X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=venn.cpp;h=66dbb8eac3ee13c069b85374503dd87cc0ae538f;hp=7c33dd7a7bb1237480c4e5d95b28187832a7b71d;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=d59f91eb1230d2c7867a92cb86138b7003100ab4 diff --git a/venn.cpp b/venn.cpp index 7c33dd7..66dbb8e 100644 --- a/venn.cpp +++ b/venn.cpp @@ -11,66 +11,77 @@ #include "ace.h" #include "sobs.h" #include "chao1.h" +#include "nseqs.h" +#include "sharedchao1.h" +#include "sharedsobscollectsummary.h" //********************************************************************************************************************** -Venn::Venn(){ +Venn::Venn(string o, bool n, string f, int fs, bool so) : outputDir(o), nseqs(n), inputfile(f), fontSize(fs), sharedOtus(so) { try { - globaldata = GlobalData::getInstance(); - format = globaldata->getFormat(); + m = MothurOut::getInstance(); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the Venn class Function Venn. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the Venn class function Venn. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "Venn", "Venn"); exit(1); } } //********************************************************************************************************************** -void Venn::getPic(SAbundVector* sabund, vector vCalcs) { +vector Venn::getPic(SAbundVector* sabund, vector vCalcs) { try { - + + vector outputNames; + for(int i=0;iinputFileName + ".venn." + sabund->getLabel() + vCalcs[i]->getName() + ".svg"; - openOutputFile(filenamesvg, outsvg); + string filenamesvg = outputDir + m->getRootName(m->getSimpleName(inputfile)) + "." + sabund->getLabel() + "." + vCalcs[i]->getName() + ".svg"; + outputNames.push_back(filenamesvg); + m->openOutputFile(filenamesvg, outsvg); + + if (m->control_pressed) { outsvg.close(); return outputNames; } vector data = vCalcs[i]->getValues(sabund); + int width = 1500; + int height = 1500; + //svg image - outsvg << "\n"; + outsvg << "\n"; outsvg << "\n"; - outsvg << ""; - outsvg << "Venn Diagram at distance " + sabund->getLabel() + "\n"; - outsvg << ""; - outsvg << "" + toString(data[0]) + "\n"; + outsvg << ""; + outsvg << "Venn Diagram at distance " + sabund->getLabel() + "\n"; + outsvg << ""; + outsvg << "" + toString(data[0]) + "\n"; if (data.size() == 3) { - outsvg << "The lower bound of the confidence interval is " + toString(data[1]) + "\n"; - outsvg << "The upper bound of the confidence interval is " + toString(data[2]) + "\n"; + outsvg << "The lower bound of the confidence interval is " + toString(data[1]) + "\n"; + outsvg << "The upper bound of the confidence interval is " + toString(data[2]) + "\n"; + } + + if (nseqs) { + outsvg << "The number of sequences represented is " + toString(sabund->getNumSeqs()) + "\n"; } outsvg << "\n\n"; outsvg.close(); } + + return outputNames; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the Venn class Function getPic. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the Venn class function getPic. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "Venn", "getPic"); exit(1); } } //********************************************************************************************************************** -void Venn::getPic(vector lookup, vector vCalcs) { +vector Venn::getPic(vector lookup, vector vCalcs) { try { + + vector subset; + vector outputNames; - //fills vector of sharedsabunds - lookup - //util->getSharedVectors(globaldata->Groups, lookup, sharedorder); //fills group vectors from order vector. + int width = 1500; + int height = 1500; /******************* 1 Group **************************/ if (lookup.size() == 1) { @@ -80,9 +91,12 @@ void Venn::getPic(vector lookup, vector vCalcs //make a file for each calculator for(int i=0;iinputFileName) + lookup[0]->getLabel() + ".venn." + vCalcs[i]->getName() + ".svg"; - openOutputFile(filenamesvg, outsvg); - + string filenamesvg = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + "." + lookup[0]->getGroup() + ".svg"; + outputNames.push_back(filenamesvg); + m->openOutputFile(filenamesvg, outsvg); + + if (m->control_pressed) { outsvg.close(); return outputNames; } + //in essence you want to run it like a single if (vCalcs[i]->getName() == "sharedsobs") { singleCalc = new Sobs(); @@ -95,26 +109,29 @@ void Venn::getPic(vector lookup, vector vCalcs vector data = singleCalc->getValues(sabund); //svg image - outsvg << "\n"; + outsvg << "\n"; outsvg << "\n"; - outsvg << ""; - outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; - outsvg << ""; - outsvg << "getGroup().length() / 2)) + "\" y=\"165\">" + lookup[0]->getGroup() + "\n"; - outsvg << "" + toString(data[0]) + "\n"; + outsvg << ""; + outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; + outsvg << ""; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.24 * height)) + "\">" + lookup[0]->getGroup() + "\n"; + outsvg << "" + toString(data[0]) + "\n"; if (data.size() == 3) { - outsvg << "The lower bound of the confidence interval is " + toString(data[1]) + "\n"; - outsvg << "The upper bound of the confidence interval is " + toString(data[2]) + "\n"; + outsvg << "The lower bound of the confidence interval is " + toString(data[1]) + "\n"; + outsvg << "The upper bound of the confidence interval is " + toString(data[2]) + "\n"; } - + + if (nseqs) { + outsvg << "The number of sequences represented is " + toString(sabund->getNumSeqs()) + "\n"; + } + outsvg << "\n\n"; outsvg.close(); delete singleCalc; } - /******************* 2 Groups **************************/ }else if (lookup.size() == 2) { @@ -125,23 +142,59 @@ void Venn::getPic(vector lookup, vector vCalcs sabundA = new SAbundVector(lookup[0]->getSAbundVector());// sabundA = &sA; sabundB = new SAbundVector(lookup[1]->getSAbundVector());// sabundB = &sB; + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); + //make a file for each calculator for(int i=0;iinputFileName) + lookup[0]->getLabel() + ".venn." + vCalcs[i]->getName() + ".svg"; - openOutputFile(filenamesvg, outsvg); + string filenamesvg = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + "." + lookup[0]->getGroup() + "-" + lookup[1]->getGroup() + ".svg"; + + outputNames.push_back(filenamesvg); + m->openOutputFile(filenamesvg, outsvg); + + if (m->control_pressed) { outsvg.close(); return outputNames; } //get estimates for sharedAB - vector shared = vCalcs[i]->getValues(lookup[0], lookup[1]); + vector labels; + vector shared = vCalcs[i]->getValues(subset, labels); //in essence you want to run it like a single if (vCalcs[i]->getName() == "sharedsobs") { singleCalc = new Sobs(); + if (sharedOtus && (labels.size() != 0)) { + string filenameShared = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + ".sharedotus"; + + outputNames.push_back(filenameShared); + ofstream outShared; + m->openOutputFile(filenameShared, outShared); + outShared << "Groups\tNumShared\tOTULabels\n"; + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup() << '\t' << labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + outShared.close(); + } }else if (vCalcs[i]->getName() == "sharedchao") { singleCalc = new Chao1(); - }else if (vCalcs[i]->getName() == "sharedace") { - singleCalc = new Ace(10); } + int sharedVal, numSeqsA, numSeqsB, uniqSeqsToA, uniqSeqsToB; + if (nseqs) { + NSeqs* nseqsCalc = new NSeqs(); + vector data = nseqsCalc->getValues(lookup); + cout << data[0] << '\t' << data[1] << endl; + sharedVal = data[0] + data[1]; + numSeqsA = sabundA->getNumSeqs(); + numSeqsB = sabundB->getNumSeqs(); + uniqSeqsToA = numSeqsA-data[0]; + uniqSeqsToB = numSeqsB-data[1]; + + delete nseqsCalc; + } + + //get estimates for numA vector numA = singleCalc->getValues(sabundA); @@ -149,44 +202,55 @@ void Venn::getPic(vector lookup, vector vCalcs vector numB = singleCalc->getValues(sabundB); //image window - outsvg << "\n"; + outsvg << "\n"; outsvg << "\n"; //draw circles - outsvg << ""; - outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; - outsvg << ""; - outsvg << ""; - outsvg << "" + toString(numA[0] - shared[0]) + "\n"; - outsvg << "" + toString(numB[0] - shared[0]) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"175\">" + lookup[0]->getGroup() + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"175\">" + lookup[1]->getGroup() + "\n"; - outsvg << "" + toString(shared[0]) + "\n"; - outsvg << "The number of species in group " + globaldata->Groups[0] + " is " + toString(numA[0]); + outsvg << ""; + outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; + outsvg << ""; + outsvg << ""; + outsvg << "" + toString(numA[0] - shared[0]) + "\n"; + outsvg << "" + toString(numB[0] - shared[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.25 * height)) + "\">" + lookup[0]->getGroup() + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.25 * height)) + "\">" + lookup[1]->getGroup() + "\n"; + outsvg << "" + toString(shared[0]) + "\n"; + outsvg << "The number of species in group " + lookup[0]->getGroup() + " is " + toString(numA[0]); if (numA.size() == 3) { - outsvg << " the lci is " + toString(numA[1]) + " and the hci is " + toString(numA[2]) + "\n"; - }else { outsvg << "\n"; } + outsvg << " the lci is " + toString(numA[1]) + " and the hci is " + toString(numA[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsA) + "; " + toString(uniqSeqsToA) + " sequences are not shared"; } + outsvg << "\n"; - outsvg << "The number of species in group " + globaldata->Groups[1] + " is " + toString(numB[0]); + outsvg << "The number of species in group " + lookup[1]->getGroup() + " is " + toString(numB[0]); if (numB.size() == 3) { - outsvg << " the lci is " + toString(numB[1]) + " and the hci is " + toString(numB[2]) + "\n"; - }else { outsvg << "\n"; } + outsvg << " the lci is " + toString(numB[1]) + " and the hci is " + toString(numB[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsB) + "; " + toString(uniqSeqsToB) + " sequences are not shared"; } + outsvg << "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[0] + " and " + globaldata->Groups[1] + " is " + toString(shared[0]) + "\n"; - outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + " and " + globaldata->Groups[1] + " is " + toString((shared[0] / (float)(numA[0] + numB[0] - shared[0]))) + "\n"; - outsvg << "The total richness for all groups is " + toString((float)(numA[0] + numB[0] - shared[0])) + "\n"; + outsvg << "The number of sepecies shared between groups " + lookup[0]->getGroup() + " and " + lookup[1]->getGroup() + " is " + toString(shared[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedVal) + "; " + toString((sharedVal / (float)(numSeqsA + numSeqsB))*100) + "% of these sequences are shared"; } + outsvg << "\n"; + + outsvg << "Percentage of species that are shared in groups " + lookup[0]->getGroup() + " and " + lookup[1]->getGroup() + " is " + toString((shared[0] / (float)(numA[0] + numB[0] - shared[0]))*100) + "\n"; + + outsvg << "The total richness for all groups is " + toString((float)(numA[0] + numB[0] - shared[0]))+ "\n";; + //close file outsvg << "\n\n"; outsvg.close(); - delete sabundA; - delete sabundB; delete singleCalc; } - /******************* 3 Groups **************************/ }else if (lookup.size() == 3) { + + height = 1600; + int windowSize = height; + + //get sabund vector pointers so you can use the single calculators //one for each group SAbundVector sA, sB, sC; @@ -194,231 +258,741 @@ void Venn::getPic(vector lookup, vector vCalcs sA = lookup[0]->getSAbundVector(); sabundA = &sA; sB = lookup[1]->getSAbundVector(); sabundB = &sB; sC = lookup[2]->getSAbundVector(); sabundC = &sC; - + //make a file for each calculator for(int i=0;iinputFileName) + lookup[0]->getLabel() + ".venn." + vCalcs[i]->getName() + ".svg"; - openOutputFile(filenamesvg, outsvg); - - //get estimates for sharedAB, sharedAC and sharedBC - vector sharedAB = vCalcs[i]->getValues(lookup[0], lookup[1]); - vector sharedAC = vCalcs[i]->getValues(lookup[0], lookup[2]); - vector sharedBC = vCalcs[i]->getValues(lookup[1], lookup[2]); - //merge BC and estimate with shared with A - SharedRAbundVector* merge = new SharedRAbundVector(); - for (int j = 0; j < lookup[1]->size(); j++) { - merge->push_back((lookup[1]->getAbundance(j) + lookup[2]->getAbundance(j)), j, ""); - } + string filenamesvg = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + "." + lookup[0]->getGroup() + "-" + lookup[1]->getGroup() + "-" + lookup[2]->getGroup() + ".svg"; + + outputNames.push_back(filenamesvg); + m->openOutputFile(filenamesvg, outsvg); - vector sharedAwithBC = vCalcs[i]->getValues(lookup[0], merge); - - delete merge; - //merge AC and estimate with shared with B - merge = new SharedRAbundVector(); - for (int j = 0; j < lookup[0]->size(); j++) { - merge->push_back((lookup[0]->getAbundance(j) + lookup[2]->getAbundance(j)), j, ""); - } - - vector sharedBwithAC = vCalcs[i]->getValues(lookup[1], merge); - - delete merge; - //merge AB and estimate with shared with C - merge = new SharedRAbundVector(); - for (int j = 0; j < lookup[0]->size(); j++) { - merge->push_back((lookup[0]->getAbundance(j) + lookup[1]->getAbundance(j)), j, ""); - } + if (m->control_pressed) { outsvg.close(); return outputNames; } - vector sharedCwithAB = vCalcs[i]->getValues(lookup[2], merge); - delete merge; + int sharedVal, sharedABVal, sharedACVal, sharedBCVal, numSeqsA, numSeqsB, numSeqsC, uniqSeqsToA, uniqSeqsToB, uniqSeqsToC; - //in essence you want to run it like a single - if (vCalcs[i]->getName() == "sharedsobs") { - singleCalc = new Sobs(); - }else if (vCalcs[i]->getName() == "sharedchao") { - singleCalc = new Chao1(); - }else if (vCalcs[i]->getName() == "sharedace") { - singleCalc = new Ace(10); + if (nseqs) { + NSeqs* nseqsCalc = new NSeqs(); + vector sharedData = nseqsCalc->getValues(lookup); + + vector mysubset; mysubset.push_back(lookup[0]); mysubset.push_back(lookup[1]); + vector sharedAB = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[2]); + vector sharedAC = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[2]); + vector sharedBC = nseqsCalc->getValues(mysubset); + + sharedVal = sharedData[0] + sharedData[1] + sharedData[2]; + sharedABVal = sharedAB[0] + sharedAB[1]; + sharedACVal = sharedAC[0] + sharedAC[1]; + sharedBCVal = sharedBC[0] + sharedBC[1]; + numSeqsA = sabundA->getNumSeqs(); + numSeqsB = sabundB->getNumSeqs(); + numSeqsC = sabundC->getNumSeqs(); + uniqSeqsToA = numSeqsA-sharedData[0]; + uniqSeqsToB = numSeqsC-sharedData[1]; + uniqSeqsToC = numSeqsB-sharedData[1]; + + delete nseqsCalc; } + - //get estimates for numA - vector numA = singleCalc->getValues(sabundA); + if (vCalcs[i]->getName() == "sharedace") { + + singleCalc = new Ace(10); + + //get estimates for numA + vector numA = singleCalc->getValues(sabundA); - //get estimates for numB - vector numB = singleCalc->getValues(sabundB); - - //get estimates for numC - vector numC = singleCalc->getValues(sabundC); + //get estimates for numB + vector numB = singleCalc->getValues(sabundB); - //find possible sharedABC values - float sharedABC1, sharedABC2, sharedABC3, sharedABC; + //get estimates for numC + vector numC = singleCalc->getValues(sabundC); + + + //get estimates for sharedAB, sharedAC and sharedBC + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); + vector sharedAB = vCalcs[i]->getValues(subset); + + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[2]); + vector sharedAC = vCalcs[i]->getValues(subset); + + subset.clear(); + subset.push_back(lookup[1]); subset.push_back(lookup[2]); + vector sharedBC = vCalcs[i]->getValues(subset); + + vector sharedAwithBC; + vector sharedBwithAC; + vector sharedCwithAB; + + //find possible sharedABC values + float sharedABC1 = 0.0; float sharedABC2 = 0.0; float sharedABC3 = 0.0; float sharedABC = 0.0; + + if (vCalcs[i]->getMultiple() == false) { + //merge BC and estimate with shared with A + SharedRAbundVector* merge = new SharedRAbundVector(); + for (int j = 0; j < lookup[1]->size(); j++) { + merge->push_back((lookup[1]->getAbundance(j) + lookup[2]->getAbundance(j)), ""); + } + + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(merge); + sharedAwithBC = vCalcs[i]->getValues(subset); - sharedABC1 = sharedAB[0] + sharedAC[0] - sharedAwithBC[0]; - sharedABC2 = sharedAB[0] + sharedBC[0] - sharedBwithAC[0]; - sharedABC3 = sharedAC[0] + sharedBC[0] - sharedCwithAB[0]; - - //if any of the possible m's are - throw them out - if (sharedABC1 < 0.0) { sharedABC1 = 0; } - if (sharedABC2 < 0.0) { sharedABC2 = 0; } - if (sharedABC3 < 0.0) { sharedABC3 = 0; } - - //sharedABC is the minimum of the 3 possibilities - if ((sharedABC1 < sharedABC2) && (sharedABC1 < sharedABC3)) { sharedABC = sharedABC1; } - else if ((sharedABC2 < sharedABC1) && (sharedABC2 < sharedABC3)) { sharedABC = sharedABC2; } - else if ((sharedABC3 < sharedABC1) && (sharedABC3 < sharedABC2)) { sharedABC = sharedABC3; } + delete merge; + //merge AC and estimate with shared with B + merge = new SharedRAbundVector(); + for (int j = 0; j < lookup[0]->size(); j++) { + merge->push_back((lookup[0]->getAbundance(j) + lookup[2]->getAbundance(j)), ""); + } + + subset.clear(); + subset.push_back(merge); subset.push_back(lookup[1]); + sharedBwithAC = vCalcs[i]->getValues(subset); + + delete merge; + //merge AB and estimate with shared with C + merge = new SharedRAbundVector(); + for (int j = 0; j < lookup[0]->size(); j++) { + merge->push_back((lookup[0]->getAbundance(j) + lookup[1]->getAbundance(j)), ""); + } + + subset.clear(); + subset.push_back(lookup[2]); subset.push_back(merge); + sharedCwithAB = vCalcs[i]->getValues(subset); + delete merge; + + sharedABC1 = sharedAB[0] + sharedAC[0] - sharedAwithBC[0]; + sharedABC2 = sharedAB[0] + sharedBC[0] - sharedBwithAC[0]; + sharedABC3 = sharedAC[0] + sharedBC[0] - sharedCwithAB[0]; + + //if any of the possible m's are - throw them out + if (sharedABC1 < 0.00001) { sharedABC1 = 0; } + if (sharedABC2 < 0.00001) { sharedABC2 = 0; } + if (sharedABC3 < 0.00001) { sharedABC3 = 0; } - //image window - outsvg << "\n"; - outsvg << "\n"; + //sharedABC is the minimum of the 3 possibilities + if ((sharedABC1 < sharedABC2) && (sharedABC1 < sharedABC3)) { sharedABC = sharedABC1; } + else if ((sharedABC2 < sharedABC1) && (sharedABC2 < sharedABC3)) { sharedABC = sharedABC2; } + else if ((sharedABC3 < sharedABC1) && (sharedABC3 < sharedABC2)) { sharedABC = sharedABC3; } + }else{ + vector data = vCalcs[i]->getValues(lookup); + sharedABC = data[0]; + sharedAwithBC.push_back(sharedAB[0] + sharedAC[0] - sharedABC); + sharedBwithAC.push_back(sharedAB[0] + sharedBC[0] - sharedABC); + sharedCwithAB.push_back(sharedAC[0] + sharedBC[0] - sharedABC); + } + + //image window + outsvg << "\n"; + outsvg << "\n"; - //draw circles - outsvg << ""; - outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; - outsvg << ""; - outsvg << ""; - outsvg << ""; -//cout << "numA = " << numA[0] << " numB = " << numB[0] << " numC = " << numC[0] << endl; -//cout << "sharedAB = " << sharedAB[0] << " sharedAC = " << sharedAC[0] << " sharedBC = " << sharedBC[0] << endl; -//cout << "sharedAwithBC = " << sharedAwithBC[0] << " sharedBwithAC = " << sharedBwithAC[0] << " sharedCwithAB = " << sharedCwithAB[0] << endl; - //place labels within overlaps - outsvg << "" + toString(numA[0]-sharedAwithBC[0]) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"150\">" + lookup[0]->getGroup() + "\n"; - outsvg << "" + toString(sharedAB[0] - sharedABC) + "\n"; - outsvg << "" + toString(numB[0]-sharedBwithAC[0]) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"150\">" + lookup[1]->getGroup() + "\n"; - outsvg << "" + toString(sharedAC[0] - sharedABC) + "\n"; - outsvg << "" + toString(numC[0]-sharedCwithAB[0]) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"410\">" + lookup[2]->getGroup() + "\n"; - outsvg << "" + toString(sharedBC[0] - sharedABC) + "\n"; - outsvg << "" + toString(sharedABC) + "\n"; - - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[0] + " and " + globaldata->Groups[1] + " is " + toString(sharedAB[0]) + "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[0] + " and " + globaldata->Groups[2] + " is " + toString(sharedAC[0]) + "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[1] + " and " + globaldata->Groups[2] + " is " + toString(sharedBC[0]) + "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[0] + " and combined groups " + globaldata->Groups[1] + globaldata->Groups[2] + " is " + toString(sharedAwithBC[0]) + "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[1] + " and combined groups " + globaldata->Groups[0] + globaldata->Groups[2] + " is " + toString(sharedBwithAC[0]) + "\n"; - outsvg << "The number of sepecies shared between groups " + globaldata->Groups[2] + " and combined groups " + globaldata->Groups[0] + globaldata->Groups[1] + " is " + toString(sharedCwithAB[0]) + "\n"; - outsvg << "The number of species in group " + globaldata->Groups[0] + " is " + toString(numA[0]); - if (numA.size() == 3) { - outsvg << " the lci is " + toString(numA[1]) + " and the hci is " + toString(numA[2]) + "\n"; - }else { outsvg << "\n"; } - - outsvg << "The number of species in group " + globaldata->Groups[1] + " is " + toString(numB[0]); - if (numB.size() == 3) { - outsvg << " the lci is " + toString(numB[1]) + " and the hci is " + toString(numB[2]) + "\n"; - }else { outsvg << "\n"; } + //draw circles + outsvg << ""; + outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; + outsvg << ""; + outsvg << ""; + outsvg << ""; + + //place labels within overlaps + outsvg << "" + toString(numA[0]-sharedAwithBC[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.19 * height)) + "\">" + lookup[0]->getGroup() + "\n"; + outsvg << "" + toString(sharedAB[0] - sharedABC) + "\n"; + outsvg << "" + toString(numB[0]-sharedBwithAC[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.19 * height)) + "\">" + lookup[1]->getGroup() + "\n"; + outsvg << "" + toString(sharedAC[0] - sharedABC) + "\n"; + outsvg << "" + toString(numC[0]-sharedCwithAB[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.52 * height)) + "\">" + lookup[2]->getGroup() + "\n"; + outsvg << "" + toString(sharedBC[0] - sharedABC) + "\n"; + outsvg << "" + toString(sharedABC) + "\n"; - outsvg << "The number of species in group " + globaldata->Groups[2] + " is " + toString(numC[0]); - if (numC.size() == 3) { - outsvg << " the lci is " + toString(numC[1]) + " and the hci is " + toString(numC[2]) + "\n"; - }else { outsvg << "\n"; } + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[1]->getGroup() + " is " + toString(sharedAB[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedABVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedAC[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedACVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedBC[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedBCVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and combined groups " + lookup[1]->getGroup() + lookup[2]->getGroup() + " is " + toString(sharedAwithBC[0]) + "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + " and combined groups " + lookup[0]->getGroup() + lookup[2]->getGroup() + " is " + toString(sharedBwithAC[0]) + "\n"; + outsvg << "The number of species shared between groups " + lookup[2]->getGroup() + " and combined groups " + lookup[0]->getGroup() + lookup[1]->getGroup() + " is " + toString(sharedCwithAB[0]) + "\n"; + outsvg << "The number of species in group " + lookup[0]->getGroup() + " is " + toString(numA[0]); + if (numA.size() == 3) { + outsvg << " the lci is " + toString(numA[1]) + " and the hci is " + toString(numA[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsA) + "; " + toString(uniqSeqsToA) + " sequences are not shared"; } + outsvg << "\n"; + + outsvg << "The number of species in group " + lookup[1]->getGroup() + " is " + toString(numB[0]); + if (numB.size() == 3) { + outsvg << " the lci is " + toString(numB[1]) + " and the hci is " + toString(numB[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsB) + "; " + toString(uniqSeqsToB) + " sequences are not shared"; } + outsvg << "\n"; + + outsvg << "The number of species in group " + lookup[2]->getGroup() + " is " + toString(numC[0]); + if (numC.size() == 3) { + outsvg << " the lci is " + toString(numC[1]) + " and the hci is " + toString(numC[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsC) + "; " + toString(uniqSeqsToC) + " sequences are not shared"; } + outsvg << "\n"; + + outsvg << "The total richness of all the groups is " + toString(numA[0] + numB[0] + numC[0] - sharedAB[0] - sharedAC[0] - sharedBC[0] + sharedABC) + "\n"; + outsvg << "The total shared richness is " + toString(sharedABC); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedVal); } + outsvg << "\n"; + + delete singleCalc; + + }else { //sharedchao and sharedsobs are multigroup + + ofstream outShared; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs")) { + string filenameShared = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + ".sharedotus"; + + outputNames.push_back(filenameShared); + + m->openOutputFile(filenameShared, outShared); + outShared << "Groups\tNumShared\tOTULabels\n"; + } + vector subset; + + //get estimates for numA + subset.push_back(lookup[0]); + vector numA = vCalcs[i]->getValues(subset); + + //get estimates for numB + subset.clear(); + subset.push_back(lookup[1]); + vector numB = vCalcs[i]->getValues(subset); + + //get estimates for numC + subset.clear(); + subset.push_back(lookup[2]); + vector numC = vCalcs[i]->getValues(subset); + + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); + vector labels; + vector sharedab = vCalcs[i]->getValues(subset, labels); + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup() << '\t' << labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[2]); + vector sharedac = vCalcs[i]->getValues(subset, labels); + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[2]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + + subset.clear(); + subset.push_back(lookup[1]); subset.push_back(lookup[2]); + vector sharedbc = vCalcs[i]->getValues(subset, labels); + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[1]->getGroup() + "-" + lookup[2]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + + + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); subset.push_back(lookup[2]); + vector sharedabc = vCalcs[i]->getValues(subset, labels); + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup() + "-" + lookup[2]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + outShared.close(); + } + + //image window + outsvg << "\n"; + outsvg << "\n"; + + //draw circles + outsvg << ""; + outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; + outsvg << ""; + outsvg << ""; + outsvg << ""; - outsvg << "The total richness of all the groups is " + toString(numA[0] + numB[0] + numC[0] - sharedAB[0] - sharedAC[0] - sharedBC[0] + sharedABC) + "\n"; + //place labels within overlaps + outsvg << "" + toString(numA[0]-sharedab[0]-sharedac[0]+sharedabc[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.19 * height)) + "\">" + lookup[0]->getGroup() + "\n"; + outsvg << "" + toString(sharedab[0] - sharedabc[0]) + "\n"; + outsvg << "" + toString(numB[0]-sharedab[0]-sharedbc[0]+sharedabc[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.19 * height)) + "\">" + lookup[1]->getGroup() + "\n"; + outsvg << "" + toString(sharedac[0] - sharedabc[0]) + "\n"; + outsvg << "" + toString(numC[0]-sharedac[0]-sharedbc[0]+sharedabc[0]) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.51 * height)) + "\">" + lookup[2]->getGroup() + "\n"; + outsvg << "" + toString(sharedbc[0] - sharedabc[0]) + "\n"; + outsvg << "" + toString(sharedabc[0]) + "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[1]->getGroup() + " is " + toString(sharedab[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedABVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedac[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedACVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedbc[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedBCVal); } + outsvg << "\n"; + + outsvg << "The number of species in group " + lookup[0]->getGroup() + " is " + toString(numA[0]); + if (numA.size() == 3) { + outsvg << " the lci is " + toString(numA[1]) + " and the hci is " + toString(numA[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsA); } + outsvg << "\n"; + + outsvg << "The number of species in group " + lookup[1]->getGroup() + " is " + toString(numB[0]); + if (numB.size() == 3) { + outsvg << " the lci is " + toString(numB[1]) + " and the hci is " + toString(numB[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsB); } + outsvg << "\n"; + + outsvg << "The number of species in group " + lookup[2]->getGroup() + " is " + toString(numC[0]); + if (numC.size() == 3) { + outsvg << " the lci is " + toString(numC[1]) + " and the hci is " + toString(numC[2]); + } + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsC); } + outsvg << "\n"; + + outsvg << "The total richness of all the groups is " + toString(numA[0] + numB[0] + numC[0] - sharedab[0] - sharedac[0] - sharedbc[0] + sharedabc[0]) + "\n"; + outsvg << "The total shared richness is " + toString(sharedabc[0]); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedVal); } + outsvg << "\n"; + + } + //close file outsvg << "\n\n"; outsvg.close(); - delete singleCalc; + + } /******************* 4 Groups **************************/ }else if (lookup.size() == 4) { + + height = 1600; + + int windowSize = height; + //calc the shared otu - int sharedABCD = 0; - int numA = 0; int numB = 0; int numC = 0; int numD = 0; - int sharedAB = 0; int sharedAC = 0; int sharedBC = 0; int sharedAD = 0; int sharedBD = 0; int sharedCD = 0; - int sharedABC = 0; int sharedACD = 0; int sharedBCD = 0; int sharedABD = 0; + float sharedABCD = 0; + float numA = 0; float numB = 0; float numC = 0; float numD = 0; + float sharedAB = 0; float sharedAC = 0; float sharedBC = 0; float sharedAD = 0; float sharedBD = 0; float sharedCD = 0; + float sharedABC = 0; float sharedACD = 0; float sharedBCD = 0; float sharedABD = 0; + vector data; + //get sabund vector pointers so you can use the single calculators + //one for each group + SAbundVector sA, sB, sC, sD; + SAbundVector* sabundA; SAbundVector* sabundB; SAbundVector* sabundC; SAbundVector* sabundD; + sA = lookup[0]->getSAbundVector(); sabundA = &sA; + sB = lookup[1]->getSAbundVector(); sabundB = &sB; + sC = lookup[2]->getSAbundVector(); sabundC = &sC; + sD = lookup[3]->getSAbundVector(); sabundD = &sD; //A = red, B = green, C = blue, D = yellow - if ((vCalcs.size() > 1) || (vCalcs[0]->getName() != "sharedsobs")) { cout << "The only calculator able to be used with 4 groups is sharedsobs. I will run that for you. " << endl; } - - //for each bin - for (int i = 0; i < lookup[0]->size(); i++) { - //are they only in one - if ((lookup[0]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) == 0) && (lookup[2]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { numA++; } - if ((lookup[1]->getAbundance(i) != 0) && (lookup[0]->getAbundance(i) == 0) && (lookup[2]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { numB++; } - if ((lookup[2]->getAbundance(i) != 0) && (lookup[0]->getAbundance(i) == 0) && (lookup[1]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { numC++; } - if ((lookup[3]->getAbundance(i) != 0) && (lookup[0]->getAbundance(i) == 0) && (lookup[1]->getAbundance(i) == 0) && (lookup[2]->getAbundance(i) == 0)) { numD++; } - //are they shared by 2 - if ((lookup[0]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { sharedAB++; } - if ((lookup[0]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { sharedAC++; } - if ((lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[0]->getAbundance(i) == 0) && (lookup[3]->getAbundance(i) == 0)) { sharedBC++; } - if ((lookup[0]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) == 0) && (lookup[1]->getAbundance(i) == 0)) { sharedAD++; } - if ((lookup[3]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) == 0) && (lookup[0]->getAbundance(i) == 0)) { sharedBD++; } - if ((lookup[2]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) == 0) && (lookup[0]->getAbundance(i) == 0)) { sharedCD++; } - //are they shared by 3 - if ((lookup[0]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) == 0)) { sharedABC++; } - if ((lookup[0]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) == 0)) { sharedACD++; } - if ((lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0) && (lookup[0]->getAbundance(i) == 0)) { sharedBCD++; } - if ((lookup[0]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) == 0)) { sharedABD++; } - //are they shared by all - if ((lookup[0]->getAbundance(i) != 0) && (lookup[1]->getAbundance(i) != 0) && (lookup[2]->getAbundance(i) != 0) && (lookup[3]->getAbundance(i) != 0)) { sharedABCD++; } - } + //make a file for each calculator + for(int i=0;iinputFileName) + lookup[0]->getLabel() + ".venn.sharedsobs.svg"; - openOutputFile(filenamesvg, outsvg); - - //image window - outsvg << "\n"; - outsvg << "\n"; + if ((vCalcs[i]->getName() != "sharedsobs") && (vCalcs[i]->getName() != "sharedchao")) { m->mothurOut(vCalcs[i]->getName() + " is not a valid calculator with four groups. It will be disregarded. "); m->mothurOutEndLine(); } + else{ + string filenamesvg = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + "." + lookup[0]->getGroup() + "-" + lookup[1]->getGroup() + "-" + lookup[2]->getGroup() + "-" + lookup[3]->getGroup() + ".svg"; + outputNames.push_back(filenamesvg); + m->openOutputFile(filenamesvg, outsvg); - //draw circles - outsvg << ""; - outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; - outsvg << "\n "; - outsvg << "\n "; - outsvg << "\n "; - outsvg << "\n "; - - //A = red, B = green, C = blue, D = yellow + if (m->control_pressed) { outsvg.close(); return outputNames; } + + //in essence you want to run it like a single + if (vCalcs[i]->getName() == "sharedsobs") { + singleCalc = new Sobs(); + }else if (vCalcs[i]->getName() == "sharedchao") { + singleCalc = new Chao1(); + } + + //get estimates for numA + data = singleCalc->getValues(sabundA); + numA = data[0]; + //cout << "num a = " << numA << endl; + + //get estimates for numB + data = singleCalc->getValues(sabundB); + numB = data[0]; + //cout << "num b = " << numB << endl; + //get estimates for numC + data = singleCalc->getValues(sabundC); + numC = data[0]; + //cout << "num c = " << numC << endl; + //get estimates for numD + data = singleCalc->getValues(sabundD); + numD = data[0]; +//cout << "num d = " << numD << endl; + + ofstream outShared; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs")) { + string filenameShared = outputDir + m->getRootName(m->getSimpleName(inputfile)) + lookup[0]->getLabel() + "." + vCalcs[i]->getName() + ".sharedotus"; + + outputNames.push_back(filenameShared); + + m->openOutputFile(filenameShared, outShared); + outShared << "Groups\tNumShared\tOTULabels\n"; + } + + //get estimates for pairs + subset.clear(); + vector labels; + subset.push_back(lookup[0]); subset.push_back(lookup[1]); + data = vCalcs[i]->getValues(subset, labels); + sharedAB = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num ab = " << sharedAB << endl; + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[2]); + data = vCalcs[i]->getValues(subset, labels); + sharedAC = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[2]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num ac = " << sharedAC << endl; + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset, labels); + sharedAD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[3]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num ad = " << sharedAD << endl; + subset.clear(); + subset.push_back(lookup[1]); subset.push_back(lookup[2]); + data = vCalcs[i]->getValues(subset, labels); + sharedBC = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[1]->getGroup() + "-" + lookup[2]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num bc = " << sharedBC << endl; + subset.clear(); + subset.push_back(lookup[1]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset, labels); + sharedBD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[1]->getGroup() + "-" + lookup[3]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num bd = " << sharedBD << endl; + subset.clear(); + subset.push_back(lookup[2]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset, labels); + sharedCD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[2]->getGroup() + "-" + lookup[3]->getGroup() << '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + + //cout << "num cd = " << sharedCD << endl; + //get estimates for combos of 3 + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); subset.push_back(lookup[2]); + data = vCalcs[i]->getValues(subset, labels); + sharedABC = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup()+ "-" + lookup[2]->getGroup()<< '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num abc = " << sharedABC << endl; + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[2]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset, labels); + sharedACD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[2]->getGroup()+ "-" + lookup[3]->getGroup()<< '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + } + //cout << "num acd = " << sharedACD << endl; + subset.clear(); + subset.push_back(lookup[1]); subset.push_back(lookup[2]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset,labels); + sharedBCD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[1]->getGroup() + "-" + lookup[2]->getGroup()+ "-" + lookup[3]->getGroup()<< '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + outShared << labels[labels.size()-1]; + outShared << endl; + } + //cout << "num bcd = " << sharedBCD << endl; + subset.clear(); + subset.push_back(lookup[0]); subset.push_back(lookup[1]); subset.push_back(lookup[3]); + data = vCalcs[i]->getValues(subset, labels); + sharedABD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup()+ "-" + lookup[3]->getGroup()<< '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + outShared << labels[labels.size()-1]; + outShared << endl; + } +//cout << "num abd = " << sharedABD << endl; + //get estimate for all four + data = vCalcs[i]->getValues(lookup, labels); + sharedABCD = data[0]; + if (sharedOtus && (vCalcs[i]->getName() == "sharedsobs") && (labels.size() != 0)) { + outShared << lookup[0]->getGroup() + "-" + lookup[1]->getGroup() + "-" + lookup[2]->getGroup()+ "-" + lookup[3]->getGroup()<< '\t'<< labels.size() << '\t'; + for (int k = 0; k < labels.size()-1; k++) { + outShared << labels[k] << ","; + } + if (labels.size() != 0) { outShared << labels[labels.size()-1]; } + outShared << endl; + outShared.close(); + } + //cout << "num abcd = " << sharedABCD << endl << endl; + int sharedVal, sharedABCVal, sharedABDVal, sharedACDVal, sharedBCDVal, sharedABVal, sharedACVal, sharedADVal, sharedBCVal, sharedBDVal, sharedCDVal, numSeqsA, numSeqsB, numSeqsC, numSeqsD; + + if (nseqs) { + NSeqs* nseqsCalc = new NSeqs(); + vector sharedData = nseqsCalc->getValues(lookup); + + vector mysubset; mysubset.push_back(lookup[0]); mysubset.push_back(lookup[1]); + vector sharedAB = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[2]); + vector sharedAC = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[3]); + vector sharedAD = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[2]); + vector sharedBC = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[3]); + vector sharedBD = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[2]); mysubset.push_back(lookup[3]); + vector sharedCD = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[2]); + vector sharedABC = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[3]); + vector sharedABD = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[0]); mysubset.push_back(lookup[2]); mysubset.push_back(lookup[3]); + vector sharedACD = nseqsCalc->getValues(mysubset); + + mysubset.clear(); mysubset.push_back(lookup[1]); mysubset.push_back(lookup[2]); mysubset.push_back(lookup[3]); + vector sharedBCD = nseqsCalc->getValues(mysubset); + + sharedVal = sharedData[0] + sharedData[1] + sharedData[2] + sharedData[3]; + sharedABCVal = sharedABC[0] + sharedABC[1] + sharedABC[2]; + sharedABDVal = sharedABD[0] + sharedABD[1] + sharedABD[2]; + sharedACDVal = sharedACD[0] + sharedACD[1] + sharedACD[2]; + sharedBCDVal = sharedBCD[0] + sharedBCD[1] + sharedBCD[2]; + sharedABVal = sharedAB[0] + sharedAB[1]; + sharedACVal = sharedAC[0] + sharedAC[1]; + sharedADVal = sharedAD[0] + sharedAD[1]; + sharedBCVal = sharedBC[0] + sharedBC[1]; + sharedBDVal = sharedBD[0] + sharedBD[1]; + sharedCDVal = sharedCD[0] + sharedCD[1]; + numSeqsA = sabundA->getNumSeqs(); + numSeqsB = sabundB->getNumSeqs(); + numSeqsC = sabundC->getNumSeqs(); + numSeqsD = sabundD->getNumSeqs(); + + delete nseqsCalc; + } + + + //image window + outsvg << "\n"; + outsvg << "\n"; + outsvg << ""; + outsvg << "Venn Diagram at distance " + lookup[0]->getLabel() + "\n"; + + outsvg << "The number of species in group " + lookup[0]->getGroup() + " is " + toString(numA); + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsA); } + outsvg << "\n"; + outsvg << "The number of species in group " + lookup[1]->getGroup() + " is " + toString(numB); + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsB); } + outsvg << "\n"; + outsvg << "The number of species in group " + lookup[2]->getGroup() + " is " + toString(numC); + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsC); } + outsvg << "\n"; + outsvg << "The number of species in group " + lookup[3]->getGroup() + " is " + toString(numD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(numSeqsD); } + outsvg << "\n"; + + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[1]->getGroup() + " is " + toString(sharedAB); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedABVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedAC); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedACVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedAD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedADVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedBC); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedBCVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedBD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedBDVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[2]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedCD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedCDVal); } + outsvg << "\n"; + + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + ", " + lookup[1]->getGroup() + " and " + lookup[2]->getGroup() + " is " + toString(sharedABC); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedABCVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + ", " + lookup[1]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedABD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedABDVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[0]->getGroup() + ", " + lookup[2]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedACD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedACDVal); } + outsvg << "\n"; + outsvg << "The number of species shared between groups " + lookup[1]->getGroup() + ", " + lookup[2]->getGroup() + " and " + lookup[3]->getGroup() + " is " + toString(sharedBCD); + if (nseqs) { outsvg << ", and the number of squences is " + toString(sharedBCDVal); } + outsvg << "\n"; + + //make adjustments + sharedABC = sharedABC - sharedABCD; + //cout << "num abc = " << sharedABC << endl; + sharedABD = sharedABD - sharedABCD; + //cout << "num abd = " << sharedABD << endl; + sharedACD = sharedACD - sharedABCD; + //cout << "num acd = " << sharedACD << endl; + sharedBCD = sharedBCD - sharedABCD; + //cout << "num bcd = " << sharedBCD << endl; + + sharedAB = sharedAB - sharedABC - sharedABCD - sharedABD; //cout << "num ab = " << sharedAB << endl; + sharedAC = sharedAC - sharedABC - sharedABCD - sharedACD; //cout << "num ac = " << sharedAC << endl; + sharedAD = sharedAD - sharedABD - sharedABCD - sharedACD; //cout << "num ad = " << sharedAD << endl; + sharedBC = sharedBC - sharedABC - sharedABCD - sharedBCD; //cout << "num bc = " << sharedBC << endl; + sharedBD = sharedBD - sharedABD - sharedABCD - sharedBCD; // cout << "num bd = " << sharedBD << endl; + sharedCD = sharedCD - sharedACD - sharedABCD - sharedBCD; //cout << "num cd = " << sharedCD << endl; + + numA = numA - sharedAB - sharedAC - sharedAD - sharedABCD - sharedABC - sharedACD - sharedABD; + //cout << "num a = " << numA << endl; + numB = numB - sharedAB - sharedBC - sharedBD - sharedABCD - sharedABC - sharedABD - sharedBCD; + //cout << "num b = " << numB << endl; + numC = numC - sharedAC - sharedBC - sharedCD - sharedABCD - sharedABC - sharedACD - sharedBCD; + //cout << "num c = " << numC << endl; + numD = numD - sharedAD - sharedBD - sharedCD - sharedABCD - sharedBCD - sharedACD - sharedABD; + //cout << "num d = " << numD << endl; + + //draw circles + outsvg << "\n "; + outsvg << "\n "; + outsvg << "\n "; + outsvg << "\n "; - //place labels within overlaps - outsvg << "" + toString(numA) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"90\">" + lookup[0]->getGroup() + "\n"; - outsvg << "" + toString(sharedAB) + "\n"; - outsvg << "" + toString(numB) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"90\">" + lookup[1]->getGroup() + "\n"; - outsvg << "" + toString(sharedAC) + "\n"; - outsvg << "" + toString(numC) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"210\">" + lookup[2]->getGroup() + "\n"; - outsvg << "" + toString(sharedBC) + "\n"; - outsvg << "" + toString(numD) + "\n"; - outsvg << "getGroup().length() / 2)) + "\" y=\"210\">" + lookup[3]->getGroup() + "\n"; - outsvg << "" + toString(sharedAD) + "\n"; - outsvg << "" + toString(sharedBD) + "\n"; - outsvg << "" + toString(sharedCD) + "\n"; - outsvg << "" + toString(sharedABD) + "\n"; - outsvg << "" + toString(sharedBCD) + "\n"; - outsvg << "" + toString(sharedACD) + "\n"; - outsvg << "" + toString(sharedABC) + "\n"; - outsvg << "" + toString(sharedABCD) + "\n"; - outsvg << "The total richness of all the groups is " + toString((float)(numA + numB + numC + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD)) + "\n"; + //A = red, B = green, C = blue, D = yellow - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + " and " + globaldata->Groups[2] + " is " + toString(((sharedAC + sharedACD + sharedABC + sharedABCD) / (float)(numA + numC + sharedAB + sharedAC + sharedAD + sharedBC + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + " and " + globaldata->Groups[3] + " is " + toString(((sharedAD + sharedACD + sharedABD + sharedABCD) / (float)(numA + numD + sharedAB + sharedAC + sharedAD + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[1] + " and " + globaldata->Groups[2] + " is " + toString(((sharedBC + sharedABC + sharedBCD + sharedABCD) / (float)(numB + numC + sharedAB + sharedAC + sharedCD + sharedBD + sharedBC + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[1] + " and " + globaldata->Groups[3] + " is " + toString(((sharedBD + sharedABD + sharedBCD + sharedABCD) / (float)(numB + numD + sharedAB + sharedAD + sharedCD + sharedBD + sharedBC + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[2] + " and " + globaldata->Groups[3] + " is " + toString(((sharedCD + sharedBCD + sharedACD + sharedABCD) / (float)(numC + numD + sharedAC + sharedAD + sharedCD + sharedBD + sharedBC + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + ", " + globaldata->Groups[1] + " and " + globaldata->Groups[2] + " is " + toString(((sharedABC + sharedABCD) / (float)(numA + numB + numC + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + ", " + globaldata->Groups[1] + " and " + globaldata->Groups[3] + " is " + toString(((sharedABD + sharedABCD) / (float)(numA + numB + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + ", " + globaldata->Groups[2] + " and " + globaldata->Groups[3] + " is " + toString(((sharedACD + sharedABCD) / (float)(numA + numC + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[1] + ", " + globaldata->Groups[2] + " and " + globaldata->Groups[3] + " is " + toString(((sharedBCD + sharedABCD) / (float)(numB + numC + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - //outsvg << "Percentage of species that are shared in groups " + globaldata->Groups[0] + ", " + globaldata->Groups[1] + ", " + globaldata->Groups[2] + " and " + globaldata->Groups[3] + " is " + toString((sharedABCD / (float)(numA + numB + numC + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD))) + "\n"; - - outsvg << "\n\n"; - outsvg.close(); - + //place labels within overlaps + outsvg << "" + toString(numA) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.11 * height)) + "\">" + lookup[0]->getGroup() + "\n"; + outsvg << "" + toString(sharedAB) + "\n"; + outsvg << "" + toString(numB) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.11 * height)) + "\">" + lookup[1]->getGroup() + "\n"; + outsvg << "" + toString(sharedAC) + "\n"; + outsvg << "" + toString(numC) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.26 * height)) + "\">" + lookup[2]->getGroup() + "\n"; + outsvg << "" + toString(sharedBD) + "\n"; + outsvg << "" + toString(numD) + "\n"; + outsvg << "getGroup().length() / 2)) + "\" y=\"" + toString(int(0.26 * height)) + "\">" + lookup[3]->getGroup() + "\n"; + outsvg << "" + toString(sharedAD) + "\n"; + outsvg << "" + toString(sharedBC) + "\n"; + outsvg << "" + toString(sharedCD) + "\n"; + outsvg << "" + toString(sharedABD) + "\n"; + outsvg << "" + toString(sharedBCD) + "\n"; + outsvg << "" + toString(sharedACD) + "\n"; + outsvg << "" + toString(sharedABC) + "\n"; + outsvg << "" + toString(sharedABCD) + "\n"; + + outsvg << "The total richness of all the groups is " + toString((float)(numA + numB + numC + numD + sharedAB + sharedAC + sharedAD + sharedBC + sharedBD + sharedCD + sharedABC + sharedABD + sharedACD + sharedBCD + sharedABCD)); + if (nseqs) { outsvg << ", and the number of squences in the otus shared by all groups is " + toString(sharedVal); } + outsvg << "\n"; + + outsvg << "\n\n"; + outsvg.close(); + delete singleCalc; + } + } } + return outputNames; + } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the Venn class Function getPic. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the Venn class function getPic. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "Venn", "getPic"); exit(1); } }