X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=mergegroupscommand.cpp;h=0ddc3d477336d34340497b82121cb0c032c9067b;hp=60b9c85481a2d455d53ab4b13a3bd46cfaf5a389;hb=cf9987b67aa49777a4c91c2d21f96e58bf17aa82;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677 diff --git a/mergegroupscommand.cpp b/mergegroupscommand.cpp index 60b9c85..0ddc3d4 100644 --- a/mergegroupscommand.cpp +++ b/mergegroupscommand.cpp @@ -11,50 +11,75 @@ #include "sharedutilities.h" //********************************************************************************************************************** -vector MergeGroupsCommand::getValidParameters(){ +vector MergeGroupsCommand::setParameters(){ try { - string Array[] = {"shared","label","outputdir","design","groups","processors","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none","shared",false,false,true); parameters.push_back(pshared); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "none","group",false,false,true); parameters.push_back(pgroup); + CommandParameter pdesign("design", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(pdesign); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + 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); } return myArray; } catch(exception& e) { - m->errorOut(e, "MergeGroupsCommand", "getValidParameters"); + m->errorOut(e, "MergeGroupsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -MergeGroupsCommand::MergeGroupsCommand(){ +string MergeGroupsCommand::getHelpString(){ try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["shared"] = tempOutNames; + string helpString = ""; + helpString += "The merge.groups command reads a shared or group file and a design file and merges the groups that are in the same grouping in the design file.\n"; + helpString += "The merge.groups command outputs a .shared file. \n"; + helpString += "The merge.groups command parameters are shared, group, groups, label and design. The design parameter is required.\n"; + helpString += "The design parameter allows you to assign your groups to sets. It is required. \n"; + helpString += "The design file looks like the group file. It is a 2 column tab delimited file, where the first column is the group name and the second column is the set the group belongs to.\n"; + helpString += "The groups parameter allows you to specify which of the groups in your shared or group file you would like included. The group names are separated by dashes.\n"; + helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n"; + helpString += "The merge.groups command should be in the following format: merge.groups(design=yourDesignFile, shared=yourSharedFile).\n"; + helpString += "Example merge.groups(design=temp.design, groups=A-B-C, shared=temp.shared).\n"; + helpString += "The default value for groups is all the groups in your sharedfile, and all labels in your inputfile will be used.\n"; + helpString += "Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "MergeGroupsCommand", "MetaStatsCommand"); + m->errorOut(e, "MergeGroupsCommand", "getHelpString"); exit(1); } } + //********************************************************************************************************************** -vector MergeGroupsCommand::getRequiredParameters(){ - try { - string Array[] = {"design", "shared"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "MergeGroupsCommand", "getRequiredParameters"); - exit(1); - } +string MergeGroupsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "shared") { pattern = "[filename],merge,[extension]"; } + else if (type == "group") { pattern = "[filename],merge,[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, "MergeGroupsCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** -vector MergeGroupsCommand::getRequiredFiles(){ +MergeGroupsCommand::MergeGroupsCommand(){ try { - string Array[] = {}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["shared"] = tempOutNames; + outputTypes["group"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "MergeGroupsCommand", "getRequiredFiles"); + m->errorOut(e, "MergeGroupsCommand", "MetaStatsCommand"); exit(1); } } @@ -62,18 +87,15 @@ vector MergeGroupsCommand::getRequiredFiles(){ MergeGroupsCommand::MergeGroupsCommand(string option) { try { - globaldata = GlobalData::getInstance(); abort = false; calledHelp = false; allLines = 1; - labels.clear(); //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 AlignArray[] = {"groups","label","outputdir","shared","design","processors","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -89,6 +111,7 @@ MergeGroupsCommand::MergeGroupsCommand(string option) { //initialize outputTypes vector tempOutNames; outputTypes["shared"] = tempOutNames; + outputTypes["group"] = 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 = ""; } @@ -113,17 +136,36 @@ MergeGroupsCommand::MergeGroupsCommand(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("group"); + //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["group"] = inputDir + it->second; } + } + } //check for required parameters designfile = validParameter.validFile(parameters, "design", true); if (designfile == "not open") { abort = true; } - else if (designfile == "not found") { designfile = ""; m->mothurOut("You must provide a design file."); m->mothurOutEndLine(); abort = true; } + else if (designfile == "not found") { + //if there is a current shared file, use it + 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 designfile and the design parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setDesignFile(designfile); } - //make sure the user has already run the read.otu command sharedfile = validParameter.validFile(parameters, "shared", true); - if (sharedfile == "not open") { abort = true; } - else if (sharedfile == "not found") { sharedfile = ""; m->mothurOut("You must provide a shared file."); m->mothurOutEndLine(); abort = true; } + if (sharedfile == "not open") { abort = true; sharedfile = ""; } + else if (sharedfile == "not found") { sharedfile = ""; } + else { m->setSharedFile(sharedfile); } + + groupfile = validParameter.validFile(parameters, "group", true); + if (groupfile == "not open") { abort = true; groupfile = ""; } + else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -137,7 +179,20 @@ MergeGroupsCommand::MergeGroupsCommand(string option) { groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = "all"; } m->splitAtDash(groups, Groups); - globaldata->Groups = Groups; + m->setGroups(Groups); + + if ((sharedfile == "") && (groupfile == "")) { + //give priority to group, then shared + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { + 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; + } + } + } } } @@ -146,51 +201,115 @@ MergeGroupsCommand::MergeGroupsCommand(string option) { exit(1); } } - //********************************************************************************************************************** -void MergeGroupsCommand::help(){ +int MergeGroupsCommand::execute(){ try { - m->mothurOut("The merge.groups command reads a shared file and a design file and merges the groups in the shared file that are in the same grouping in the design file.\n"); - m->mothurOut("The merge.groups command outputs a .shared file. \n"); - m->mothurOut("The merge.groups command parameters are shared, groups, label and design. The design and shared parameter are required.\n"); - m->mothurOut("The design parameter allows you to assign your groups to sets when you are running metastat. mothur will run all pairwise comparisons of the sets. It is required. \n"); - m->mothurOut("The design file looks like the group file. It is a 2 column tab delimited file, where the first column is the group name and the second column is the set the group belongs to.\n"); - m->mothurOut("The groups parameter allows you to specify which of the groups in your shared you would like included. The group names are separated by dashes.\n"); - m->mothurOut("The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n"); - m->mothurOut("The merge.groups command should be in the following format: merge.groups(design=yourDesignFile, shared=yourSharedFile).\n"); - m->mothurOut("Example merge.groups(design=temp.design, groups=A-B-C, shared=temp.shared).\n"); - m->mothurOut("The default value for groups is all the groups in your sharedfile, and all labels in your inputfile will be used.\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + designMap = new GroupMap(designfile); + designMap->readDesignMap(); + + if (groupfile != "") { processGroupFile(designMap); } + if (sharedfile != "") { processSharedFile(designMap); } + + //reset groups parameter + m->clearGroups(); + delete designMap; + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0;} + + + //set shared file as new current sharedfile + string current = ""; + itTypes = outputTypes.find("shared"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + 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) { - m->errorOut(e, "MergeGroupsCommand", "help"); + m->errorOut(e, "MergeGroupsCommand", "execute"); exit(1); } } - //********************************************************************************************************************** -MergeGroupsCommand::~MergeGroupsCommand(){} - +int MergeGroupsCommand::process(vector& thisLookUp, ofstream& out){ + try { + + map merged; + map::iterator it; + + for (int i = 0; i < thisLookUp.size(); i++) { + + if (m->control_pressed) { return 0; } + + //what grouping does this group belong to + string grouping = designMap->getGroup(thisLookUp[i]->getGroup()); + if (grouping == "not found") { m->mothurOut("[ERROR]: " + thisLookUp[i]->getGroup() + " is not in your design file. Ignoring!"); m->mothurOutEndLine(); grouping = "NOTFOUND"; } + + else { + //do we already have a member of this grouping? + it = merged.find(grouping); + + if (it == merged.end()) { //nope, so create it + merged[grouping] = *thisLookUp[i]; + merged[grouping].setGroup(grouping); + }else { //yes, merge it + + for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) { + int abund = (it->second).getAbundance(j); + abund += thisLookUp[i]->getAbundance(j); + + (it->second).set(j, abund, grouping); + } + } + } + } + + //print new file + for (it = merged.begin(); it != merged.end(); it++) { + out << (it->second).getLabel() << '\t' << it->first << '\t'; + (it->second).print(out); + } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "MergeGroupsCommand", "process"); + exit(1); + } +} //********************************************************************************************************************** -int MergeGroupsCommand::execute(){ +int MergeGroupsCommand::processSharedFile(GroupMap*& designMap){ try { - if (abort == true) { if (calledHelp) { return 0; } return 2; } - - if (outputDir == "") { outputDir += m->hasPath(sharedfile); } - string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "merge" + m->getExtension(sharedfile); - outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[extension]"] = m->getExtension(sharedfile); + string outputFileName = getOutputFileName("shared", variables); + outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; m->openOutputFile(outputFileName, out); - designMap = new GroupMap(designfile); - designMap->readDesignMap(); - InputData input(sharedfile, "sharedfile"); lookup = input.getSharedRAbundVectors(); string lastLabel = lookup[0]->getLabel(); @@ -202,11 +321,13 @@ int MergeGroupsCommand::execute(){ //as long as you are not at the end of the file or done wih the lines you want while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { - if (m->control_pressed) { out.close(); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } globaldata->Groups.clear(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { out.close(); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } m->clearGroups(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + + if (!m->printedSharedHeaders) { lookup[0]->printHeaders(out); } process(lookup, out); processedLabels.insert(lookup[0]->getLabel()); @@ -220,6 +341,7 @@ int MergeGroupsCommand::execute(){ lookup = input.getSharedRAbundVectors(lastLabel); m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + if (!m->printedSharedHeaders) { lookup[0]->printHeaders(out); } process(lookup, out); processedLabels.insert(lookup[0]->getLabel()); @@ -233,13 +355,13 @@ int MergeGroupsCommand::execute(){ //prevent memory leak for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; } - if (m->control_pressed) { out.close(); globaldata->Groups.clear(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { out.close(); m->clearGroups(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } //get next line to process lookup = input.getSharedRAbundVectors(); } - if (m->control_pressed) { out.close(); globaldata->Groups.clear(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { out.close(); m->clearGroups(); delete designMap; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } //output error messages about any remaining user labels set::iterator it; @@ -261,84 +383,78 @@ int MergeGroupsCommand::execute(){ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + if (!m->printedSharedHeaders) { lookup[0]->printHeaders(out); } process(lookup, out); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } } out.close(); - //reset groups parameter - globaldata->Groups.clear(); - delete designMap; - - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0;} - - - //set shared file as new current sharedfile - string current = ""; - itTypes = outputTypes.find("shared"); - if (itTypes != outputTypes.end()) { - if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } - } - - 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) { - m->errorOut(e, "MergeGroupsCommand", "execute"); + m->errorOut(e, "MergeGroupsCommand", "processSharedFile"); exit(1); } } //********************************************************************************************************************** -int MergeGroupsCommand::process(vector& thisLookUp, ofstream& out){ +int MergeGroupsCommand::processGroupFile(GroupMap*& designMap){ try { - map merged; - map::iterator it; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); + outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); - for (int i = 0; i < thisLookUp.size(); i++) { + ofstream out; + m->openOutputFile(outputFileName, out); + + //read groupfile + GroupMap groupMap(groupfile); + groupMap.readMap(); + + //fill Groups - checks for "all" and for any typo groups + SharedUtil* util = new SharedUtil(); + vector nameGroups = groupMap.getNamesOfGroups(); + util->setGroups(Groups, nameGroups); + delete util; + + vector namesOfSeqs = groupMap.getNamesSeqs(); + bool error = false; + + for (int i = 0; i < namesOfSeqs.size(); i++) { - if (m->control_pressed) { return 0; } + if (m->control_pressed) { break; } - //what grouping does this group belong to - string grouping = designMap->getGroup(thisLookUp[i]->getGroup()); - if (grouping == "not found") { m->mothurOut("[ERROR]: " + thisLookUp[i]->getGroup() + " is not in your design file. Ignoring!"); m->mothurOutEndLine(); grouping = "NOTFOUND"; } + string thisGroup = groupMap.getGroup(namesOfSeqs[i]); - else { - //do we already have a member of this grouping? - it = merged.find(grouping); + //are you in a group the user wants + if (m->inUsersGroups(thisGroup, Groups)) { + string thisGrouping = designMap->getGroup(thisGroup); - if (it == merged.end()) { //nope, so create it - merged[grouping] = *thisLookUp[i]; - merged[grouping].setGroup(grouping); - }else { //yes, merge it - - for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) { - int abund = (it->second).getAbundance(j); - abund += thisLookUp[i]->getAbundance(j); - - (it->second).set(j, abund, grouping); - } + if (thisGrouping == "not found") { m->mothurOut("[ERROR]: " + namesOfSeqs[i] + " is from group " + thisGroup + " which is not in your design file, please correct."); m->mothurOutEndLine(); error = true; } + else { + out << namesOfSeqs[i] << '\t' << thisGrouping << endl; } } } - //print new file - for (it = merged.begin(); it != merged.end(); it++) { - out << (it->second).getLabel() << '\t' << it->first << '\t'; - (it->second).print(out); - } + if (error) { m->control_pressed = true; } + + out.close(); return 0; } catch(exception& e) { - m->errorOut(e, "MergeGroupsCommand", "process"); + m->errorOut(e, "MergeGroupsCommand", "processGroupFile"); exit(1); } }