X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracunweightedcommand.cpp;h=7836eb682f19d444ae2ffb7f82fe538efdb7d933;hb=bd93b1a6f9fe9a6a4a7ac2e9f106e5c83a438856;hp=f1326a82ca524a396f102bdeb8fa53f7264d971f;hpb=38922fcff5a03abfedffda3e06a45fad2270a044;p=mothur.git diff --git a/unifracunweightedcommand.cpp b/unifracunweightedcommand.cpp index f1326a8..7836eb6 100644 --- a/unifracunweightedcommand.cpp +++ b/unifracunweightedcommand.cpp @@ -10,271 +10,363 @@ #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", "processors","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; - T = globaldata->gTree; - tmap = globaldata->gTreemap; - unweightedFile = globaldata->getTreeFile() + ".unweighted"; - openOutputFile(unweightedFile, out); - //column headers - out << "Comb" << '\t' << "Score" << '\t' << "UserFreq" << '\t' << "UserCumul" << '\t' << "RandFreq" << '\t' << "RandCumul" << endl; + //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 += 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 { + m->splitAtDash(groups, Groups); + globaldata->Groups = Groups; + } - sumFile = globaldata->getTreeFile() + ".uwsummary"; - openOutputFile(sumFile, outSum); - //column headers - outSum << "Tree#" << '\t' << "Comb" << '\t' << "UWScore" << '\t' << '\t' << "UWSig" << endl; - - setGroups(); //sets users groups to analyze - convert(globaldata->getIters(), iters); //how many random trees to generate - unweighted = new Unweighted(tmap); - + 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); + + 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 = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; + outputNames.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 + util->getCombos(groupComb, globaldata->Groups, numComp); + + if (numGroups == 1) { numComp++; groupComb.push_back(allGroups); } + + 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 false, meaning compare don't 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; } + + 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 - randT = new Tree(); - + + 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++) { + 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 + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString); + outputNames.push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); + } + + //get unweighted for users tree rscoreFreq.resize(numComp); - uscoreFreq.resize(numComp); rCumul.resize(numComp); - uCumul.resize(numComp); - validScores.resize(numComp); utreeScores.resize(numComp); UWScoreSig.resize(numComp); - cout << "Processing tree " << i+1 << endl; - outSum << "Tree#" << i+1 << endl; - out << "Tree#" << i+1 << endl; - 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++) { - //update uscoreFreq - it = uscoreFreq[k].find(userData[k]); - if (it == uscoreFreq[k].end()) {//new score - uscoreFreq[k][userData[k]] = 1; - }else{ uscoreFreq[k][userData[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]; } - //copy T[i]'s info. - randT->getCopy(T[i]); - - //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(randT, "", ""); + //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 ucumul = 1.0000; - 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++) { - it2 = uscoreFreq[a].find(it->first); - //make uCumul map - uCumul[a][it->first] = ucumul; - //user data has that score - if (it2 != uscoreFreq[a].end()) { uscoreFreq[a][it->first] /= T.size(); ucumul-= it2->second; } - else { uscoreFreq[a][it->first] = 0.0000; } //no user trees with that score - - //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; + + 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); } + + } + + + 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; } - UWScoreSig[a].push_back(rCumul[a][userData[a]]); + + //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(); + + outSum.close(); - rscoreFreq.clear(); - uscoreFreq.clear(); - rCumul.clear(); - uCumul.clear(); - validScores.clear(); - utreeScores.clear(); - UWScoreSig.clear(); - } - //reset groups parameter - globaldata->Groups.clear(); globaldata->setGroups(""); + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - delete randT; + 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); } } /***********************************************************/ void UnifracUnweightedCommand::printUnweightedFile() { try { - //format output - out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); + vector data; + vector tags; + 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 (it = validScores[a].begin(); it != validScores[a].end(); it++) { - out << setprecision(6) << groupComb[a] << '\t' << it->first << '\t' << '\t' << uscoreFreq[a][it->first] << '\t' << uCumul[a][it->first] << '\t' << rscoreFreq[a][it->first] << '\t' << rCumul[a][it->first] << endl; + 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(); } + output->resetFile(); } - out.close(); - } 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 i = 0; i< T.size(); i++) { - for(int a = 0; a < numComp; a++) { - outSum << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << '\t' << utreeScores[a][i] << '\t' << UWScoreSig[a][i] << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << '\t' << utreeScores[a][i] << '\t' << UWScoreSig[a][i] << endl; - } + + for(int a = 0; a < numComp; a++) { + outSum << i+1 << '\t'; + m->mothurOut(toString(i+1) + "\t"); + + 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 { + 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{ + 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(); + } } - outSum.close(); } 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"; + m->errorOut(e, "UnifracUnweightedCommand", "printUWSummaryFile"); exit(1); } } /***********************************************************/ - -void UnifracUnweightedCommand::setGroups() { +void UnifracUnweightedCommand::createPhylipFile(int i) { 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); - } - } + string phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist"; + outputNames.push_back(phylipFileName); + + ofstream out; + m->openOutputFile(phylipFileName, out); - //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]; - } - }else { - for (int i = 0; i < globaldata->Groups.size(); i++) { - allGroups += globaldata->Groups[i]; - numGroups++; - } - } - }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]; - } - numGroups = 1; + //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); } - //calculate number of comparsions - numComp = 0; - for (int r=0; rGroups[r]+globaldata->Groups[l]); - numComp++; + //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++; } } - //ABC - if (numComp != 1) { - groupComb.push_back(allGroups); - numComp++; + //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 setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracUnweightedCommand", "createPhylipFile"); 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); - } - } -/*****************************************************************/ +/***********************************************************/ + +