X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=rarefactcommand.cpp;h=75a87efa3a2f95259488b0abf15887fb39ee1955;hp=82211144eda568cf86f3ca0684a67c2fe64e0bb3;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=19fcbbdba99658f5eca244803280f9ee7f9f6607 diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index 8221114..75a87ef 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -28,18 +28,19 @@ //********************************************************************************************************************** vector RareFactCommand::setParameters(){ try { - CommandParameter plist("list", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(plist); - CommandParameter prabund("rabund", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(prabund); - CommandParameter psabund("sabund", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(psabund); - CommandParameter pshared("shared", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(pshared); - CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); - CommandParameter pfreq("freq", "Number", "", "100", "", "", "",false,false); parameters.push_back(pfreq); - CommandParameter piters("iters", "Number", "", "1000", "", "", "",false,false); parameters.push_back(piters); - CommandParameter pcalc("calc", "Multiple", "sobs-chao-nseqs-coverage-ace-jack-shannon-shannoneven-npshannon-heip-smithwilson-simpson-simpsoneven-invsimpson-bootstrap", "sobs", "", "", "",true,false); parameters.push_back(pcalc); - CommandParameter pabund("abund", "Number", "", "10", "", "", "",false,false); parameters.push_back(pabund); - CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter plist("list", "InputTypes", "", "", "LRSS", "LRSS", "none","",false,false,true); parameters.push_back(plist); + CommandParameter prabund("rabund", "InputTypes", "", "", "LRSS", "LRSS", "none","",false,false); parameters.push_back(prabund); + CommandParameter psabund("sabund", "InputTypes", "", "", "LRSS", "LRSS", "none","",false,false); parameters.push_back(psabund); + CommandParameter pshared("shared", "InputTypes", "", "", "LRSS", "LRSS", "none","",false,false,true); parameters.push_back(pshared); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter pfreq("freq", "Number", "", "100", "", "", "","",false,false); parameters.push_back(pfreq); + CommandParameter piters("iters", "Number", "", "1000", "", "", "","",false,false); parameters.push_back(piters); + CommandParameter pcalc("calc", "Multiple", "sobs-chao-nseqs-coverage-ace-jack-shannon-shannoneven-npshannon-heip-smithwilson-simpson-simpsoneven-invsimpson-bootstrap", "sobs", "", "", "","",true,false,true); parameters.push_back(pcalc); + CommandParameter pabund("abund", "Number", "", "10", "", "", "","",false,false); parameters.push_back(pabund); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors); + CommandParameter pgroupmode("groupmode", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pgroupmode); + 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); } @@ -55,7 +56,7 @@ string RareFactCommand::getHelpString(){ try { ValidCalculators validCalculator; string helpString = ""; - helpString += "The rarefaction.single command parameters are list, sabund, rabund, shared, label, iters, freq, calc, processors and abund. list, sabund, rabund or shared is required unless you have a valid current file. \n"; + helpString += "The rarefaction.single command parameters are list, sabund, rabund, shared, label, iters, freq, calc, processors, groupmode and abund. list, sabund, rabund or shared is required unless you have a valid current file. \n"; helpString += "The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n"; helpString += "The processors parameter allows you to specify the number of processors to use. The default is 1.\n"; helpString += "The rarefaction.single command should be in the following format: \n"; @@ -63,6 +64,7 @@ string RareFactCommand::getHelpString(){ helpString += "Example rarefaction.single(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-rchao-race-rjack-rbootstrap-rshannon-rnpshannon-rsimpson).\n"; helpString += "The default values for iters is 1000, freq is 100, and calc is rarefaction which calculates the rarefaction curve for the observed richness.\n"; validCalculator.printCalc("rarefaction"); + helpString += "If you are running rarefaction.single with a shared file and would like your results collated in one file, set groupmode=t. (Default=true).\n"; helpString += "The label parameter is used to analyze specific labels in your input.\n"; helpString += "Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n"; return helpString; @@ -72,7 +74,34 @@ string RareFactCommand::getHelpString(){ exit(1); } } - +//********************************************************************************************************************** +string RareFactCommand::getOutputPattern(string type) { + try { + string pattern = ""; + if (type == "rarefaction") { pattern = "[filename],rarefaction"; } + else if (type == "r_chao") { pattern = "[filename],r_chao"; } + else if (type == "r_ace") { pattern = "[filename],r_ace"; } + else if (type == "r_jack") { pattern = "[filename],r_jack"; } + else if (type == "r_shannon") { pattern = "[filename],r_shannon"; } + else if (type == "r_shannoneven") { pattern = "[filename],r_shannoneven"; } + else if (type == "r_smithwilson") { pattern = "[filename],r_smithwilson"; } + else if (type == "r_npshannon") { pattern = "[filename],r_npshannon"; } + else if (type == "r_simpson") { pattern = "[filename],r_simpson"; } + else if (type == "r_simpsoneven") { pattern = "[filename],r_simpsoneven"; } + else if (type == "r_invsimpson") { pattern = "[filename],r_invsimpson"; } + else if (type == "r_bootstrap") { pattern = "[filename],r_bootstrap"; } + else if (type == "r_coverage") { pattern = "[filename],r_coverage"; } + else if (type == "r_nseqs") { pattern = "[filename],r_nseqs"; } + else if (type == "r_heip") { pattern = "[filename],r_heip"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "getOutputPattern"); + exit(1); + } +} //********************************************************************************************************************** RareFactCommand::RareFactCommand(){ try { @@ -251,17 +280,20 @@ RareFactCommand::RareFactCommand(string option) { string temp; temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } - convert(temp, freq); + m->mothurConvert(temp, freq); temp = validParameter.validFile(parameters, "abund", false); if (temp == "not found") { temp = "10"; } - convert(temp, abund); + m->mothurConvert(temp, abund); temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } - convert(temp, nIters); + m->mothurConvert(temp, nIters); temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } m->setProcessors(temp); - convert(temp, processors); + m->mothurConvert(temp, processors); + + temp = validParameter.validFile(parameters, "groupmode", false); if (temp == "not found") { temp = "T"; } + groupMode = m->isTrue(temp); } } @@ -277,16 +309,18 @@ int RareFactCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } + map > labelToEnds; if ((format != "sharedfile")) { inputFileNames.push_back(inputfile); } - else { inputFileNames = parseSharedFile(sharedfile); format = "rabund"; } - - if (m->control_pressed) { return 0; } + else { inputFileNames = parseSharedFile(sharedfile, labelToEnds); format = "rabund"; } + + if (m->control_pressed) { return 0; } + map file2Group; //index in outputNames[i] -> group for (int p = 0; p < inputFileNames.size(); p++) { string fileNameRoot = outputDir + m->getRootName(m->getSimpleName(inputFileNames[p])); - if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } m->Groups.clear(); return 0; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } m->clearGroups(); return 0; } if (inputFileNames.size() > 1) { m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); @@ -294,57 +328,60 @@ int RareFactCommand::execute(){ int i; ValidCalculators validCalculator; + map variables; + variables["[filename]"] = fileNameRoot; for (i=0; i 1) { file2Group[outputNames.size()-1] = groups[p]; } } } @@ -371,7 +408,10 @@ int RareFactCommand::execute(){ if(allLines == 1 || labels.count(order->getLabel()) == 1){ m->mothurOut(order->getLabel()); m->mothurOutEndLine(); - rCurve = new Rarefact(order, rDisplays, processors); + map >::iterator itEndings = labelToEnds.find(order->getLabel()); + set ends; + if (itEndings != labelToEnds.end()) { ends = itEndings->second; } + rCurve = new Rarefact(order, rDisplays, processors, ends); rCurve->getCurve(freq, nIters); delete rCurve; @@ -386,7 +426,11 @@ int RareFactCommand::execute(){ order = (input->getOrderVector(lastLabel)); m->mothurOut(order->getLabel()); m->mothurOutEndLine(); - rCurve = new Rarefact(order, rDisplays, processors); + map >::iterator itEndings = labelToEnds.find(order->getLabel()); + set ends; + if (itEndings != labelToEnds.end()) { ends = itEndings->second; } + rCurve = new Rarefact(order, rDisplays, processors, ends); + rCurve->getCurve(freq, nIters); delete rCurve; @@ -426,7 +470,11 @@ int RareFactCommand::execute(){ order = (input->getOrderVector(lastLabel)); m->mothurOut(order->getLabel()); m->mothurOutEndLine(); - rCurve = new Rarefact(order, rDisplays, processors); + map >::iterator itEndings = labelToEnds.find(order->getLabel()); + set ends; + if (itEndings != labelToEnds.end()) { ends = itEndings->second; } + rCurve = new Rarefact(order, rDisplays, processors, ends); + rCurve->getCurve(freq, nIters); delete rCurve; @@ -440,6 +488,11 @@ int RareFactCommand::execute(){ } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + //create summary file containing all the groups data for each label - this function just combines the info from the files already created. + if ((sharedfile != "") && (groupMode)) { outputNames = createGroupFile(outputNames, file2Group); } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } m->mothurOutEndLine(); @@ -455,7 +508,165 @@ int RareFactCommand::execute(){ } } //********************************************************************************************************************** -vector RareFactCommand::parseSharedFile(string filename) { +vector RareFactCommand::createGroupFile(vector& outputNames, map file2Group) { + try { + + vector newFileNames; + + //find different types of files + map > typesFiles; + map > > fileLabels; //combofile name to labels. each label is a vector because it may be unique lci hci. + vector groupNames; + for (int i = 0; i < outputNames.size(); i++) { + + string extension = m->getExtension(outputNames[i]); + string combineFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "groups" + extension; + m->mothurRemove(combineFileName); //remove old file + + ifstream in; + m->openInputFile(outputNames[i], in); + + string labels = m->getline(in); + + istringstream iss (labels,istringstream::in); + string newLabel = ""; vector theseLabels; + while(!iss.eof()) { iss >> newLabel; m->gobble(iss); theseLabels.push_back(newLabel); } + vector< vector > allLabels; + vector thisSet; thisSet.push_back(theseLabels[0]); allLabels.push_back(thisSet); thisSet.clear(); //makes "numSampled" its own grouping + for (int j = 1; j < theseLabels.size()-1; j++) { + if (theseLabels[j+1] == "lci") { + thisSet.push_back(theseLabels[j]); + thisSet.push_back(theseLabels[j+1]); + thisSet.push_back(theseLabels[j+2]); + j++; j++; + }else{ //no lci or hci for this calc. + thisSet.push_back(theseLabels[j]); + } + allLabels.push_back(thisSet); + thisSet.clear(); + } + fileLabels[combineFileName] = allLabels; + + map >::iterator itfind = typesFiles.find(extension); + if (itfind != typesFiles.end()) { + (itfind->second)[outputNames[i]] = file2Group[i]; + }else { + map temp; + temp[outputNames[i]] = file2Group[i]; + typesFiles[extension] = temp; + } + if (!(m->inUsersGroups(file2Group[i], groupNames))) { groupNames.push_back(file2Group[i]); } + } + + //for each type create a combo file + + for (map >::iterator it = typesFiles.begin(); it != typesFiles.end(); it++) { + + ofstream out; + string combineFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "groups" + it->first; + m->openOutputFileAppend(combineFileName, out); + newFileNames.push_back(combineFileName); + map thisTypesFiles = it->second; //it->second maps filename to group + set numSampledSet; + + //open each type summary file + map > > > files; //maps file name to lines in file + int maxLines = 0; + for (map::iterator itFileNameGroup = thisTypesFiles.begin(); itFileNameGroup != thisTypesFiles.end(); itFileNameGroup++) { + + string thisfilename = itFileNameGroup->first; + string group = itFileNameGroup->second; + + ifstream temp; + m->openInputFile(thisfilename, temp); + + //read through first line - labels + m->getline(temp); m->gobble(temp); + + map > > thisFilesLines; + while (!temp.eof()){ + int numSampled = 0; + temp >> numSampled; m->gobble(temp); + + vector< vector > theseReads; + vector thisSet; thisSet.push_back(toString(numSampled)); theseReads.push_back(thisSet); thisSet.clear(); + for (int k = 1; k < fileLabels[combineFileName].size(); k++) { //output thing like 0.03-A lci-A hci-A + vector reads; + string next = ""; + for (int l = 0; l < fileLabels[combineFileName][k].size(); l++) { //output modified labels + temp >> next; m->gobble(temp); + reads.push_back(next); + } + theseReads.push_back(reads); + } + thisFilesLines[numSampled] = theseReads; + m->gobble(temp); + + numSampledSet.insert(numSampled); + } + + files[group] = thisFilesLines; + + //save longest file for below + if (maxLines < thisFilesLines.size()) { maxLines = thisFilesLines.size(); } + + temp.close(); + m->mothurRemove(thisfilename); + } + + //output new labels line + out << fileLabels[combineFileName][0][0] << '\t'; + for (int k = 1; k < fileLabels[combineFileName].size(); k++) { //output thing like 0.03-A lci-A hci-A + for (int n = 0; n < groupNames.size(); n++) { // for each group + for (int l = 0; l < fileLabels[combineFileName][k].size(); l++) { //output modified labels + out << fileLabels[combineFileName][k][l] << '-' << groupNames[n] << '\t'; + } + } + } + out << endl; + + //for each label + for (set::iterator itNumSampled = numSampledSet.begin(); itNumSampled != numSampledSet.end(); itNumSampled++) { + + out << (*itNumSampled) << '\t'; + + if (m->control_pressed) { break; } + + for (int k = 1; k < fileLabels[combineFileName].size(); k++) { //each chunk + //grab data for each group + for (map > > >::iterator itFileNameGroup = files.begin(); itFileNameGroup != files.end(); itFileNameGroup++) { + + string group = itFileNameGroup->first; + + map > >::iterator itLine = files[group].find(*itNumSampled); + if (itLine != files[group].end()) { + for (int l = 0; l < (itLine->second)[k].size(); l++) { + out << (itLine->second)[k][l] << '\t'; + + } + }else { + for (int l = 0; l < fileLabels[combineFileName][k].size(); l++) { + out << "NA" << '\t'; + } + } + } + } + out << endl; + } + out.close(); + } + + //return combine file name + return newFileNames; + + } + catch(exception& e) { + m->errorOut(e, "RareFactCommand", "createGroupFile"); + exit(1); + } +} +//********************************************************************************************************************** +vector RareFactCommand::parseSharedFile(string filename, map >& label2Ends) { try { vector filenames; @@ -487,6 +698,7 @@ vector RareFactCommand::parseSharedFile(string filename) { m->openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()])); rav.print(*(filehandles[lookup[i]->getGroup()])); (*(filehandles[lookup[i]->getGroup()])).close(); + label2Ends[lookup[i]->getLabel()].insert(rav.getNumSeqs()); } for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } @@ -499,7 +711,7 @@ vector RareFactCommand::parseSharedFile(string filename) { } delete input; - m->Groups.clear(); + m->clearGroups(); return filenames; }