X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracunweightedcommand.cpp;h=fbbc4f1de67cebeb1b9e57a4dce47f499e272f63;hb=edad2fa8defaa6856b3606a215bf64b91340eeb4;hp=a50d147de23d7cbc882be909e4a78870a867d4c3;hpb=a98eb683e17d8e49583bf2d215ab7562a4cdca75;p=mothur.git diff --git a/unifracunweightedcommand.cpp b/unifracunweightedcommand.cpp index a50d147..fbbc4f1 100644 --- a/unifracunweightedcommand.cpp +++ b/unifracunweightedcommand.cpp @@ -9,15 +9,67 @@ #include "unifracunweightedcommand.h" +//********************************************************************************************************************** +vector UnifracUnweightedCommand::getValidParameters(){ + try { + string Array[] = {"groups","iters","distance","random", "processors","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "UnifracUnweightedCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +UnifracUnweightedCommand::UnifracUnweightedCommand(){ + try { + globaldata = GlobalData::getInstance(); + abort = true; calledHelp = true; + vector tempOutNames; + outputTypes["unweighted"] = tempOutNames; + outputTypes["uwsummary"] = tempOutNames; + outputTypes["phylip"] = tempOutNames; + outputTypes["column"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "UnifracUnweightedCommand", "UnifracUnweightedCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector UnifracUnweightedCommand::getRequiredParameters(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "UnifracUnweightedCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector UnifracUnweightedCommand::getRequiredFiles(){ + try { + string Array[] = {"tree","group"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + return myArray; + } + catch(exception& e) { + m->errorOut(e, "UnifracUnweightedCommand", "getRequiredFiles"); + exit(1); + } +} /***********************************************************/ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { try { globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; Groups.clear(); //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } else { //valid paramters for this command @@ -34,6 +86,13 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["unweighted"] = tempOutNames; + outputTypes["uwsummary"] = tempOutNames; + outputTypes["phylip"] = tempOutNames; + outputTypes["column"] = tempOutNames; + if (globaldata->gTree.size() == 0) {//no trees were read m->mothurOut("You must execute the read.tree command, before you may execute the unifrac.unweighted command."); m->mothurOutEndLine(); abort = true; } @@ -55,8 +114,12 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { itersString = validParameter.validFile(parameters, "iters", false); if (itersString == "not found") { itersString = "1000"; } convert(itersString, iters); - string temp = validParameter.validFile(parameters, "distance", false); if (temp == "not found") { temp = "false"; } - phylip = m->isTrue(temp); + string temp = validParameter.validFile(parameters, "distance", false); + if (temp == "not found") { phylip = false; outputForm = ""; } + else{ + if ((temp == "lt") || (temp == "column") || (temp == "square")) { phylip = true; outputForm = temp; } + else { m->mothurOut("Options for distance are: lt, square, or column. Using lt."); m->mothurOutEndLine(); phylip = true; outputForm = "lt"; } + } temp = validParameter.validFile(parameters, "random", false); if (temp == "not found") { temp = "f"; } random = m->isTrue(temp); @@ -77,7 +140,7 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { T = globaldata->gTree; tmap = globaldata->gTreemap; sumFile = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; - outputNames.push_back(sumFile); + outputNames.push_back(sumFile); outputTypes["uwsummary"].push_back(sumFile); m->openOutputFile(sumFile, outSum); util = new SharedUtil(); @@ -104,11 +167,12 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { void UnifracUnweightedCommand::help(){ try { m->mothurOut("The unifrac.unweighted command can only be executed after a successful read.tree command.\n"); - m->mothurOut("The unifrac.unweighted command parameters are groups, iters, distance and random. No parameters are required.\n"); + m->mothurOut("The unifrac.unweighted command parameters are groups, iters, distance, processors and random. No parameters are required.\n"); m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 1 valid group.\n"); m->mothurOut("The group names are separated by dashes. The iters parameter allows you to specify how many random trees you would like compared to your tree.\n"); - m->mothurOut("The distance parameter allows you to create a distance file from the results. The default is false.\n"); + m->mothurOut("The distance parameter allows you to create a distance file from the results. The default is false. You may set distance to lt, square or column.\n"); m->mothurOut("The random parameter allows you to shut off the comparison to random trees. The default is false, meaning compare don't your trees with randomly generated trees.\n"); + m->mothurOut("The processors parameter allows you to specify the number of processors to use. The default is 1.\n"); m->mothurOut("The unifrac.unweighted command should be in the following format: unifrac.unweighted(groups=yourGroups, iters=yourIters).\n"); m->mothurOut("Example unifrac.unweighted(groups=A-B-C, iters=500).\n"); m->mothurOut("The default value for groups is all the groups in your groupfile, and iters is 1000.\n"); @@ -126,7 +190,7 @@ void UnifracUnweightedCommand::help(){ int UnifracUnweightedCommand::execute() { try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } int start = time(NULL); @@ -134,6 +198,8 @@ int UnifracUnweightedCommand::execute() { randomData.resize(numComp,0); //data[0] = unweightedscore //create new tree with same num nodes and leaves as users + if (numComp < processors) { processors = numComp; } + outSum << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" <<'\t' << "UWSig" << endl; m->mothurOut("Tree#\tGroups\tUWScore\tUWSig"); m->mothurOutEndLine(); @@ -150,6 +216,7 @@ int UnifracUnweightedCommand::execute() { if (random) { output = new ColumnFile(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString); outputNames.push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); + outputTypes["unweighted"].push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); } @@ -194,7 +261,7 @@ int UnifracUnweightedCommand::execute() { } //report progress - m->mothurOut("Iter: " + toString(j+1)); m->mothurOutEndLine(); +// m->mothurOut("Iter: " + toString(j+1)); m->mothurOutEndLine(); } for(int a = 0; a < numComp; a++) { @@ -314,15 +381,23 @@ void UnifracUnweightedCommand::printUWSummaryFile(int i) { /***********************************************************/ void UnifracUnweightedCommand::createPhylipFile(int i) { try { - string phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist"; - outputNames.push_back(phylipFileName); + string phylipFileName; + if ((outputForm == "lt") || (outputForm == "square")) { + phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.phylip.dist"; + outputNames.push_back(phylipFileName); outputTypes["phylip"].push_back(phylipFileName); + }else { //column + phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.column.dist"; + outputNames.push_back(phylipFileName); outputTypes["column"].push_back(phylipFileName); + } ofstream out; m->openOutputFile(phylipFileName, out); - - //output numSeqs - out << globaldata->Groups.size() << endl; - + + if ((outputForm == "lt") || (outputForm == "square")) { + //output numSeqs + out << globaldata->Groups.size() << endl; + } + //make matrix with scores in it vector< vector > dists; dists.resize(globaldata->Groups.size()); for (int i = 0; i < globaldata->Groups.size(); i++) { @@ -332,7 +407,7 @@ void UnifracUnweightedCommand::createPhylipFile(int i) { //flip it so you can print it int count = 0; for (int r=0; rGroups.size(); r++) { - for (int l = r+1; l < globaldata->Groups.size(); l++) { + for (int l = 0; l < r; l++) { dists[r][l] = utreeScores[count][0]; dists[l][r] = utreeScores[count][0]; count++; @@ -346,11 +421,30 @@ void UnifracUnweightedCommand::createPhylipFile(int i) { if (name.length() < 10) { //pad with spaces to make compatible while (name.length() < 10) { name += " "; } } - out << name << '\t'; - //output distances - for (int l = 0; l < r; l++) { out << dists[r][l] << '\t'; } - out << endl; + if (outputForm == "lt") { + out << name << '\t'; + + //output distances + for (int l = 0; l < r; l++) { out << dists[r][l] << '\t'; } + out << endl; + }else if (outputForm == "square") { + out << name << '\t'; + + //output distances + for (int l = 0; l < globaldata->Groups.size(); l++) { out << setprecision(11) << dists[r][l] << '\t'; } + out << endl; + }else{ + //output distances + for (int l = 0; l < r; l++) { + string otherName = globaldata->Groups[l]; + if (otherName.length() < 10) { //pad with spaces to make compatible + while (otherName.length() < 10) { otherName += " "; } + } + + out << name << '\t' << otherName << dists[r][l] << endl; + } + } } out.close(); }