X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=collectsharedcommand.cpp;h=697bc5340d66d54f9bdfcd8505bd8927a7e0ac57;hb=e911fa88572a16ef40e0b51fb132ab6e02370797;hp=3c1ad527c1ce7e881305fb79bf08b027058e9113;hpb=83950cc7a80a36c79dededb484daec5ec26b330f;p=mothur.git diff --git a/collectsharedcommand.cpp b/collectsharedcommand.cpp index 3c1ad52..697bc53 100644 --- a/collectsharedcommand.cpp +++ b/collectsharedcommand.cpp @@ -20,225 +20,304 @@ #include "sharedthetayc.h" #include "sharedthetan.h" #include "sharedkstest.h" -#include "sharedbdiversity.h" +#include "whittaker.h" #include "sharednseqs.h" #include "sharedochiai.h" -//#include "sharedanderberg.h" +#include "sharedanderbergs.h" #include "sharedkulczynski.h" #include "sharedkulczynskicody.h" #include "sharedlennon.h" #include "sharedmorisitahorn.h" #include "sharedbraycurtis.h" +#include "sharedjackknife.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(); + abort = false; + allLines = 1; + lines.clear(); + labels.clear(); + Estimators.clear(); + Groups.clear(); - 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] == "sharedjabund") { - cDisplays.push_back(new CollectDisplay(new SharedJAbund(), new SharedOneColumnFile(fileNameRoot+"shared.jabund"))); - }else if (globaldata->Estimators[i] == "sharedsorensonabund") { - cDisplays.push_back(new CollectDisplay(new SharedSorAbund(), new SharedOneColumnFile(fileNameRoot+"shared.sorabund"))); - }else if (globaldata->Estimators[i] == "sharedjclass") { - cDisplays.push_back(new CollectDisplay(new SharedJclass(), new SharedOneColumnFile(fileNameRoot+"shared.jclass"))); - }else if (globaldata->Estimators[i] == "sharedsorclass") { - cDisplays.push_back(new CollectDisplay(new SharedSorClass(), new SharedOneColumnFile(fileNameRoot+"shared.sorclass"))); - }else if (globaldata->Estimators[i] == "sharedjest") { - cDisplays.push_back(new CollectDisplay(new SharedJest(), new SharedOneColumnFile(fileNameRoot+"shared.jest"))); - }else if (globaldata->Estimators[i] == "sharedsorest") { - cDisplays.push_back(new CollectDisplay(new SharedSorEst(), new SharedOneColumnFile(fileNameRoot+"shared.sorest"))); - }else if (globaldata->Estimators[i] == "sharedthetayc") { - cDisplays.push_back(new CollectDisplay(new SharedThetaYC(), new SharedOneColumnFile(fileNameRoot+"shared.thetayc"))); - }else if (globaldata->Estimators[i] == "sharedthetan") { - cDisplays.push_back(new CollectDisplay(new SharedThetaN(), new SharedOneColumnFile(fileNameRoot+"shared.thetan"))); - }else if (globaldata->Estimators[i] == "sharedkstest") { - cDisplays.push_back(new CollectDisplay(new SharedKSTest(), new SharedOneColumnFile(fileNameRoot+"shared.kstest"))); - }else if (globaldata->Estimators[i] == "sharedbdiversity") { - cDisplays.push_back(new CollectDisplay(new SharedBDiversity(), new SharedOneColumnFile(fileNameRoot+"shared.bdiversity"))); - }else if (globaldata->Estimators[i] == "sharednseqs") { - cDisplays.push_back(new CollectDisplay(new SharedNSeqs(), new SharedOneColumnFile(fileNameRoot+"shared.nseqs"))); - }else if (globaldata->Estimators[i] == "sharedochiai") { - cDisplays.push_back(new CollectDisplay(new SharedOchiai(), new SharedOneColumnFile(fileNameRoot+"shared.ochiai"))); - //}else if (globaldata->Estimators[i] == "sharedanderberg") { - // cDisplays.push_back(new CollectDisplay(new SharedAnderberg(), new SharedOneColumnFile(fileNameRoot+"shared.anderberg"))); - }else if (globaldata->Estimators[i] == "sharedkulczynski") { - cDisplays.push_back(new CollectDisplay(new SharedKulczynski(), new SharedOneColumnFile(fileNameRoot+"shared.kulczynski"))); - }else if (globaldata->Estimators[i] == "sharedkulczynskicody") { - cDisplays.push_back(new CollectDisplay(new SharedKulczynskiCody(), new SharedOneColumnFile(fileNameRoot+"shared.kulczynskicody"))); - }else if (globaldata->Estimators[i] == "sharedlennon") { - cDisplays.push_back(new CollectDisplay(new SharedLennon(), new SharedOneColumnFile(fileNameRoot+"shared.lennon"))); - }else if (globaldata->Estimators[i] == "sharedmorisitahorn") { - cDisplays.push_back(new CollectDisplay(new SharedMorHorn(), new SharedOneColumnFile(fileNameRoot+"shared.morisitahorn"))); - }else if (globaldata->Estimators[i] == "sharedbraycurtis") { - cDisplays.push_back(new CollectDisplay(new SharedBrayCurtis(), new SharedOneColumnFile(fileNameRoot+"shared.braycurtis"))); - } + //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))); + + 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() == "") { mothurOut("You must read a list and a group, or a shared before you can use the collect.shared command."); mothurOutEndLine(); abort = true; } + else if (globaldata->getGroupFile() == "") { mothurOut("You must read a list and a group, or a shared before you can use the collect.shared command."); mothurOutEndLine(); 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 != "")) { mothurOut("You cannot use both the line and label parameters at the same time. "); mothurOutEndLine(); 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); + + 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) { - cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function CollectSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "CollectSharedCommand", "CollectSharedCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the CollectSharedCommand class function CollectSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +//********************************************************************************************************************** + +void CollectSharedCommand::help(){ + try { + mothurOut("The collect.shared command can only be executed after a successful read.otu command.\n"); + mothurOut("The collect.shared command parameters are label, line, freq, calc and groups. No parameters are required, but you may not use \n"); + mothurOut("both the line and label parameters at the same time. The collect.shared command should be in the following format: \n"); + mothurOut("collect.shared(label=yourLabel, line=yourLines, freq=yourFreq, calc=yourEstimators, groups=yourGroups).\n"); + mothurOut("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"); + mothurOut("The default values for freq is 100 and calc are sharedsobs-sharedchao-sharedace-jabund-sorensonabund-jclass-sorclass-jest-sorest-thetayc-thetan.\n"); + mothurOut("The default value for groups is all the groups in your groupfile.\n"); + validCalculator->printCalc("shared", cout); + mothurOut("The label and line parameters are used to analyze specific lines in your input.\n"); + 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"); + mothurOut("Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n\n"); + + } + catch(exception& e) { + errorOut(e, "CollectSharedCommand", "help"); exit(1); - } - + } } //********************************************************************************************************************** CollectSharedCommand::~CollectSharedCommand(){ - delete order; - delete input; - delete cCurve; - delete read; + if (abort == false) { + delete input; globaldata->ginput = NULL; + delete read; + delete util; + delete validCalculator; + globaldata->gorder = NULL; + } } //********************************************************************************************************************** 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 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; - SharedList = globaldata->gSharedList; - order = SharedList->getSharedOrderVector(); - } - set orderList; + input = globaldata->ginput; + order = input->getSharedOrderVector(); + string lastLabel = order->getLabel(); + //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; + set userLines = lines; + //set users groups - setGroups(); + util->setGroups(globaldata->Groups, globaldata->gGroupmap->namesOfGroups, "collect"); + util->updateGroupIndex(globaldata->Groups, globaldata->gGroupmap->groupIndex); + + while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) { - while(order != NULL){ - orderList.insert(order->getLabel()); - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){ + if(allLines == 1 || lines.count(count) == 1 || labels.count(order->getLabel()) == 1){ + //create collectors curve cCurve = new Collect(order, cDisplays); - convert(globaldata->getFreq(), freq); cCurve->getSharedCurve(freq); + delete cCurve; + + mothurOut(order->getLabel()); mothurOutEndLine(); + 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(lastLabel) != 1)) { + delete order; + order = input->getSharedOrderVector(lastLabel); + + //create collectors curve + cCurve = new Collect(order, cDisplays); + cCurve->getSharedCurve(freq); delete cCurve; - cout << order->getLabel() << '\t' << count << endl; + mothurOut(order->getLabel()); mothurOutEndLine(); + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); } + + lastLabel = order->getLabel(); + //get next line to process - if (format == "sharedfile") { - order = input->getSharedOrderVector(); + delete order; + 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++) { + mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + mothurOut(". I will use " + lastLabel + "."); 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; - } + mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); } + } + + //run last line if you need to + if (needToRun == true) { + if (order != NULL) { delete order; } + order = input->getSharedOrderVector(lastLabel); + + cCurve = new Collect(order, cDisplays); + cCurve->getSharedCurve(freq); + delete cCurve; - count++; + mothurOut(order->getLabel()); mothurOutEndLine(); + delete order; } - 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"; + for(int i=0;iGroups.clear(); globaldata->setGroups(""); + globaldata->Groups.clear(); return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "CollectSharedCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the CollectSharedCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } - -//********************************************************************************************************************** -void CollectSharedCommand::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 CollectSharedCommand class Function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the CollectSharedCommand class function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - -} /***********************************************************/ -