X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=removegroupscommand.cpp;h=64f9ab6822301310e975e6bbe58736e953eed4f2;hp=49674f57ea9c11a46bd987e587e3678b10fb1c4b;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=ecd4f324189cf1cb49a3eb49d5cff58562f27b7f diff --git a/removegroupscommand.cpp b/removegroupscommand.cpp index 49674f5..64f9ab6 100644 --- a/removegroupscommand.cpp +++ b/removegroupscommand.cpp @@ -16,17 +16,18 @@ //********************************************************************************************************************** vector RemoveGroupsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta); - CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared); - CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup); - CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign); - CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos); - CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT","fasta",false,false,true); parameters.push_back(pfasta); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none","shared",false,false,true); parameters.push_back(pshared); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","name",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false,true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT","group",false,false,true); parameters.push_back(pgroup); + CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT","design",false,false); parameters.push_back(pdesign); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT","list",false,false,true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT","taxonomy",false,false,true); parameters.push_back(ptaxonomy); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); + 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); } @@ -41,9 +42,9 @@ vector RemoveGroupsCommand::setParameters(){ string RemoveGroupsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or sharedfile.\n"; + helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, count, list, taxonomy, design or sharedfile.\n"; helpString += "It outputs a file containing the sequences NOT in the those specified groups, or with a sharedfile eliminates the groups you selected.\n"; - helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group parameter is required, unless you have a current group file or are using a sharedfile.\n"; + helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group or count parameter is required, unless you have a current group or count file or are using a sharedfile.\n"; helpString += "You must also provide an accnos containing the list of groups to remove or set the groups parameter to the groups you wish to remove.\n"; helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like removed. You can separate group names with dashes.\n"; helpString += "The remove.groups command should be in the following format: remove.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n"; @@ -57,7 +58,28 @@ string RemoveGroupsCommand::getHelpString(){ exit(1); } } - +//********************************************************************************************************************** +string RemoveGroupsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "name") { pattern = "[filename],pick,[extension]"; } + else if (type == "group") { pattern = "[filename],pick,[extension]"; } + else if (type == "count") { pattern = "[filename],pick,[extension]"; } + else if (type == "list") { pattern = "[filename],pick,[extension]"; } + else if (type == "shared") { pattern = "[filename],[tag],pick,[extension]"; } + else if (type == "design") { pattern = "[filename],pick,[extension]"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "RemoveGroupsCommand", "getOutputPattern"); + exit(1); + } +} //********************************************************************************************************************** RemoveGroupsCommand::RemoveGroupsCommand(){ try { @@ -71,6 +93,7 @@ RemoveGroupsCommand::RemoveGroupsCommand(){ outputTypes["list"] = tempOutNames; outputTypes["shared"] = tempOutNames; outputTypes["design"] = tempOutNames; + outputTypes["count"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand"); @@ -109,6 +132,7 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { outputTypes["list"] = tempOutNames; outputTypes["shared"] = tempOutNames; outputTypes["design"] = tempOutNames; + outputTypes["count"] = tempOutNames; //if the user changes the output directory command factory will send this info to us in the output parameter @@ -182,6 +206,14 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["design"] = 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; } + } } @@ -233,12 +265,22 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { else if (sharedfile == "not found") { sharedfile = ""; } else { m->setSharedFile(sharedfile); } - groupfile = validParameter.validFile(parameters, "group", true); - if (groupfile == "not open") { groupfile = ""; abort = true; } - else if (groupfile == "not found") { groupfile = ""; } - else { m->setGroupFile(groupfile); } - if ((sharedfile == "") && (groupfile == "") && (designfile == "")) { + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((namefile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true; + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } + + + if ((sharedfile == "") && (groupfile == "") && (designfile == "") && (countfile == "")) { //is there are current file available for any of these? if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) { //give priority to group, then shared @@ -248,7 +290,11 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { sharedfile = m->getSharedFile(); if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } else { - m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true; + countfile = m->getCountTableFile(); + if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true; + } } } }else { @@ -262,7 +308,12 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { designfile = m->getDesignFile(); if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); } else { - m->mothurOut("You have no current groupfile or sharedfile or designfile and one is required."); m->mothurOutEndLine(); abort = true; + countfile = m->getCountTableFile(); + if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile, designfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true; + } + } } } @@ -271,14 +322,15 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file containing group names or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (sharedfile == "") && (designfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design or list."); m->mothurOutEndLine(); abort = true; } - if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; } - - if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ - vector files; files.push_back(fastafile); files.push_back(taxfile); - parser.getNameFile(files); - } - + if ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design, count or list."); m->mothurOutEndLine(); abort = true; } + if (((groupfile == "") && (countfile == "")) && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group or count file."); m->mothurOutEndLine(); abort = true; } + + if (countfile == "") { + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } + } } } @@ -295,7 +347,7 @@ int RemoveGroupsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //get groups you want to remove - if (accnosfile != "") { readAccnos(); } + if (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); } if (groupfile != "") { groupMap = new GroupMap(groupfile); @@ -303,16 +355,45 @@ int RemoveGroupsCommand::execute(){ //make sure groups are valid //takes care of user setting groupNames that are invalid or setting groups=all - SharedUtil* util = new SharedUtil(); vector namesGroups = groupMap->getNamesOfGroups(); - util->setGroups(Groups, namesGroups); - delete util; - + vector checkedGroups; + for (int i = 0; i < Groups.size(); i++) { + if (m->inUsersGroups(Groups[i], namesGroups)) { checkedGroups.push_back(Groups[i]); } + else { m->mothurOut("[WARNING]: " + Groups[i] + " is not a valid group in your groupfile, ignoring.\n"); } + } + + if (checkedGroups.size() == 0) { m->mothurOut("[ERROR]: no valid groups, aborting.\n"); delete groupMap; return 0; } + else { + Groups = checkedGroups; + m->setGroups(Groups); + } + //fill names with names of sequences that are from the groups we want to remove fillNames(); delete groupMap; - } + }else if (countfile != ""){ + if ((fastafile != "") || (listfile != "") || (taxfile != "")) { + m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n"); + } + CountTable ct; + ct.readTable(countfile, true); + if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; } + + vector gNamesOfGroups = ct.getNamesOfGroups(); + SharedUtil util; + util.setGroups(Groups, gNamesOfGroups); + vector namesOfSeqs = ct.getNamesOfSeqs(); + sort(Groups.begin(), Groups.end()); + + for (int i = 0; i < namesOfSeqs.size(); i++) { + vector thisSeqsGroups = ct.getGroups(namesOfSeqs[i]); + if (m->isSubset(Groups, thisSeqsGroups)) { //you only have seqs from these groups so remove you + names.insert(namesOfSeqs[i]); + } + } + } + if (m->control_pressed) { return 0; } @@ -320,6 +401,7 @@ int RemoveGroupsCommand::execute(){ if (namefile != "") { readName(); } if (fastafile != "") { readFasta(); } if (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } if (sharedfile != "") { readShared(); } @@ -369,6 +451,11 @@ int RemoveGroupsCommand::execute(){ if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); } } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -385,7 +472,10 @@ int RemoveGroupsCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -446,6 +536,10 @@ int RemoveGroupsCommand::readShared(){ //that way we can take advantage of the reads in inputdata and sharedRabundVector InputData* tempInput = new InputData(sharedfile, "sharedfile"); vector lookup = tempInput->getSharedRAbundVectors(); + + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[extension]"] = m->getExtension(sharedfile); //save m->Groups vector allGroupsNames = m->getAllGroups(); @@ -465,7 +559,6 @@ int RemoveGroupsCommand::readShared(){ delete tempInput; m->setGroups(groupsToKeep); m->clearAllGroups(); - m->names.clear(); m->saveNextLabel = ""; m->printedHeaders = false; m->currentBinLabels.clear(); @@ -478,7 +571,8 @@ int RemoveGroupsCommand::readShared(){ while(lookup[0] != NULL) { - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".pick" + m->getExtension(sharedfile); + variables["[tag]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("shared", variables); ofstream out; m->openOutputFile(outputFileName, out); outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -526,7 +620,11 @@ int RemoveGroupsCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + string outputFileName = getOutputFileName("list", variables); + ofstream out; m->openOutputFile(outputFileName, out); @@ -616,8 +714,10 @@ int RemoveGroupsCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); - + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -697,8 +797,10 @@ int RemoveGroupsCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); - + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -740,11 +842,98 @@ int RemoveGroupsCommand::readGroup(){ } } //********************************************************************************************************************** +int RemoveGroupsCommand::readCount(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(countfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[extension]"] = m->getExtension(countfile); + string outputFileName = getOutputFileName("count", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(countfile, in); + + bool wroteSomething = false; + int removedCount = 0; + + string headers = m->getline(in); m->gobble(in); + vector columnHeaders = m->splitWhiteSpace(headers); + + vector groups; + map originalGroupIndexes; + map GroupIndexes; + set indexOfGroupsChosen; + for (int i = 2; i < columnHeaders.size(); i++) { groups.push_back(columnHeaders[i]); originalGroupIndexes[i-2] = columnHeaders[i]; } + //sort groups to keep consistent with how we store the groups in groupmap + sort(groups.begin(), groups.end()); + for (int i = 0; i < groups.size(); i++) { GroupIndexes[groups[i]] = i; } + + vector groupsToKeep; + for (int i = 0; i < groups.size(); i++) { + if (!m->inUsersGroups(groups[i], Groups)) { groupsToKeep.push_back(groups[i]); } + } + sort(groupsToKeep.begin(), groupsToKeep.end()); + out << "Representative_Sequence\ttotal\t"; + for (int i = 0; i < groupsToKeep.size(); i++) { out << groupsToKeep[i] << '\t'; indexOfGroupsChosen.insert(GroupIndexes[groupsToKeep[i]]); } + out << endl; + + string name; int oldTotal; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; m->gobble(in); in >> oldTotal; m->gobble(in); + if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + toString(oldTotal) + "\n"); } + + if (names.count(name) == 0) { + //if group info, then read it + vector selectedCounts; int thisTotal = 0; int temp; + for (int i = 0; i < groups.size(); i++) { + int thisIndex = GroupIndexes[originalGroupIndexes[i]]; + in >> temp; m->gobble(in); + if (indexOfGroupsChosen.count(thisIndex) != 0) { //we want this group + selectedCounts.push_back(temp); thisTotal += temp; + } + } + + out << name << '\t' << thisTotal << '\t'; + for (int i = 0; i < selectedCounts.size(); i++) { out << selectedCounts[i] << '\t'; } + out << endl; + + wroteSomething = true; + removedCount+= (oldTotal - thisTotal); + }else { m->getline(in); removedCount += oldTotal; } + + m->gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } + outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your count file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "RemoveGroupsCommand", "readCount"); + exit(1); + } +} +//********************************************************************************************************************** int RemoveGroupsCommand::readDesign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(designfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(designfile)) + "pick" + m->getExtension(designfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(designfile)); + variables["[extension]"] = m->getExtension(designfile); + string outputFileName = getOutputFileName("design", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -792,7 +981,10 @@ int RemoveGroupsCommand::readTax(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)); + variables["[extension]"] = m->getExtension(taxfile); + string outputFileName = getOutputFileName("taxonomy", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -838,32 +1030,6 @@ int RemoveGroupsCommand::readTax(){ } } //********************************************************************************************************************** -void RemoveGroupsCommand::readAccnos(){ - try { - Groups.clear(); - - ifstream in; - m->openInputFile(accnosfile, in); - string name; - - while(!in.eof()){ - in >> name; - - Groups.push_back(name); - - m->gobble(in); - } - in.close(); - - m->setGroups(Groups); - - } - catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "readAccnos"); - exit(1); - } -} -//********************************************************************************************************************** int RemoveGroupsCommand::fillNames(){ try { vector seqs = groupMap->getNamesSeqs();