoveRareCommand(){ +string RemoveRareCommand::getHelpString(){ try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["rabund"] = tempOutNames; - outputTypes["sabund"] = tempOutNames; - outputTypes["list"] = tempOutNames; - outputTypes["group"] = tempOutNames; - outputTypes["shared"] = tempOutNames; + string helpString = ""; + helpString += "The remove.rare command parameters are list, rabund, sabund, shared, group, label, groups, bygroup and nseqs.\n"; + helpString += "The remove.rare command reads one of the following file types: list, rabund, sabund or shared file. It outputs a new file after removing the rare otus.\n"; + helpString += "The groups parameter allows you to specify which of the groups you would like analyzed. Default=all. You may separate group names with dashes.\n"; + helpString += "The label parameter is used to analyze specific labels in your input. default=all. You may separate label names with dashes.\n"; + helpString += "The bygroup parameter is only valid with the shared file. default=f, meaning remove any OTU that has nseqs or fewer sequences across all groups.\n"; + helpString += "bygroups=T means remove any OTU that has nseqs or fewer sequences in each group (if groupA has 1 sequence and group B has 100 sequences in OTUZ and nseqs=1, then set the groupA count for OTUZ to 0 and keep groupB's count at 100.) \n"; + helpString += "The nseqs parameter allows you to set the cutoff for an otu to be deemed rare. It is required.\n"; + helpString += "The remove.rare command should be in the following format: remove.rare(shared=yourSharedFile, nseqs=yourRareCutoff).\n"; + helpString += "Example remove.rare(shared=amazon.fn.shared, nseqs=2).\n"; + helpString += "Note: No spaces between parameter labels (i.e. shared), '=' and parameters (i.e.yourSharedFile).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "RemoveRareCommand", "RemoveRareCommand"); + m->errorOut(e, "RemoveRareCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector RemoveRareCommand::getRequiredParameters(){ +string RemoveRareCommand::getOutputFileNameTag(string type, string inputName=""){ try { - string Array[] = {"nseqs"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string outputFileName = ""; + map >::iterator it; + + //is this a type this command creates + it = outputTypes.find(type); + if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } + else { + if (type == "rabund") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "sabund") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "shared") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } + } + return outputFileName; } catch(exception& e) { - m->errorOut(e, "RemoveRareCommand", "getRequiredParameters"); + m->errorOut(e, "RemoveRareCommand", "getOutputFileNameTag"); exit(1); } } + //********************************************************************************************************************** -vector RemoveRareCommand::getRequiredFiles(){ +RemoveRareCommand::RemoveRareCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["rabund"] = tempOutNames; + outputTypes["sabund"] = tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["shared"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "RemoveRareCommand", "getRequiredFiles"); + m->errorOut(e, "RemoveRareCommand", "RemoveRareCommand"); exit(1); } } //********************************************************************************************************************** RemoveRareCommand::RemoveRareCommand(string option) { try { - globaldata = GlobalData::getInstance(); abort = false; calledHelp = false; allLines = 1; //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"rabund","sabund", "group", "list", "shared", "bygroup", "nseqs","groups","label","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -151,25 +185,52 @@ RemoveRareCommand::RemoveRareCommand(string option) { //check for file parameters listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } - else if (listfile == "not found") { listfile = ""; } + else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } sabundfile = validParameter.validFile(parameters, "sabund", true); if (sabundfile == "not open") { abort = true; } else if (sabundfile == "not found") { sabundfile = ""; } + else { m->setSabundFile(sabundfile); } rabundfile = validParameter.validFile(parameters, "rabund", true); if (rabundfile == "not open") { abort = true; } else if (rabundfile == "not found") { rabundfile = ""; } + else { m->setRabundFile(rabundfile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { groupfile = ""; abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } sharedfile = validParameter.validFile(parameters, "shared", true); if (sharedfile == "not open") { sharedfile = ""; abort = true; } else if (sharedfile == "not found") { sharedfile = ""; } - - if ((sabundfile == "") && (rabundfile == "") && (sharedfile == "") && (listfile == "")) { m->mothurOut("You must provide at least one of the following: rabund, sabund, shared or list."); m->mothurOutEndLine(); abort = true; } + else { m->setSharedFile(sharedfile); } + + if ((sharedfile == "") && (listfile == "") && (rabundfile == "") && (sabundfile == "")) { + //is there are current file available for any of these? + //give priority to shared, then list, then rabund, then sabund + //if there is a current shared file, use it + sharedfile = m->getSharedFile(); + if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { + listfile = m->getListFile(); + if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { + rabundfile = m->getRabundFile(); + if (rabundfile != "") { m->mothurOut("Using " + rabundfile + " as input file for the rabund parameter."); m->mothurOutEndLine(); } + else { + sabundfile = m->getSabundFile(); + if (sabundfile != "") { m->mothurOut("Using " + sabundfile + " as input file for the sabund parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current files. You must provide a list, sabund, rabund or shared file."); m->mothurOutEndLine(); + abort = true; + } + } + } + } + } groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = "all"; } @@ -184,7 +245,7 @@ RemoveRareCommand::RemoveRareCommand(string option) { string temp = validParameter.validFile(parameters, "nseqs", false); if (temp == "not found") { m->mothurOut("nseqs is a required parameter."); m->mothurOutEndLine(); abort = true; } - else { convert(temp, nseqs); } + else { m->mothurConvert(temp, nseqs); } temp = validParameter.validFile(parameters, "bygroup", false); if (temp == "not found") { temp = "f"; } byGroup = m->isTrue(temp); @@ -202,27 +263,6 @@ RemoveRareCommand::RemoveRareCommand(string option) { } //********************************************************************************************************************** -void RemoveRareCommand::help(){ - try { - m->mothurOut("The remove.rare command parameters are list, rabund, sabund, shared, group, label, groups, bygroup and nseqs.\n"); - m->mothurOut("The remove.rare command reads one of the following file types: list, rabund, sabund or shared file. It outputs a new file after removing the rare otus.\n"); - m->mothurOut("The groups parameter allows you to specify which of the groups you would like analyzed. Default=all. You may separate group names with dashes.\n"); - m->mothurOut("The label parameter is used to analyze specific labels in your input. default=all. You may separate label names with dashes.\n"); - m->mothurOut("The bygroup parameter is only valid with the shared file. default=f, meaning remove any OTU that has nseqs or fewer sequences across all groups.\n"); - m->mothurOut("bygroups=T means remove any OTU that has nseqs or fewer sequences in each group (if groupA has 1 sequence and group B has 100 sequences in OTUZ and nseqs=1, then set the groupA count for OTUZ to 0 and keep groupB's count at 100.) \n"); - m->mothurOut("The nseqs parameter allows you to set the cutoff for an otu to be deemed rare. It is required.\n"); - m->mothurOut("The remove.rare command should be in the following format: remove.rare(shared=yourSharedFile, nseqs=yourRareCutoff).\n"); - m->mothurOut("Example remove.rare(shared=amazon.fn.shared, nseqs=2).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. shared), '=' and parameters (i.e.yourSharedFile).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "RemoveRareCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int RemoveRareCommand::execute(){ try { @@ -236,7 +276,7 @@ int RemoveRareCommand::execute(){ if (listfile != "") { processList(); } if (sharedfile != "") { processShared(); } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } if (outputNames.size() != 0) { m->mothurOutEndLine(); @@ -286,9 +326,8 @@ int RemoveRareCommand::processList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); - string outputGroupFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); + string outputGroupFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile); ofstream out, outGroup; m->openOutputFile(outputFileName, out); @@ -338,7 +377,8 @@ int RemoveRareCommand::processList(){ if (groupfile != "") { groupMap = new GroupMap(groupfile); groupMap->readMap(); SharedUtil util; - util.setGroups(Groups, groupMap->namesOfGroups); + vector namesGroups = groupMap->getNamesOfGroups(); + util.setGroups(Groups, namesGroups); m->openOutputFile(outputGroupFileName, outGroup); } @@ -350,7 +390,7 @@ int RemoveRareCommand::processList(){ //for each bin for (int i = 0; i < list->getNumBins(); i++) { - if (m->control_pressed) { if (groupfile != "") { delete groupMap; outGroup.close(); remove(outputGroupFileName.c_str()); } out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { if (groupfile != "") { delete groupMap; outGroup.close(); m->mothurRemove(outputGroupFileName); } out.close(); m->mothurRemove(outputFileName); return 0; } //parse out names that are in accnos file string binnames = list->get(i); @@ -407,7 +447,7 @@ int RemoveRareCommand::processSabund(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(sabundfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sabundfile)) + "pick" + m->getExtension(sabundfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sabundfile)) + getOutputFileNameTag("sabund", sabundfile); outputTypes["sabund"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -506,7 +546,7 @@ int RemoveRareCommand::processRabund(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(rabundfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(rabundfile)) + "pick" + m->getExtension(rabundfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(rabundfile)) + getOutputFileNameTag("rabund", rabundfile); outputTypes["rabund"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -609,11 +649,11 @@ int RemoveRareCommand::processRabund(){ //********************************************************************************************************************** int RemoveRareCommand::processShared(){ try { - globaldata->Groups = Groups; + m->setGroups(Groups); string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + "pick" + m->getExtension(sharedfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + getOutputFileNameTag("shared", sharedfile); outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -636,6 +676,7 @@ int RemoveRareCommand::processShared(){ processedLabels.insert(lookup[0]->getLabel()); userLabels.erase(lookup[0]->getLabel()); + if (!m->printedHeaders) { lookup[0]->printHeaders(out); } processLookup(lookup, out); } @@ -649,6 +690,7 @@ int RemoveRareCommand::processShared(){ processedLabels.insert(lookup[0]->getLabel()); userLabels.erase(lookup[0]->getLabel()); + if (!m->printedHeaders) { lookup[0]->printHeaders(out); } processLookup(lookup, out); //restore real lastlabel to save below @@ -683,6 +725,7 @@ int RemoveRareCommand::processShared(){ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + if (!m->printedHeaders) { lookup[0]->printHeaders(out); } processLookup(lookup, out); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }