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);
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;
exit(1);
}
}
+//**********************************************************************************************************************
+string RareFactCommand::getOutputFileNameTag(string type, string inputName=""){
+ try {
+ string outputFileName = "";
+ map<string, vector<string> >::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 == "rarefaction") { outputFileName = "rarefaction"; }
+ else if (type == "r_chao") { outputFileName = "r_chao"; }
+ else if (type == "r_ace") { outputFileName = "r_ace"; }
+ else if (type == "r_jack") { outputFileName = "r_jack"; }
+ else if (type == "r_shannon") { outputFileName = "r_shannon"; }
+ else if (type == "r_shannoneven") { outputFileName = "r_shannoneven"; }
+ else if (type == "r_smithwilson") { outputFileName = "r_smithwilson"; }
+ else if (type == "r_npshannon") { outputFileName = "r_npshannon"; }
+ else if (type == "r_simpson") { outputFileName = "r_simpson"; }
+ else if (type == "r_simpsoneven") { outputFileName = "r_simpsoneven"; }
+ else if (type == "r_invsimpson") { outputFileName = "r_invsimpson"; }
+ else if (type == "r_bootstrap") { outputFileName = "r_bootstrap"; }
+ else if (type == "r_coverage") { outputFileName = "r_coverage"; }
+ else if (type == "r_nseqs") { outputFileName = "r_nseqs"; }
+ 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, "RareFactCommand", "getOutputFileNameTag");
+ exit(1);
+ }
+}
//**********************************************************************************************************************
RareFactCommand::RareFactCommand(){
listfile = validParameter.validFile(parameters, "list", true);
if (listfile == "not open") { listfile = ""; abort = true; }
else if (listfile == "not found") { listfile = ""; }
- else { format = "list"; inputfile = listfile; }
+ else { format = "list"; inputfile = listfile; m->setListFile(listfile); }
sabundfile = validParameter.validFile(parameters, "sabund", true);
if (sabundfile == "not open") { sabundfile = ""; abort = true; }
else if (sabundfile == "not found") { sabundfile = ""; }
- else { format = "sabund"; inputfile = sabundfile; }
+ else { format = "sabund"; inputfile = sabundfile; m->setSabundFile(sabundfile); }
rabundfile = validParameter.validFile(parameters, "rabund", true);
if (rabundfile == "not open") { rabundfile = ""; abort = true; }
else if (rabundfile == "not found") { rabundfile = ""; }
- else { format = "rabund"; inputfile = rabundfile; }
+ else { format = "rabund"; inputfile = rabundfile; m->setRabundFile(rabundfile); }
sharedfile = validParameter.validFile(parameters, "shared", true);
if (sharedfile == "not open") { sharedfile = ""; abort = true; }
else if (sharedfile == "not found") { sharedfile = ""; }
- else { format = "sharedfile"; inputfile = sharedfile; }
+ else { format = "sharedfile"; inputfile = sharedfile; m->setSharedFile(sharedfile); }
if ((sharedfile == "") && (listfile == "") && (rabundfile == "") && (sabundfile == "")) {
//is there are current file available for any of these?
if (calc == "default") { calc = "sobs"; }
}
m->splitAtDash(calc, Estimators);
+ if (m->inUsersGroups("citation", Estimators)) {
+ ValidCalculators validCalc; validCalc.printCitations(Estimators);
+ //remove citation from list of calcs
+ for (int i = 0; i < Estimators.size(); i++) { if (Estimators[i] == "citation") { Estimators.erase(Estimators.begin()+i); break; } }
+ }
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);
}
}
if (abort == true) { if (calledHelp) { return 0; } return 2; }
+ map<string, set<int> > 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<int, string> 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++) { remove(outputNames[i].c_str()); } 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();
for (i=0; i<Estimators.size(); i++) {
if (validCalculator.isValidCalculator("rarefaction", Estimators[i]) == true) {
if (Estimators[i] == "sobs") {
- rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+"rarefaction")));
- outputNames.push_back(fileNameRoot+"rarefaction"); outputTypes["rarefaction"].push_back(fileNameRoot+"rarefaction");
+ rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("rarefaction"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("rarefaction")); outputTypes["rarefaction"].push_back(fileNameRoot+getOutputFileNameTag("rarefaction"));
}else if (Estimators[i] == "chao") {
- rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"r_chao")));
- outputNames.push_back(fileNameRoot+"r_chao"); outputTypes["r_chao"].push_back(fileNameRoot+"r_chao");
+ rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_chao"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_chao")); outputTypes["r_chao"].push_back(fileNameRoot+getOutputFileNameTag("r_chao"));
}else if (Estimators[i] == "ace") {
if(abund < 5)
abund = 10;
- rDisplays.push_back(new RareDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"r_ace")));
- outputNames.push_back(fileNameRoot+"r_ace"); outputTypes["r_ace"].push_back(fileNameRoot+"r_ace");
+ rDisplays.push_back(new RareDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_ace"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_ace")); outputTypes["r_ace"].push_back(fileNameRoot+getOutputFileNameTag("r_ace"));
}else if (Estimators[i] == "jack") {
- rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"r_jack")));
- outputNames.push_back(fileNameRoot+"r_jack"); outputTypes["r_jack"].push_back(fileNameRoot+"r_jack");
+ rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_jack"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_jack")); outputTypes["r_jack"].push_back(fileNameRoot+getOutputFileNameTag("r_jack"));
}else if (Estimators[i] == "shannon") {
- rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"r_shannon")));
- outputNames.push_back(fileNameRoot+"r_shannon"); outputTypes["r_shannon"].push_back(fileNameRoot+"r_shannon");
+ rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_shannon"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_shannon")); outputTypes["r_shannon"].push_back(fileNameRoot+getOutputFileNameTag("r_shannon"));
}else if (Estimators[i] == "shannoneven") {
- rDisplays.push_back(new RareDisplay(new ShannonEven(), new ThreeColumnFile(fileNameRoot+"r_shannoneven")));
- outputNames.push_back(fileNameRoot+"r_shannoneven"); outputTypes["r_shannoneven"].push_back(fileNameRoot+"r_shannoneven");
+ rDisplays.push_back(new RareDisplay(new ShannonEven(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_shannoneven"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_shannoneven")); outputTypes["r_shannoneven"].push_back(fileNameRoot+getOutputFileNameTag("r_shannoneven"));
}else if (Estimators[i] == "heip") {
- rDisplays.push_back(new RareDisplay(new Heip(), new ThreeColumnFile(fileNameRoot+"r_heip")));
- outputNames.push_back(fileNameRoot+"r_heip"); outputTypes["r_heip"].push_back(fileNameRoot+"r_heip");
+ rDisplays.push_back(new RareDisplay(new Heip(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_heip"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_heip")); outputTypes["r_heip"].push_back(fileNameRoot+getOutputFileNameTag("r_heip"));
}else if (Estimators[i] == "smithwilson") {
- rDisplays.push_back(new RareDisplay(new SmithWilson(), new ThreeColumnFile(fileNameRoot+"r_smithwilson")));
- outputNames.push_back(fileNameRoot+"r_smithwilson"); outputTypes["r_smithwilson"].push_back(fileNameRoot+"r_smithwilson");
+ rDisplays.push_back(new RareDisplay(new SmithWilson(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_smithwilson"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_smithwilson")); outputTypes["r_smithwilson"].push_back(fileNameRoot+getOutputFileNameTag("r_smithwilson"));
}else if (Estimators[i] == "npshannon") {
- rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+"r_npshannon")));
- outputNames.push_back(fileNameRoot+"r_npshannon"); outputTypes["r_npshannon"].push_back(fileNameRoot+"r_npshannon");
+ rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_npshannon"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_npshannon")); outputTypes["r_npshannon"].push_back(fileNameRoot+getOutputFileNameTag("r_npshannon"));
}else if (Estimators[i] == "simpson") {
- rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"r_simpson")));
- outputNames.push_back(fileNameRoot+"r_simpson"); outputTypes["r_simpson"].push_back(fileNameRoot+"r_simpson");
+ rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_simpson"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_simpson")); outputTypes["r_simpson"].push_back(fileNameRoot+getOutputFileNameTag("r_simpson"));
}else if (Estimators[i] == "simpsoneven") {
- rDisplays.push_back(new RareDisplay(new SimpsonEven(), new ThreeColumnFile(fileNameRoot+"r_simpsoneven")));
- outputNames.push_back(fileNameRoot+"r_simpsoneven"); outputTypes["r_simpsoneven"].push_back(fileNameRoot+"r_simpsoneven");
+ rDisplays.push_back(new RareDisplay(new SimpsonEven(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_simpsoneven"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_simpsoneven")); outputTypes["r_simpsoneven"].push_back(fileNameRoot+getOutputFileNameTag("r_simpsoneven"));
}else if (Estimators[i] == "invsimpson") {
- rDisplays.push_back(new RareDisplay(new InvSimpson(), new ThreeColumnFile(fileNameRoot+"r_invsimpson")));
- outputNames.push_back(fileNameRoot+"r_invsimpson"); outputTypes["r_invsimpson"].push_back(fileNameRoot+"r_invsimpson");
+ rDisplays.push_back(new RareDisplay(new InvSimpson(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_invsimpson"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_invsimpson")); outputTypes["r_invsimpson"].push_back(fileNameRoot+getOutputFileNameTag("r_invsimpson"));
}else if (Estimators[i] == "bootstrap") {
- rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+"r_bootstrap")));
- outputNames.push_back(fileNameRoot+"r_bootstrap"); outputTypes["r_bootstrap"].push_back(fileNameRoot+"r_bootstrap");
+ rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_bootstrap"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_bootstrap")); outputTypes["r_bootstrap"].push_back(fileNameRoot+getOutputFileNameTag("r_bootstrap"));
}else if (Estimators[i] == "coverage") {
- rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+"r_coverage")));
- outputNames.push_back(fileNameRoot+"r_coverage"); outputTypes["r_coverage"].push_back(fileNameRoot+"r_coverage");
+ rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_coverage"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_coverage")); outputTypes["r_coverage"].push_back(fileNameRoot+getOutputFileNameTag("r_coverage"));
}else if (Estimators[i] == "nseqs") {
- rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+"r_nseqs")));
- outputNames.push_back(fileNameRoot+"r_nseqs"); outputTypes["r_nseqs"].push_back(fileNameRoot+"r_nseqs");
+ rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(fileNameRoot+getOutputFileNameTag("r_nseqs"))));
+ outputNames.push_back(fileNameRoot+getOutputFileNameTag("r_nseqs")); outputTypes["r_nseqs"].push_back(fileNameRoot+getOutputFileNameTag("r_nseqs"));
}
+ if (inputFileNames.size() > 1) { file2Group[outputNames.size()-1] = groups[p]; }
}
}
set<string> processedLabels;
set<string> userLabels = labels;
- if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; delete order; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; delete order; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//as long as you are not at the end of the file or done wih the lines you want
while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
- if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; delete order; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; delete order; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
if(allLines == 1 || labels.count(order->getLabel()) == 1){
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
- rCurve = new Rarefact(order, rDisplays, processors);
+ map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
+ set<int> ends;
+ if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
+ rCurve = new Rarefact(order, rDisplays, processors, ends);
rCurve->getCurve(freq, nIters);
delete rCurve;
order = (input->getOrderVector(lastLabel));
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
- rCurve = new Rarefact(order, rDisplays, processors);
+ map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
+ set<int> ends;
+ if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
+ rCurve = new Rarefact(order, rDisplays, processors, ends);
+
rCurve->getCurve(freq, nIters);
delete rCurve;
order = (input->getOrderVector());
}
- if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//output error messages about any remaining user labels
set<string>::iterator it;
}
}
- if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete input; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//run last label if you need to
if (needToRun == true) {
order = (input->getOrderVector(lastLabel));
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
- rCurve = new Rarefact(order, rDisplays, processors);
+ map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
+ set<int> ends;
+ if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
+ rCurve = new Rarefact(order, rDisplays, processors, ends);
+
rCurve->getCurve(freq, nIters);
delete rCurve;
}
- 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; }
+
+ //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();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
}
}
//**********************************************************************************************************************
-vector<string> RareFactCommand::parseSharedFile(string filename) {
+vector<string> RareFactCommand::createGroupFile(vector<string>& outputNames, map<int, string> file2Group) {
+ try {
+
+ vector<string> newFileNames;
+
+ //find different types of files
+ map<string, map<string, string> > typesFiles;
+ map<string, vector< vector<string> > > fileLabels; //combofile name to labels. each label is a vector because it may be unique lci hci.
+ vector<string> 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<string> theseLabels;
+ while(!iss.eof()) { iss >> newLabel; m->gobble(iss); theseLabels.push_back(newLabel); }
+ vector< vector<string> > allLabels;
+ vector<string> 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<string, map<string, string> >::iterator itfind = typesFiles.find(extension);
+ if (itfind != typesFiles.end()) {
+ (itfind->second)[outputNames[i]] = file2Group[i];
+ }else {
+ map<string, string> 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<string, map<string, string> >::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<string, string> thisTypesFiles = it->second; //it->second maps filename to group
+ set<int> numSampledSet;
+
+ //open each type summary file
+ map<string, map<int, vector< vector<string> > > > files; //maps file name to lines in file
+ int maxLines = 0;
+ for (map<string, string>::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<int, vector< vector<string> > > thisFilesLines;
+ while (!temp.eof()){
+ int numSampled = 0;
+ temp >> numSampled; m->gobble(temp);
+
+ vector< vector<string> > theseReads;
+ vector<string> 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<string> 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<int>::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<string, map<int, vector< vector<string> > > >::iterator itFileNameGroup = files.begin(); itFileNameGroup != files.end(); itFileNameGroup++) {
+
+ string group = itFileNameGroup->first;
+
+ map<int, vector< vector<string> > >::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<string> RareFactCommand::parseSharedFile(string filename, map<string, set<int> >& label2Ends) {
try {
vector<string> filenames;
//clears file before we start to write to it below
for (int i=0; i<lookup.size(); i++) {
- remove((sharedFileRoot + lookup[i]->getGroup() + ".rabund").c_str());
+ m->mothurRemove((sharedFileRoot + lookup[i]->getGroup() + ".rabund"));
filenames.push_back((sharedFileRoot + lookup[i]->getGroup() + ".rabund"));
}
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]; }
}
delete input;
- m->Groups.clear();
+ m->clearGroups();
return filenames;
}
projects / mothur.git / blobdiff