X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracweightedcommand.cpp;h=f9cdd5a86458c6f3039e4392e6e8b27f7d5eaa08;hb=d5bf2c1354d0811a33394d918b15620606560d58;hp=7cb8f058e8a36cea95dcefd32196b3acab024b5e;hpb=9ca2caadbeac83bb84b3330d9204b1b659d62941;p=mothur.git diff --git a/unifracweightedcommand.cpp b/unifracweightedcommand.cpp index 7cb8f05..f9cdd5a 100644 --- a/unifracweightedcommand.cpp +++ b/unifracweightedcommand.cpp @@ -10,32 +10,107 @@ #include "unifracweightedcommand.h" /***********************************************************/ -UnifracWeightedCommand::UnifracWeightedCommand() { +UnifracWeightedCommand::UnifracWeightedCommand(string option) { try { globaldata = GlobalData::getInstance(); + abort = false; + Groups.clear(); - T = globaldata->gTree; - tmap = globaldata->gTreemap; - sumFile = globaldata->getTreeFile() + ".wsummary"; - openOutputFile(sumFile, outSum); + //allow user to run help + if(option == "help") { help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"groups","iters","distance","random"}; + 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 + mothurOut("You must execute the read.tree command, before you may execute the unifrac.weighted command."); mothurOutEndLine(); abort = true; } + + //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; + } - setGroups(); //sets the groups the user wants to analyze - convert(globaldata->getIters(), iters); //how many random trees to generate - weighted = new Weighted(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 = 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 (abort == false) { + T = globaldata->gTree; + tmap = globaldata->gTreemap; + sumFile = globaldata->getTreeFile() + ".wsummary"; + openOutputFile(sumFile, outSum); + + util = new SharedUtil(); + string s; //to make work with setgroups + util->setGroups(globaldata->Groups, tmap->namesOfGroups, s, numGroups, "weighted"); //sets the groups the user wants to analyze + util->getCombos(groupComb, globaldata->Groups, numComp); + + weighted = new Weighted(tmap); + + } + } + + } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function UnifracWeightedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "UnifracWeightedCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function UnifracWeightedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +//********************************************************************************************************************** + +void UnifracWeightedCommand::help(){ + try { + mothurOut("The unifrac.weighted command can only be executed after a successful read.tree command.\n"); + mothurOut("The unifrac.weighted command parameters are groups, iters, distance and random. No parameters are required.\n"); + mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 2 valid groups.\n"); + 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"); + mothurOut("The distance parameter allows you to create a distance file from the results. The default is false.\n"); + 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"); + mothurOut("The unifrac.weighted command should be in the following format: unifrac.weighted(groups=yourGroups, iters=yourIters).\n"); + mothurOut("Example unifrac.weighted(groups=A-B-C, iters=500).\n"); + mothurOut("The default value for groups is all the groups in your groupfile, and iters is 1000.\n"); + mothurOut("The unifrac.weighted command output two files: .weighted and .wsummary their descriptions are in the manual.\n"); + mothurOut("Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n\n"); + } + catch(exception& e) { + errorOut(e, "UnifracWeightedCommand", "help"); exit(1); } } + /***********************************************************/ int UnifracWeightedCommand::execute() { try { + + if (abort == true) { return 0; } + + Progress* reading; + if (random) { reading = new Progress("Comparing to random:", iters); } //get weighted for users tree userData.resize(numComp,0); //data[0] = weightedscore AB, data[1] = weightedscore AC... @@ -49,8 +124,8 @@ int UnifracWeightedCommand::execute() { counter = 0; rScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... uScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... - weightedFile = globaldata->getTreeFile() + toString(i+1) + ".weighted"; - weightedFileout = globaldata->getTreeFile() + "temp." + toString(i+1) + ".weighted"; + + if (random) { output = new ColumnFile(globaldata->getTreeFile() + toString(i+1) + ".weighted", itersString); } userData = weighted->getValues(T[i]); //userData[0] = weightedscore @@ -81,36 +156,49 @@ int UnifracWeightedCommand::execute() { count++; } } + + //update progress bar + reading->update(j); + } //removeValidScoresDuplicates(); //find the signifigance of the score for summary file - for (int f = 0; f < numComp; f++) { - //sort random scores - sort(rScores[f].begin(), rScores[f].end()); + if (random) { + for (int f = 0; f < numComp; f++) { + //sort random scores + sort(rScores[f].begin(), rScores[f].end()); + + //the index of the score higher than yours is returned + //so if you have 1000 random trees the index returned is 100 + //then there are 900 trees with a score greater then you. + //giving you a signifigance of 0.900 + int index = findIndex(userData[f], f); if (index == -1) { mothurOut("error in UnifracWeightedCommand"); mothurOutEndLine(); exit(1); } //error code + + //the signifigance is the number of trees with the users score or higher + WScoreSig.push_back((iters-index)/(float)iters); + } - //the index of the score higher than yours is returned - //so if you have 1000 random trees the index returned is 100 - //then there are 900 trees with a score greater then you. - //giving you a signifigance of 0.900 - int index = findIndex(userData[f], f); if (index == -1) { cout << "error in UnifracWeightedCommand" << endl; exit(1); } //error code - - //the signifigance is the number of trees with the users score or higher - WScoreSig.push_back((iters-index)/(float)iters); + //out << "Tree# " << i << endl; + calculateFreqsCumuls(); + printWeightedFile(); + + delete output; } - //out << "Tree# " << i << endl; - calculateFreqsCumuls(); - printWeightedFile(); - //clear data rScores.clear(); uScores.clear(); validScores.clear(); } + //finish progress bar + if (random) { reading->finish(); delete reading; } + printWSummaryFile(); + if (phylip) { createPhylipFile(); } + //clear out users groups globaldata->Groups.clear(); @@ -120,11 +208,7 @@ int UnifracWeightedCommand::execute() { } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "execute"); exit(1); } } @@ -132,29 +216,22 @@ int UnifracWeightedCommand::execute() { void UnifracWeightedCommand::printWeightedFile() { 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.begin(); it != validScores.end(); it++) { + 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(data); + output->output(data); data.clear(); } - resetFile(); + output->resetFile(); } - - out.close(); - inFile.close(); - remove(weightedFileout.c_str()); - } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function printWeightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function printWeightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "printWeightedFile"); exit(1); } } @@ -165,7 +242,7 @@ void UnifracWeightedCommand::printWSummaryFile() { try { //column headers outSum << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; - cout << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; + mothurOut("Tree#\tGroups\tWScore\tWSig"); mothurOutEndLine(); //format output outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); @@ -174,12 +251,20 @@ void UnifracWeightedCommand::printWSummaryFile() { int count = 0; for (int i = 0; i < T.size(); i++) { for (int j = 0; j < numComp; j++) { - if (WScoreSig[count] > (1/(float)iters)) { - outSum << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << WScoreSig[count] << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << WScoreSig[count] << endl; + if (random) { + if (WScoreSig[count] > (1/(float)iters)) { + outSum << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(itersString.length()) << WScoreSig[count] << endl; + cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(itersString.length()) << WScoreSig[count] << endl; + mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t" + toString(WScoreSig[count])); mothurOutEndLine(); + }else{ + outSum << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; + cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; + mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t<" + toString((1/float(iters)))); mothurOutEndLine(); + } }else{ - outSum << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << "<" << (1/float(iters)) << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << "<" << (1/float(iters)) << endl; + outSum << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << "0.00" << endl; + cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << "0.00" << endl; + mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t0.00"); mothurOutEndLine(); } count++; } @@ -187,94 +272,66 @@ void UnifracWeightedCommand::printWSummaryFile() { outSum.close(); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function printWeightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function printWeightedFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "printWSummaryFile"); exit(1); } } - /***********************************************************/ -int UnifracWeightedCommand::findIndex(float score, int index) { - try{ - for (int i = 0; i < rScores[index].size(); i++) { - if (rScores[index][i] >= score) { return i; } - } - return rScores[index].size(); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function findIndex. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function findIndex. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} - -/***********************************************************/ -void UnifracWeightedCommand::setGroups() { +void UnifracWeightedCommand::createPhylipFile() { try { - //if the user has not entered specific groups to analyze then do them all - if (globaldata->Groups.size() == 0) { - numGroups = tmap->getNumGroups(); - for (int i=0; i < numGroups; i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); + int count = 0; + //for each tree + for (int i = 0; i < T.size(); i++) { + + string phylipFileName = globaldata->getTreeFile() + toString(i+1) + ".weighted.dist"; + 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); } - }else { - if (globaldata->getGroups() != "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); - } - } - //if the user only entered invalid groups - if (globaldata->Groups.size() == 0) { - numGroups = tmap->getNumGroups(); - for (int i=0; i < numGroups; i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); - } - cout << "When using the groups parameter you must have at least 2 valid groups. I will run the command using all the groups in your groupfile." << endl; - }else if (globaldata->Groups.size() == 1) { - cout << "When using the groups parameter you must have at least 2 valid groups. I will run the command using all the groups in your groupfile." << endl; - numGroups = tmap->getNumGroups(); - globaldata->Groups.clear(); - for (int i=0; i < numGroups; i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); - } - }else { numGroups = globaldata->Groups.size(); } - }else { //users wants all groups - numGroups = tmap->getNumGroups(); - globaldata->Groups.clear(); - globaldata->setGroups(""); - for (int i=0; i < numGroups; i++) { - globaldata->Groups.push_back(tmap->namesOfGroups[i]); + //flip it so you can print it + for (int r=0; rGroups.size(); r++) { + for (int l = r+1; l < globaldata->Groups.size(); l++) { + dists[r][l] = (1.0 - utreeScores[count]); + dists[l][r] = (1.0 - utreeScores[count]); + count++; } } - } - - //calculate number of comparisons i.e. with groups A,B,C = AB, AC, BC = 3; - numComp = 0; - for (int i=0; iGroups[i] + "-" + globaldata->Groups[l]); + + //output to file + for (int r=0; rGroups.size(); r++) { + //output name + out << globaldata->Groups[r] << '\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 UnifracWeightedCommand class Function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "createPhylipFile"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +/***********************************************************/ +int UnifracWeightedCommand::findIndex(float score, int index) { + try{ + for (int i = 0; i < rScores[index].size(); i++) { + if (rScores[index][i] >= score) { return i; } + } + return rScores[index].size(); + } + catch(exception& e) { + errorOut(e, "UnifracWeightedCommand", "findIndex"); exit(1); } } @@ -294,7 +351,7 @@ void UnifracWeightedCommand::calculateFreqsCumuls() { for (int f = 0; f < numComp; f++) { for (int i = 0; i < rScores[f].size(); i++) { //looks like 0,0,1,1,1,2,4,7... you want to make a map that say rScoreFreq[0] = 2, rScoreFreq[1] = 3... validScores[rScores[f][i]] = rScores[f][i]; - it = rScoreFreq[f].find(rScores[f][i]); + map::iterator it = rScoreFreq[f].find(rScores[f][i]); if (it != rScoreFreq[f].end()) { rScoreFreq[f][rScores[f][i]]++; }else{ @@ -307,9 +364,9 @@ void UnifracWeightedCommand::calculateFreqsCumuls() { 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.begin(); it != validScores.end(); it++) { + for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { //make rscoreFreq map and rCumul - it2 = rScoreFreq[a].find(it->first); + 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; } @@ -319,95 +376,14 @@ void UnifracWeightedCommand::calculateFreqsCumuls() { } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function calculateFreqsCums. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function calculateFreqsCums. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - -} - -/*****************************************************************/ - -void UnifracWeightedCommand::initFile(string label){ - try { - if(counter != 0){ - openOutputFile(weightedFileout, out); - openInputFile(weightedFile, inFile); - - string inputBuffer; - getline(inFile, inputBuffer); - - out << inputBuffer << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; - }else{ - openOutputFile(weightedFileout, out); - out << label + "Score" << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl; - } - - out.setf(ios::fixed, ios::floatfield); - out.setf(ios::showpoint); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "UnifracWeightedCommand", "calculateFreqsCums"); exit(1); } } -/***********************************************************************/ +/***********************************************************/ -void UnifracWeightedCommand::output(vector data){ - try { - if(counter != 0){ - string inputBuffer; - getline(inFile, inputBuffer); - out << inputBuffer << '\t' << setprecision(6) << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << 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 UnifracWeightedCommand class Function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -}; -/***********************************************************************/ - -void UnifracWeightedCommand::resetFile(){ - try { - if(counter != 0){ - out.close(); - inFile.close(); - } - else{ - out.close(); - } - counter = 1; - - remove(weightedFile.c_str()); - rename(weightedFileout.c_str(), weightedFile.c_str()); - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -}