X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracunweightedcommand.cpp;h=77cd4d7d686ed5607c11eb07d2245c62f2ef2deb;hb=438aa88dbc092d9c1c80ec3fa20c8e47f97101c4;hp=5a7cc367cd12212743f836cda998a10c339b5c09;hpb=626e77d477ecca8b03c942bdc66f8bb8c413b356;p=mothur.git diff --git a/unifracunweightedcommand.cpp b/unifracunweightedcommand.cpp index 5a7cc36..77cd4d7 100644 --- a/unifracunweightedcommand.cpp +++ b/unifracunweightedcommand.cpp @@ -10,120 +10,245 @@ #include "unifracunweightedcommand.h" /***********************************************************/ -UnifracUnweightedCommand::UnifracUnweightedCommand() { +UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { try { globaldata = GlobalData::getInstance(); + abort = false; + Groups.clear(); + + //allow user to run help + if(option == "help") { help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"groups","iters","distance","random", "outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + + //check to make sure all parameters are valid for command + for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + 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; } + + //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 += 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); + globaldata->Groups = Groups; + } + + 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 = isTrue(temp); + + temp = validParameter.validFile(parameters, "random", false); if (temp == "not found") { temp = "true"; } + random = isTrue(temp); + + 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"; + splitAtDash(groups, Groups); + globaldata->Groups = Groups; + } + + if (abort == false) { + T = globaldata->gTree; + tmap = globaldata->gTreemap; + sumFile = outputDir + getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; + outputNames.push_back(sumFile); + openOutputFile(sumFile, outSum); + + util = new SharedUtil(); + util->setGroups(globaldata->Groups, tmap->namesOfGroups, allGroups, numGroups, "unweighted"); //sets the groups the user wants to analyze + util->getCombos(groupComb, globaldata->Groups, numComp); + + if (numGroups == 1) { numComp++; groupComb.push_back(allGroups); } + + unweighted = new Unweighted(tmap); + + } + + } - T = globaldata->gTree; - tmap = globaldata->gTreemap; - sumFile = globaldata->getTreeFile() + ".uwsummary"; - openOutputFile(sumFile, outSum); - - setGroups(); //sets users groups to analyze - convert(globaldata->getIters(), iters); //how many random trees to generate - unweighted = new Unweighted(tmap); - } 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"; + m->errorOut(e, "UnifracUnweightedCommand", "UnifracUnweightedCommand"); 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"; +} + +//********************************************************************************************************************** + +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 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 random parameter allows you to shut off the comparison to random trees. The default is true, meaning compare your trees with randomly generated trees.\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) { + m->errorOut(e, "UnifracUnweightedCommand", "help"); exit(1); } } + + /***********************************************************/ int UnifracUnweightedCommand::execute() { try { - + + if (abort == true) { return 0; } + 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; + m->mothurOut("Tree#\tGroups\tUWScore\tUWSig"); m->mothurOutEndLine(); + //get pscores for users trees for (int i = 0; i < T.size(); i++) { - unweightedFile = globaldata->getTreeFile() + toString(i+1) + ".unweighted"; - unweightedFileout = globaldata->getTreeFile() + "temp." + toString(i+1) + ".unweighted"; - //column headers - outSum << "Tree# " << i+1 << endl; - outSum << "Comb" << '\t' << "UWScore" << '\t' << '\t' << "UWSig" << endl; - + if (m->control_pressed) { + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + + counter = 0; + + if (random) { + output = new ColumnFile(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString); + outputNames.push_back(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); + } + + //get unweighted for users tree rscoreFreq.resize(numComp); rCumul.resize(numComp); - validScores.resize(numComp); utreeScores.resize(numComp); UWScoreSig.resize(numComp); - cout << "Processing tree " << i+1 << endl; userData = unweighted->getValues(T[i]); //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++) { - //add users score to valid scores - validScores[k][userData[k]] = userData[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 + //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], "", ""); + 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++) { -//cout << "iter " << j << " comp " << k << " = " << randomData[k] << endl; //add trees unweighted score to map of scores - it2 = rscoreFreq[k].find(randomData[k]); - if (it2 != rscoreFreq[k].end()) {//already have that score + map::iterator it = rscoreFreq[k].find(randomData[k]); + if (it != rscoreFreq[k].end()) {//already have that score rscoreFreq[k][randomData[k]]++; }else{//first time we have seen this score rscoreFreq[k][randomData[k]] = 1; } //add randoms score to validscores - validScores[k][randomData[k]] = randomData[k]; + validScores[randomData[k]] = randomData[k]; } } - 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 (it = validScores[a].begin(); it != validScores[a].end(); it++) { - //make rscoreFreq map and rCumul - 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 + 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 + } + + if (random) { UWScoreSig[a].push_back(rCumul[a][userData[a]]); } + else { UWScoreSig[a].push_back(0.0); } } - UWScoreSig[a].push_back(rCumul[a][userData[a]]); + + + 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); } + + rscoreFreq.clear(); + rCumul.clear(); + validScores.clear(); + utreeScores.clear(); + UWScoreSig.clear(); } - printUnweightedFile(); - printUWSummaryFile(); - - rscoreFreq.clear(); - rCumul.clear(); - validScores.clear(); - utreeScores.clear(); - UWScoreSig.clear(); - } - //reset groups parameter - globaldata->Groups.clear(); globaldata->setGroups(""); + outSum.close(); + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + 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); } } @@ -131,206 +256,113 @@ int UnifracUnweightedCommand::execute() { void UnifracUnweightedCommand::printUnweightedFile() { try { vector data; + vector tags; + tags.push_back("Score"); + tags.push_back("RandFreq"); tags.push_back("RandCumul"); + for(int a = 0; a < numComp; a++) { - initFile(groupComb[a]); + output->initFile(groupComb[a], tags); //print each line - for (it = validScores[a].begin(); it != validScores[a].end(); it++) { - data.push_back(it->first); data.push_back(rscoreFreq[a][it->first]); data.push_back(rCumul[a][it->first]); - output(data); + 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]); + output->output(data); data.clear(); } - resetFile(); + output->resetFile(); } - - out.close(); - inFile.close(); - remove(unweightedFileout.c_str()); - } 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); } } /***********************************************************/ -void UnifracUnweightedCommand::printUWSummaryFile() { +void UnifracUnweightedCommand::printUWSummaryFile(int i) { try { //format output outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); - + //print each line - for(int a = 0; a < numComp; a++) { - outSum << setprecision(6) << groupComb[a] << '\t' << '\t' << utreeScores[a][0] << '\t' << UWScoreSig[a][0] << endl; - cout << setprecision(6) << groupComb[a] << '\t' << '\t' << utreeScores[a][0] << '\t' << UWScoreSig[a][0] << endl; - } - - } - 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"; - 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"; - exit(1); - } -} -/***********************************************************/ -void UnifracUnweightedCommand::setGroups() { - try { - string allGroups = ""; - numGroups = 0; - //if the user has not entered specific groups to analyze then do them all - if (globaldata->Groups.size() != 0) { - if (globaldata->Groups[0] != "all") { - //check that groups are valid - for (int i = 0; i < globaldata->Groups.size(); i++) { - if (tmap->isValidGroup(globaldata->Groups[i]) != true) { - cout << globaldata->Groups[i] << " is not a valid group, and will be disregarded." << endl; - // erase the invalid group from globaldata->Groups - globaldata->Groups.erase(globaldata->Groups.begin()+i); - } - } + for(int a = 0; a < numComp; a++) { + outSum << i+1 << '\t'; + m->mothurOut(toString(i+1) + "\t"); - //if the user only entered invalid groups - if (globaldata->Groups.size() == 0) { - cout << "When using the groups parameter you must have at least 1 valid group. I will run the command using all the groups in your groupfile." << endl; - for (int i = 0; i < tmap->namesOfGroups.size(); i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); - numGroups++; - allGroups += tmap->namesOfGroups[i]; - } + 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])); m->mothurOutEndLine(); }else { - for (int i = 0; i < globaldata->Groups.size(); i++) { - allGroups += globaldata->Groups[i]; - numGroups++; - } + 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)))); m->mothurOutEndLine(); } - }else{//user has enter "all" and wants the default groups - for (int i = 0; i < tmap->namesOfGroups.size(); i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); - numGroups++; - allGroups += tmap->namesOfGroups[i]; - } - globaldata->setGroups(""); - } - }else { - for (int i = 0; i < tmap->namesOfGroups.size(); i++) { - allGroups += tmap->namesOfGroups[i]; + }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"); m->mothurOutEndLine(); } - numGroups = 1; } - //calculate number of comparsions - numComp = 0; - for (int r=0; rGroups[r]+globaldata->Groups[l]); - numComp++; - } - } - - //ABC - if (numComp != 1) { - groupComb.push_back(allGroups); - numComp++; - } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function setGroups. 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 setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - } -/*****************************************************************/ - -void UnifracUnweightedCommand::initFile(string label){ +/***********************************************************/ +void UnifracUnweightedCommand::createPhylipFile(int i) { try { - if(counter != 0){ - openOutputFile(unweightedFileout, out); - openInputFile(unweightedFile, inFile); - - string inputBuffer; - getline(inFile, inputBuffer); + string phylipFileName = outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist"; + outputNames.push_back(phylipFileName); - out << inputBuffer << '\t' << label + "Score" << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; - }else{ - openOutputFile(unweightedFileout, out); - out << label + "Score" << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; + ofstream out; + openOutputFile(phylipFileName, out); + + //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); } - - out.setf(ios::fixed, ios::floatfield); - out.setf(ios::showpoint); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} - -/***********************************************************************/ - -void UnifracUnweightedCommand::output(vector data){ - try { - if(counter != 0){ - string inputBuffer; - getline(inFile, inputBuffer); - out << inputBuffer << setprecision(6) << '\t' << data[0] << '\t' << data[1] << '\t' << data[2] << endl; + //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++) { + dists[r][l] = utreeScores[count][0]; + dists[l][r] = utreeScores[count][0]; + count++; + } } - else{ - out << setprecision(6) << data[0] << '\t' << data[1] << '\t' << data[2] << endl; + + //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 += " "; } + } + out << name << '\t'; + + //output distances + for (int l = 0; l < r; l++) { out << dists[r][l] << '\t'; } + out << endl; } - + out.close(); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "createPhylipFile"); exit(1); } -}; +} +/***********************************************************/ -/***********************************************************************/ -void UnifracUnweightedCommand::resetFile(){ - try { - if(counter != 0){ - out.close(); - inFile.close(); - } - else{ - out.close(); - } - counter = 1; - - remove(unweightedFile.c_str()); - rename(unweightedFileout.c_str(), unweightedFile.c_str()); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracUnweightedCommand class function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -}