X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracweightedcommand.cpp;h=f092b0f2cf03c8e00d70e437af2219ad9c8def44;hb=438aa88dbc092d9c1c80ec3fa20c8e47f97101c4;hp=cf54e6420e6b1e4e2c54c87672142b0fb89dc655;hpb=cd37904452dc95b183ff313ff05720c562902487;p=mothur.git diff --git a/unifracweightedcommand.cpp b/unifracweightedcommand.cpp index cf54e64..f092b0f 100644 --- a/unifracweightedcommand.cpp +++ b/unifracweightedcommand.cpp @@ -15,13 +15,13 @@ UnifracWeightedCommand::UnifracWeightedCommand(string option) { 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"}; + string Array[] = {"groups","iters","distance","random","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -35,8 +35,14 @@ UnifracWeightedCommand::UnifracWeightedCommand(string option) { } if (globaldata->gTree.size() == 0) {//no trees were read - cout << "You must execute the read.tree command, before you may execute the unifrac.weighted command." << endl; abort = true; } - + m->mothurOut("You must execute the read.tree command, before you may execute the unifrac.weighted 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); @@ -48,13 +54,22 @@ UnifracWeightedCommand::UnifracWeightedCommand(string option) { 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"; + sumFile = outputDir + getSimpleName(globaldata->getTreeFile()) + ".wsummary"; openOutputFile(sumFile, outSum); + outputNames.push_back(sumFile); util = new SharedUtil(); string s; //to make work with setgroups @@ -69,11 +84,7 @@ UnifracWeightedCommand::UnifracWeightedCommand(string option) { } 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"; - 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"; + m->errorOut(e, "UnifracWeightedCommand", "UnifracWeightedCommand"); exit(1); } } @@ -81,24 +92,22 @@ UnifracWeightedCommand::UnifracWeightedCommand(string option) { void UnifracWeightedCommand::help(){ try { - cout << "The unifrac.weighted command can only be executed after a successful read.tree command." << "\n"; - cout << "The unifrac.weighted 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 2 valid groups." << "\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.weighted command should be in the following format: unifrac.weighted(groups=yourGroups, iters=yourIters)." << "\n"; - cout << "Example unifrac.weighted(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.weighted command output two files: .weighted and .wsummary 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.weighted command can only be executed after a successful read.tree command.\n"); + m->mothurOut("The unifrac.weighted 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 2 valid groups.\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.weighted command should be in the following format: unifrac.weighted(groups=yourGroups, iters=yourIters).\n"); + m->mothurOut("Example unifrac.weighted(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.weighted command output two files: .weighted and .wsummary 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 UnifracWeightedCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "UnifracWeightedCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } /***********************************************************/ @@ -108,7 +117,7 @@ int UnifracWeightedCommand::execute() { if (abort == true) { return 0; } Progress* reading; - reading = new Progress("Comparing to random:", iters); + 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... @@ -119,14 +128,35 @@ int UnifracWeightedCommand::execute() { //get weighted scores for users trees for (int i = 0; i < T.size(); i++) { + + if (m->control_pressed) { + delete randT; + if (random) { delete reading; } + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + counter = 0; rScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... uScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... - output = new ColumnFile(globaldata->getTreeFile() + toString(i+1) + ".weighted", itersString); + if (random) { + output = new ColumnFile(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".weighted", itersString); + outputNames.push_back(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".weighted"); + } userData = weighted->getValues(T[i]); //userData[0] = weightedscore + if (m->control_pressed) { + delete randT; + if (random) { delete reading; delete output; } + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + + //save users score for (int s=0; sassembleRandomUnifracTree(globaldata->Groups[r], globaldata->Groups[l]); + + if (m->control_pressed) { + delete randT; + if (random) { delete reading; delete output; } + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + + //get wscore of random tree randomData = weighted->getValues(randT, globaldata->Groups[r], globaldata->Groups[l]); + if (m->control_pressed) { + delete randT; + if (random) { delete reading; delete output; } + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + //save scores rScores[count].push_back(randomData[0]); count++; @@ -162,52 +210,70 @@ int UnifracWeightedCommand::execute() { //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) { m->mothurOut("error in UnifracWeightedCommand"); m->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(); - - delete output; - //clear data rScores.clear(); uScores.clear(); validScores.clear(); } + + if (m->control_pressed) { + delete randT; + if (random) { delete reading; } + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + //finish progress bar - reading->finish(); - delete reading; + if (random) { reading->finish(); delete reading; } printWSummaryFile(); + if (phylip) { createPhylipFile(); } + //clear out users groups globaldata->Groups.clear(); delete randT; + 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 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"; + m->errorOut(e, "UnifracWeightedCommand", "execute"); exit(1); } } @@ -230,11 +296,7 @@ void UnifracWeightedCommand::printWeightedFile() { } } 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"; + m->errorOut(e, "UnifracWeightedCommand", "printWeightedFile"); exit(1); } } @@ -245,7 +307,7 @@ void UnifracWeightedCommand::printWSummaryFile() { try { //column headers outSum << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; - cout << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; + m->mothurOut("Tree#\tGroups\tWScore\tWSig"); m->mothurOutEndLine(); //format output outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); @@ -254,12 +316,20 @@ 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(itersString.length()) << WScoreSig[count] << endl; - cout << setprecision(6) << i+1 << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << setprecision(itersString.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; + m->mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t" + toString(WScoreSig[count])); m->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; + m->mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t<" + toString((1/float(iters)))); m->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; + 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; + m->mothurOutJustToLog(toString(i+1) +"\t" + groupComb[j] +"\t" + toString(utreeScores[count]) +"\t0.00"); m->mothurOutEndLine(); } count++; } @@ -267,15 +337,61 @@ 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"; + m->errorOut(e, "UnifracWeightedCommand", "printWSummaryFile"); 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"; +} +/***********************************************************/ +void UnifracWeightedCommand::createPhylipFile() { + try { + int count = 0; + //for each tree + for (int i = 0; i < T.size(); i++) { + + string phylipFileName = outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".weighted.dist"; + outputNames.push_back(phylipFileName); + 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); + } + + //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] = utreeScores[count]; + dists[l][r] = utreeScores[count]; + 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 += " "; } + } + out << name << '\t'; + + //output distances + for (int l = 0; l < r; l++) { out << dists[r][l] << '\t'; } + out << endl; + } + out.close(); + } + } + catch(exception& e) { + m->errorOut(e, "UnifracWeightedCommand", "createPhylipFile"); exit(1); } } - /***********************************************************/ int UnifracWeightedCommand::findIndex(float score, int index) { try{ @@ -285,11 +401,7 @@ int UnifracWeightedCommand::findIndex(float score, int index) { 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"; + m->errorOut(e, "UnifracWeightedCommand", "findIndex"); exit(1); } } @@ -334,14 +446,9 @@ 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"; + m->errorOut(e, "UnifracWeightedCommand", "calculateFreqsCums"); 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); - } - } /***********************************************************/