X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=matrixoutputcommand.cpp;h=4ea8f021d3046a3f25be73b201869a73b98898ce;hb=e150b0b0664caec517485ee6d69dcdade6dcae77;hp=3ecf6df36e5ea33266d409fecee2620aec7a2d9f;hpb=a8f5a612bba54ceb74e17efc027d3a7f5aa93c9a;p=mothur.git diff --git a/matrixoutputcommand.cpp b/matrixoutputcommand.cpp index 3ecf6df..4ea8f02 100644 --- a/matrixoutputcommand.cpp +++ b/matrixoutputcommand.cpp @@ -8,6 +8,10 @@ */ #include "matrixoutputcommand.h" +#include "sharedsobscollectsummary.h" +#include "sharedchao1.h" +#include "sharedace.h" +#include "sharednseqs.h" #include "sharedjabund.h" #include "sharedsorabund.h" #include "sharedjclass.h" @@ -16,180 +20,424 @@ #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" +#include "odum.h" +#include "canberra.h" +#include "structeuclidean.h" +#include "structchord.h" +#include "hellinger.h" +#include "manhattan.h" +#include "structpearson.h" +#include "soergel.h" +#include "spearman.h" +#include "structkulczynski.h" +#include "structchi2.h" +#include "speciesprofile.h" +#include "hamming.h" +#include "gower.h" +#include "memchi2.h" +#include "memchord.h" +#include "memeuclidean.h" +#include "mempearson.h" - +//********************************************************************************************************************** +vector MatrixOutputCommand::setParameters(){ + try { + CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pshared); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + 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); parameters.push_back(pcalc); + CommandParameter poutput("output", "Multiple", "lt-square", "lt", "", "", "",false,false); parameters.push_back(poutput); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "MatrixOutputCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string MatrixOutputCommand::getHelpString(){ + try { + string helpString = ""; + ValidCalculators validCalculator; + helpString += "The dist.shared command parameters are shared, groups, calc, output and label. shared is a required, unless you have a valid current file.\n"; + helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included used.\n"; + helpString += "The group names are separated by dashes. The label parameter allows you to select what distance levels you would like distance matrices created for, and is also separated by dashes.\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 += "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"; + helpString += "The default value for calc is jclass and thetayc.\n"; + helpString += validCalculator.printCalc("matrix"); + helpString += "The dist.shared command outputs a .dist file for each calculator you specify at each distance you choose.\n"; + helpString += "Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "MatrixOutputCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +MatrixOutputCommand::MatrixOutputCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["phylip"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "MatrixOutputCommand", "MatrixOutputCommand"); + exit(1); + } +} //********************************************************************************************************************** -MatrixOutputCommand::MatrixOutputCommand(){ +MatrixOutputCommand::MatrixOutputCommand(string option) { try { - globaldata = GlobalData::getInstance(); - validCalculator = new ValidCalculators(); + abort = false; calledHelp = false; + allLines = 1; + + //allow user to run help + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} + + else { + vector myArray = setParameters(); + + OptionParser parser(option); + map parameters = parser.getParameters(); + map::iterator it; + + ValidParameters validParameter; + + //check to make sure all parameters are valid for command + for (it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + //initialize outputTypes + vector tempOutNames; + outputTypes["phylip"] = tempOutNames; + + //if the user changes the input directory command factory will send this info to us in the output parameter + string inputDir = validParameter.validFile(parameters, "inputdir", false); + if (inputDir == "not found"){ inputDir = ""; } + else { + string path; + it = parameters.find("shared"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["shared"] = inputDir + it->second; } + } + } + + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not found") { + //if there is a current shared file, use it + sharedfile = m->getSharedFile(); + if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current sharedfile and the shared parameter is required."); m->mothurOutEndLine(); abort = true; } + }else if (sharedfile == "not open") { sharedfile = ""; abort = true; } + + //if the user changes the output directory command factory will send this info to us in the output parameter + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ + outputDir = ""; + outputDir += m->hasPath(sharedfile); //if user entered a file with a path then preserve it + } + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + 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"; } + + groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { groups = ""; } + else { + m->splitAtDash(groups, Groups); + m->Groups = Groups; + } + + calc = validParameter.validFile(parameters, "calc", false); + if (calc == "not found") { calc = "jclass-thetayc"; } + else { + if (calc == "default") { calc = "jclass-thetayc"; } + } + m->splitAtDash(calc, Estimators); + + if (abort == false) { - int i; - for (i=0; iEstimators.size(); i++) { - if (validCalculator->isValidCalculator("matrix", globaldata->Estimators[i]) == true) { - if (globaldata->Estimators[i] == "jabund") { - matrixCalculators.push_back(new JAbund()); - }else if (globaldata->Estimators[i] == "sorabund") { - matrixCalculators.push_back(new SorAbund()); - }else if (globaldata->Estimators[i] == "jclass") { - matrixCalculators.push_back(new Jclass()); - }else if (globaldata->Estimators[i] == "sorclass") { - matrixCalculators.push_back(new SorClass()); - }else if (globaldata->Estimators[i] == "jest") { - matrixCalculators.push_back(new Jest()); - }else if (globaldata->Estimators[i] == "sorest") { - matrixCalculators.push_back(new SorEst()); - }else if (globaldata->Estimators[i] == "thetayc") { - matrixCalculators.push_back(new ThetaYC()); - }else if (globaldata->Estimators[i] == "thetan") { - matrixCalculators.push_back(new ThetaN()); - }else if (globaldata->Estimators[i] == "morisitahorn") { - matrixCalculators.push_back(new MorHorn()); - }else if (globaldata->Estimators[i] == "braycurtis") { - matrixCalculators.push_back(new BrayCurtis()); + ValidCalculators validCalculator; + + int i; + for (i=0; isetCalc(""); - } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the MatrixOutputCommand class Function MatrixOutputCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "MatrixOutputCommand", "MatrixOutputCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the MatrixOutputCommand class function MatrixOutputCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } + //********************************************************************************************************************** -MatrixOutputCommand::~MatrixOutputCommand(){ - delete input; - delete read; -} +MatrixOutputCommand::~MatrixOutputCommand(){} //********************************************************************************************************************** int MatrixOutputCommand::execute(){ try { - int count = 1; - + + if (abort == true) { if (calledHelp) { return 0; } return 2; } + //if the users entered no valid calculators don't execute command - if (matrixCalculators.size() == 0) { cout << "No valid calculators." << endl; return 0; } - - //you have groups - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); + if (matrixCalculators.size() == 0) { m->mothurOut("No valid calculators."); m->mothurOutEndLine(); return 0; } - input = globaldata->ginput; + input = new InputData(sharedfile, "sharedfile"); lookup = input->getSharedRAbundVectors(); - vector lastLookup = lookup; + string lastLabel = lookup[0]->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 = globaldata->labels; - - if (lookup.size() < 2) { cout << "You have not provided enough valid groups. I cannot run the command." << endl; return 0;} + set userLabels = labels; + + if (lookup.size() < 2) { m->mothurOut("You have not provided enough valid groups. I cannot run the command."); m->mothurOutEndLine(); delete input; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0;} + + numGroups = lookup.size(); - numGroups = globaldata->Groups.size(); + if (m->control_pressed) { delete input; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } m->Groups.clear(); return 0; } //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))) { + while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if (m->control_pressed) { outputTypes.clear(); delete input; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } m->Groups.clear(); return 0; } - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(lookup[0]->getLabel()) == 1){ - cout << lookup[0]->getLabel() << '\t' << count << endl; + if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); process(lookup); processedLabels.insert(lookup[0]->getLabel()); userLabels.erase(lookup[0]->getLabel()); } - if ((anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLookup[0]->getLabel()) != 1)) { - cout << lastLookup[0]->getLabel() << '\t' << count << endl; - process(lastLookup); + if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = lookup[0]->getLabel(); - processedLabels.insert(lastLookup[0]->getLabel()); - userLabels.erase(lastLookup[0]->getLabel()); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input->getSharedRAbundVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + process(lookup); + + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + + //restore real lastlabel to save below + lookup[0]->setLabel(saveLabel); } - //prevent memory leak - if (count != 1) { for (int i = 0; i < lastLookup.size(); i++) { delete lastLookup[i]; } } - lastLookup = lookup; + lastLabel = lookup[0]->getLabel(); //get next line to process + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } lookup = input->getSharedRAbundVectors(); - count++; } + if (m->control_pressed) { outputTypes.clear(); delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } m->Groups.clear(); return 0; } + //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; + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - cout << ". Please refer to " << lastLookup[0]->getLabel() << "." << endl; + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } - //run last line if you need to + if (m->control_pressed) { outputTypes.clear(); delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } m->Groups.clear(); return 0; } + + //run last label if you need to if (needToRun == true) { - cout << lastLookup[0]->getLabel() << '\t' << count << endl; - process(lastLookup); + for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } } + lookup = input->getSharedRAbundVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + process(lookup); + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } } - for (int i = 0; i < lastLookup.size(); i++) { delete lastLookup[i]; } - + if (m->control_pressed) { outputTypes.clear(); delete input; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } m->Groups.clear(); return 0; } //reset groups parameter - globaldata->Groups.clear(); globaldata->setGroups(""); + m->Groups.clear(); + + //set phylip file as new current phylipfile + string current = ""; + itTypes = outputTypes.find("phylip"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setPhylipFile(current); } + } + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the MatrixOutputCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "MatrixOutputCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the MatrixOutputCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /***********************************************************/ void MatrixOutputCommand::printSims(ostream& out) { try { - //output column headers + out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); + + //output num seqs out << simMatrix.size() << endl; - for (int m = 0; m < simMatrix.size(); m++) { - out << lookup[m]->getGroup() << '\t'; - for (int n = 0; n < m; n++) { - out << simMatrix[m][n] << '\t'; + if (output == "lt") { + for (int m = 0; m < simMatrix.size(); m++) { + out << lookup[m]->getGroup() << '\t'; + for (int n = 0; n < m; n++) { + out << simMatrix[m][n] << '\t'; + } + out << endl; + } + }else{ + for (int m = 0; m < simMatrix.size(); m++) { + out << lookup[m]->getGroup() << '\t'; + for (int n = 0; n < simMatrix[m].size(); n++) { + out << simMatrix[m][n] << '\t'; + } + out << endl; } - out << endl; } - } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the MatrixOutputCommand class Function printSims. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "MatrixOutputCommand", "printSims"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the MatrixOutputCommand class function printSims. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /***********************************************************/ -void MatrixOutputCommand::process(vector thisLookup){ +int MatrixOutputCommand::process(vector thisLookup){ try { EstOutput data; @@ -201,9 +449,9 @@ void MatrixOutputCommand::process(vector thisLookup){ //initialize simMatrix simMatrix.clear(); simMatrix.resize(numGroups); - for (int m = 0; m < simMatrix.size(); m++) { + for (int p = 0; p < simMatrix.size(); p++) { for (int j = 0; j < simMatrix.size(); j++) { - simMatrix[m].push_back(0.0); + simMatrix[p].push_back(0.0); } } @@ -212,10 +460,20 @@ void MatrixOutputCommand::process(vector thisLookup){ if (k != l) { //we dont need to similiarity of a groups to itself //get estimated similarity between 2 groups + if (m->control_pressed) { return 0; } + subset.clear(); //clear out old pair of sharedrabunds //add new pair of sharedrabunds subset.push_back(thisLookup[k]); subset.push_back(thisLookup[l]); + //if this calc needs all groups to calculate the pair load all groups + if (matrixCalculators[i]->getNeedsAll()) { + //load subset with rest of lookup for those calcs that need everyone to calc for a pair + for (int w = 0; w < thisLookup.size(); w++) { + if ((w != k) && (w != l)) { subset.push_back(thisLookup[w]); } + } + } + data = matrixCalculators[i]->getValues(subset); //saves the calculator outputs //save values in similarity matrix simMatrix[k][l] = 1.0 - data[0]; //convert similiarity to distance @@ -224,24 +482,22 @@ void MatrixOutputCommand::process(vector thisLookup){ } } - exportFileName = getRootName(globaldata->inputFileName) + matrixCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + ".dist"; - openOutputFile(exportFileName, out); + exportFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + matrixCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + "." + output + ".dist"; + m->openOutputFile(exportFileName, out); + outputNames.push_back(exportFileName); outputTypes["phylip"].push_back(exportFileName); + printSims(out); out.close(); } - + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the MatrixOutputCommand class Function process. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "MatrixOutputCommand", "process"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the MatrixOutputCommand class function process. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /***********************************************************/