#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"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+
+ OptionParser parser(option);
+ map<string,string> parameters=parser.getParameters();
+
+ ValidParameters validParameter;
+
+ //check to make sure all parameters are valid for command
+ for (map<string,string>::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
+ 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);
+
+
+ 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";
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);
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";
+
+ output = new ColumnFile(globaldata->getTreeFile() + toString(i+1) + ".weighted", itersString);
userData = weighted->getValues(T[i]); //userData[0] = weightedscore
calculateFreqsCumuls();
printWeightedFile();
+ delete output;
+
//clear data
rScores.clear();
uScores.clear();
void UnifracWeightedCommand::printWeightedFile() {
try {
vector<double> data;
+ vector<string> 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<float,float>::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";
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;
+ 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(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' << 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++;
}
}
}
-/***********************************************************/
-void UnifracWeightedCommand::setGroups() {
- try {
- numGroups = 0;
- //if the user has not entered specific groups to analyze then do them all
- if (globaldata->Groups.size() == 0) {
- for (int i=0; i < tmap->getNumGroups(); i++) {
- if (tmap->namesOfGroups[i] != "xxx") {
- globaldata->Groups.push_back(tmap->namesOfGroups[i]);
- numGroups++;
- }
- }
- }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) {
- for (int i=0; i < tmap->getNumGroups(); i++) {
- if (tmap->namesOfGroups[i] != "xxx") {
- globaldata->Groups.push_back(tmap->namesOfGroups[i]);
- numGroups++;
- }
- }
- 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;
- globaldata->Groups.clear();
- for (int i=0; i < tmap->getNumGroups(); i++) {
- if (tmap->namesOfGroups[i] != "xxx") {
- globaldata->Groups.push_back(tmap->namesOfGroups[i]);
- numGroups++;
- }
- }
- }else { numGroups = globaldata->Groups.size(); }
- }else { //users wants all groups
- globaldata->Groups.clear();
- globaldata->setGroups("");
- for (int i=0; i < tmap->getNumGroups(); i++) {
- if (tmap->namesOfGroups[i] != "xxx") {
- globaldata->Groups.push_back(tmap->namesOfGroups[i]);
- numGroups++;
- }
- }
- }
- }
-
- //calculate number of comparisons i.e. with groups A,B,C = AB, AC, BC = 3;
- numComp = 0;
- for (int i=0; i<numGroups; i++) {
- numComp += i;
- for (int l = i+1; l < numGroups; l++) {
- //set group comparison labels
- groupComb.push_back(globaldata->Groups[i] + "-" + globaldata->Groups[l]);
- }
- }
- }
- 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";
- 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";
- exit(1);
- }
-}
-
/***********************************************************/
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<float,float>::iterator it = rScoreFreq[f].find(rScores[f][i]);
if (it != rScoreFreq[f].end()) {
rScoreFreq[f][rScores[f][i]]++;
}else{
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<float,float>::iterator it = validScores.begin(); it != validScores.end(); it++) {
//make rscoreFreq map and rCumul
- it2 = rScoreFreq[a].find(it->first);
+ map<float,float>::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; }
}
-/*****************************************************************/
-
-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<double> 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);
- }
-}
projects / mothur.git / blobdiff