X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=rarefactcommand.cpp;h=75a87efa3a2f95259488b0abf15887fb39ee1955;hp=b8c1c6f1a6420f8a139eb5c71b0320b87277035e;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=0ca63a8165baa0afa459e644ebe140ba496d5ba0 diff --git a/rarefactcommand.cpp b/rarefactcommand.cpp index b8c1c6f..75a87ef 100644 --- a/rarefactcommand.cpp +++ b/rarefactcommand.cpp @@ -28,19 +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 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); + 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); } @@ -56,7 +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"; @@ -74,7 +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 { @@ -282,12 +309,13 @@ 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 nameMap; + map file2Group; //index in outputNames[i] -> group for (int p = 0; p < inputFileNames.size(); p++) { string fileNameRoot = outputDir + m->getRootName(m->getSimpleName(inputFileNames[p])); @@ -296,62 +324,64 @@ int RareFactCommand::execute(){ if (inputFileNames.size() > 1) { m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); - nameMap[fileNameRoot] = groups[p]; } int i; ValidCalculators validCalculator; + map variables; + variables["[filename]"] = fileNameRoot; for (i=0; i 1) { file2Group[outputNames.size()-1] = groups[p]; } } } @@ -378,7 +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; @@ -393,7 +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; @@ -433,7 +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; @@ -450,7 +491,7 @@ 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, nameMap); } + 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; } @@ -467,124 +508,152 @@ int RareFactCommand::execute(){ } } //********************************************************************************************************************** -vector RareFactCommand::createGroupFile(vector& outputNames, map nameMap) { +vector RareFactCommand::createGroupFile(vector& outputNames, map file2Group) { try { vector newFileNames; //find different types of files - map > typesFiles; + 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); - string newLine = labels.substr(0, labels.find_first_of('\t')); - - newLine += "\tGroup" + labels.substr(labels.find_first_of('\t')); - - typesFiles[extension].push_back(outputNames[i]); - - string combineFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "groups" + extension; - - //print headers - ofstream out; - m->openOutputFile(combineFileName, out); - out << newLine << endl; - out.close(); - + + 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 - map lineToNumber; - for (map >::iterator it = typesFiles.begin(); it != typesFiles.end(); it++) { + + 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); - - vector thisTypesFiles = it->second; - + 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 + map > > > files; //maps file name to lines in file int maxLines = 0; - int numColumns = 0; - for (int i=0; i::iterator itFileNameGroup = thisTypesFiles.begin(); itFileNameGroup != thisTypesFiles.end(); itFileNameGroup++) { + + string thisfilename = itFileNameGroup->first; + string group = itFileNameGroup->second; + ifstream temp; - m->openInputFile(thisTypesFiles[i], temp); + m->openInputFile(thisfilename, temp); //read through first line - labels m->getline(temp); m->gobble(temp); - vector thisFilesLines; - string fileNameRoot = m->getRootName(thisTypesFiles[i]); - map::iterator itName = nameMap.find(fileNameRoot); - string group = ""; - if (itName != nameMap.end()) { - group = itName->second; - }else { - group = "not found" + i; - m->mothurOut("[ERROR]: can't parse filename."); m->mothurOutEndLine(); - } - - thisFilesLines.push_back(group); - int count = 1; + map > > thisFilesLines; while (!temp.eof()){ - - string thisLine = m->getline(temp); - - string numSampled = thisLine.substr(0, thisLine.find_first_of('\t')); - int num = 0; - convert(numSampled, num); - numColumns = m->getNumChar(thisLine, '\t'); - lineToNumber[count] = num; - count++; - - thisFilesLines.push_back(thisLine); - - m->gobble(temp); + 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[thisTypesFiles[i]] = thisFilesLines; + files[group] = thisFilesLines; //save longest file for below if (maxLines < thisFilesLines.size()) { maxLines = thisFilesLines.size(); } temp.close(); - m->mothurRemove(thisTypesFiles[i]); + 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 (int k = 1; k < maxLines; k++) { + for (set::iterator itNumSampled = numSampledSet.begin(); itNumSampled != numSampledSet.end(); itNumSampled++) { - //grab data for each group - for (int i=0; i::iterator itLine = lineToNumber.find(k); - if (itLine != lineToNumber.end()) { - string output = toString(itLine->second); - if (k < files[thisTypesFiles[i]].size()) { - string line = files[thisTypesFiles[i]][k]; - output = line.substr(0, line.find_first_of('\t')); - output += '\t' + files[thisTypesFiles[i]][0] + '\t' + line.substr(line.find_first_of('\t')); - }else{ - output += '\t' + files[thisTypesFiles[i]][0] + '\t'; - for (int h = 0; h < numColumns; h++) { - output += "NA\t"; - } - } - out << output << endl; - }else { m->mothurOut("[ERROR]: parsing results, cant find " + toString(k)); m->mothurOutEndLine(); } - } + 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 @@ -597,7 +666,7 @@ vector RareFactCommand::createGroupFile(vector& outputNames, map } } //********************************************************************************************************************** -vector RareFactCommand::parseSharedFile(string filename) { +vector RareFactCommand::parseSharedFile(string filename, map >& label2Ends) { try { vector filenames; @@ -629,6 +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]; }