X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=matrixoutputcommand.cpp;h=5665426e537deca591a971a560f58283020eb9d3;hb=aca78ed4a47dff8672ea8fd93cef0dfbaf0f7495;hp=3844e18c1e687ef47fae1dda09d10e61973ab798;hpb=4b54ce99af7db8019ea907cd7c2edf789369ada9;p=mothur.git diff --git a/matrixoutputcommand.cpp b/matrixoutputcommand.cpp index 3844e18..5665426 100644 --- a/matrixoutputcommand.cpp +++ b/matrixoutputcommand.cpp @@ -17,8 +17,8 @@ vector MatrixOutputCommand::setParameters(){ CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); CommandParameter psubsample("subsample", "String", "", "", "", "", "","",false,false); parameters.push_back(psubsample); CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); - CommandParameter pcalc("calc", "Multiple", "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan-kstest-sharednseqs-ochiai-anderberg-kulczynski-kulczynskicody-lennon-morisitahorn-braycurtis-whittaker-odum-canberra-structeuclidean-structchord-hellinger-manhattan-structpearson-soergel-spearman-structkulczynski-speciesprofile-hamming-structchi2-gower-memchi2-memchord-memeuclidean-mempearson", "jclass-thetayc", "", "", "","",true,false,true); parameters.push_back(pcalc); - CommandParameter poutput("output", "Multiple", "lt-square", "lt", "", "", "","",false,false); parameters.push_back(poutput); + CommandParameter pcalc("calc", "Multiple", "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan-kstest-sharednseqs-ochiai-anderberg-kulczynski-kulczynskicody-lennon-morisitahorn-braycurtis-whittaker-odum-canberra-structeuclidean-structchord-hellinger-manhattan-structpearson-soergel-spearman-structkulczynski-speciesprofile-hamming-structchi2-gower-memchi2-memchord-memeuclidean-mempearson-jsd-rjsd", "jclass-thetayc", "", "", "","",true,false,true); parameters.push_back(pcalc); + CommandParameter poutput("output", "Multiple", "lt-square-column", "lt", "", "", "","",false,false); parameters.push_back(poutput); CommandParameter pmode("mode", "Multiple", "average-median", "average", "", "", "","",false,false); parameters.push_back(pmode); CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors); CommandParameter piters("iters", "Number", "", "1000", "", "", "","",false,false); parameters.push_back(piters); @@ -45,7 +45,7 @@ string MatrixOutputCommand::getHelpString(){ helpString += "The iters parameter allows you to choose the number of times you would like to run the subsample.\n"; helpString += "The subsample parameter allows you to enter the size pergroup of the sample or you can set subsample=T and mothur will use the size of your smallest group.\n"; helpString += "The dist.shared command should be in the following format: dist.shared(groups=yourGroups, calc=yourCalcs, label=yourLabels).\n"; - helpString += "The output parameter allows you to specify format of your distance matrix. Options are lt, and square. The default is lt.\n"; + helpString += "The output parameter allows you to specify format of your distance matrix. Options are lt, column and square. The default is lt.\n"; helpString += "The mode parameter allows you to specify if you want the average or the median values reported when subsampling. Options are average, and median. The default is average.\n"; helpString += "Example dist.shared(groups=A-B-C, calc=jabund-sorabund).\n"; helpString += "The default value for groups is all the groups in your groupfile.\n"; @@ -156,7 +156,7 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { } output = validParameter.validFile(parameters, "output", false); if(output == "not found"){ output = "lt"; } - if ((output != "lt") && (output != "square")) { m->mothurOut(output + " is not a valid output form. Options are lt and square. I will use lt."); m->mothurOutEndLine(); output = "lt"; } + if ((output != "lt") && (output != "square") && (output != "column")) { m->mothurOut(output + " is not a valid output form. Options are lt, column and square. I will use lt."); m->mothurOutEndLine(); output = "lt"; } mode = validParameter.validFile(parameters, "mode", false); if(mode == "not found"){ mode = "average"; } if ((mode != "average") && (mode != "median")) { m->mothurOut(mode + " is not a valid mode. Options are average and medina. I will use average."); m->mothurOutEndLine(); output = "average"; } @@ -281,6 +281,10 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { matrixCalculators.push_back(new MemEuclidean()); }else if (Estimators[i] == "mempearson") { matrixCalculators.push_back(new MemPearson()); + }else if (Estimators[i] == "jsd") { + matrixCalculators.push_back(new JSD()); + }else if (Estimators[i] == "rjsd") { + matrixCalculators.push_back(new RJSD()); } } } @@ -428,7 +432,7 @@ int MatrixOutputCommand::execute(){ string current = ""; itTypes = outputTypes.find("phylip"); if (itTypes != outputTypes.end()) { - if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setPhylipFile(current); } + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; if (!subsample) { m->setPhylipFile(current); } } } m->mothurOutEndLine(); @@ -449,11 +453,9 @@ void MatrixOutputCommand::printSims(ostream& out, vector< vector >& simM try { out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); - - //output num seqs - out << simMatrix.size() << endl; - + if (output == "lt") { + out << simMatrix.size() << endl; for (int b = 0; b < simMatrix.size(); b++) { out << lookup[b]->getGroup() << '\t'; for (int n = 0; n < b; n++) { @@ -461,7 +463,14 @@ void MatrixOutputCommand::printSims(ostream& out, vector< vector >& simM } out << endl; } + }else if (output == "column") { + for (int b = 0; b < simMatrix.size(); b++) { + for (int n = 0; n < b; n++) { + out << lookup[b]->getGroup() << '\t' << lookup[n]->getGroup() << '\t' << simMatrix[b][n] << endl; + } + } }else{ + out << simMatrix.size() << endl; for (int b = 0; b < simMatrix.size(); b++) { out << lookup[b]->getGroup() << '\t'; for (int n = 0; n < simMatrix[b].size(); n++) { @@ -522,7 +531,7 @@ int MatrixOutputCommand::process(vector thisLookup){ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) //loop through and create all the processes you want while (process != processors) { - int pid = fork(); + pid_t pid = fork(); if (pid > 0) { processIDS.push_back(pid); @@ -531,7 +540,7 @@ int MatrixOutputCommand::process(vector thisLookup){ driver(thisItersLookup, lines[process].start, lines[process].end, calcDists); - string tempdistFileName = m->getRootName(m->getSimpleName(sharedfile)) + toString(getpid()) + ".dist"; + string tempdistFileName = m->getRootName(m->getSimpleName(sharedfile)) + m->mothurGetpid(process) + ".dist"; ofstream outtemp; m->openOutputFile(tempdistFileName, outtemp); @@ -629,6 +638,9 @@ int MatrixOutputCommand::process(vector thisLookup){ //Close all thread handles and free memory allocations. for(int i=0; i < pDataArray.size(); i++){ + if (pDataArray[i]->count != (pDataArray[i]->end-pDataArray[i]->start)) { + m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->count) + " of " + toString(pDataArray[i]->end-pDataArray[i]->start) + " groups assigned to it, quitting. \n"); m->control_pressed = true; + } for (int j = 0; j < pDataArray[i]->thisLookup.size(); j++) { delete pDataArray[i]->thisLookup[j]; } for (int k = 0; k < calcDists.size(); k++) { @@ -644,7 +656,7 @@ int MatrixOutputCommand::process(vector thisLookup){ } if (subsample && (thisIter != 0)) { - if((thisIter) % 100 == 0){ m->mothurOut(toString(thisIter)); m->mothurOutEndLine(); } + if((thisIter) % 100 == 0){ m->mothurOutJustToScreen(toString(thisIter)+"\n"); } calcDistsTotals.push_back(calcDists); for (int i = 0; i < calcDists.size(); i++) { for (int j = 0; j < calcDists[i].size(); j++) { @@ -727,6 +739,8 @@ int MatrixOutputCommand::process(vector thisLookup){ variables["[calc]"] = matrixCalculators[i]->getName(); string distFileName = getOutputFileName("phylip",variables); outputNames.push_back(distFileName); outputTypes["phylip"].push_back(distFileName); + //set current phylip file to average distance matrix + m->setPhylipFile(distFileName); ofstream outAve; m->openOutputFile(distFileName, outAve); outAve.setf(ios::fixed, ios::floatfield); outAve.setf(ios::showpoint); @@ -783,7 +797,7 @@ int MatrixOutputCommand::driver(vector thisLookup, int star vector tempdata = matrixCalculators[i]->getValues(subset); //saves the calculator outputs if (m->control_pressed) { return 1; } - + seqDist temp(l, k, tempdata[0]); calcDists[i].push_back(temp); }