X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;ds=sidebyside;f=matrixoutputcommand.cpp;h=5dfba366b1247956a2b2c655a8bf790b902e9ba1;hb=77ac47e1ea0b5a0c6f55eb25e6bc7d7494ed3ad2;hp=020ccff57c813168625132e83c9c198eb113a121;hpb=8bc3e5b38c2317a1715f53be22fa96455868c281;p=mothur.git diff --git a/matrixoutputcommand.cpp b/matrixoutputcommand.cpp index 020ccff..5dfba36 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" @@ -16,53 +20,89 @@ #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::getValidParameters(){ +vector MatrixOutputCommand::setParameters(){ try { - string Array[] = {"label","calc","groups","outputdir","inputdir", "output"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + 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", "getValidParameters"); + m->errorOut(e, "MatrixOutputCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -MatrixOutputCommand::MatrixOutputCommand(){ +string MatrixOutputCommand::getHelpString(){ try { - //initialize outputTypes - vector tempOutNames; - outputTypes["phylip"] = tempOutNames; + 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", "MatrixOutputCommand"); + m->errorOut(e, "MatrixOutputCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector MatrixOutputCommand::getRequiredParameters(){ - try { - vector myArray; - return myArray; - } - catch(exception& e) { - m->errorOut(e, "MatrixOutputCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector MatrixOutputCommand::getRequiredFiles(){ +MatrixOutputCommand::MatrixOutputCommand(){ try { - string Array[] = {"shared"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["phylip"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "MatrixOutputCommand", "getRequiredFiles"); + m->errorOut(e, "MatrixOutputCommand", "MatrixOutputCommand"); exit(1); } } @@ -70,28 +110,23 @@ vector MatrixOutputCommand::getRequiredFiles(){ MatrixOutputCommand::MatrixOutputCommand(string option) { try { - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; allLines = 1; - labels.clear(); - Groups.clear(); - Estimators.clear(); - + //allow user to run help - if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } else { - //valid paramters for this command - string Array[] = {"label","calc","groups","outputdir","inputdir", "output"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + 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 (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + for (it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } @@ -99,16 +134,32 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { 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(globaldata->inputFileName); //if user entered a file with a path then preserve it - } - - //make sure the user has already run the read.otu command - if (globaldata->getSharedFile() == "") { - if (globaldata->getListFile() == "") { m->mothurOut("You must read a list and a group, or a shared before you can use the dist.shared command."); m->mothurOutEndLine(); abort = true; } - else if (globaldata->getGroupFile() == "") { m->mothurOut("You must read a list and a group, or a shared before you can use the dist.shared command."); m->mothurOutEndLine(); abort = true; } + outputDir += m->hasPath(sharedfile); //if user entered a file with a path then preserve it } //check for optional parameter and set defaults @@ -123,17 +174,11 @@ 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 the user has not specified any labels use the ones from read.otu - if (label == "") { - allLines = globaldata->allLines; - labels = globaldata->labels; - } - groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } else { m->splitAtDash(groups, Groups); - globaldata->Groups = Groups; + m->Groups = Groups; } calc = validParameter.validFile(parameters, "calc", false); @@ -145,12 +190,18 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { if (abort == false) { - validCalculator = new ValidCalculators(); + ValidCalculators validCalculator; int i; for (i=0; iisValidCalculator("matrix", Estimators[i]) == true) { - if (Estimators[i] == "jabund") { + if (validCalculator.isValidCalculator("matrix", Estimators[i]) == true) { + if (Estimators[i] == "sharedsobs") { + matrixCalculators.push_back(new SharedSobsCS()); + }else if (Estimators[i] == "sharedchao") { + matrixCalculators.push_back(new SharedChao1()); + }else if (Estimators[i] == "sharedace") { + matrixCalculators.push_back(new SharedAce()); + }else if (Estimators[i] == "jabund") { matrixCalculators.push_back(new JAbund()); }else if (Estimators[i] == "sorabund") { matrixCalculators.push_back(new SorAbund()); @@ -166,10 +217,62 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { matrixCalculators.push_back(new ThetaYC()); }else if (Estimators[i] == "thetan") { matrixCalculators.push_back(new ThetaN()); + }else if (Estimators[i] == "kstest") { + matrixCalculators.push_back(new KSTest()); + }else if (Estimators[i] == "sharednseqs") { + matrixCalculators.push_back(new SharedNSeqs()); + }else if (Estimators[i] == "ochiai") { + matrixCalculators.push_back(new Ochiai()); + }else if (Estimators[i] == "anderberg") { + matrixCalculators.push_back(new Anderberg()); + }else if (Estimators[i] == "kulczynski") { + matrixCalculators.push_back(new Kulczynski()); + }else if (Estimators[i] == "kulczynskicody") { + matrixCalculators.push_back(new KulczynskiCody()); + }else if (Estimators[i] == "lennon") { + matrixCalculators.push_back(new Lennon()); }else if (Estimators[i] == "morisitahorn") { matrixCalculators.push_back(new MorHorn()); }else if (Estimators[i] == "braycurtis") { matrixCalculators.push_back(new BrayCurtis()); + }else if (Estimators[i] == "whittaker") { + matrixCalculators.push_back(new Whittaker()); + }else if (Estimators[i] == "odum") { + matrixCalculators.push_back(new Odum()); + }else if (Estimators[i] == "canberra") { + matrixCalculators.push_back(new Canberra()); + }else if (Estimators[i] == "structeuclidean") { + matrixCalculators.push_back(new StructEuclidean()); + }else if (Estimators[i] == "structchord") { + matrixCalculators.push_back(new StructChord()); + }else if (Estimators[i] == "hellinger") { + matrixCalculators.push_back(new Hellinger()); + }else if (Estimators[i] == "manhattan") { + matrixCalculators.push_back(new Manhattan()); + }else if (Estimators[i] == "structpearson") { + matrixCalculators.push_back(new StructPearson()); + }else if (Estimators[i] == "soergel") { + matrixCalculators.push_back(new Soergel()); + }else if (Estimators[i] == "spearman") { + matrixCalculators.push_back(new Spearman()); + }else if (Estimators[i] == "structkulczynski") { + matrixCalculators.push_back(new StructKulczynski()); + }else if (Estimators[i] == "speciesprofile") { + matrixCalculators.push_back(new SpeciesProfile()); + }else if (Estimators[i] == "hamming") { + matrixCalculators.push_back(new Hamming()); + }else if (Estimators[i] == "structchi2") { + matrixCalculators.push_back(new StructChi2()); + }else if (Estimators[i] == "gower") { + matrixCalculators.push_back(new Gower()); + }else if (Estimators[i] == "memchi2") { + matrixCalculators.push_back(new MemChi2()); + }else if (Estimators[i] == "memchord") { + matrixCalculators.push_back(new MemChord()); + }else if (Estimators[i] == "memeuclidean") { + matrixCalculators.push_back(new MemEuclidean()); + }else if (Estimators[i] == "mempearson") { + matrixCalculators.push_back(new MemPearson()); } } } @@ -186,53 +289,19 @@ MatrixOutputCommand::MatrixOutputCommand(string option) { //********************************************************************************************************************** -void MatrixOutputCommand::help(){ - try { - m->mothurOut("The dist.shared command can only be executed after a successful read.otu command.\n"); - m->mothurOut("The dist.shared command parameters are groups, calc, output and label. No parameters are required.\n"); - m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like included used.\n"); - m->mothurOut("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"); - m->mothurOut("The dist.shared command should be in the following format: dist.shared(groups=yourGroups, calc=yourCalcs, label=yourLabels).\n"); - m->mothurOut("The output parameter allows you to specify format of your distance matrix. Options are lt, and square. The default is lt.\n"); - m->mothurOut("Example dist.shared(groups=A-B-C, calc=jabund-sorabund).\n"); - m->mothurOut("The default value for groups is all the groups in your groupfile.\n"); - m->mothurOut("The default value for calc is jclass and thetayc.\n"); - validCalculator->printCalc("matrix", cout); - m->mothurOut("The dist.shared command outputs a .dist file for each calculator you specify at each distance you choose.\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "MatrixOutputCommand", "help"); - exit(1); - } -} - - -//********************************************************************************************************************** - -MatrixOutputCommand::~MatrixOutputCommand(){ - if (abort == false) { - delete input; globaldata->ginput = NULL; - delete read; - delete validCalculator; - } -} +MatrixOutputCommand::~MatrixOutputCommand(){} //********************************************************************************************************************** int MatrixOutputCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } //if the users entered no valid calculators don't execute command if (matrixCalculators.size() == 0) { m->mothurOut("No valid calculators."); m->mothurOutEndLine(); return 0; } - - //you have groups - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); - input = globaldata->ginput; + input = new InputData(sharedfile, "sharedfile"); lookup = input->getSharedRAbundVectors(); string lastLabel = lookup[0]->getLabel(); @@ -240,16 +309,16 @@ int MatrixOutputCommand::execute(){ set processedLabels; set userLabels = labels; - if (lookup.size() < 2) { m->mothurOut("You have not provided enough valid groups. I cannot run the command."); m->mothurOutEndLine(); return 0;} + 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(); - if (m->control_pressed) { delete read; delete input; globaldata->ginput = NULL; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } globaldata->Groups.clear(); return 0; } + 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) && ((allLines == 1) || (userLabels.size() != 0))) { - if (m->control_pressed) { outputTypes.clear(); delete read; delete input; globaldata->ginput = NULL; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); return 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(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); @@ -282,7 +351,7 @@ int MatrixOutputCommand::execute(){ lookup = input->getSharedRAbundVectors(); } - if (m->control_pressed) { outputTypes.clear(); delete read; delete input; globaldata->ginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); return 0; } + 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; @@ -297,7 +366,7 @@ int MatrixOutputCommand::execute(){ } } - if (m->control_pressed) { outputTypes.clear(); delete read; delete input; globaldata->ginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); return 0; } + 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) { @@ -309,10 +378,17 @@ int MatrixOutputCommand::execute(){ for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } } - if (m->control_pressed) { outputTypes.clear(); delete read; delete input; globaldata->ginput = NULL; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); return 0; } + 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(); + 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(); @@ -389,6 +465,14 @@ int MatrixOutputCommand::process(vector thisLookup){ //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 @@ -397,7 +481,7 @@ int MatrixOutputCommand::process(vector thisLookup){ } } - exportFileName = outputDir + m->getRootName(m->getSimpleName(globaldata->inputFileName)) + matrixCalculators[i]->getName() + "." + thisLookup[0]->getLabel() + "." + output + ".dist"; + 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);