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;
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 (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++) { 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();
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");
}
+ if (inputFileNames.size() > 1) { file2Group[outputNames.size()-1] = groups[p]; }
}
}
}
+ 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();
}
}
//**********************************************************************************************************************
+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, string> temp;
+ for (int i = 0; i < outputNames.size(); i++) {
+ string extension = m->getExtension(outputNames[i]);
+
+ 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'));
+
+ temp[outputNames[i]] = file2Group[i];
+ typesFiles[extension] = temp;
+
+ string combineFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + "groups" + extension;
+
+ //print headers
+ ofstream out;
+ m->openOutputFile(combineFileName, out);
+ out << newLine << endl;
+ out.close();
+
+ }
+
+ //for each type create a combo file
+ map<int, int> lineToNumber;
+ 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;
+
+ //open each type summary file
+ map<string, vector<string> > files; //maps file name to lines in file
+ int maxLines = 0;
+ int numColumns = 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);
+
+ vector<string> thisFilesLines;
+
+ thisFilesLines.push_back(group);
+ int count = 1;
+ 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);
+ }
+
+ files[thisfilename] = thisFilesLines;
+
+ //save longest file for below
+ if (maxLines < thisFilesLines.size()) { maxLines = thisFilesLines.size(); }
+
+ temp.close();
+ m->mothurRemove(thisfilename);
+ }
+
+
+ //for each label
+ for (int k = 1; k < maxLines; k++) {
+
+ //grab data for each group
+ for (map<string, string>::iterator itFileNameGroup = thisTypesFiles.begin(); itFileNameGroup != thisTypesFiles.end(); itFileNameGroup++) {
+
+ string thisfilename = itFileNameGroup->first;
+
+ map<int, int>::iterator itLine = lineToNumber.find(k);
+ if (itLine != lineToNumber.end()) {
+ string output = toString(itLine->second);
+ if (k < files[thisfilename].size()) {
+ string line = files[thisfilename][k];
+ output = line.substr(0, line.find_first_of('\t'));
+ output += '\t' + files[thisfilename][0] + '\t' + line.substr(line.find_first_of('\t'));
+ }else{
+ output += '\t' + files[thisfilename][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.close();
+
+ }
+
+ //return combine file name
+ return newFileNames;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "RareFactCommand", "createGroupFile");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
vector<string> RareFactCommand::parseSharedFile(string filename) {
try {
vector<string> filenames;
}
delete input;
- m->Groups.clear();
+ m->clearGroups();
return filenames;
}