]> git.donarmstrong.com Git - mothur.git/blobdiff - collectcommand.cpp
paralellized phylo.diversity
[mothur.git] / collectcommand.cpp
index 9bf2c9a88c49f49f27d8a641aabc4d9f8d2ab3fe..2d952fa9b9a60ea762a83f967dc7e6c125fff61d 100644 (file)
 #include "chao1.h"
 #include "bootstrap.h"
 #include "simpson.h"
+#include "simpsoneven.h"
+#include "invsimpson.h"
 #include "npshannon.h"
 #include "shannon.h"
+#include "smithwilson.h"
+#include "heip.h"
+#include "shannoneven.h"
 #include "jackknife.h"
 #include "geom.h"
 #include "qstat.h"
@@ -68,7 +73,7 @@ CollectCommand::CollectCommand(string option)  {
                        label = validParameter.validFile(parameters, "label", false);                   
                        if (label == "not found") { label = ""; }
                        else { 
-                               if(label != "all") {  splitAtDash(label, labels);  allLines = 0;  }
+                               if(label != "all") {  m->splitAtDash(label, labels);  allLines = 0;  }
                                else { allLines = 1;  }
                        }
                        
@@ -83,7 +88,7 @@ CollectCommand::CollectCommand(string option)  {
                        else { 
                                 if (calc == "default")  {  calc = "sobs-chao-ace-jack-shannon-npshannon-simpson";  }
                        }
-                       splitAtDash(calc, Estimators);
+                       m->splitAtDash(calc, Estimators);
 
                        string temp;
                        temp = validParameter.validFile(parameters, "freq", false);                     if (temp == "not found") { temp = "100"; }
@@ -110,6 +115,7 @@ void CollectCommand::help(){
                m->mothurOut("The collect.single command can be executed after a successful cluster command.  It will use the .list file from the output of the cluster.\n");
                m->mothurOut("The collect.single command parameters are label, freq, calc and abund.  No parameters are required. \n");
                m->mothurOut("The collect.single command should be in the following format: \n");
+               m->mothurOut("The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n");
                m->mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n");
                m->mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n");
                m->mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n");
@@ -136,15 +142,16 @@ int CollectCommand::execute(){
                
                vector<string> outputNames;
                
+               string hadShared = "";
                if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName);  }
-               else {  inputFileNames = parseSharedFile(globaldata->getSharedFile());  globaldata->setFormat("rabund");  }
+               else { hadShared = globaldata->getSharedFile(); inputFileNames = parseSharedFile(globaldata->getSharedFile());  globaldata->setFormat("rabund");  }
        
                for (int p = 0; p < inputFileNames.size(); p++) {
                        
-                       if (m->control_pressed) {  for (int i = 0; i < outputNames.size(); i++) {       remove(outputNames[i].c_str());         }  globaldata->Groups.clear(); return 0; }
+                       if (m->control_pressed) {  for (int i = 0; i < outputNames.size(); i++) {       remove(outputNames[i].c_str());         }  globaldata->Groups.clear(); if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  } return 0; }
                        
-                       if (outputDir == "") { outputDir += hasPath(inputFileNames[p]); }
-                       string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p]));
+                       if (outputDir == "") { outputDir += m->hasPath(inputFileNames[p]); }
+                       string fileNameRoot = outputDir + m->getRootName(m->getSimpleName(inputFileNames[p]));
                        globaldata->inputFileName = inputFileNames[p];
                
                        if (inputFileNames.size() > 1) {
@@ -176,12 +183,27 @@ int CollectCommand::execute(){
                                        }else if (Estimators[i] == "shannon") { 
                                                cDisplays.push_back(new CollectDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"shannon")));
                                                outputNames.push_back(fileNameRoot+"shannon");
+                                       }else if (Estimators[i] == "shannoneven") { 
+                                               cDisplays.push_back(new CollectDisplay(new ShannonEven(), new OneColumnFile(fileNameRoot+"shannoneven")));
+                                               outputNames.push_back(fileNameRoot+"shannoneven");
                                        }else if (Estimators[i] == "npshannon") { 
                                                cDisplays.push_back(new CollectDisplay(new NPShannon(), new OneColumnFile(fileNameRoot+"np_shannon")));
                                                outputNames.push_back(fileNameRoot+"np_shannon");
+                                       }else if (Estimators[i] == "heip") { 
+                                               cDisplays.push_back(new CollectDisplay(new Heip(), new OneColumnFile(fileNameRoot+"heip")));
+                                               outputNames.push_back(fileNameRoot+"heip");
+                                       }else if (Estimators[i] == "smithwilson") { 
+                                               cDisplays.push_back(new CollectDisplay(new SmithWilson(), new OneColumnFile(fileNameRoot+"smithwilson")));
+                                               outputNames.push_back(fileNameRoot+"smithwilson");
                                        }else if (Estimators[i] == "simpson") { 
                                                cDisplays.push_back(new CollectDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"simpson")));
                                                outputNames.push_back(fileNameRoot+"simpson");
+                                       }else if (Estimators[i] == "simpsoneven") { 
+                                               cDisplays.push_back(new CollectDisplay(new SimpsonEven(), new OneColumnFile(fileNameRoot+"simpsoneven")));
+                                               outputNames.push_back(fileNameRoot+"simpsoneven");
+                                       }else if (Estimators[i] == "invsimpson") { 
+                                               cDisplays.push_back(new CollectDisplay(new InvSimpson(), new ThreeColumnFile(fileNameRoot+"invsimpson")));
+                                               outputNames.push_back(fileNameRoot+"invsimpson");
                                        }else if (Estimators[i] == "bootstrap") { 
                                                cDisplays.push_back(new CollectDisplay(new Bootstrap(), new OneColumnFile(fileNameRoot+"bootstrap")));
                                                outputNames.push_back(fileNameRoot+"bootstrap");
@@ -220,7 +242,7 @@ int CollectCommand::execute(){
                        }
                
                        //if the users entered no valid calculators don't execute command
-                       if (cDisplays.size() == 0) { return 0; }
+                       if (cDisplays.size() == 0) { if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  } return 0; }
                        
                        read = new ReadOTUFile(inputFileNames[p]);      
                        read->read(&*globaldata); 
@@ -234,65 +256,58 @@ int CollectCommand::execute(){
                        set<string> userLabels = labels;
                        
                        if (m->control_pressed) {  
-                               for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }  
                                for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
+                               for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }
                                delete input;  globaldata->ginput = NULL;
                                delete read;
                                delete order; globaldata->gorder = NULL;
                                delete validCalculator;
                                globaldata->Groups.clear();
+                               if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  }
                                return 0;
                        }
 
 
                        while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
+                       
+                               if (m->control_pressed) { 
+                                       for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
+                                       for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }
+                                       delete input;  globaldata->ginput = NULL;
+                                       delete read;
+                                       delete order; globaldata->gorder = NULL;
+                                       delete validCalculator;
+                                       globaldata->Groups.clear();
+                                       if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  }
+                                       return 0;
+                               }
+
                                
                                if(allLines == 1 || labels.count(order->getLabel()) == 1){
-                                       
+                               
+                                       m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                        cCurve = new Collect(order, cDisplays);
-                                       int error = cCurve->getCurve(freq);
+                                       cCurve->getCurve(freq);
                                        delete cCurve;
                                        
-                                       if (error == 1) {
-                                               for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }  
-                                               for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
-                                               delete input;  globaldata->ginput = NULL;
-                                               delete read;
-                                               delete order; globaldata->gorder = NULL;
-                                               delete validCalculator;
-                                               globaldata->Groups.clear();
-                                               return 0;
-                                       }
-                                       
-                                       m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                        processedLabels.insert(order->getLabel());
                                        userLabels.erase(order->getLabel());
                                        
                                        
                                }
                                //you have a label the user want that is smaller than this label and the last label has not already been processed 
-                               if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
+                               if ((m->anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
                                        string saveLabel = order->getLabel();
                                        
                                        delete order;
                                        order = (input->getOrderVector(lastLabel));
                                        
+                                       m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                        cCurve = new Collect(order, cDisplays);
-                                       int error = cCurve->getCurve(freq);
+                                       cCurve->getCurve(freq);
                                        delete cCurve;
                                        
-                                       if (error == 1) {
-                                               for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }  
-                                               for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
-                                               delete input;  globaldata->ginput = NULL;
-                                               delete read;
-                                               delete order; globaldata->gorder = NULL;
-                                               delete validCalculator;
-                                               globaldata->Groups.clear();
-                                               return 0;
-                                       }
                                        
-                                       m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                        processedLabels.insert(order->getLabel());
                                        userLabels.erase(order->getLabel());
                                        
@@ -306,6 +321,18 @@ int CollectCommand::execute(){
                                order = (input->getOrderVector());
                        }
                        
+                       
+                       if (m->control_pressed) { 
+                                       for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
+                                       for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }
+                                       delete input;  globaldata->ginput = NULL;
+                                       delete read;
+                                       delete validCalculator;
+                                       globaldata->Groups.clear();
+                                       if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  }
+                                       return 0;
+                       }
+                               
                        //output error messages about any remaining user labels
                        set<string>::iterator it;
                        bool needToRun = false;
@@ -327,17 +354,18 @@ int CollectCommand::execute(){
                                m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                
                                cCurve = new Collect(order, cDisplays);
-                               int error = cCurve->getCurve(freq);
+                               cCurve->getCurve(freq);
                                delete cCurve;
                                
-                               if (error == 1) {
-                                       for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }  
+                               if (m->control_pressed) { 
                                        for(int i=0;i<cDisplays.size();i++){    delete cDisplays[i];    }
+                                       for (int i = 0; i < outputNames.size(); i++) {  remove(outputNames[i].c_str());         }
                                        delete input;  globaldata->ginput = NULL;
                                        delete read;
                                        delete order; globaldata->gorder = NULL;
                                        delete validCalculator;
                                        globaldata->Groups.clear();
+                                       if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  }
                                        return 0;
                                }
                                delete order;
@@ -351,6 +379,11 @@ int CollectCommand::execute(){
                        delete validCalculator;
                }
                
+               //return to shared mode if you changed above
+               if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  }
+
+               if (m->control_pressed) { 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();    }
@@ -381,7 +414,7 @@ vector<string> CollectCommand::parseSharedFile(string filename) {
                input = globaldata->ginput;
                vector<SharedRAbundVector*> lookup = input->getSharedRAbundVectors();
                
-               string sharedFileRoot = getRootName(filename);
+               string sharedFileRoot = m->getRootName(filename);
                
                //clears file before we start to write to it below
                for (int i=0; i<lookup.size(); i++) {
@@ -400,7 +433,7 @@ vector<string> CollectCommand::parseSharedFile(string filename) {
                
                        for (int i = 0; i < lookup.size(); i++) {
                                RAbundVector rav = lookup[i]->getRAbundVector();
-                               openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()]));
+                               m->openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()]));
                                rav.print(*(filehandles[lookup[i]->getGroup()]));
                                (*(filehandles[lookup[i]->getGroup()])).close();
                        }