X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracunweightedcommand.cpp;h=634bf0caff8d279e259c64fb76f28737aaaa8219;hb=0486bc2eed084ac387d2f59b6d23d13b2382daf7;hp=154c528a851eb297a0783e26bb206aae80fc278c;hpb=cd37904452dc95b183ff313ff05720c562902487;p=mothur.git diff --git a/unifracunweightedcommand.cpp b/unifracunweightedcommand.cpp index 154c528..634bf0c 100644 --- a/unifracunweightedcommand.cpp +++ b/unifracunweightedcommand.cpp @@ -9,19 +9,71 @@ #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) { +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 - string Array[] = {"groups","iters"}; + string Array[] = {"groups","iters","distance","random", "processors","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -34,27 +86,62 @@ 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 - cout << "You must execute the read.tree command, before you may execute the unifrac.unweighted command." << endl; abort = true; } - + m->mothurOut("You must execute the read.tree command, before you may execute the unifrac.unweighted command."); m->mothurOutEndLine(); 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 + } + //check for optional parameter and set defaults // ...at some point should added some additional type checking... groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } else { - splitAtDash(groups, Groups); + m->splitAtDash(groups, Groups); globaldata->Groups = Groups; } - itersString = validParameter.validFile(parameters, "iters", false); if (itersString == "not found") { itersString = "1000"; } + 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") { 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); + + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } + convert(temp, processors); + + if (!random) { iters = 0; } //turn off random calcs + //if user selects distance = true and no groups it won't calc the pairwise + if ((phylip) && (Groups.size() == 0)) { + groups = "all"; + m->splitAtDash(groups, Groups); + globaldata->Groups = Groups; + } + if (abort == false) { T = globaldata->gTree; tmap = globaldata->gTreemap; - sumFile = globaldata->getTreeFile() + ".uwsummary"; - openOutputFile(sumFile, outSum); + sumFile = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; + outputNames.push_back(sumFile); outputTypes["uwsummary"].push_back(sumFile); + m->openOutputFile(sumFile, outSum); util = new SharedUtil(); util->setGroups(globaldata->Groups, tmap->namesOfGroups, allGroups, numGroups, "unweighted"); //sets the groups the user wants to analyze @@ -70,11 +157,7 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function UnifracUnweightedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function UnifracUnweightedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "UnifracUnweightedCommand"); exit(1); } } @@ -83,24 +166,23 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { void UnifracUnweightedCommand::help(){ try { - cout << "The unifrac.unweighted command can only be executed after a successful read.tree command." << "\n"; - cout << "The unifrac.unweighted command parameters are groups and iters. No parameters are required." << "\n"; - cout << "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"; - cout << "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"; - cout << "The unifrac.unweighted command should be in the following format: unifrac.unweighted(groups=yourGroups, iters=yourIters)." << "\n"; - cout << "Example unifrac.unweighted(groups=A-B-C, iters=500)." << "\n"; - cout << "The default value for groups is all the groups in your groupfile, and iters is 1000." << "\n"; - cout << "The unifrac.unweighted command output two files: .unweighted and .uwsummary their descriptions are in the manual." << "\n"; - cout << "Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups)." << "\n" << "\n"; + 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, 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. 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"); + m->mothurOut("The unifrac.unweighted command output two files: .unweighted and .uwsummary their descriptions are in the manual.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } @@ -108,20 +190,33 @@ 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); userData.resize(numComp,0); //data[0] = unweightedscore randomData.resize(numComp,0); //data[0] = unweightedscore //create new tree with same num nodes and leaves as users outSum << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" <<'\t' << "UWSig" << endl; - cout << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" << '\t' << "UWSig" << endl; + m->mothurOut("Tree#\tGroups\tUWScore\tUWSig"); m->mothurOutEndLine(); //get pscores for users trees for (int i = 0; i < T.size(); i++) { + if (m->control_pressed) { + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + counter = 0; - output = new ColumnFile(globaldata->getTreeFile() + toString(i+1) + ".unweighted", itersString); + 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"); + } + //get unweighted for users tree rscoreFreq.resize(numComp); @@ -129,20 +224,27 @@ int UnifracUnweightedCommand::execute() { utreeScores.resize(numComp); UWScoreSig.resize(numComp); - userData = unweighted->getValues(T[i]); //userData[0] = unweightedscore + userData = unweighted->getValues(T[i], processors, outputDir); //userData[0] = unweightedscore + + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }return 0; } //output scores for each combination for(int k = 0; k < numComp; k++) { //saves users score utreeScores[k].push_back(userData[k]); - + + //add users score to validscores + validScores[userData[k]] = userData[k]; } - - //get unweighted scores for random trees + + //get unweighted scores for random trees - if random is false iters = 0 for (int j = 0; j < iters; j++) { - //we need a different getValues because when we swap the labels we only want to swap those in each parwise comparison - randomData = unweighted->getValues(T[i], "", ""); + + //we need a different getValues because when we swap the labels we only want to swap those in each pairwise comparison + randomData = unweighted->getValues(T[i], "", "", processors, outputDir); + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + for(int k = 0; k < numComp; k++) { //add trees unweighted score to map of scores map::iterator it = rscoreFreq[k].find(randomData[k]); @@ -156,28 +258,35 @@ int UnifracUnweightedCommand::execute() { validScores[randomData[k]] = randomData[k]; } + //report progress +// m->mothurOut("Iter: " + toString(j+1)); m->mothurOutEndLine(); } - + for(int a = 0; a < numComp; a++) { float rcumul = 1.0000; - //this loop fills the cumulative maps and put 0.0000 in the score freq map to make it easier to print. - for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { - //make rscoreFreq map and rCumul - map::iterator it2 = rscoreFreq[a].find(it->first); - rCumul[a][it->first] = rcumul; - //get percentage of random trees with that info - if (it2 != rscoreFreq[a].end()) { rscoreFreq[a][it->first] /= iters; rcumul-= it2->second; } - else { rscoreFreq[a][it->first] = 0.0000; } //no random trees with that score - } - UWScoreSig[a].push_back(rCumul[a][userData[a]]); + + if (random) { + //this loop fills the cumulative maps and put 0.0000 in the score freq map to make it easier to print. + for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { + //make rscoreFreq map and rCumul + map::iterator it2 = rscoreFreq[a].find(it->first); + rCumul[a][it->first] = rcumul; + //get percentage of random trees with that info + if (it2 != rscoreFreq[a].end()) { rscoreFreq[a][it->first] /= iters; rcumul-= it2->second; } + else { rscoreFreq[a][it->first] = 0.0000; } //no random trees with that score + } + UWScoreSig[a].push_back(rCumul[a][userData[a]]); + }else { UWScoreSig[a].push_back(0.0); } + } - - - - printUnweightedFile(); + + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + //print output files printUWSummaryFile(i); + if (random) { printUnweightedFile(); delete output; } + if (phylip) { createPhylipFile(i); } - delete output; rscoreFreq.clear(); rCumul.clear(); validScores.clear(); @@ -185,19 +294,23 @@ int UnifracUnweightedCommand::execute() { UWScoreSig.clear(); } - //reset groups parameter - globaldata->Groups.clear(); + outSum.close(); + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run unifrac.unweighted."); m->mothurOutEndLine(); + + 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 UnifracUnweightedCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "execute"); exit(1); } } @@ -206,13 +319,15 @@ void UnifracUnweightedCommand::printUnweightedFile() { try { vector data; vector tags; - tags.push_back("Score"); tags.push_back("RandFreq"); tags.push_back("RandCumul"); + tags.push_back("Score"); + tags.push_back("RandFreq"); tags.push_back("RandCumul"); + for(int a = 0; a < numComp; a++) { output->initFile(groupComb[a], tags); //print each line for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { - data.push_back(it->first); data.push_back(rscoreFreq[a][it->first]); data.push_back(rCumul[a][it->first]); + data.push_back(it->first); data.push_back(rscoreFreq[a][it->first]); data.push_back(rCumul[a][it->first]); output->output(data); data.clear(); } @@ -220,11 +335,7 @@ void UnifracUnweightedCommand::printUnweightedFile() { } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function printUnweightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function printUnweightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "printUnweightedFile"); exit(1); } } @@ -240,28 +351,107 @@ void UnifracUnweightedCommand::printUWSummaryFile(int i) { for(int a = 0; a < numComp; a++) { outSum << i+1 << '\t'; - cout << i+1 << '\t'; + m->mothurOut(toString(i+1) + "\t"); - if (UWScoreSig[a][0] > (1/(float)iters)) { - outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; - cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; - }else { - outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; - cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; + if (random) { + if (UWScoreSig[a][0] > (1/(float)iters)) { + outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; + cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t" + toString(UWScoreSig[a][0])+ "\n"); + }else { + outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; + cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t<" + toString((1/float(iters))) + "\n"); + } + }else{ + outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl; + cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl; + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t0.00\n"); } } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function printUWSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "printUWSummaryFile"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function printUWSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +/***********************************************************/ +void UnifracUnweightedCommand::createPhylipFile(int i) { + try { + 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); + + 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++) { + dists[i].resize(globaldata->Groups.size(), 0.0); + } + + //flip it so you can print it + int count = 0; + for (int r=0; rGroups.size(); r++) { + for (int l = 0; l < r; l++) { + dists[r][l] = utreeScores[count][0]; + dists[l][r] = utreeScores[count][0]; + count++; + } + } + + //output to file + for (int r=0; rGroups.size(); r++) { + //output name + string name = globaldata->Groups[r]; + if (name.length() < 10) { //pad with spaces to make compatible + while (name.length() < 10) { name += " "; } + } + + 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 << 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(); + } + catch(exception& e) { + m->errorOut(e, "UnifracUnweightedCommand", "createPhylipFile"); exit(1); } } - /***********************************************************/ +