X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=summarysharedcommand.cpp;h=6a09ada5d3e8e4141c56a0c0ef4943beae6ef815;hb=4f4070ac3fbb5da75f834b48062e9123364b006e;hp=b9fd08debd294870af590f5be48fdc4a7c7ba890;hpb=20a2d0350a737a434c89f303662d64a8eeea7b05;p=mothur.git diff --git a/summarysharedcommand.cpp b/summarysharedcommand.cpp index b9fd08d..6a09ada 100644 --- a/summarysharedcommand.cpp +++ b/summarysharedcommand.cpp @@ -8,8 +8,10 @@ */ #include "summarysharedcommand.h" +#include "sharedsobscollectsummary.h" #include "sharedchao1.h" #include "sharedace.h" +#include "sharednseqs.h" #include "sharedjabund.h" #include "sharedsorabund.h" #include "sharedjclass.h" @@ -18,37 +20,81 @@ #include "sharedsorest.h" #include "sharedthetayc.h" #include "sharedthetan.h" +#include "sharedkstest.h" +#include "whittaker.h" +#include "sharedochiai.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" + //********************************************************************************************************************** SummarySharedCommand::SummarySharedCommand(){ try { globaldata = GlobalData::getInstance(); + outputFileName = ((getRootName(globaldata->inputFileName)) + "shared.summary"); + openOutputFile(outputFileName, outputFileHandle); + format = globaldata->getFormat(); + validCalculator = new ValidCalculators(); + mult = false; int i; - for (i=0; isharedSummaryEstimators.size(); i++) { - if (globaldata->sharedSummaryEstimators[i] == "sharedChao") { - sumCalculators.push_back(new SharedChao1()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedAce") { - sumCalculators.push_back(new SharedAce()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedJabund") { - sumCalculators.push_back(new SharedJAbund()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorensonAbund") { - sumCalculators.push_back(new SharedSorAbund()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedJclass") { - sumCalculators.push_back(new SharedJclass()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorClass") { - sumCalculators.push_back(new SharedSorClass()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedJest") { - sumCalculators.push_back(new SharedJest()); - }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorEst") { - sumCalculators.push_back(new SharedSorEst()); - }else if (globaldata->sharedSummaryEstimators[i] == "SharedThetaYC") { - sumCalculators.push_back(new SharedThetaYC()); - }else if (globaldata->sharedSummaryEstimators[i] == "SharedThetaN") { - sumCalculators.push_back(new SharedThetaN()); + for (i=0; iEstimators.size(); i++) { + if (validCalculator->isValidCalculator("sharedsummary", globaldata->Estimators[i]) == true) { + if (globaldata->Estimators[i] == "sharedsobs") { + sumCalculators.push_back(new SharedSobsCS()); + }else if (globaldata->Estimators[i] == "sharedchao") { + sumCalculators.push_back(new SharedChao1()); + }else if (globaldata->Estimators[i] == "sharedace") { + sumCalculators.push_back(new SharedAce()); + }else if (globaldata->Estimators[i] == "jabund") { + sumCalculators.push_back(new JAbund()); + }else if (globaldata->Estimators[i] == "sorabund") { + sumCalculators.push_back(new SorAbund()); + }else if (globaldata->Estimators[i] == "jclass") { + sumCalculators.push_back(new Jclass()); + }else if (globaldata->Estimators[i] == "sorclass") { + sumCalculators.push_back(new SorClass()); + }else if (globaldata->Estimators[i] == "jest") { + sumCalculators.push_back(new Jest()); + }else if (globaldata->Estimators[i] == "sorest") { + sumCalculators.push_back(new SorEst()); + }else if (globaldata->Estimators[i] == "thetayc") { + sumCalculators.push_back(new ThetaYC()); + }else if (globaldata->Estimators[i] == "thetan") { + sumCalculators.push_back(new ThetaN()); + }else if (globaldata->Estimators[i] == "kstest") { + sumCalculators.push_back(new KSTest()); + }else if (globaldata->Estimators[i] == "sharednseqs") { + sumCalculators.push_back(new SharedNSeqs()); + }else if (globaldata->Estimators[i] == "ochiai") { + sumCalculators.push_back(new Ochiai()); + }else if (globaldata->Estimators[i] == "anderberg") { + sumCalculators.push_back(new Anderberg()); + }else if (globaldata->Estimators[i] == "kulczynski") { + sumCalculators.push_back(new Kulczynski()); + }else if (globaldata->Estimators[i] == "kulczynskicody") { + sumCalculators.push_back(new KulczynskiCody()); + }else if (globaldata->Estimators[i] == "lennon") { + sumCalculators.push_back(new Lennon()); + }else if (globaldata->Estimators[i] == "morisitahorn") { + sumCalculators.push_back(new MorHorn()); + }else if (globaldata->Estimators[i] == "braycurtis") { + sumCalculators.push_back(new BrayCurtis()); + }else if (globaldata->Estimators[i] == "whittaker") { + sumCalculators.push_back(new Whittaker()); + } } } + //reset calc for next command + globaldata->setCalc(""); + } catch(exception& e) { cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function SummarySharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; @@ -70,58 +116,124 @@ SummarySharedCommand::~SummarySharedCommand(){ int SummarySharedCommand::execute(){ try { - outputFileName = ((getRootName(globaldata->inputFileName)) + "sharedSummary"); - openOutputFile(outputFileName, outputFileHandle); + int count = 1; - read = new ReadPhilFile(globaldata->inputFileName); + //if the users entered no valid calculators don't execute command + if (sumCalculators.size() == 0) { return 0; } + //check if any calcs can do multiples + else{ + for (int i = 0; i < sumCalculators.size(); i++) { + if (sumCalculators[i]->getMultiple() == true) { mult = true; } + } + } + + //read first line + read = new ReadOTUFile(globaldata->inputFileName); read->read(&*globaldata); + + input = globaldata->ginput; + lookup = input->getSharedRAbundVectors(); + vector lastLookup = lookup; - outputFileHandle << '\t' << '\t' << '\t' << '\t'; //pads file for labels and groupnames + //output estimator names as column headers + outputFileHandle << "label" <<'\t' << "comparison" << '\t'; for(int i=0;igetName(); } outputFileHandle << endl; - list = globaldata->glist; - input = globaldata->ginput; - order = list->getSharedOrderVector(); - getGroupComb(); + //create file and put column headers for multiple groups file + if (mult == true) { + outAllFileName = ((getRootName(globaldata->inputFileName)) + "sharedmultiple.summary"); + openOutputFile(outAllFileName, outAll); + + outAll << "label" <<'\t' << "comparison" << '\t'; + for(int i=0;igetMultiple() == true) { + outAll << '\t' << sumCalculators[i]->getName(); + } + } + outAll << endl; + } - int count = 1; - while(order != NULL){ + if (lookup.size() < 2) { + cout << "I cannot run the command without at least 2 valid groups."; + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + + //close files and clean up + outputFileHandle.close(); remove(outputFileName.c_str()); + if (mult == true) { outAll.close(); remove(outAllFileName.c_str()); } + return 0; + //if you only have 2 groups you don't need a .sharedmultiple file + }else if ((lookup.size() == 2) && (mult == true)) { + mult = false; + outAll.close(); + remove(outAllFileName.c_str()); + } + + //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; - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){ - - cout << order->getLabel() << '\t' << count << endl; - getSharedVectors(); //fills group vectors from order vector. + //as long as you are not at the end of the file or done wih the lines you want + while((lookup[0] != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) { + + if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(lookup[0]->getLabel()) == 1){ + cout << lookup[0]->getLabel() << '\t' << count << endl; + process(lookup); - //randomize group order - if (globaldata->getJumble() == "1") { random_shuffle(lookup.begin(), lookup.end()); } - - int n = 1; - for (int k = 0; k < (lookup.size() - 1); k++) { // pass cdd each set of groups to commpare - for (int l = n; l < lookup.size(); l++) { - outputFileHandle << order->getLabel() << '\t' << groupComb[n-1] << '\t'; //print out label and group - for(int i=0;igetValues(lookup[k], lookup[l]); //saves the calculator outputs - outputFileHandle << '\t'; - sumCalculators[i]->print(outputFileHandle); - } - outputFileHandle << endl; - } - n++; - } + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + userLines.erase(count); + } + + if ((anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLookup[0]->getLabel()) != 1)) { + cout << lastLookup[0]->getLabel() << '\t' << count << endl; + process(lastLookup); + + processedLabels.insert(lastLookup[0]->getLabel()); + userLabels.erase(lastLookup[0]->getLabel()); } + + + //prevent memory leak + if (count != 1) { for (int i = 0; i < lastLookup.size(); i++) { delete lastLookup[i]; } } + lastLookup = lookup; + + //get next line to process + lookup = input->getSharedRAbundVectors(); + count++; + } - list = input->getListVector(); //get new list vector to process - if (list != NULL) { - order = list->getSharedOrderVector(); //gets new order vector with group info. - 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(lastLookup[0]->getLabel()) != 1) { + cout << ". I will use " << lastLookup[0]->getLabel() << "." << endl; + needToRun = true; }else { - break; + cout << ". Please refer to " << lastLookup[0]->getLabel() << "." << endl; } } - + + //run last line if you need to + if (needToRun == true) { + cout << lastLookup[0]->getLabel() << '\t' << count << endl; + process(lastLookup); + } + + for (int i = 0; i < lastLookup.size(); i++) { delete lastLookup[i]; } + + //reset groups parameter + globaldata->Groups.clear(); globaldata->setGroups(""); + + //close files + outputFileHandle.close(); + if (mult == true) { outAll.close(); } + return 0; } catch(exception& e) { @@ -134,70 +246,70 @@ int SummarySharedCommand::execute(){ } } -//********************************************************************************************************************** - -void SummarySharedCommand::getSharedVectors(){ -try { - lookup.clear(); - //create and initialize vector of sharedvectors, one for each group - for (int i = 0; i < globaldata->gGroupmap->getNumGroups(); i++) { - SharedRAbundVector* temp = new SharedRAbundVector(order->getNumBins()); - temp->setLabel(order->getLabel()); - temp->setGroup(globaldata->gGroupmap->namesOfGroups[i]); - lookup.push_back(temp); - } - - int numSeqs = order->size(); - //sample all the members - for(int i=0;iget(i); - int abundance; +/***********************************************************/ +void SummarySharedCommand::process(vector thisLookup) { + try { + //loop through calculators and add to file all for all calcs that can do mutiple groups + if (mult == true) { + //output label + outAll << thisLookup[0]->getLabel() << '\t'; + + //output groups names + string outNames = ""; + for (int j = 0; j < thisLookup.size(); j++) { + outNames += thisLookup[j]->getGroup() + "-"; + } + outNames = outNames.substr(0, outNames.length()-1); //rip off extra '-'; + outAll << outNames << '\t'; - //set info for sharedvector in chosens group - for (int j = 0; j < lookup.size(); j++) { - if (chosen.group == lookup[j]->getGroup()) { - abundance = lookup[j]->getAbundance(chosen.bin); - lookup[j]->set(chosen.bin, (abundance + 1), chosen.group); - break; + for(int i=0;igetMultiple() == true) { + sumCalculators[i]->getValues(thisLookup); + outAll << '\t'; + sumCalculators[i]->print(outAll); + } + } + outAll << endl; } - } - - } - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function getSharedVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the SummarySharedCommand class function getSharedVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } + + int n = 1; + vector subset; + for (int k = 0; k < (thisLookup.size() - 1); k++) { // pass cdd each set of groups to commpare + for (int l = n; l < thisLookup.size(); l++) { + + outputFileHandle << thisLookup[0]->getLabel() << '\t'; + + subset.clear(); //clear out old pair of sharedrabunds + //add new pair of sharedrabunds + subset.push_back(thisLookup[k]); subset.push_back(thisLookup[l]); + + //sort groups to be alphanumeric + if (thisLookup[k]->getGroup() > thisLookup[l]->getGroup()) { + outputFileHandle << (thisLookup[l]->getGroup() +'\t' + thisLookup[k]->getGroup()) << '\t'; //print out groups + }else{ + outputFileHandle << (thisLookup[k]->getGroup() +'\t' + thisLookup[l]->getGroup()) << '\t'; //print out groups + } + + for(int i=0;igetValues(subset); //saves the calculator outputs + outputFileHandle << '\t'; + sumCalculators[i]->print(outputFileHandle); + } + outputFileHandle << endl; + } + n++; + } -/**************************************************************************************/ -void SummarySharedCommand::getGroupComb() { - try { - string group; - - int n = 1; - for (int i = 0; i < (globaldata->gGroupmap->getNumGroups() - 1); i++) { - for (int l = n; l < globaldata->gGroupmap->getNumGroups(); l++) { - group = globaldata->gGroupmap->namesOfGroups[i] + globaldata->gGroupmap->namesOfGroups[l]; - groupComb.push_back(group); - } - n++; - } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function getGroupComb. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function process. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; exit(1); } catch(...) { - cout << "An unknown error has occurred in the SummarySharedCommand class function getGroupComb. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + cout << "An unknown error has occurred in the SummarySharedCommand class function process. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; exit(1); - } - + } } +/***********************************************************/ \ No newline at end of file