OrderVector SAbundVector::getOrderVector(map<string,int>* hold = NULL){
try {
OrderVector ov;
int binIndex = 0;
for(int i=1;i<data.size();i++){
for(int j=0;j<data[i];j++){
for(int k=0;k<i;k++){
ov.push_back(binIndex);
}
binIndex++;
}
}
random_shuffle(ov.begin(), ov.end());
ov.setLabel(label);
ov.getNumBins();
return ov;
}
catch(exception& e) {
m->errorOut(e, "SAbundVector", "getOrderVector");
exit(1);
}
}
OrderVector ListVector::getOrderVector(map<string,int>* orderMap = NULL) {
try {
if(orderMap == NULL) {
OrderVector ov;
for(int i=0; i<data.size(); i++) {
int binSize = m->getNumNames(data[i]);
for(int j=0; j<binSize; j++) {
ov.push_back(i);
}
}
random_shuffle(ov.begin(), ov.end());
ov.setLabel(label);
ov.getNumBins();
return ov;
}
else {
OrderVector ov(numSeqs);
for(int i=0; i<data.size(); i++) {
string listOTU = data[i];
int length = listOTU.size();
string seqName="";
for(int j=0; j<length; j++) {
if(listOTU[j] != ',') {
seqName += listOTU[j];
}
else {
if(orderMap->count(seqName) == 0) {
m->mothurOut(seqName + " not found, check *.names file\n");
exit(1);
}
ov.set((*orderMap)[seqName], i);
seqName = "";
}
}
if(orderMap->count(seqName) == 0) {
m->mothurOut(seqName + " not found, check *.names file\n");
exit(1);
}
ov.set((*orderMap)[seqName], i);
}
ov.setLabel(label);
ov.getNumBins();
return ov;
}
}
catch(exception& e) {
m->errorOut(e, "ListVector", "getOrderVector");
exit(1);
}
}
int RareFactCommand::execute(){
try {
if (abort) { if (calledHelp) { return 0; } return 2; }
long start = time(NULL);
map<string, set<int> > labelToEnds;
if ((format != "sharedfile")) { inputFileNames.push_back(inputfile); }
else { inputFileNames = parseSharedFile(sharedfile, labelToEnds); format = "rabund"; }
if (m->getControl_pressed()) { return 0; }
map<int, string> file2Group; //index in outputNames[i] -> group
for (int p = 0; p < inputFileNames.size(); p++) {
string fileNameRoot = outputDir + util.getRootName(util.getSimpleName(inputFileNames[p]));
if (m->getControl_pressed()) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
if (inputFileNames.size() > 1) {
m->mothurOutEndLine(); m->mothurOut("Processing group " + Groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine();
}
int i;
ValidCalculators validCalculator;
map<string, string> variables;
variables["[filename]"] = fileNameRoot;
for (i=0; i<Estimators.size(); i++) {
if (validCalculator.isValidCalculator("rarefaction", Estimators[i]) ) {
if (Estimators[i] == "sobs") {
rDisplays.push_back(new RareDisplay(new Sobs(), new ThreeColumnFile(getOutputFileName("rarefaction",variables))));
outputNames.push_back(getOutputFileName("rarefaction",variables)); outputTypes["rarefaction"].push_back(getOutputFileName("rarefaction",variables));
}else if (Estimators[i] == "chao") {
rDisplays.push_back(new RareDisplay(new Chao1(), new ThreeColumnFile(getOutputFileName("r_chao",variables))));
outputNames.push_back(getOutputFileName("r_chao",variables)); outputTypes["r_chao"].push_back(getOutputFileName("r_chao",variables));
}else if (Estimators[i] == "ace") {
if(abund < 5)
abund = 10;
rDisplays.push_back(new RareDisplay(new Ace(abund), new ThreeColumnFile(getOutputFileName("r_ace",variables))));
outputNames.push_back(getOutputFileName("r_ace",variables)); outputTypes["r_ace"].push_back(getOutputFileName("r_ace",variables));
}else if (Estimators[i] == "jack") {
rDisplays.push_back(new RareDisplay(new Jackknife(), new ThreeColumnFile(getOutputFileName("r_jack",variables))));
outputNames.push_back(getOutputFileName("r_jack",variables)); outputTypes["r_jack"].push_back(getOutputFileName("r_jack",variables));
}else if (Estimators[i] == "shannon") {
rDisplays.push_back(new RareDisplay(new Shannon(), new ThreeColumnFile(getOutputFileName("r_shannon",variables))));
outputNames.push_back(getOutputFileName("r_shannon",variables)); outputTypes["r_shannon"].push_back(getOutputFileName("r_shannon",variables));
}else if (Estimators[i] == "shannoneven") {
rDisplays.push_back(new RareDisplay(new ShannonEven(), new ThreeColumnFile(getOutputFileName("r_shannoneven",variables))));
outputNames.push_back(getOutputFileName("r_shannoneven",variables)); outputTypes["r_shannoneven"].push_back(getOutputFileName("r_shannoneven",variables));
}else if (Estimators[i] == "heip") {
rDisplays.push_back(new RareDisplay(new Heip(), new ThreeColumnFile(getOutputFileName("r_heip",variables))));
outputNames.push_back(getOutputFileName("r_heip",variables)); outputTypes["r_heip"].push_back(getOutputFileName("r_heip",variables));
}else if (Estimators[i] == "r_shannonrange") {
rDisplays.push_back(new RareDisplay(new RangeShannon(alpha), new ThreeColumnFile(getOutputFileName("r_shannonrange", variables))));
outputNames.push_back(getOutputFileName("r_shannonrange", variables)); outputTypes["r_shannoneven"].push_back(getOutputFileName("r_shannonrange", variables));
}else if (Estimators[i] == "smithwilson") {
rDisplays.push_back(new RareDisplay(new SmithWilson(), new ThreeColumnFile(getOutputFileName("r_smithwilson",variables))));
outputNames.push_back(getOutputFileName("r_smithwilson",variables)); outputTypes["r_smithwilson"].push_back(getOutputFileName("r_smithwilson",variables));
}else if (Estimators[i] == "npshannon") {
rDisplays.push_back(new RareDisplay(new NPShannon(), new ThreeColumnFile(getOutputFileName("r_npshannon",variables))));
outputNames.push_back(getOutputFileName("r_npshannon",variables)); outputTypes["r_npshannon"].push_back(getOutputFileName("r_npshannon",variables));
}else if (Estimators[i] == "simpson") {
rDisplays.push_back(new RareDisplay(new Simpson(), new ThreeColumnFile(getOutputFileName("r_simpson",variables))));
outputNames.push_back(getOutputFileName("r_simpson",variables)); outputTypes["r_simpson"].push_back(getOutputFileName("r_simpson",variables));
}else if (Estimators[i] == "simpsoneven") {
rDisplays.push_back(new RareDisplay(new SimpsonEven(), new ThreeColumnFile(getOutputFileName("r_simpsoneven",variables))));
outputNames.push_back(getOutputFileName("r_simpsoneven",variables)); outputTypes["r_simpsoneven"].push_back(getOutputFileName("r_simpsoneven",variables));
}else if (Estimators[i] == "invsimpson") {
rDisplays.push_back(new RareDisplay(new InvSimpson(), new ThreeColumnFile(getOutputFileName("r_invsimpson",variables))));
outputNames.push_back(getOutputFileName("r_invsimpson",variables)); outputTypes["r_invsimpson"].push_back(getOutputFileName("r_invsimpson",variables));
}else if (Estimators[i] == "bootstrap") {
rDisplays.push_back(new RareDisplay(new Bootstrap(), new ThreeColumnFile(getOutputFileName("r_bootstrap",variables))));
outputNames.push_back(getOutputFileName("r_bootstrap",variables)); outputTypes["r_bootstrap"].push_back(getOutputFileName("r_bootstrap",variables));
}else if (Estimators[i] == "coverage") {
rDisplays.push_back(new RareDisplay(new Coverage(), new ThreeColumnFile(getOutputFileName("r_coverage",variables))));
outputNames.push_back(getOutputFileName("r_coverage",variables)); outputTypes["r_coverage"].push_back(getOutputFileName("r_coverage",variables));
}else if (Estimators[i] == "nseqs") {
rDisplays.push_back(new RareDisplay(new NSeqs(), new ThreeColumnFile(getOutputFileName("r_nseqs",variables))));
outputNames.push_back(getOutputFileName("r_nseqs",variables)); outputTypes["r_nseqs"].push_back(getOutputFileName("r_nseqs",variables));
}
if (inputFileNames.size() > 1) { file2Group[outputNames.size()-1] = Groups[p]; }
}
}
//if the users entered no valid calculators don't execute command
if (rDisplays.size() == 0) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } return 0; }
InputData input(inputFileNames[p], format, nullVector);
OrderVector* order = input.getOrderVector();
string lastLabel = order->getLabel();
//if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
set<string> processedLabels;
set<string> userLabels = labels;
if (m->getControl_pressed()) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete order; for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
//as long as you are not at the end of the file or done wih the lines you want
while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
if (m->getControl_pressed()) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } delete order; for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
if(allLines == 1 || labels.count(order->getLabel()) == 1){
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
set<int> ends;
if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
rCurve = new Rarefact(*order, rDisplays, ends, processors);
rCurve->getCurve(freq, nIters);
delete rCurve;
processedLabels.insert(order->getLabel());
userLabels.erase(order->getLabel());
}
if ((util.anyLabelsToProcess(order->getLabel(), userLabels, "") ) && (processedLabels.count(lastLabel) != 1)) {
string saveLabel = order->getLabel();
delete order;
order = (input.getOrderVector(lastLabel));
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
set<int> ends;
if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
rCurve = new Rarefact(*order, rDisplays, ends, processors);
rCurve->getCurve(freq, nIters);
delete rCurve;
processedLabels.insert(order->getLabel());
userLabels.erase(order->getLabel());
//restore real lastlabel to save below
order->setLabel(saveLabel);
}
lastLabel = order->getLabel();
delete order;
order = (input.getOrderVector());
}
if (m->getControl_pressed()) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
//output error messages about any remaining user labels
set<string>::iterator it;
bool needToRun = false;
for (it = userLabels.begin(); it != userLabels.end(); it++) {
m->mothurOut("Your file does not include the label " + *it);
if (processedLabels.count(lastLabel) != 1) {
m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine();
needToRun = true;
}else {
m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine();
}
}
if (m->getControl_pressed()) { for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; } for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
//run last label if you need to
if (needToRun ) {
if (order != NULL) { delete order; }
order = (input.getOrderVector(lastLabel));
m->mothurOut(order->getLabel()); m->mothurOutEndLine();
map<string, set<int> >::iterator itEndings = labelToEnds.find(order->getLabel());
set<int> ends;
if (itEndings != labelToEnds.end()) { ends = itEndings->second; }
rCurve = new Rarefact(*order, rDisplays, ends, processors);
rCurve->getCurve(freq, nIters);
delete rCurve;
delete order;
}
for(int i=0;i<rDisplays.size();i++){ delete rDisplays[i]; }
rDisplays.clear();
}
if (m->getControl_pressed()) { for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
//create summary file containing all the groups data for each label - this function just combines the info from the files already created.
if ((sharedfile != "") && (groupMode)) { outputNames = createGroupFile(outputNames, file2Group); }
if (m->getControl_pressed()) { for (int i = 0; i < outputNames.size(); i++) { util.mothurRemove(outputNames[i]); } return 0; }
m->mothurOut("\nIt took " + toString(time(NULL) - start) + " secs to run rarefaction.single.\n");
m->mothurOut("\nOutput File Names: \n");
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i] +"\n"); } m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
m->errorOut(e, "RareFactCommand", "execute");
exit(1);
}
}
