X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=parsimonycommand.cpp;h=3295de2d5c4db657b2a828c8be090476109d0f9a;hb=260ae19c36cb11a53ddc5a75b5e507f8dd8b31d6;hp=4fa4ec5ed0943614bf4da9d5a1f03b5d8f706a42;hpb=c5c7502f435e1413c19e373dab1dfebcaa67588d;p=mothur.git diff --git a/parsimonycommand.cpp b/parsimonycommand.cpp index 4fa4ec5..3295de2 100644 --- a/parsimonycommand.cpp +++ b/parsimonycommand.cpp @@ -10,60 +10,136 @@ #include "parsimonycommand.h" /***********************************************************/ -ParsimonyCommand::ParsimonyCommand() { +ParsimonyCommand::ParsimonyCommand(string option) { try { globaldata = GlobalData::getInstance(); + abort = false; + Groups.clear(); + + //allow user to run help + if(option == "help") { help(); abort = true; } - //randomtree will tell us if user had their own treefile or if they just want the random distribution - randomtree = globaldata->getRandomTree(); - - //user has entered their own tree - if (randomtree == "") { - T = globaldata->gTree; - tmap = globaldata->gTreemap; - parsFile = globaldata->getTreeFile() + ".parsimony"; - parsFileout = globaldata->getTreeFile() + "temp" + ".parsimony"; - sumFile = globaldata->getTreeFile() + ".psummary"; - openOutputFile(sumFile, outSum); - }else { //user wants random distribution - savetmap = globaldata->gTreemap; - getUserInput(); - parsFile = randomtree; - parsFileout = globaldata->getTreeFile() + "temp"; - } - - //set users groups to analyze - 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); - globaldata->setGroups(""); + else { + //valid paramters for this command + string Array[] = {"random","groups","iters","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; - //ABC - if (numComp != 1) { - groupComb.push_back(allGroups); - numComp++; + //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; } + } + + randomtree = validParameter.validFile(parameters, "random", false); if (randomtree == "not found") { randomtree = ""; } + + //are you trying to use parsimony without reading a tree or saying you want random distribution + if (randomtree == "") { + if (globaldata->gTree.size() == 0) { + m->mothurOut("You must read a treefile and a groupfile or set the randomtree parameter to the output filename you wish, before you may execute the parsimony command."); m->mothurOutEndLine(); abort = true; } + } + + //if the user changes the output directory command factory will send this info to us in the output parameter + string outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } + + //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 = ""; globaldata->Groups.clear(); } + else { + m->splitAtDash(groups, Groups); + globaldata->Groups = Groups; + } + + itersString = validParameter.validFile(parameters, "iters", false); if (itersString == "not found") { itersString = "1000"; } + convert(itersString, iters); + + if (abort == false) { + //randomtree will tell us if user had their own treefile or if they just want the random distribution + //user has entered their own tree + if (randomtree == "") { + T = globaldata->gTree; + tmap = globaldata->gTreemap; + + if(outputDir == "") { outputDir += m->hasPath(globaldata->getTreeFile()); } + output = new ColumnFile(outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".parsimony", itersString); + outputNames.push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".parsimony"); + + sumFile = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".psummary"; + m->openOutputFile(sumFile, outSum); + outputNames.push_back(sumFile); + }else { //user wants random distribution + savetmap = globaldata->gTreemap; + getUserInput(); + + if(outputDir == "") { outputDir += m->hasPath(randomtree); } + output = new ColumnFile(outputDir+ m->getSimpleName(randomtree), itersString); + outputNames.push_back(outputDir+ m->getSimpleName(randomtree)); + } + + //set users groups to analyze + util = new SharedUtil(); + util->setGroups(globaldata->Groups, tmap->namesOfGroups, allGroups, numGroups, "parsimony"); //sets the groups the user wants to analyze + util->getCombos(groupComb, globaldata->Groups, numComp); + + if (numGroups == 1) { numComp++; groupComb.push_back(allGroups); } + + pars = new Parsimony(tmap); + counter = 0; + + } + } - convert(globaldata->getIters(), iters); //how many random trees to generate - pars = new Parsimony(tmap); - counter = 0; - } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function ParsimonyCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ParsimonyCommand", "ParsimonyCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function ParsimonyCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} + +//********************************************************************************************************************** + +void ParsimonyCommand::help(){ + try { + m->mothurOut("The parsimony command can only be executed after a successful read.tree command, unless you use the random parameter.\n"); + m->mothurOut("The parsimony command parameters are random, groups and iters. 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 parsimony command should be in the following format: parsimony(random=yourOutputFilename, groups=yourGroups, iters=yourIters).\n"); + m->mothurOut("Example parsimony(random=out, iters=500).\n"); + m->mothurOut("The default value for random is "" (meaning you want to use the trees in your inputfile, randomtree=out means you just want the random distribution of trees outputted to out.rd_parsimony),\n"); + m->mothurOut("and iters is 1000. The parsimony command output two files: .parsimony and .psummary their descriptions are in the manual.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. random), '=' and parameters (i.e.yourOutputFilename).\n\n"); + } + catch(exception& e) { + m->errorOut(e, "ParsimonyCommand", "help"); exit(1); } } + + /***********************************************************/ int ParsimonyCommand::execute() { try { + + if (abort == true) { return 0; } + Progress* reading; reading = new Progress("Comparing to random:", iters); + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; + if (randomtree == "") { outSum.close(); } + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } + + //get pscore for users tree userData.resize(numComp,0); //data = AB, AC, BC, ABC. randomData.resize(numComp,0); //data = AB, AC, BC, ABC. @@ -78,12 +154,21 @@ int ParsimonyCommand::execute() { //get pscores for users trees for (int i = 0; i < T.size(); i++) { userData = pars->getValues(T[i]); //data = AB, AC, BC, ABC. + + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; + if (randomtree == "") { outSum.close(); } + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } + //output scores for each combination for(int k = 0; k < numComp; k++) { //update uscoreFreq - it = uscoreFreq[k].find(userData[k]); + map::iterator it = uscoreFreq[k].find(userData[k]); if (it == uscoreFreq[k].end()) {//new score uscoreFreq[k][userData[k]] = 1; }else{ uscoreFreq[k][userData[k]]++; } @@ -98,6 +183,7 @@ int ParsimonyCommand::execute() { //get pscores for random trees for (int j = 0; j < iters; j++) { + //create new tree with same num nodes and leaves as users randT = new Tree(); @@ -106,11 +192,19 @@ int ParsimonyCommand::execute() { //get pscore of random tree randomData = pars->getValues(randT); + + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; delete randT; + if (randomtree == "") { outSum.close(); } + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } for(int r = 0; r < numComp; r++) { //add trees pscore to map of scores - it2 = rscoreFreq[r].find(randomData[r]); - if (it2 != rscoreFreq[r].end()) {//already have that score + map::iterator it = rscoreFreq[r].find(randomData[r]); + if (it != rscoreFreq[r].end()) {//already have that score rscoreFreq[r][randomData[r]]++; }else{//first time we have seen this score rscoreFreq[r][randomData[r]] = 1; @@ -129,19 +223,37 @@ int ParsimonyCommand::execute() { }else { //get pscores for random trees for (int j = 0; j < iters; j++) { + //create new tree with same num nodes and leaves as users randT = new Tree(); //create random relationships between nodes randT->assembleRandomTree(); + + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; delete randT; + globaldata->gTreemap = savetmap; + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } + //get pscore of random tree randomData = pars->getValues(randT); + + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; delete randT; + globaldata->gTreemap = savetmap; + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } for(int r = 0; r < numComp; r++) { //add trees pscore to map of scores - it2 = rscoreFreq[r].find(randomData[r]); - if (it2 != rscoreFreq[r].end()) {//already have that score + map::iterator it = rscoreFreq[r].find(randomData[r]); + if (it != rscoreFreq[r].end()) {//already have that score rscoreFreq[r][randomData[r]]++; }else{//first time we have seen this score rscoreFreq[r][randomData[r]] = 1; @@ -162,9 +274,9 @@ int ParsimonyCommand::execute() { float rcumul = 0.0000; float ucumul = 0.0000; //this loop fills the cumulative maps and put 0.0000 in the score freq map to make it easier to print. - for (it = validScores.begin(); it != validScores.end(); it++) { + for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { if (randomtree == "") { - it2 = uscoreFreq[a].find(it->first); + map::iterator it2 = uscoreFreq[a].find(it->first); //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 @@ -173,7 +285,7 @@ int ParsimonyCommand::execute() { } //make rscoreFreq map and rCumul - it2 = rscoreFreq[a].find(it->first); + map::iterator it2 = rscoreFreq[a].find(it->first); //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 @@ -186,6 +298,15 @@ int ParsimonyCommand::execute() { } } + if (m->control_pressed) { + delete reading; delete pars; delete util; delete output; + if (randomtree == "") { outSum.close(); } + else { globaldata->gTreemap = savetmap; } + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + globaldata->Groups.clear(); + return 0; + } + //finish progress bar reading->finish(); delete reading; @@ -201,20 +322,26 @@ int ParsimonyCommand::execute() { globaldata->gTreemap = savetmap; } - //reset randomTree parameter to "" - globaldata->setRandomTree(""); //reset groups parameter globaldata->Groups.clear(); + if (m->control_pressed) { + delete pars; delete util; delete output; + 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 ParsimonyCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ParsimonyCommand", "execute"); exit(1); } } @@ -223,44 +350,40 @@ int ParsimonyCommand::execute() { void ParsimonyCommand::printParsimonyFile() { try { vector data; + vector tags; - //format output - out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); + if (randomtree == "") { + tags.push_back("Score"); tags.push_back("UserFreq"); tags.push_back("UserCumul"); tags.push_back("RandFreq"); tags.push_back("RandCumul"); + }else { + 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.begin(); it != validScores.end(); it++) { + for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { if (randomtree == "") { data.push_back(it->first); data.push_back(uscoreFreq[a][it->first]); data.push_back(uCumul[a][it->first]); data.push_back(rscoreFreq[a][it->first]); data.push_back(rCumul[a][it->first]); }else{ data.push_back(it->first); data.push_back(rscoreFreq[a][it->first]); data.push_back(rCumul[a][it->first]); } - output(data); + output->output(data); data.clear(); } - resetFile(); + output->resetFile(); } - - out.close(); - inFile.close(); - remove(parsFileout.c_str()); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function printParsimonyFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function printParsimonyFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ParsimonyCommand", "printParsimonyFile"); exit(1); } } /***********************************************************/ -void ParsimonyCommand::printUSummaryFile() { +int ParsimonyCommand::printUSummaryFile() { try { //column headers outSum << "Tree#" << '\t' << "Groups" << '\t' << "ParsScore" << '\t' << "ParsSig" << endl; - cout << "Tree#" << '\t' << "Groups" << '\t' << "ParsScore" << '\t' << "ParsSig" << endl; + m->mothurOut("Tree#\tGroups\tParsScore\tParsSig"); m->mothurOutEndLine(); //format output outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); @@ -269,24 +392,24 @@ void ParsimonyCommand::printUSummaryFile() { //print each line for (int i = 0; i< T.size(); i++) { for(int a = 0; a < numComp; a++) { + if (m->control_pressed) { outSum.close(); return 0; } if (UScoreSig[a][i] > (1/(float)iters)) { - outSum << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(globaldata->getIters().length()) << '\t' << UScoreSig[a][i] << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(globaldata->getIters().length()) << '\t' << UScoreSig[a][i] << endl; + outSum << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(itersString.length()) << '\t' << UScoreSig[a][i] << endl; + cout << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(itersString.length()) << '\t' << UScoreSig[a][i] << endl; + m->mothurOutJustToLog(toString(i+1) + "\t" + groupComb[a] + "\t" + toString(userTreeScores[a][i]) + "\t" + toString(UScoreSig[a][i])); m->mothurOutEndLine(); }else { - outSum << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(globaldata->getIters().length()) << '\t' << "<" << (1/float(iters)) << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(globaldata->getIters().length()) << '\t' << "<" << (1/float(iters)) << endl; + outSum << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(itersString.length()) << '\t' << "<" << (1/float(iters)) << endl; + cout << setprecision(6) << i+1 << '\t' << groupComb[a] << '\t' << userTreeScores[a][i] << setprecision(itersString.length()) << '\t' << "<" << (1/float(iters)) << endl; + m->mothurOutJustToLog(toString(i+1) + "\t" + groupComb[a] + "\t" + toString(userTreeScores[a][i]) + "\t" + toString((1/float(iters)))); m->mothurOutEndLine(); } } } outSum.close(); + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function printUSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function printUSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ParsimonyCommand", "printUSummaryFile"); exit(1); } } @@ -298,16 +421,18 @@ void ParsimonyCommand::getUserInput() { //create treemap tmap = new TreeMap(); - cout << "Please enter the number of groups you would like to analyze: "; + m->mothurOut("Please enter the number of groups you would like to analyze: "); cin >> numGroups; - + m->mothurOutJustToLog(toString(numGroups)); m->mothurOutEndLine(); + int num, count; count = 1; numEachGroup.resize(numGroups, 0); for (int i = 1; i <= numGroups; i++) { - cout << "Please enter the number of sequences in group " << i << ": "; + m->mothurOut("Please enter the number of sequences in group " + toString(i) + ": "); cin >> num; + m->mothurOutJustToLog(toString(num)); m->mothurOutEndLine(); //set tmaps seqsPerGroup tmap->seqsPerGroup[toString(i)] = num; @@ -329,113 +454,15 @@ void ParsimonyCommand::getUserInput() { //memory leak prevention //if (globaldata->gTreemap != NULL) { delete globaldata->gTreemap; } globaldata->gTreemap = tmap; + globaldata->Treenames = tmap->namesOfSeqs; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function getUserInput. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function getUserInput. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} -/*****************************************************************/ - -void ParsimonyCommand::initFile(string label){ - try { - if(counter != 0){ - openOutputFile(parsFileout, out); - openInputFile(parsFile, inFile); - - string inputBuffer; - getline(inFile, inputBuffer); - - if (randomtree == "") { - out << inputBuffer << '\t' << label + "Score" << '\t' << label + "UserFreq" << '\t' << label + "UserCumul" << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; - }else { - out << inputBuffer << '\t' << "Score" << '\t' << "RandFreq" << '\t' << "RandCumul" << endl; - } - }else{ - openOutputFile(parsFileout, out); - //column headers - if (randomtree == "") { - out << label + "Score" << '\t' << label + "UserFreq" << '\t' << label + "UserCumul" << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; - }else { - out << "Score" << '\t' << "RandFreq" << '\t' << "RandCumul" << endl; - } - } - - out.setf(ios::fixed, ios::floatfield); - out.setf(ios::showpoint); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} - -/***********************************************************************/ - -void ParsimonyCommand::output(vector data){ - try { - if(counter != 0){ - string inputBuffer; - getline(inFile, inputBuffer); - - if (randomtree == "") { - out << inputBuffer << '\t' << setprecision(6) << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << '\t' << data[3] << '\t' << data[4] << endl; - }else{ - out << inputBuffer << '\t' << setprecision(6) << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << endl; - } - } - else{ - if (randomtree == "") { - out << setprecision(6) << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << '\t' << data[3] << '\t' << data[4] << endl; - }else{ - out << setprecision(6) << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << endl; - } - } - - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ParsimonyCommand", "getUserInput"); exit(1); } } -/***********************************************************************/ - -void ParsimonyCommand::resetFile(){ - try { - if(counter != 0){ - out.close(); - inFile.close(); - } - else{ - out.close(); - } - counter = 1; - - remove(parsFile.c_str()); - rename(parsFileout.c_str(), parsFile.c_str()); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ParsimonyCommand class Function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ParsimonyCommand class function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} +/***********************************************************/