X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rarefactsharedcommand.cpp;h=324f02852189c175ec7383d44a4e498fa4ccc7d5;hb=291eaab661778e1fd02c5c22bc388daa97bb1d54;hp=6a4fe85b76b56dd5903b98155f0b01121f0f0002;hpb=9ca2caadbeac83bb84b3330d9204b1b659d62941;p=mothur.git diff --git a/rarefactsharedcommand.cpp b/rarefactsharedcommand.cpp index 6a4fe85..324f028 100644 --- a/rarefactsharedcommand.cpp +++ b/rarefactsharedcommand.cpp @@ -13,172 +13,294 @@ //********************************************************************************************************************** -RareFactSharedCommand::RareFactSharedCommand(){ +RareFactSharedCommand::RareFactSharedCommand(string option) { try { globaldata = GlobalData::getInstance(); - string fileNameRoot; - fileNameRoot = getRootName(globaldata->inputFileName); - format = globaldata->getFormat(); - validCalculator = new ValidCalculators(); + + abort = false; + allLines = 1; + labels.clear(); + Estimators.clear(); + Groups.clear(); - int i; - for (i=0; iEstimators.size(); i++) { - if (validCalculator->isValidCalculator("sharedrarefaction", globaldata->Estimators[i]) == true) { - if (globaldata->Estimators[i] == "sharedobserved") { - rDisplays.push_back(new RareDisplay(new SharedSobs(), new SharedThreeColumnFile(fileNameRoot+"shared.rarefaction", ""))); - }else if (globaldata->Estimators[i] == "sharednseqs") { - rDisplays.push_back(new RareDisplay(new SharedNSeqs(), new SharedThreeColumnFile(fileNameRoot+"shared.r_nseqs", ""))); - } + //allow user to run help + if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"iters","freq","label","calc","groups", "jumble","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + + //check to make sure all parameters are valid for command + for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + //make sure the user has already run the read.otu command + if (globaldata->getSharedFile() == "") { + if (globaldata->getListFile() == "") { m->mothurOut("You must read a list and a group, or a shared before you can use the collect.shared command."); m->mothurOutEndLine(); abort = true; } + else if (globaldata->getGroupFile() == "") { m->mothurOut("You must read a list and a group, or a shared before you can use the collect.shared command."); m->mothurOutEndLine(); abort = true; } + } + + //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 = ""; + outputDir += hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it + } + + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + //if the user has not specified any labels use the ones from read.otu + if(label == "") { + allLines = globaldata->allLines; + labels = globaldata->labels; + } + + calc = validParameter.validFile(parameters, "calc", false); + if (calc == "not found") { calc = "sharedobserved"; } + else { + if (calc == "default") { calc = "sharedobserved"; } + } + splitAtDash(calc, Estimators); + + groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { groups = ""; } + else { + splitAtDash(groups, Groups); + } + globaldata->Groups = Groups; + + string temp; + temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } + convert(temp, freq); + + temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } + convert(temp, nIters); + + temp = validParameter.validFile(parameters, "jumble", false); if (temp == "not found") { temp = "T"; } + if (isTrue(temp)) { jumble = true; } + else { jumble = false; } + globaldata->jumble = jumble; + + if (abort == false) { + + string fileNameRoot = outputDir + getRootName(getSimpleName(globaldata->inputFileName)); +// format = globaldata->getFormat(); + + validCalculator = new ValidCalculators(); + + for (int i=0; iisValidCalculator("sharedrarefaction", Estimators[i]) == true) { + if (Estimators[i] == "sharedobserved") { + rDisplays.push_back(new RareDisplay(new SharedSobs(), new SharedThreeColumnFile(fileNameRoot+"shared.rarefaction", ""))); + outputNames.push_back(fileNameRoot+"shared.rarefaction"); + }else if (Estimators[i] == "sharednseqs") { + rDisplays.push_back(new RareDisplay(new SharedNSeqs(), new SharedThreeColumnFile(fileNameRoot+"shared.r_nseqs", ""))); + outputNames.push_back(fileNameRoot+"shared.r_nseqs"); + } + } + } } + } - - //reset calc for next command - globaldata->setCalc(""); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactSharedCommand class Function RareFactSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "RareFactSharedCommand", "RareFactSharedCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the RareFactSharedCommand class function RareFactSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} + +//********************************************************************************************************************** + +void RareFactSharedCommand::help(){ + try { + m->mothurOut("The rarefaction.shared command can only be executed after a successful read.otu command.\n"); + m->mothurOut("The rarefaction.shared command parameters are label, iters, groups, jumble and calc. No parameters are required.\n"); + m->mothurOut("The rarefaction command should be in the following format: \n"); + m->mothurOut("rarefaction.shared(label=yourLabel, iters=yourIters, calc=yourEstimators, jumble=yourJumble, groups=yourGroups).\n"); + m->mothurOut("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"); + m->mothurOut("Example rarefaction.shared(label=unique-0.01-0.03, iters=10000, groups=B-C, jumble=T, calc=sharedobserved).\n"); + m->mothurOut("The default values for iters is 1000, freq is 100, and calc is sharedobserved which calculates the shared rarefaction curve for the observed richness.\n"); + m->mothurOut("The default value for groups is all the groups in your groupfile, and jumble is true.\n"); + validCalculator->printCalc("sharedrarefaction", cout); + m->mothurOut("The label parameter is used to analyze specific labels in your input.\n"); + m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 2 valid groups.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); + } + catch(exception& e) { + m->errorOut(e, "RareFactSharedCommand", "help"); exit(1); - } - + } } //********************************************************************************************************************** RareFactSharedCommand::~RareFactSharedCommand(){ - delete order; - delete input; - delete rCurve; - delete read; + if (abort == false) { + delete input; globaldata->ginput = NULL; + delete read; + delete validCalculator; + } } //********************************************************************************************************************** int RareFactSharedCommand::execute(){ try { - int count = 1; + + if (abort == true) { return 0; } //if the users entered no valid calculators don't execute command if (rDisplays.size() == 0) { return 0; } - if (format == "sharedfile") { - read = new ReadPhilFile(globaldata->inputFileName); - read->read(&*globaldata); + read = new ReadOTUFile(globaldata->inputFileName); + read->read(&*globaldata); - input = globaldata->ginput; - order = input->getSharedOrderVector(); - }else { - //you are using a list and a groupfile - read = new ReadPhilFile(globaldata->inputFileName); - read->read(&*globaldata); + input = globaldata->ginput; + lookup = input->getSharedRAbundVectors(); + string lastLabel = lookup[0]->getLabel(); - input = globaldata->ginput; - SharedList = globaldata->gSharedList; - order = SharedList->getSharedOrderVector(); + if (m->control_pressed) { + globaldata->Groups.clear(); + for(int i=0;imothurOut("I cannot run the command without at least 2 valid groups."); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + return 0; } - //set users groups - setGroups(); - - while(order != NULL){ - - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){ - //create collectors curve - rCurve = new Rarefact(order, rDisplays); - convert(globaldata->getFreq(), freq); - convert(globaldata->getIters(), nIters); - rCurve->getSharedCurve(freq, nIters); + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. + set processedLabels; + set userLabels = labels; + + //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) { + globaldata->Groups.clear(); + for(int i=0;igetLabel()) == 1){ + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(lookup, rDisplays); + rCurve->getSharedCurve(freq, nIters); delete rCurve; - cout << order->getLabel() << '\t' << count << endl; + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + } + + if ((anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = lookup[0]->getLabel(); + + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input->getSharedRAbundVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(lookup, rDisplays); + rCurve->getSharedCurve(freq, nIters); + delete rCurve; + + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + + //restore real lastlabel to save below + lookup[0]->setLabel(saveLabel); } + + + lastLabel = lookup[0]->getLabel(); //get next line to process - if (format == "sharedfile") { - order = input->getSharedOrderVector(); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input->getSharedRAbundVectors(); + } + + if (m->control_pressed) { + globaldata->Groups.clear(); + for(int i=0;i::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; }else { - //you are using a list and a groupfile - SharedList = input->getSharedListVector(); //get new list vector to process - if (SharedList != NULL) { - order = SharedList->getSharedOrderVector(); //gets new order vector with group info. - }else { - break; - } + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } - - count++; } - + + if (m->control_pressed) { + globaldata->Groups.clear(); + for(int i=0;igetSharedRAbundVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + rCurve = new Rarefact(lookup, rDisplays); + rCurve->getSharedCurve(freq, nIters); + delete rCurve; + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + } + for(int i=0;iGroups.clear(); globaldata->setGroups(""); + globaldata->Groups.clear(); + + if (m->control_pressed) { + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + + 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) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactSharedCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "RareFactSharedCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the RareFactSharedCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** - -void RareFactSharedCommand::setGroups() { - try { - //if the user has not entered specific groups to analyze then do them all - if (globaldata->Groups.size() != 0) { - if (globaldata->Groups[0] != "all") { - //check that groups are valid - for (int i = 0; i < globaldata->Groups.size(); i++) { - if (globaldata->gGroupmap->isValidGroup(globaldata->Groups[i]) != true) { - cout << globaldata->Groups[i] << " is not a valid group, and will be disregarded." << endl; - // erase the invalid group from globaldata->Groups - globaldata->Groups.erase(globaldata->Groups.begin()+i); - } - } - - //if the user only entered invalid groups - if ((globaldata->Groups.size() == 0) || (globaldata->Groups.size() == 1)) { - cout << "When using the groups parameter you must have at least 2 valid groups. I will run the command using all the groups in your groupfile." << endl; - for (int i = 0; i < globaldata->gGroupmap->namesOfGroups.size(); i++) { - globaldata->Groups.push_back(globaldata->gGroupmap->namesOfGroups[i]); - } - } - }else{//user has enter "all" and wants the default groups - globaldata->Groups.clear(); - for (int i = 0; i < globaldata->gGroupmap->namesOfGroups.size(); i++) { - globaldata->Groups.push_back(globaldata->gGroupmap->namesOfGroups[i]); - } - globaldata->setGroups(""); - } - }else { - for (int i = 0; i < globaldata->gGroupmap->namesOfGroups.size(); i++) { - globaldata->Groups.push_back(globaldata->gGroupmap->namesOfGroups[i]); - } - } - - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the RareFactSharedCommand class Function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the RareFactSharedCommand class function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - -} -/***********************************************************/ -