X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removerarecommand.cpp;h=ded26bbae7b81082f45710c03066dd27145c95a9;hb=79a7d3273749b08d4f9f8dfe350c964ff0c4351e;hp=41355b9560e910c03be93e527524e4363b86be11;hpb=ca9ac1d80c62f57270b0dcd49410ebe08a8aecd6;p=mothur.git diff --git a/removerarecommand.cpp b/removerarecommand.cpp index 41355b9..ded26bb 100644 --- a/removerarecommand.cpp +++ b/removerarecommand.cpp @@ -20,7 +20,8 @@ vector RemoveRareCommand::setParameters(){ 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 pcount("count", "InputTypes", "", "", "CountGroup", "none", "none",false,false); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none",false,false); 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); @@ -41,7 +42,7 @@ vector RemoveRareCommand::setParameters(){ string RemoveRareCommand::getHelpString(){ try { 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 parameters are list, rabund, sabund, shared, group, count, 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"; @@ -50,7 +51,7 @@ string RemoveRareCommand::getHelpString(){ 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\n"; + helpString += "Note: No spaces between parameter labels (i.e. shared), '=' and parameters (i.e.yourSharedFile).\n"; return helpString; } catch(exception& e) { @@ -58,6 +59,32 @@ string RemoveRareCommand::getHelpString(){ exit(1); } } +//********************************************************************************************************************** +string RemoveRareCommand::getOutputFileNameTag(string type, string inputName=""){ + try { + 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 == "count") { 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", "getOutputFileNameTag"); + exit(1); + } +} + //********************************************************************************************************************** RemoveRareCommand::RemoveRareCommand(){ try { @@ -68,6 +95,7 @@ RemoveRareCommand::RemoveRareCommand(){ outputTypes["sabund"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["group"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["shared"] = tempOutNames; } catch(exception& e) { @@ -83,6 +111,7 @@ RemoveRareCommand::RemoveRareCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -105,6 +134,7 @@ RemoveRareCommand::RemoveRareCommand(string option) { outputTypes["list"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["shared"] = tempOutNames; + outputTypes["count"] = 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 = ""; } @@ -153,29 +183,51 @@ RemoveRareCommand::RemoveRareCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["shared"] = inputDir + it->second; } } + + it = parameters.find("count"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["count"] = inputDir + it->second; } + } } //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 = ""; } + else { m->setSharedFile(sharedfile); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } if ((sharedfile == "") && (listfile == "") && (rabundfile == "") && (sabundfile == "")) { //is there are current file available for any of these? @@ -214,14 +266,14 @@ 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); if (byGroup && (sharedfile == "")) { m->mothurOut("The byGroup parameter is only valid with a shared file."); m->mothurOutEndLine(); } - if ((groupfile != "") && (listfile == "")) { m->mothurOut("A groupfile is only valid with a list file."); m->mothurOutEndLine(); groupfile = ""; } + if (((groupfile != "") || (countfile != "")) && (listfile == "")) { m->mothurOut("A group or count file is only valid with a list file."); m->mothurOutEndLine(); groupfile = ""; countfile = ""; } } } @@ -245,7 +297,7 @@ 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(); @@ -279,6 +331,11 @@ int RemoveRareCommand::execute(){ if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -295,9 +352,10 @@ 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); + string outputCountFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile); + ofstream out, outGroup; m->openOutputFile(outputFileName, out); @@ -344,12 +402,21 @@ int RemoveRareCommand::processList(){ //if groupfile is given then use it GroupMap* groupMap; + CountTable ct; 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); - } + }else if (countfile != "") { + ct.readTable(countfile); + if (ct.hasGroupInfo()) { + vector namesGroups = ct.getNamesOfGroups(); + SharedUtil util; + util.setGroups(Groups, namesGroups); + } + } if (list != NULL) { @@ -359,13 +426,14 @@ 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); vector names; string saveBinNames = binnames; m->splitAtComma(binnames, names); + int binsize = names.size(); vector newGroupFile; if (groupfile != "") { @@ -381,14 +449,38 @@ int RemoveRareCommand::processList(){ saveBinNames += names[k] + ","; } } - names = newNames; + names = newNames; binsize = names.size(); saveBinNames = saveBinNames.substr(0, saveBinNames.length()-1); - } + }else if (countfile != "") { + saveBinNames = ""; + binsize = 0; + for(int k = 0; k < names.size(); k++) { + if (ct.hasGroupInfo()) { + vector thisSeqsGroups = ct.getGroups(names[k]); + + int thisSeqsCount = 0; + for (int n = 0; n < thisSeqsGroups.size(); n++) { + if (m->inUsersGroups(thisSeqsGroups[n], Groups)) { + thisSeqsCount += ct.getGroupCount(names[k], thisSeqsGroups[n]); + } + } + binsize += thisSeqsCount; + //if you don't have any seqs from the groups the user wants, then remove you. + if (thisSeqsCount == 0) { newGroupFile.push_back(names[k]); } + else { saveBinNames += names[k] + ","; } + }else { + binsize += ct.getNumSeqs(names[k]); + saveBinNames += names[k] + ","; + } + } + saveBinNames = saveBinNames.substr(0, saveBinNames.length()-1); + } - if (names.size() > nseqs) { //keep bin + if (binsize > nseqs) { //keep bin newList.push_back(saveBinNames); - for(int k = 0; k < newGroupFile.size(); k++) { outGroup << newGroupFile[k] << endl; } - } + if (groupfile != "") { for(int k = 0; k < newGroupFile.size(); k++) { outGroup << newGroupFile[k] << endl; } } + else if (countfile != "") { for(int k = 0; k < newGroupFile.size(); k++) { ct.remove(newGroupFile[k]); } } + }else { if (countfile != "") { for(int k = 0; k < names.size(); k++) { ct.remove(names[k]); } } } } //print new listvector @@ -400,6 +492,17 @@ int RemoveRareCommand::processList(){ out.close(); if (groupfile != "") { outGroup.close(); outputTypes["group"].push_back(outputGroupFileName); outputNames.push_back(outputGroupFileName); } + if (countfile != "") { + if (ct.hasGroupInfo()) { + vector allGroups = ct.getNamesOfGroups(); + for (int i = 0; i < allGroups.size(); i++) { + if (!m->inUsersGroups(allGroups[i], Groups)) { ct.removeGroup(allGroups[i]); } + } + + } + ct.printTable(outputCountFileName); + outputTypes["count"].push_back(outputCountFileName); outputNames.push_back(outputCountFileName); + } if (wroteSomething == false) { m->mothurOut("Your file contains only rare sequences."); m->mothurOutEndLine(); } outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -416,7 +519,7 @@ 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; @@ -515,7 +618,7 @@ 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; @@ -618,11 +721,11 @@ int RemoveRareCommand::processRabund(){ //********************************************************************************************************************** int RemoveRareCommand::processShared(){ try { - m->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; @@ -645,6 +748,7 @@ int RemoveRareCommand::processShared(){ processedLabels.insert(lookup[0]->getLabel()); userLabels.erase(lookup[0]->getLabel()); + if (!m->printedHeaders) { lookup[0]->printHeaders(out); } processLookup(lookup, out); } @@ -658,6 +762,7 @@ 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 @@ -692,6 +797,7 @@ 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]; }