X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracweightedcommand.cpp;h=69b32aa11a84f2c435651e52dec92f400a868a8b;hb=8fd4a602269974e6548f4a387dddd6bd80a999ab;hp=a99459deeef74b6e99eab76c43b7a76787366b20;hpb=b2c44d69197045c26c1f4e62d248ab882c79a393;p=mothur.git diff --git a/unifracweightedcommand.cpp b/unifracweightedcommand.cpp index a99459d..69b32aa 100644 --- a/unifracweightedcommand.cpp +++ b/unifracweightedcommand.cpp @@ -16,11 +16,6 @@ UnifracWeightedCommand::UnifracWeightedCommand() { T = globaldata->gTree; tmap = globaldata->gTreemap; - weightedFile = globaldata->getTreeFile() + ".weighted"; - openOutputFile(weightedFile, out); - //column headers - out << "Group" << '\t' << "Score" << '\t' << "UserFreq" << '\t' << "UserCumul" << '\t' << "RandFreq" << '\t' << "RandCumul" << endl; - sumFile = globaldata->getTreeFile() + ".wsummary"; openOutputFile(sumFile, outSum); @@ -49,13 +44,14 @@ int UnifracWeightedCommand::execute() { //create new tree with same num nodes and leaves as users randT = new Tree(); - //get pscores for users trees + //get weighted scores for users trees for (int i = 0; i < T.size(); i++) { + counter = 0; rScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... uScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC... - validScores.resize(numComp); - - cout << "Processing tree " << i+1 << endl; + weightedFile = globaldata->getTreeFile() + toString(i+1) + ".weighted"; + weightedFileout = globaldata->getTreeFile() + "temp." + toString(i+1) + ".weighted"; + userData = weighted->getValues(T[i]); //userData[0] = weightedscore //save users score @@ -63,45 +59,31 @@ int UnifracWeightedCommand::execute() { //add users score to vector of user scores uScores[s].push_back(userData[s]); - //add users score to vector of valid scores - validScores[s].push_back(userData[s]); - //save users tree score for summary file utreeScores.push_back(userData[s]); } //get scores for random trees for (int j = 0; j < iters; j++) { -// int n = 1; int count = 0; for (int r=0; rgetCopy(T[i]); - if (globaldata->Groups.size() != 0) { - //create a random tree with same topology as T[i], but different labels - randT->assembleRandomUnifracTree(globaldata->Groups[r], globaldata->Groups[l]); - //get wscore of random tree - randomData = weighted->getValues(randT, globaldata->Groups[r], globaldata->Groups[l]); - }else { - //create a random tree with same topology as T[i], but different labels - randT->assembleRandomUnifracTree(tmap->namesOfGroups[r], tmap->namesOfGroups[l]); - //get wscore of random tree - randomData = weighted->getValues(randT, tmap->namesOfGroups[r], tmap->namesOfGroups[l]); - } -// randT->createNewickFile("hold"+toString(r)+toString(l)+toString(j)); - + //create a random tree with same topology as T[i], but different labels + randT->assembleRandomUnifracTree(globaldata->Groups[r], globaldata->Groups[l]); + //get wscore of random tree + randomData = weighted->getValues(randT, globaldata->Groups[r], globaldata->Groups[l]); + //save scores rScores[count].push_back(randomData[0]); - validScores[count][randomData[0]] = randomData[0]; count++; } -// n++; } } - removeValidScoresDuplicates(); + //removeValidScoresDuplicates(); //find the signifigance of the score for summary file for (int f = 0; f < numComp; f++) { //sort random scores @@ -117,8 +99,9 @@ int UnifracWeightedCommand::execute() { WScoreSig.push_back((iters-index)/(float)iters); } - out << "Tree# " << i << endl; - //printWeightedFile(); + //out << "Tree# " << i << endl; + calculateFreqsCumuls(); + printWeightedFile(); //clear data rScores.clear(); @@ -145,22 +128,25 @@ int UnifracWeightedCommand::execute() { exit(1); } } -/*********************************************************** +/***********************************************************/ void UnifracWeightedCommand::printWeightedFile() { try { - - //format output - out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); + vector data; - //for each group - for (int e = 0; e < numComp; e++) { - //print each line in that group - for (i = 0; i < validScores[e].size(); i++) { - out << setprecision(6) << groupComb[e] << '\t' << validScores[e][i] << '\t' << '\t' << uscoreFreq[e][it->first] << '\t' << uCumul[e][it->first] << '\t' << rscoreFreq[e][it->first] << '\t' << rCumul[e][it->first] << endl; + for(int a = 0; a < numComp; a++) { + initFile(groupComb[a]); + //print each line + for (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); + data.clear(); } + resetFile(); } out.close(); + inFile.close(); + remove(weightedFileout.c_str()); } catch(exception& e) { @@ -178,8 +164,8 @@ void UnifracWeightedCommand::printWeightedFile() { void UnifracWeightedCommand::printWSummaryFile() { try { //column headers - outSum << "Tree#" << '\t' << "Groups" << '\t' << '\t' << "WScore" << '\t' << '\t' << "WSig" << endl; - cout << "Tree#" << '\t' << "Groups" << '\t' << '\t' << "WScore" << '\t' << '\t' << "WSig" << endl; + outSum << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; + cout << "Tree#" << '\t' << "Groups" << '\t' << "WScore" << '\t' << "WSig" << endl; //format output outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); @@ -188,8 +174,13 @@ void UnifracWeightedCommand::printWSummaryFile() { int count = 0; for (int i = 0; i < T.size(); i++) { for (int j = 0; j < numComp; j++) { - outSum << setprecision(6) << i+1 << '\t' << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << WScoreSig[count] << endl; - cout << setprecision(6) << i+1 << '\t' << '\t' << groupComb[j] << '\t' << utreeScores[count] << '\t' << WScoreSig[count] << endl; + if (WScoreSig[count] > (1/(float)iters)) { + outSum << setprecision(6) << i+1 << '\t' << '\t' << groupComb[j] << '\t' << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << WScoreSig[count] << endl; + cout << setprecision(6) << i+1 << '\t' << '\t' << groupComb[j] << '\t' << '\t' << utreeScores[count] << '\t' << setprecision(globaldata->getIters().length()) << WScoreSig[count] << endl; + }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; + } count++; } } @@ -205,28 +196,6 @@ void UnifracWeightedCommand::printWSummaryFile() { } } -/***********************************************************/ -void UnifracWeightedCommand::removeValidScoresDuplicates() { - try { - for (int e = 0; e < numComp; e++) { - //sort valid scores - sort(validScores[e].begin(), validScores[e].end()); - - for (int i = 0; i< validScores[e].size()-1; i++) { - if (validScores[e][i] == validScores[e][i+1]) { validScores[e].erase(validScores[e].begin()+i); } - } - } - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the UnifracWeightedCommand class Function removeValidScoresDuplicates. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the UnifracWeightedCommand class function removeValidScoresDuplicates. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} - /***********************************************************/ int UnifracWeightedCommand::findIndex(float score, int index) { try{ @@ -251,6 +220,9 @@ void UnifracWeightedCommand::setGroups() { //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]); + } }else { if (globaldata->getGroups() != "all") { //check that groups are valid @@ -265,33 +237,36 @@ void UnifracWeightedCommand::setGroups() { //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]); + } } } //calculate number of comparisons i.e. with groups A,B,C = AB, AC, BC = 3; numComp = 0; - int n = 1; - for (int i=1; iGroups.size() != 0) { - groupComb.push_back(globaldata->Groups[i-1]+globaldata->Groups[l]); - }else { - groupComb.push_back(tmap->namesOfGroups[i-1]+tmap->namesOfGroups[l]); - } + groupComb.push_back(globaldata->Groups[i] + "-" + globaldata->Groups[l]); } - n++; } } catch(exception& e) { @@ -304,3 +279,135 @@ void UnifracWeightedCommand::setGroups() { } } +/***********************************************************/ + +void UnifracWeightedCommand::calculateFreqsCumuls() { + try { + //clear out old tree values + rScoreFreq.clear(); + rScoreFreq.resize(numComp); + rCumul.clear(); + rCumul.resize(numComp); + validScores.clear(); + + //calculate frequency + 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]); + if (it != rScoreFreq[f].end()) { + rScoreFreq[f][rScores[f][i]]++; + }else{ + rScoreFreq[f][rScores[f][i]] = 1; + } + } + } + + //calculate rcumul + 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++) { + //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 + } + } + + } + 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"; + 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); + } +} +