X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=collectsharedcommand.cpp;h=2b6cbacd2afed90b8a23674c49171da9654a6033;hb=0470f6d037aacb3563c3f7010708120a4a67d4e6;hp=96e495a58f9dd1bdc58256baf1ae47c51a9c87b2;hpb=c196b6b4768ccb84955d773ff0f22e4994d1ba7b;p=mothur.git diff --git a/collectsharedcommand.cpp b/collectsharedcommand.cpp index 96e495a..2b6cbac 100644 --- a/collectsharedcommand.cpp +++ b/collectsharedcommand.cpp @@ -30,73 +30,149 @@ #include "sharedmorisitahorn.h" #include "sharedbraycurtis.h" #include "sharedjackknife.h" -#include "sharedwhittaker.h" +#include "whittaker.h" //********************************************************************************************************************** -CollectSharedCommand::CollectSharedCommand(){ +CollectSharedCommand::CollectSharedCommand(string option){ try { globaldata = GlobalData::getInstance(); - string fileNameRoot; - fileNameRoot = getRootName(globaldata->inputFileName); - format = globaldata->getFormat(); - validCalculator = new ValidCalculators(); - util = new SharedUtil(); + abort = false; + allLines = 1; + lines.clear(); + labels.clear(); + Estimators.clear(); + + //allow user to run help + if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"freq","line","label","calc","groups"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + parser = new OptionParser(); + parser->parse(option, parameters); delete parser; + + ValidParameters* validParameter = new ValidParameters(); - int i; - for (i=0; iEstimators.size(); i++) { - if (validCalculator->isValidCalculator("shared", globaldata->Estimators[i]) == true) { - if (globaldata->Estimators[i] == "sharedchao") { - cDisplays.push_back(new CollectDisplay(new SharedChao1(), new SharedOneColumnFile(fileNameRoot+"shared.chao"))); - }else if (globaldata->Estimators[i] == "sharedsobs") { - cDisplays.push_back(new CollectDisplay(new SharedSobsCS(), new SharedOneColumnFile(fileNameRoot+"shared.sobs"))); - }else if (globaldata->Estimators[i] == "sharedace") { - cDisplays.push_back(new CollectDisplay(new SharedAce(), new SharedOneColumnFile(fileNameRoot+"shared.ace"))); - }else if (globaldata->Estimators[i] == "jabund") { - cDisplays.push_back(new CollectDisplay(new JAbund(), new SharedOneColumnFile(fileNameRoot+"jabund"))); - }else if (globaldata->Estimators[i] == "sorabund") { - cDisplays.push_back(new CollectDisplay(new SorAbund(), new SharedOneColumnFile(fileNameRoot+"sorabund"))); - }else if (globaldata->Estimators[i] == "jclass") { - cDisplays.push_back(new CollectDisplay(new Jclass(), new SharedOneColumnFile(fileNameRoot+"jclass"))); - }else if (globaldata->Estimators[i] == "sorclass") { - cDisplays.push_back(new CollectDisplay(new SorClass(), new SharedOneColumnFile(fileNameRoot+"sorclass"))); - }else if (globaldata->Estimators[i] == "jest") { - cDisplays.push_back(new CollectDisplay(new Jest(), new SharedOneColumnFile(fileNameRoot+"jest"))); - }else if (globaldata->Estimators[i] == "sorest") { - cDisplays.push_back(new CollectDisplay(new SorEst(), new SharedOneColumnFile(fileNameRoot+"sorest"))); - }else if (globaldata->Estimators[i] == "thetayc") { - cDisplays.push_back(new CollectDisplay(new ThetaYC(), new SharedOneColumnFile(fileNameRoot+"thetayc"))); - }else if (globaldata->Estimators[i] == "thetan") { - cDisplays.push_back(new CollectDisplay(new ThetaN(), new SharedOneColumnFile(fileNameRoot+"thetan"))); - }else if (globaldata->Estimators[i] == "kstest") { - cDisplays.push_back(new CollectDisplay(new KSTest(), new SharedOneColumnFile(fileNameRoot+"kstest"))); - }else if (globaldata->Estimators[i] == "whittaker") { - cDisplays.push_back(new CollectDisplay(new Whittaker(), new SharedOneColumnFile(fileNameRoot+"whittaker"))); - }else if (globaldata->Estimators[i] == "sharednseqs") { - cDisplays.push_back(new CollectDisplay(new SharedNSeqs(), new SharedOneColumnFile(fileNameRoot+"shared.nseqs"))); - - }else if (globaldata->Estimators[i] == "ochiai") { - cDisplays.push_back(new CollectDisplay(new Ochiai(), new SharedOneColumnFile(fileNameRoot+"ochiai"))); - }else if (globaldata->Estimators[i] == "anderberg") { - cDisplays.push_back(new CollectDisplay(new Anderberg(), new SharedOneColumnFile(fileNameRoot+"anderberg"))); - }else if (globaldata->Estimators[i] == "skulczynski") { - cDisplays.push_back(new CollectDisplay(new Kulczynski(), new SharedOneColumnFile(fileNameRoot+"kulczynski"))); - }else if (globaldata->Estimators[i] == "kulczynskicody") { - cDisplays.push_back(new CollectDisplay(new KulczynskiCody(), new SharedOneColumnFile(fileNameRoot+"kulczynskicody"))); - }else if (globaldata->Estimators[i] == "lennon") { - cDisplays.push_back(new CollectDisplay(new Lennon(), new SharedOneColumnFile(fileNameRoot+"lennon"))); - }else if (globaldata->Estimators[i] == "morisitahorn") { - cDisplays.push_back(new CollectDisplay(new MorHorn(), new SharedOneColumnFile(fileNameRoot+"morisitahorn"))); - }else if (globaldata->Estimators[i] == "braycurtis") { - cDisplays.push_back(new CollectDisplay(new BrayCurtis(), new SharedOneColumnFile(fileNameRoot+"braycurtis"))); - } + //check to make sure all parameters are valid for command + for (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() == "") { cout << "You must read a list and a group, or a shared before you can use the collect.shared command." << endl; abort = true; } + else if (globaldata->getGroupFile() == "") { cout << "You must read a list and a group, or a shared before you can use the collect.shared command." << endl; abort = true; } + } + + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + line = validParameter->validFile(parameters, "line", false); + if (line == "not found") { line = ""; } + else { + if(line != "all") { splitAtDash(line, lines); allLines = 0; } + else { allLines = 1; } + } + + label = validParameter->validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + //make sure user did not use both the line and label parameters + if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; } + //if the user has not specified any line or labels use the ones from read.otu + else if((line == "") && (label == "")) { + allLines = globaldata->allLines; + labels = globaldata->labels; + lines = globaldata->lines; + } + + calc = validParameter->validFile(parameters, "calc", false); + if (calc == "not found") { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; } + else { + if (calc == "default") { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; } + } + 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); + + delete validParameter; + + if (abort == false) { + + string fileNameRoot = getRootName(globaldata->inputFileName); + format = globaldata->getFormat(); + int i; + + validCalculator = new ValidCalculators(); + util = new SharedUtil(); + + for (i=0; iisValidCalculator("shared", Estimators[i]) == true) { + if (Estimators[i] == "sharedchao") { + cDisplays.push_back(new CollectDisplay(new SharedChao1(), new SharedOneColumnFile(fileNameRoot+"shared.chao"))); + }else if (Estimators[i] == "sharedsobs") { + cDisplays.push_back(new CollectDisplay(new SharedSobsCS(), new SharedOneColumnFile(fileNameRoot+"shared.sobs"))); + }else if (Estimators[i] == "sharedace") { + cDisplays.push_back(new CollectDisplay(new SharedAce(), new SharedOneColumnFile(fileNameRoot+"shared.ace"))); + }else if (Estimators[i] == "jabund") { + cDisplays.push_back(new CollectDisplay(new JAbund(), new SharedOneColumnFile(fileNameRoot+"jabund"))); + }else if (Estimators[i] == "sorabund") { + cDisplays.push_back(new CollectDisplay(new SorAbund(), new SharedOneColumnFile(fileNameRoot+"sorabund"))); + }else if (Estimators[i] == "jclass") { + cDisplays.push_back(new CollectDisplay(new Jclass(), new SharedOneColumnFile(fileNameRoot+"jclass"))); + }else if (Estimators[i] == "sorclass") { + cDisplays.push_back(new CollectDisplay(new SorClass(), new SharedOneColumnFile(fileNameRoot+"sorclass"))); + }else if (Estimators[i] == "jest") { + cDisplays.push_back(new CollectDisplay(new Jest(), new SharedOneColumnFile(fileNameRoot+"jest"))); + }else if (Estimators[i] == "sorest") { + cDisplays.push_back(new CollectDisplay(new SorEst(), new SharedOneColumnFile(fileNameRoot+"sorest"))); + }else if (Estimators[i] == "thetayc") { + cDisplays.push_back(new CollectDisplay(new ThetaYC(), new SharedOneColumnFile(fileNameRoot+"thetayc"))); + }else if (Estimators[i] == "thetan") { + cDisplays.push_back(new CollectDisplay(new ThetaN(), new SharedOneColumnFile(fileNameRoot+"thetan"))); + }else if (Estimators[i] == "kstest") { + cDisplays.push_back(new CollectDisplay(new KSTest(), new SharedOneColumnFile(fileNameRoot+"kstest"))); + }else if (Estimators[i] == "whittaker") { + cDisplays.push_back(new CollectDisplay(new Whittaker(), new SharedOneColumnFile(fileNameRoot+"whittaker"))); + }else if (Estimators[i] == "sharednseqs") { + cDisplays.push_back(new CollectDisplay(new SharedNSeqs(), new SharedOneColumnFile(fileNameRoot+"shared.nseqs"))); + }else if (Estimators[i] == "ochiai") { + cDisplays.push_back(new CollectDisplay(new Ochiai(), new SharedOneColumnFile(fileNameRoot+"ochiai"))); + }else if (Estimators[i] == "anderberg") { + cDisplays.push_back(new CollectDisplay(new Anderberg(), new SharedOneColumnFile(fileNameRoot+"anderberg"))); + }else if (Estimators[i] == "skulczynski") { + cDisplays.push_back(new CollectDisplay(new Kulczynski(), new SharedOneColumnFile(fileNameRoot+"kulczynski"))); + }else if (Estimators[i] == "kulczynskicody") { + cDisplays.push_back(new CollectDisplay(new KulczynskiCody(), new SharedOneColumnFile(fileNameRoot+"kulczynskicody"))); + }else if (Estimators[i] == "lennon") { + cDisplays.push_back(new CollectDisplay(new Lennon(), new SharedOneColumnFile(fileNameRoot+"lennon"))); + }else if (Estimators[i] == "morisitahorn") { + cDisplays.push_back(new CollectDisplay(new MorHorn(), new SharedOneColumnFile(fileNameRoot+"morisitahorn"))); + }else if (Estimators[i] == "braycurtis") { + cDisplays.push_back(new CollectDisplay(new BrayCurtis(), new SharedOneColumnFile(fileNameRoot+"braycurtis"))); + } + } + } } } - - //reset calc for next command - globaldata->setCalc(""); } catch(exception& e) { @@ -109,6 +185,32 @@ CollectSharedCommand::CollectSharedCommand(){ } } +//********************************************************************************************************************** + +void CollectSharedCommand::help(){ + try { + cout << "The collect.shared command can only be executed after a successful read.otu command." << "\n"; + cout << "The collect.shared command parameters are label, line, freq, calc and groups. No parameters are required, but you may not use " << "\n"; + cout << "both the line and label parameters at the same time. The collect.shared command should be in the following format: " << "\n"; + cout << "collect.shared(label=yourLabel, line=yourLines, freq=yourFreq, calc=yourEstimators, groups=yourGroups)." << "\n"; + cout << "Example collect.shared(label=unique-.01-.03, line=0-5-10, freq=10, groups=B-C, calc=sharedchao-sharedace-jabund-sorensonabund-jclass-sorclass-jest-sorest-thetayc-thetan)." << "\n"; + cout << "The default values for freq is 100 and calc are sharedsobs-sharedchao-sharedace-jabund-sorensonabund-jclass-sorclass-jest-sorest-thetayc-thetan." << "\n"; + cout << "The default value for groups is all the groups in your groupfile." << "\n"; + validCalculator->printCalc("shared", cout); + cout << "The label and line parameters are used to analyze specific lines in your input." << "\n"; + cout << "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"; + cout << "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile)." << "\n" << "\n"; + + } + catch(exception& e) { + cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + exit(1); + } + catch(...) { + cout << "An unknown error has occurred in the CollectSharedCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + exit(1); + } +} //********************************************************************************************************************** @@ -118,74 +220,100 @@ CollectSharedCommand::~CollectSharedCommand(){ delete cCurve; delete read; delete util; + delete validCalculator; } //********************************************************************************************************************** int CollectSharedCommand::execute(){ try { + + if (abort == true) { return 0; } + int count = 1; //if the users entered no valid calculators don't execute command if (cDisplays.size() == 0) { return 0; } - if (format == "sharedfile") { - read = new ReadOTUFile(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 ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); - - input = globaldata->ginput; - SharedList = globaldata->gSharedList; - order = SharedList->getSharedOrderVector(); - } - set orderList; + input = globaldata->ginput; + order = input->getSharedOrderVector(); + SharedOrderVector* lastOrder = order; + //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 = globaldata->labels; + set userLines = globaldata->lines; + //set users groups util->setGroups(globaldata->Groups, globaldata->gGroupmap->namesOfGroups, "collect"); util->updateGroupIndex(globaldata->Groups, globaldata->gGroupmap->groupIndex); - while(order != NULL){ - orderList.insert(order->getLabel()); + while((order != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) { + if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){ + //create collectors curve cCurve = new Collect(order, cDisplays); - convert(globaldata->getFreq(), freq); cCurve->getSharedCurve(freq); - delete cCurve; cout << order->getLabel() << '\t' << count << endl; + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); + userLines.erase(count); + + //you have a label the user want that is smaller than this line and the last line has not already been processed } + if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastOrder->getLabel()) != 1)) { + //create collectors curve + cCurve = new Collect(lastOrder, cDisplays); + cCurve->getSharedCurve(freq); + delete cCurve; + + cout << lastOrder->getLabel() << '\t' << count << endl; + processedLabels.insert(lastOrder->getLabel()); + userLabels.erase(lastOrder->getLabel()); + } + + if (count != 1) { delete lastOrder; } + lastOrder = order; + //get next line to process - if (format == "sharedfile") { - order = input->getSharedOrderVector(); + order = input->getSharedOrderVector(); + count++; + } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + cout << "Your file does not include the label "<< *it; + if (processedLabels.count(lastOrder->getLabel()) != 1) { + cout << ". I will use " << lastOrder->getLabel() << "." << endl; + 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; - } + cout << ". Please refer to " << lastOrder->getLabel() << "." << endl; } + } + + //run last line if you need to + if (needToRun == true) { + cCurve = new Collect(lastOrder, cDisplays); + cCurve->getCurve(freq); + delete cCurve; - count++; + cout << lastOrder->getLabel() << '\t' << count << endl; } - set::iterator i; - for(i = globaldata->labels.begin(); i != globaldata->labels.end(); ++i) - if(orderList.count(*i) == 0) - cout << "'" << *i << "'" << " is not a valid label.\n"; + + delete lastOrder; for(int i=0;iGroups.clear(); globaldata->setGroups(""); + globaldata->Groups.clear(); return 0; }