X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracweightedcommand.cpp;h=a7a41f37b820cb8af77ede45cf31d0b0f4885d84;hb=0470f6d037aacb3563c3f7010708120a4a67d4e6;hp=f7ad5253bb019f785ff01dd36317219b61db4c24;hpb=5318771152ee5b1a280b3dc50aedd887dd1da8a8;p=mothur.git diff --git a/unifracweightedcommand.cpp b/unifracweightedcommand.cpp index f7ad525..a7a41f3 100644 --- a/unifracweightedcommand.cpp +++ b/unifracweightedcommand.cpp @@ -10,24 +10,64 @@ #include "unifracweightedcommand.h" /***********************************************************/ -UnifracWeightedCommand::UnifracWeightedCommand() { +UnifracWeightedCommand::UnifracWeightedCommand(string option) { try { globaldata = GlobalData::getInstance(); + abort = false; + Groups.clear(); - 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); + //allow user to run help + if(option == "help") { help(); abort = true; } + + else { + //valid paramters for this command + string Array[] = {"groups","iters"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + parser = new OptionParser(); + parser->parse(option, parameters); delete parser; + + ValidParameters* validParameter = new ValidParameters(); + + //check to make sure all parameters are valid for command + for (it4 = parameters.begin(); it4 != parameters.end(); it4++) { + if (validParameter->isValidParameter(it4->first, myArray, it4->second) != true) { abort = true; } + } + + 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; } + + //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); + + delete validParameter; + + 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"; @@ -38,9 +78,38 @@ UnifracWeightedCommand::UnifracWeightedCommand() { exit(1); } } +//********************************************************************************************************************** + +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"; + } + 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"; + 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); + } +} + /***********************************************************/ int UnifracWeightedCommand::execute() { try { + + if (abort == true) { return 0; } + + Progress* reading; + reading = new Progress("Comparing to random:", iters); //get weighted for users tree userData.resize(numComp,0); //data[0] = weightedscore AB, data[1] = weightedscore AC... @@ -49,13 +118,14 @@ 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; + + output = new ColumnFile(globaldata->getTreeFile() + toString(i+1) + ".weighted", itersString); + userData = weighted->getValues(T[i]); //userData[0] = weightedscore //save users score @@ -63,9 +133,6 @@ 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]); } @@ -78,26 +145,23 @@ int UnifracWeightedCommand::execute() { //copy T[i]'s info. randT->getCopy(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]); - } + //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++; } } + + //update progress bar + reading->update(j); + } - removeValidScoresDuplicates(); + //removeValidScoresDuplicates(); //find the signifigance of the score for summary file for (int f = 0; f < numComp; f++) { //sort random scores @@ -113,8 +177,11 @@ int UnifracWeightedCommand::execute() { WScoreSig.push_back((iters-index)/(float)iters); } - out << "Tree# " << i << endl; - //printWeightedFile(); + //out << "Tree# " << i << endl; + calculateFreqsCumuls(); + printWeightedFile(); + + delete output; //clear data rScores.clear(); @@ -122,6 +189,10 @@ int UnifracWeightedCommand::execute() { validScores.clear(); } + //finish progress bar + reading->finish(); + delete reading; + printWSummaryFile(); //clear out users groups @@ -141,23 +212,23 @@ int UnifracWeightedCommand::execute() { exit(1); } } -/*********************************************************** +/***********************************************************/ void UnifracWeightedCommand::printWeightedFile() { 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 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++) { + output->initFile(groupComb[a], tags); + //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->output(data); + data.clear(); } + output->resetFile(); } - - out.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"; @@ -174,8 +245,8 @@ 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); @@ -184,8 +255,13 @@ 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' << 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; + }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; + } count++; } } @@ -201,28 +277,6 @@ 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{ @@ -242,61 +296,58 @@ int UnifracWeightedCommand::findIndex(float score, int index) { } /***********************************************************/ -void UnifracWeightedCommand::setGroups() { + +void UnifracWeightedCommand::calculateFreqsCumuls() { try { - //if the user has not entered specific groups to analyze then do them all - if (globaldata->Groups.size() == 0) { - numGroups = tmap->getNumGroups(); - }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); - } + //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; } - - //if the user only entered invalid groups - if (globaldata->Groups.size() == 0) { - numGroups = tmap->getNumGroups(); - 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(); - }else { numGroups = globaldata->Groups.size(); } - }else { //users wants all groups - numGroups = tmap->getNumGroups(); - globaldata->Groups.clear(); - globaldata->setGroups(""); } } - //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]); - } + //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 } - n++; } + } 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"; + 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 setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + cout << "An unknown error has occurred in the UnifracWeightedCommand class function calculateFreqsCums. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; exit(1); } + } +/***********************************************************/ + + + + +