T = globaldata->gTree;
tmap = globaldata->gTreemap;
- unweightedFile = globaldata->getTreeFile() + ".unweighted";
- openOutputFile(unweightedFile, out);
sumFile = globaldata->getTreeFile() + ".uwsummary";
openOutputFile(sumFile, outSum);
- distFile = globaldata->getTreeFile() + ".uwdistrib";
- openOutputFile(distFile, outDist);
+
setGroups(); //sets users groups to analyze
convert(globaldata->getIters(), iters); //how many random trees to generate
unweighted = new Unweighted(tmap);
/***********************************************************/
int UnifracUnweightedCommand::execute() {
try {
+
+ userData.resize(numComp,0); //data[0] = unweightedscore
+ randomData.resize(numComp,0); //data[0] = unweightedscore
+ //create new tree with same num nodes and leaves as users
- //get unweighted for users tree
- userData.resize(1,0); //data[0] = unweightedscore
- randomData.resize(1,0); //data[0] = unweightedscore
-
- //format output
- outDist.setf(ios::fixed, ios::floatfield); outDist.setf(ios::showpoint);
-
- outDist << "Groups Used ";
- for (int m = 0; m < globaldata->Groups.size(); m++) {
- outDist << globaldata->Groups[m] << " ";
- }
- outDist << endl;
-
- outDist << "Tree#" << '\t' << "Iter" << '\t' << "UWScore" << endl;
+ outSum << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" <<'\t' << "UWSig" << endl;
+ cout << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" << '\t' << "UWSig" << endl;
- //create new tree with same num nodes and leaves as users
- randT = new Tree();
-
//get pscores for users trees
for (int i = 0; i < T.size(); i++) {
- cout << "Processing tree " << i+1 << endl;
- userData = unweighted->getValues(T[i]); //userData[0] = unweightedscore
-
- //update uscoreFreq
- it = uscoreFreq.find(userData[0]);
- if (it == uscoreFreq.end()) {//new score
- uscoreFreq[userData[0]] = 1;
- }else{ uscoreFreq[userData[0]]++; }
+ counter = 0;
+ unweightedFile = globaldata->getTreeFile() + toString(i+1) + ".unweighted";
+ unweightedFileout = globaldata->getTreeFile() + "temp." + toString(i+1) + ".unweighted";
- //add users score to valid scores
- validScores[userData[0]] = userData[0];
+ outSum << i+1 << '\t';
+ cout << i+1 << '\t';
- //saves users score
- utreeScores.push_back(userData[0]);
+ //get unweighted for users tree
+ rscoreFreq.resize(numComp);
+ rCumul.resize(numComp);
+ utreeScores.resize(numComp);
+ UWScoreSig.resize(numComp);
+
+ userData = unweighted->getValues(T[i]); //userData[0] = unweightedscore
- //copy T[i]'s info.
- randT->getCopy(T[i]);
+ //output scores for each combination
+ for(int k = 0; k < numComp; k++) {
+ //saves users score
+ utreeScores[k].push_back(userData[k]);
+
+ }
//get unweighted scores for random trees
for (int j = 0; j < iters; j++) {
- //create a random tree with same topology as T[i], but different labels
- randT->assembleRandomUnifracTree();
- //get pscore of random tree
- randomData = unweighted->getValues(randT);
-
- //add trees unweighted score to map of scores
- it2 = rscoreFreq.find(randomData[0]);
- if (it2 != rscoreFreq.end()) {//already have that score
- rscoreFreq[randomData[0]]++;
- }else{//first time we have seen this score
- rscoreFreq[randomData[0]] = 1;
- }
+ //we need a different getValues because when we swap the labels we only want to swap those in each parwise comparison
+ randomData = unweighted->getValues(T[i], "", "");
- //add randoms score to validscores
- validScores[randomData[0]] = randomData[0];
+ for(int k = 0; k < numComp; k++) {
+ //add trees unweighted score to map of scores
+ it2 = rscoreFreq[k].find(randomData[k]);
+ if (it2 != rscoreFreq[k].end()) {//already have that score
+ rscoreFreq[k][randomData[k]]++;
+ }else{//first time we have seen this score
+ rscoreFreq[k][randomData[k]] = 1;
+ }
- //output info to uwdistrib file
- outDist << i+1 << '\t' << '\t'<< j+1 << '\t' << '\t' << randomData[0] << endl;
+ //add randoms score to validscores
+ validScores[randomData[k]] = randomData[k];
+ }
}
-
- saveRandomScores(); //save all random scores for unweighted file
-
- //find the signifigance of the score
+
+ for(int a = 0; a < numComp; a++) {
float rcumul = 1.0000;
- for (it = rscoreFreq.begin(); it != rscoreFreq.end(); it++) {
- rCumul[it->first] = rcumul;
+ //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
- rscoreFreq[it->first] /= iters;
- rcumul-= it->second;
-
+ 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
}
-
- //save the signifigance of the users score for printing later
- UWScoreSig.push_back(rCumul[userData[0]]);
-
-
- //clear random data
- rscoreFreq.clear(); //you clear this because in the summary file you want the unweighted signifinance to be relative to these 1000 trees.
- rCumul.clear();
- }
-
- float ucumul = 1.0000;
- 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++) {
- it2 = uscoreFreq.find(it->first);
- //make uCumul map
- uCumul[it->first] = ucumul;
- //user data has that score
- if (it2 != uscoreFreq.end()) { uscoreFreq[it->first] /= T.size(); ucumul-= it2->second; }
- else { uscoreFreq[it->first] = 0.0000; } //no user trees with that score
-
- //make rscoreFreq map and rCumul
- it2 = totalrscoreFreq.find(it->first);
- rCumul[it->first] = rcumul;
- //get percentage of random trees with that info
- if (it2 != totalrscoreFreq.end()) { totalrscoreFreq[it->first] /= (iters*T.size()); rcumul-= it2->second; }
- else { totalrscoreFreq[it->first] = 0.0000; } //no random trees with that score
-
+ UWScoreSig[a].push_back(rCumul[a][userData[a]]);
}
printUnweightedFile();
printUWSummaryFile();
+ rscoreFreq.clear();
+ rCumul.clear();
+ validScores.clear();
+ utreeScores.clear();
+ UWScoreSig.clear();
+ }
//reset groups parameter
- globaldata->Groups.clear();
-
- delete randT;
+ globaldata->Groups.clear(); globaldata->setGroups("");
+ outSum.close();
return 0;
/***********************************************************/
void UnifracUnweightedCommand::printUnweightedFile() {
try {
- //column headers
+ vector<double> data;
- out << "Groups Used ";
- for (int m = 0; m < globaldata->Groups.size(); m++) {
- out << globaldata->Groups[m] << " ";
+ 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 << endl;
-
- out << "Score" << '\t' << "UserFreq" << '\t' << "UserCumul" << '\t' << "RandFreq" << '\t' << "RandCumul" << endl;
-
- //format output
- out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint);
-
- //print each line
- for (it = validScores.begin(); it != validScores.end(); it++) {
- out << setprecision(6) << it->first << '\t' << '\t' << uscoreFreq[it->first] << '\t' << uCumul[it->first] << '\t' << totalrscoreFreq[it->first] << '\t' << rCumul[it->first] << endl;
- }
out.close();
+ inFile.close();
+ remove(unweightedFileout.c_str());
}
catch(exception& e) {
/***********************************************************/
void UnifracUnweightedCommand::printUWSummaryFile() {
try {
- //column headers
-
- outSum << "Groups Used ";
- for (int m = 0; m < globaldata->Groups.size(); m++) {
- outSum << globaldata->Groups[m] << " ";
- }
- outSum << endl;
-
- outSum << "Tree#" << '\t' << "UWScore" << '\t' << '\t' << "UWSig" << endl;
-
+
//format output
outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint);
-
+
//print each line
- for (int i = 0; i< T.size(); i++) {
- outSum << setprecision(6) << i+1 << '\t' << '\t' << utreeScores[i] << '\t' << UWScoreSig[i] << endl;
+
+ for(int a = 0; a < numComp; a++) {
+ if (UWScoreSig[a][0] > (1/(float)iters)) {
+ outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(globaldata->getIters().length()) << UWScoreSig[a][0] << endl;
+ cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(globaldata->getIters().length()) << UWScoreSig[a][0] << endl;
+ }else {
+ outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(globaldata->getIters().length()) << "<" << (1/float(iters)) << endl;
+ cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(globaldata->getIters().length()) << "<" << (1/float(iters)) << endl;
+ }
}
- outSum.close();
}
catch(exception& e) {
cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function printUWSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
exit(1);
}
}
-/***********************************************************/
-void UnifracUnweightedCommand::saveRandomScores() {
- try {
- for (it = rscoreFreq.begin(); it != rscoreFreq.end(); it++) {
- //does this score already exist in the total map
- it2 = totalrscoreFreq.find(it->first);
- //if yes then add them
- if (it2 != totalrscoreFreq.end()) {
- totalrscoreFreq[it->first] += rscoreFreq[it->first];
- }else{ //its a new score
- totalrscoreFreq[it->first] = rscoreFreq[it->first];
- }
- }
- }
- catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function saveRandomScores. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
- catch(...) {
- cout << "An unknown error has occurred in the UnifracUnweightedCommand class function saveRandomScores. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
- exit(1);
- }
-}
-
/***********************************************************/
void UnifracUnweightedCommand::setGroups() {
try {
+ string allGroups = "";
+ numGroups = 0;
//if the user has not entered specific groups to analyze then do them all
if (globaldata->Groups.size() != 0) {
- //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 (globaldata->Groups[0] != "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) {
- cout << "When using the groups parameter you must have at least 1 valid group. I will run the command using all the groups in your groupfile." << endl;
+ //if the user only entered invalid groups
+ if (globaldata->Groups.size() == 0) {
+ cout << "When using the groups parameter you must have at least 1 valid group. I will run the command using all the groups in your groupfile." << endl;
+ for (int i = 0; i < tmap->namesOfGroups.size(); i++) {
+ globaldata->Groups.push_back(tmap->namesOfGroups[i]);
+ numGroups++;
+ allGroups += tmap->namesOfGroups[i] + "-";
+ }
+ allGroups = allGroups.substr(0, allGroups.length()-1);
+ }else {
+ for (int i = 0; i < globaldata->Groups.size(); i++) {
+ allGroups += globaldata->Groups[i] + "-";
+ numGroups++;
+ }
+ allGroups = allGroups.substr(0, allGroups.length()-1);
+ }
+ }else{//user has enter "all" and wants the default groups
+ globaldata->Groups.clear();
for (int i = 0; i < tmap->namesOfGroups.size(); i++) {
globaldata->Groups.push_back(tmap->namesOfGroups[i]);
+ numGroups++;
+ allGroups += tmap->namesOfGroups[i] + "-";
}
+ allGroups = allGroups.substr(0, allGroups.length()-1);
+ globaldata->setGroups("");
}
-
}else {
for (int i = 0; i < tmap->namesOfGroups.size(); i++) {
- globaldata->Groups.push_back(tmap->namesOfGroups[i]);
+ allGroups += tmap->namesOfGroups[i] + "-";
}
+ allGroups = allGroups.substr(0, allGroups.length()-1);
+ numGroups = 1;
+ }
+
+ //calculate number of comparsions
+ numComp = 0;
+ for (int r=0; r<numGroups; r++) {
+ for (int l = r+1; l < numGroups; l++) {
+ groupComb.push_back(globaldata->Groups[r]+ "-" + globaldata->Groups[l]);
+ numComp++;
+ }
+ }
+
+ //ABC
+ if (numComp != 1) {
+ groupComb.push_back(allGroups);
+ numComp++;
}
}
catch(exception& e) {
}
/*****************************************************************/
+void UnifracUnweightedCommand::initFile(string label){
+ try {
+ if(counter != 0){
+ openOutputFile(unweightedFileout, out);
+ openInputFile(unweightedFile, inFile);
+
+ string inputBuffer;
+ getline(inFile, inputBuffer);
+
+ out << inputBuffer << '\t' << label + "RandFreq" << '\t' << label + "RandCumul" << endl;
+ }else{
+ openOutputFile(unweightedFileout, 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 UnifracUnweightedCommand class Function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+ catch(...) {
+ cout << "An unknown error has occurred in the UnifracUnweightedCommand class function initFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+}
+
+/***********************************************************************/
+
+void UnifracUnweightedCommand::output(vector<double> data){
+ try {
+ if(counter != 0){
+ string inputBuffer;
+ getline(inFile, inputBuffer);
+// out << inputBuffer << setprecision(6) << '\t' << data[0] << setprecision(globaldata->getIters().length()) << '\t' << data[1] << '\t' << data[2] << endl;
+
+ 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 UnifracUnweightedCommand class Function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+ catch(...) {
+ cout << "An unknown error has occurred in the UnifracUnweightedCommand class function output. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+};
+
+/***********************************************************************/
+
+void UnifracUnweightedCommand::resetFile(){
+ try {
+ if(counter != 0){
+ out.close();
+ inFile.close();
+ }
+ else{
+ out.close();
+ }
+ counter = 1;
+
+ remove(unweightedFile.c_str());
+ rename(unweightedFileout.c_str(), unweightedFile.c_str());
+ }
+ catch(exception& e) {
+ cout << "Standard Error: " << e.what() << " has occurred in the UnifracUnweightedCommand class Function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+ catch(...) {
+ cout << "An unknown error has occurred in the UnifracUnweightedCommand class function resetFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ exit(1);
+ }
+}
+