//**********************************************************************************************************************
-LibShuffCommand::LibShuffCommand(){
+LibShuffCommand::LibShuffCommand(string option){
try {
- srand( (unsigned)time( NULL ) );
-
globaldata = GlobalData::getInstance();
- convert(globaldata->getCutOff(), cutOff); //get the cutoff
- convert(globaldata->getIters(), iters); //get the number of iterations
- convert(globaldata->getStep(), step); //get the step size for the discrete command
- matrix = globaldata->gMatrix; //get the distance matrix
- setGroups(); //set the groups to be analyzed
+ abort = false;
+ Groups.clear();
+
+
+ //allow user to run help
+ if(option == "help") { help(); abort = true; }
+
+ else {
+ //valid paramters for this command
+ string Array[] = {"iters","groups","step","form","cutoff","outputdir","inputdir"};
+ 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 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 += 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)) {
+ mothurOut("You must read in a matrix and groupfile using the read.dist command, before you use the libshuff command. "); mothurOutEndLine(); 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 = ""; savegroups = groups; }
+ else {
+ savegroups = groups;
+ splitAtDash(groups, Groups);
+ globaldata->Groups = Groups;
+ }
+
+ string temp;
+ temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "10000"; }
+ convert(temp, iters);
+
+ temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "1.0"; }
+ convert(temp, cutOff);
+
+ temp = validParameter.validFile(parameters, "step", false); if (temp == "not found") { temp = "0.01"; }
+ convert(temp, step);
+
+ 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 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<int> 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(globaldata->getForm() == "discrete"){
- form = new DLibshuff(matrix, iters, step, cutOff);
- }
- else{
- form = new SLibshuff(matrix, iters, cutOff);
+ if(userform == "discrete"){
+ form = new DLibshuff(matrix, iters, step, cutOff);
+ }
+ else{
+ form = new SLibshuff(matrix, iters, cutOff);
+ }
+ }
+
}
+
}
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";
+ 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";
+}
+//**********************************************************************************************************************
+
+void LibShuffCommand::help(){
+ try {
+ mothurOut("The libshuff command can only be executed after a successful read.dist command including a groupfile.\n");
+ mothurOut("The libshuff command parameters are groups, iters, step, form and cutoff. No parameters are required.\n");
+ 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");
+ 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");
+ 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");
+ 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");
+ mothurOut("The libshuff command should be in the following format: libshuff(groups=yourGroups, iters=yourIters, cutOff=yourCutOff, form=yourForm, step=yourStep).\n");
+ mothurOut("Example libshuff(groups=A-B-C, iters=500, form=discrete, step=0.01, cutOff=2.0).\n");
+ 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");
+ mothurOut("The libshuff command output two files: .coverage and .slsummary their descriptions are in the manual.\n");
+ mothurOut("Note: No spaces between parameter labels (i.e. iters), '=' and parameters (i.e.yourIters).\n\n");
+ }
+ catch(exception& e) {
+ errorOut(e, "LibShuffCommand", "help");
exit(1);
- }
-
+ }
}
//**********************************************************************************************************************
int LibShuffCommand::execute(){
try {
-
+
+ if (abort == true) { return 0; }
+
savedDXYValues = form->evaluateAll();
savedMinValues = form->getSavedMins();
-
+
pValueCounts.resize(numGroups);
for(int i=0;i<numGroups;i++){
pValueCounts[i].assign(numGroups, 0);
for(int i=0;i<numGroups-1;i++) {
for(int j=i+1;j<numGroups;j++) {
reading->newLine(groupNames[i]+'-'+groupNames[j], iters);
+ 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;p<iters;p++) {
- form->randomizeGroups(i,j);
- if(form->evaluatePair(i,j) >= savedDXYValues[i][j]) { pValueCounts[i][j]++; }
- if(form->evaluatePair(j,i) >= savedDXYValues[j][i]) { pValueCounts[j][i]++; }
+ 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]++; }
reading->update(p);
}
- form->resetGroup(i);
- form->resetGroup(j);
+ form->resetGroup(spoti);
+ form->resetGroup(spotj);
}
}
reading->finish();
delete reading;
- cout << endl;
+ mothurOutEndLine();
printSummaryFile();
printCoverageFile();
globaldata->Groups.clear();
delete form;
+ //delete globaldata's copy of the gmatrix to free up memory
+ delete globaldata->gMatrix; globaldata->gMatrix = NULL;
+
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";
+ 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);
- }
}
//**********************************************************************************************************************
try {
ofstream outCov;
- summaryFile = getRootName(globaldata->getPhylipFile()) + "libshuff.coverage";
+ summaryFile = outputDir + getRootName(getSimpleName(globaldata->getPhylipFile())) + "libshuff.coverage";
openOutputFile(summaryFile, outCov);
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<double,vector<int> > allDistances;
map<double,vector<int> >::iterator it;
indices[i].assign(numGroups,0);
for(int j=0;j<numGroups;j++){
indices[i][j] = index++;
- for(int k=0;k<savedMinValues[i][j].size();k++){
- if(allDistances[savedMinValues[i][j][k]].size() != 0){
- allDistances[savedMinValues[i][j][k]][indices[i][j]]++;
+
+ 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 k=0;k<savedMinValues[spoti][spotj].size();k++){
+ 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<int> prevRow = it->second;
it++;
- for(it;it!=allDistances.end();it++){
+ for(;it!=allDistances.end();it++){
for(int i=0;i<it->second.size();i++){
it->second[i] += prevRow[i];
}
}
outCov << endl;
}
-
+ outCov.close();
}
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";
+ 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);
- }
}
//**********************************************************************************************************************
try {
ofstream outSum;
- summaryFile = getRootName(globaldata->getPhylipFile()) + "libshuff.summary";
+ summaryFile = outputDir + getRootName(getSimpleName(globaldata->getPhylipFile())) + "libshuff.summary";
openOutputFile(summaryFile, outSum);
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;
+ mothurOutJustToLog("Comparison\tdCXYScore\tSignificance"); mothurOutEndLine();
outSum << setw(20) << left << "Comparison" << '\t' << setprecision(8) << "dCXYScore" << '\t' << "Significance" << endl;
int precision = (int)log10(iters);
for(int i=0;i<numGroups;i++){
for(int j=i+1;j<numGroups;j++){
+ 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;
+ mothurOutJustToLog(groupNames[i]+"-"+groupNames[j] + "\t" + toString(savedDXYValues[spoti][spotj]) + "\t" + toString((pValueCounts[i][j]/(float)iters))); 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' << '<' <<setprecision(precision) << 1/(float)iters << endl;
- outSum << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[i][j] << '\t' << '<' <<setprecision(precision) << 1/(float)iters << endl;
+ cout << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[spoti][spotj] << '\t' << '<' <<setprecision(precision) << 1/(float)iters << endl;
+ mothurOutJustToLog(groupNames[i]+"-"+groupNames[j] + "\t" + toString(savedDXYValues[spoti][spotj]) + "\t" + toString((1/(float)iters))); mothurOutEndLine();
+ outSum << setw(20) << left << groupNames[i]+'-'+groupNames[j] << '\t' << setprecision(8) << savedDXYValues[spoti][spotj] << '\t' << '<' <<setprecision(precision) << 1/(float)iters << endl;
}
if(pValueCounts[j][i]){
- cout << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[j][i] << '\t' << setprecision (precision) << pValueCounts[j][i]/(float)iters << endl;
- outSum << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[j][i] << '\t' << setprecision (precision) << pValueCounts[j][i]/(float)iters << endl;
+ cout << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[spotj][spoti] << '\t' << setprecision (precision) << pValueCounts[j][i]/(float)iters << endl;
+ mothurOutJustToLog(groupNames[j]+"-"+groupNames[i] + "\t" + toString(savedDXYValues[spotj][spoti]) + "\t" + toString((pValueCounts[j][i]/(float)iters))); 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' << '<' <<setprecision (precision) << 1/(float)iters << endl;
- outSum << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[j][i] << '\t' << '<' <<setprecision (precision) << 1/(float)iters << endl;
+ cout << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[spotj][spoti] << '\t' << '<' <<setprecision (precision) << 1/(float)iters << endl;
+ mothurOutJustToLog(groupNames[j]+"-"+groupNames[i] + "\t" + toString(savedDXYValues[spotj][spoti]) + "\t" + toString((1/(float)iters))); mothurOutEndLine();
+ outSum << setw(20) << left << groupNames[j]+'-'+groupNames[i] << '\t' << setprecision(8) << savedDXYValues[spotj][spoti] << '\t' << '<' <<setprecision (precision) << 1/(float)iters << endl;
}
}
}
-
+ outSum.close();
}
catch(exception& e) {
- cout << "Standard Error: " << e.what() << " has occurred in the LibShuffCommand class Function printSummaryFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
+ 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);
- }
}
//**********************************************************************************************************************
globaldata->Groups.push_back(globaldata->gGroupmap->namesOfGroups[i]);
}
} else {
- if (globaldata->getGroups() != "all") {
+ if (savegroups != "all") {
//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;
+ mothurOut(globaldata->Groups[i] + " is not a valid group, and will be disregarded."); mothurOutEndLine();
// erase the invalid group from globaldata->Groups
- globaldata->Groups.erase (globaldata->Groups.begin()+i);
+ globaldata->Groups.erase(globaldata->Groups.begin()+i);
}
}
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;
+ 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."); mothurOutEndLine();
} else { numGroups = globaldata->Groups.size(); }
} else { //users wants all groups
numGroups = globaldata->gGroupmap->getNumGroups();
//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; i<numGroups; i++) {
-// for (int l = 0; 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 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";
+ errorOut(e, "LibShuffCommand", "setGroups");
exit(1);
}
}
projects / mothur.git / blobdiff