X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=libshuffcommand.cpp;h=129c9700c4f945813cbb639f028d71a57b88d7b1;hb=264c8a3c759d9a999c485236e98dac98d4f0db5f;hp=9a71a038cd4d0bd29d7eaeeeaae96d9847d81fa8;hpb=cd37904452dc95b183ff313ff05720c562902487;p=mothur.git diff --git a/libshuffcommand.cpp b/libshuffcommand.cpp index 9a71a03..129c970 100644 --- a/libshuffcommand.cpp +++ b/libshuffcommand.cpp @@ -18,23 +18,68 @@ #include "slibshuff.h" #include "dlibshuff.h" +//********************************************************************************************************************** +vector LibShuffCommand::getValidParameters(){ + try { + string Array[] = {"iters","groups","step","form","cutoff","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "LibShuffCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +LibShuffCommand::LibShuffCommand(){ + try { + abort = true; calledHelp = true; + vector tempOutNames; + outputTypes["coverage"] = tempOutNames; + outputTypes["libshuffsummary"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "LibShuffCommand", "LibShuffCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector LibShuffCommand::getRequiredParameters(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "LibShuffCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector LibShuffCommand::getRequiredFiles(){ + try { + string Array[] = {"phylip","group"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "LibShuffCommand", "getRequiredFiles"); + exit(1); + } +} //********************************************************************************************************************** -LibShuffCommand::LibShuffCommand(string option){ +LibShuffCommand::LibShuffCommand(string option) { try { - srand( (unsigned)time( NULL ) ); - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; Groups.clear(); - //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } else { //valid paramters for this command - string Array[] = {"iters","groups","step","form","cutoff"}; + string Array[] = {"iters","groups","step","form","cutoff","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -47,9 +92,20 @@ LibShuffCommand::LibShuffCommand(string option){ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["coverage"] = tempOutNames; + outputTypes["libshuffsummary"] = tempOutNames; + + //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 += m->hasPath(globaldata->getPhylipFile()); //if user entered a file with a path then preserve it + } + //make sure the user has already run the read.dist command if ((globaldata->gMatrix == NULL) || (globaldata->gGroupmap == NULL)) { - cout << "You must read in a matrix and groupfile using the read.dist command, before you use the libshuff command. " << endl; abort = true;; + m->mothurOut("You must read in a matrix and groupfile using the read.dist command, before you use the libshuff command. "); m->mothurOutEndLine(); abort = true;; } //check for optional parameter and set defaults @@ -58,7 +114,7 @@ LibShuffCommand::LibShuffCommand(string option){ if (groups == "not found") { groups = ""; savegroups = groups; } else { savegroups = groups; - splitAtDash(groups, Groups); + m->splitAtDash(groups, Groups); globaldata->Groups = Groups; } @@ -75,9 +131,19 @@ LibShuffCommand::LibShuffCommand(string option){ userform = validParameter.validFile(parameters, "form", false); if (userform == "not found") { userform = "integral"; } if (abort == false) { - + matrix = globaldata->gMatrix; //get the distance matrix - setGroups(); //set the groups to be analyzed + setGroups(); //set the groups to be analyzed and sorts them + + /********************************************************************************************/ + //this is needed because when we read the matrix we sort it into groups in alphabetical order + //the rest of the command and the classes used in this command assume specific order + /********************************************************************************************/ + matrix->setGroups(globaldata->gGroupmap->namesOfGroups); + vector sizes; + for (int i = 0; i < globaldata->gGroupmap->namesOfGroups.size(); i++) { sizes.push_back(globaldata->gGroupmap->getNumSeqs(globaldata->gGroupmap->namesOfGroups[i])); } + matrix->setSizes(sizes); + if(userform == "discrete"){ form = new DLibshuff(matrix, iters, step, cutOff); @@ -91,39 +157,30 @@ LibShuffCommand::LibShuffCommand(string option){ } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the LibShuffCommand class Function LibShuffCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "LibShuffCommand", "LibShuffCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function LibShuffCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - } //********************************************************************************************************************** void LibShuffCommand::help(){ try { - cout << "The libshuff command can only be executed after a successful read.dist command including a groupfile." << "\n"; - cout << "The libshuff command parameters are groups, iters, step, form and cutoff. 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 matrices you would like compared to your matrix." << "\n"; - cout << "The step parameter allows you to specify change in distance you would like between each output if you are using the discrete form." << "\n"; - cout << "The form parameter allows you to specify if you would like to analyze your matrix using the discrete or integral form. Your options are integral or discrete." << "\n"; - cout << "The libshuff command should be in the following format: libshuff(groups=yourGroups, iters=yourIters, cutOff=yourCutOff, form=yourForm, step=yourStep)." << "\n"; - cout << "Example libshuff(groups=A-B-C, iters=500, form=discrete, step=0.01, cutOff=2.0)." << "\n"; - cout << "The default value for groups is all the groups in your groupfile, iters is 10000, cutoff is 1.0, form is integral and step is 0.01." << "\n"; - cout << "The libshuff command output two files: .coverage and .slsummary their descriptions are in the manual." << "\n"; - cout << "Note: No spaces between parameter labels (i.e. iters), '=' and parameters (i.e.yourIters)." << "\n" << "\n"; + m->mothurOut("The libshuff command can only be executed after a successful read.dist command including a groupfile.\n"); + m->mothurOut("The libshuff command parameters are groups, iters, step, form and cutoff. 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 matrices you would like compared to your matrix.\n"); + m->mothurOut("The step parameter allows you to specify change in distance you would like between each output if you are using the discrete form.\n"); + m->mothurOut("The form parameter allows you to specify if you would like to analyze your matrix using the discrete or integral form. Your options are integral or discrete.\n"); + m->mothurOut("The libshuff command should be in the following format: libshuff(groups=yourGroups, iters=yourIters, cutOff=yourCutOff, form=yourForm, step=yourStep).\n"); + m->mothurOut("Example libshuff(groups=A-B-C, iters=500, form=discrete, step=0.01, cutOff=2.0).\n"); + m->mothurOut("The default value for groups is all the groups in your groupfile, iters is 10000, cutoff is 1.0, form is integral and step is 0.01.\n"); + m->mothurOut("The libshuff command output two files: .coverage and .slsummary their descriptions are in the manual.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. iters), '=' and parameters (i.e.yourIters).\n\n"); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the LibShuffCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "LibShuffCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** @@ -131,38 +188,57 @@ void LibShuffCommand::help(){ int LibShuffCommand::execute(){ try { - if (abort == true) { return 0; } - + if (abort == true) { if (calledHelp) { return 0; } return 2; } + savedDXYValues = form->evaluateAll(); savedMinValues = form->getSavedMins(); + if (m->control_pressed) { delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; return 0; } + pValueCounts.resize(numGroups); for(int i=0;icontrol_pressed) { outputTypes.clear(); delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; return 0; } + Progress* reading = new Progress(); for(int i=0;icontrol_pressed) { outputTypes.clear(); delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; delete reading; return 0; } + reading->newLine(groupNames[i]+'-'+groupNames[j], iters); - for(int p=0;prandomizeGroups(i,j); - if(form->evaluatePair(i,j) >= savedDXYValues[i][j]) { pValueCounts[i][j]++; } - if(form->evaluatePair(j,i) >= savedDXYValues[j][i]) { pValueCounts[j][i]++; } + int spoti = globaldata->gGroupmap->groupIndex[groupNames[i]]; //neccessary in case user selects groups so you know where they are in the matrix + int spotj = globaldata->gGroupmap->groupIndex[groupNames[j]]; + + for(int p=0;pcontrol_pressed) { outputTypes.clear(); delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; delete reading; return 0; } + + form->randomizeGroups(spoti,spotj); + if(form->evaluatePair(spoti,spotj) >= savedDXYValues[spoti][spotj]) { pValueCounts[i][j]++; } + if(form->evaluatePair(spotj,spoti) >= savedDXYValues[spotj][spoti]) { pValueCounts[j][i]++; } + + if (m->control_pressed) { outputTypes.clear(); delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; delete reading; return 0; } + reading->update(p); } - form->resetGroup(i); - form->resetGroup(j); + form->resetGroup(spoti); + form->resetGroup(spotj); } } + + if (m->control_pressed) { outputTypes.clear(); delete form; globaldata->Groups.clear(); delete globaldata->gMatrix; globaldata->gMatrix = NULL; delete reading; return 0; } + reading->finish(); delete reading; - cout << endl; + m->mothurOutEndLine(); printSummaryFile(); printCoverageFile(); - + //clear out users groups globaldata->Groups.clear(); delete form; @@ -170,28 +246,33 @@ int LibShuffCommand::execute(){ //delete globaldata's copy of the gmatrix to free up memory delete globaldata->gMatrix; globaldata->gMatrix = NULL; + if (m->control_pressed) { outputTypes.clear(); 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 LibShuffCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "LibShuffCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** -void LibShuffCommand::printCoverageFile() { +int LibShuffCommand::printCoverageFile() { try { ofstream outCov; - summaryFile = getRootName(globaldata->getPhylipFile()) + "libshuff.coverage"; - openOutputFile(summaryFile, outCov); + summaryFile = outputDir + m->getRootName(m->getSimpleName(globaldata->getPhylipFile())) + "libshuff.coverage"; + m->openOutputFile(summaryFile, outCov); + outputNames.push_back(summaryFile); outputTypes["coverage"].push_back(summaryFile); outCov.setf(ios::fixed, ios::floatfield); outCov.setf(ios::showpoint); - cout.setf(ios::fixed, ios::floatfield); cout.setf(ios::showpoint); + //cout.setf(ios::fixed, ios::floatfield); cout.setf(ios::showpoint); map > allDistances; map >::iterator it; @@ -204,25 +285,32 @@ void LibShuffCommand::printCoverageFile() { indices[i].assign(numGroups,0); for(int j=0;jgGroupmap->groupIndex[groupNames[i]]; //neccessary in case user selects groups so you know where they are in the matrix + int spotj = globaldata->gGroupmap->groupIndex[groupNames[j]]; + + for(int k=0;kcontrol_pressed) { outCov.close(); return 0; } + + if(allDistances[savedMinValues[spoti][spotj][k]].size() != 0){ + allDistances[savedMinValues[spoti][spotj][k]][indices[i][j]]++; } else{ - allDistances[savedMinValues[i][j][k]].assign(numIndices, 0); - allDistances[savedMinValues[i][j][k]][indices[i][j]] = 1; + allDistances[savedMinValues[spoti][spotj][k]].assign(numIndices, 0); + allDistances[savedMinValues[spoti][spotj][k]][indices[i][j]] = 1; } } } } it=allDistances.begin(); - cout << setprecision(8); + //cout << setprecision(8); vector prevRow = it->second; it++; - for(it;it!=allDistances.end();it++){ + for(;it!=allDistances.end();it++){ for(int i=0;isecond.size();i++){ it->second[i] += prevRow[i]; } @@ -238,6 +326,7 @@ void LibShuffCommand::printCoverageFile() { } for (int i=0;icontrol_pressed) { outCov.close(); return 0; } outCov << '\t' << groupNames[i] << '-' << groupNames[j] << '\t'; outCov << groupNames[j] << '-' << groupNames[i]; } @@ -251,71 +340,79 @@ void LibShuffCommand::printCoverageFile() { } for(int i=0;icontrol_pressed) { outCov.close(); return 0; } + outCov << it->second[indices[i][j]]/(float)lastRow[indices[i][j]] << '\t'; outCov << it->second[indices[j][i]]/(float)lastRow[indices[j][i]] << '\t'; } } outCov << endl; } + outCov.close(); + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the LibShuffCommand class Function printCoverageFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "LibShuffCommand", "printCoverageFile"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function printCoverageFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** -void LibShuffCommand::printSummaryFile() { +int LibShuffCommand::printSummaryFile() { try { ofstream outSum; - summaryFile = getRootName(globaldata->getPhylipFile()) + "libshuff.summary"; - openOutputFile(summaryFile, outSum); + summaryFile = outputDir + m->getRootName(m->getSimpleName(globaldata->getPhylipFile())) + "libshuff.summary"; + m->openOutputFile(summaryFile, outSum); + outputNames.push_back(summaryFile); outputTypes["libshuffsummary"].push_back(summaryFile); outSum.setf(ios::fixed, ios::floatfield); outSum.setf(ios::showpoint); cout.setf(ios::fixed, ios::floatfield); cout.setf(ios::showpoint); cout << setw(20) << left << "Comparison" << '\t' << setprecision(8) << "dCXYScore" << '\t' << "Significance" << endl; + m->mothurOutJustToLog("Comparison\tdCXYScore\tSignificance"); m->mothurOutEndLine(); outSum << setw(20) << left << "Comparison" << '\t' << setprecision(8) << "dCXYScore" << '\t' << "Significance" << endl; int precision = (int)log10(iters); for(int i=0;icontrol_pressed) { outSum.close(); return 0; } + + int spoti = globaldata->gGroupmap->groupIndex[groupNames[i]]; //neccessary in case user selects groups so you know where they are in the matrix + int spotj = globaldata->gGroupmap->groupIndex[groupNames[j]]; + if(pValueCounts[i][j]){ - cout << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[i][j] << '\t' << setprecision(precision) << pValueCounts[i][j]/(float)iters << endl; - outSum << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[i][j] << '\t' << setprecision(precision) << pValueCounts[i][j]/(float)iters << endl; + cout << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[spoti][spotj] << '\t' << setprecision(precision) << pValueCounts[i][j]/(float)iters << endl; + m->mothurOutJustToLog(groupNames[i]+"-"+groupNames[j] + "\t" + toString(savedDXYValues[spoti][spotj]) + "\t" + toString((pValueCounts[i][j]/(float)iters))); m->mothurOutEndLine(); + outSum << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[spoti][spotj] << '\t' << setprecision(precision) << pValueCounts[i][j]/(float)iters << endl; } else{ - cout << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[i][j] << '\t' << '<' <mothurOutJustToLog(groupNames[i]+"-"+groupNames[j] + "\t" + toString(savedDXYValues[spoti][spotj]) + "\t" + toString((1/(float)iters))); m->mothurOutEndLine(); + outSum << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[spoti][spotj] << '\t' << '<' <mothurOutJustToLog(groupNames[j]+"-"+groupNames[i] + "\t" + toString(savedDXYValues[spotj][spoti]) + "\t" + toString((pValueCounts[j][i]/(float)iters))); m->mothurOutEndLine(); + outSum << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[spotj][spoti] << '\t' << setprecision (precision) << pValueCounts[j][i]/(float)iters << endl; } else{ - cout << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[j][i] << '\t' << '<' <mothurOutJustToLog(groupNames[j]+"-"+groupNames[i] + "\t" + toString(savedDXYValues[spotj][spoti]) + "\t" + toString((1/(float)iters))); m->mothurOutEndLine(); + outSum << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[spotj][spoti] << '\t' << '<' <errorOut(e, "LibShuffCommand", "printSummaryFile"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function printSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** @@ -333,7 +430,7 @@ void LibShuffCommand::setGroups() { //check that groups are valid for (int i = 0; i < globaldata->Groups.size(); i++) { if (globaldata->gGroupmap->isValidGroup(globaldata->Groups[i]) != true) { - cout << globaldata->Groups[i] << " is not a valid group, and will be disregarded." << endl; + m->mothurOut(globaldata->Groups[i] + " is not a valid group, and will be disregarded."); m->mothurOutEndLine(); // erase the invalid group from globaldata->Groups globaldata->Groups.erase(globaldata->Groups.begin()+i); } @@ -345,7 +442,7 @@ void LibShuffCommand::setGroups() { for (int i=0; i < numGroups; i++) { globaldata->Groups.push_back(globaldata->gGroupmap->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; + m->mothurOut("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."); m->mothurOutEndLine(); } else { numGroups = globaldata->Groups.size(); } } else { //users wants all groups numGroups = globaldata->gGroupmap->getNumGroups(); @@ -361,23 +458,14 @@ void LibShuffCommand::setGroups() { //sort sort(globaldata->gGroupmap->namesOfGroups.begin(), globaldata->gGroupmap->namesOfGroups.end()); + + for (int i = 0; i < globaldata->gGroupmap->namesOfGroups.size(); i++) { globaldata->gGroupmap->groupIndex[globaldata->gGroupmap->namesOfGroups[i]] = i; } groupNames = globaldata->Groups; - // number of comparisons i.e. with groups A,B,C = AA, AB, AC, BA, BB, BC...; -// for (int i=0; iGroups[i] + "-" + globaldata->Groups[l]); -// } -// } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the LibShuffCommand class Function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the LibShuffCommand class function setGroups. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "LibShuffCommand", "setGroups"); exit(1); } }