]> git.donarmstrong.com Git - mothur.git/blobdiff - collectcommand.cpp
added a few evenness calculators and fixed a couple of bugs in filter.seqs and pre...
[mothur.git] / collectcommand.cpp
index a31883cf3c65aabf3955d12191b91b9ad9fe050c..ca48d75d276a274ff5b2259ffe211b653a02f1a9 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"
@@ -31,7 +36,7 @@
 
 
 //**********************************************************************************************************************
-CollectCommand::CollectCommand(string option){
+CollectCommand::CollectCommand(string option)  {
        try {
                globaldata = GlobalData::getInstance();
                abort = false;
@@ -61,7 +66,7 @@ CollectCommand::CollectCommand(string option){
                        outputDir = validParameter.validFile(parameters, "outputdir", false);           if (outputDir == "not found"){  outputDir = "";         }
                        
                        //make sure the user has already run the read.otu command
-                       if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { mothurOut("You must read a list, sabund, rabund or shared file before you can use the collect.single command."); mothurOutEndLine(); abort = true; }
+                       if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { m->mothurOut("You must read a list, sabund, rabund or shared file before you can use the collect.single command."); m->mothurOutEndLine(); abort = true; }
                        
                        //check for optional parameter and set defaults
                        // ...at some point should added some additional type checking...
@@ -98,7 +103,7 @@ CollectCommand::CollectCommand(string option){
                
        }
        catch(exception& e) {
-               errorOut(e, "CollectCommand", "CollectCommand");
+               m->errorOut(e, "CollectCommand", "CollectCommand");
                exit(1);
        }                       
 }
@@ -106,19 +111,20 @@ CollectCommand::CollectCommand(string option){
 
 void CollectCommand::help(){
        try {
-               mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n");
-               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");
-               mothurOut("The collect.single command parameters are label, freq, calc and abund.  No parameters are required. \n");
-               mothurOut("The collect.single command should be in the following format: \n");
-               mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n");
-               mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n");
-               mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n");
+               m->mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n");
+               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");
                validCalculator->printCalc("single", cout);
-               mothurOut("The label parameter is used to analyze specific labels in your input.\n");
-               mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n");
+               m->mothurOut("The label parameter is used to analyze specific labels in your input.\n");
+               m->mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n");
        }
        catch(exception& e) {
-               errorOut(e, "CollectCommand", "help");
+               m->errorOut(e, "CollectCommand", "help");
                exit(1);
        }
 }
@@ -134,74 +140,113 @@ int CollectCommand::execute(){
                
                if (abort == true) { return 0; }
                
-               if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName);  }
-               else {  inputFileNames = parseSharedFile(globaldata->getSharedFile());  globaldata->setFormat("rabund");  }
+               vector<string> outputNames;
                
+               string hadShared = "";
+               if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName);  }
+               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(); if (hadShared != "") {  globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile");  } return 0; }
+                       
                        if (outputDir == "") { outputDir += hasPath(inputFileNames[p]); }
                        string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p]));
                        globaldata->inputFileName = inputFileNames[p];
-                       
+               
                        if (inputFileNames.size() > 1) {
-                               mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine();
+                               m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine();
                        }
-                       
+               
                        validCalculator = new ValidCalculators();
                        
                        for (int i=0; i<Estimators.size(); i++) {
                                if (validCalculator->isValidCalculator("single", Estimators[i]) == true) { 
                                        if (Estimators[i] == "sobs") { 
                                                cDisplays.push_back(new CollectDisplay(new Sobs(), new OneColumnFile(fileNameRoot+"sobs")));
+                                               outputNames.push_back(fileNameRoot+"sobs");
                                        }else if (Estimators[i] == "chao") { 
                                                cDisplays.push_back(new CollectDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"chao")));
+                                               outputNames.push_back(fileNameRoot+"chao");
                                        }else if (Estimators[i] == "nseqs") { 
                                                cDisplays.push_back(new CollectDisplay(new NSeqs(), new OneColumnFile(fileNameRoot+"nseqs")));
+                                               outputNames.push_back(fileNameRoot+"nseqs");
                                        }else if (Estimators[i] == "coverage") { 
                                                cDisplays.push_back(new CollectDisplay(new Coverage(), new OneColumnFile(fileNameRoot+"coverage")));
+                                               outputNames.push_back(fileNameRoot+"coverage");
                                        }else if (Estimators[i] == "ace") { 
                                                cDisplays.push_back(new CollectDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"ace")));
+                                               outputNames.push_back(fileNameRoot+"ace");
                                        }else if (Estimators[i] == "jack") { 
                                                cDisplays.push_back(new CollectDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"jack")));
+                                               outputNames.push_back(fileNameRoot+"jack");
                                        }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");
                                        }else if (Estimators[i] == "geometric") { 
                                                cDisplays.push_back(new CollectDisplay(new Geom(), new OneColumnFile(fileNameRoot+"geometric")));
+                                               outputNames.push_back(fileNameRoot+"geometric");
                                        }else if (Estimators[i] == "qstat") { 
                                                cDisplays.push_back(new CollectDisplay(new QStat(), new OneColumnFile(fileNameRoot+"qstat")));
+                                               outputNames.push_back(fileNameRoot+"qstat");
                                        }else if (Estimators[i] == "logseries") { 
                                                cDisplays.push_back(new CollectDisplay(new LogSD(), new OneColumnFile(fileNameRoot+"logseries")));
+                                               outputNames.push_back(fileNameRoot+"logseries");
                                        }else if (Estimators[i] == "bergerparker") { 
                                                cDisplays.push_back(new CollectDisplay(new BergerParker(), new OneColumnFile(fileNameRoot+"bergerparker")));
+                                               outputNames.push_back(fileNameRoot+"bergerparker");
                                        }else if (Estimators[i] == "bstick") { 
                                                cDisplays.push_back(new CollectDisplay(new BStick(), new ThreeColumnFile(fileNameRoot+"bstick")));
+                                               outputNames.push_back(fileNameRoot+"bstick");
                                        }else if (Estimators[i] == "goodscoverage") { 
                                                cDisplays.push_back(new CollectDisplay(new GoodsCoverage(), new OneColumnFile(fileNameRoot+"goodscoverage")));
+                                               outputNames.push_back(fileNameRoot+"goodscoverage");
                                        }else if (Estimators[i] == "efron") {
                                                cDisplays.push_back(new CollectDisplay(new Efron(size), new OneColumnFile(fileNameRoot+"efron")));
+                                               outputNames.push_back(fileNameRoot+"efron");
                                        }else if (Estimators[i] == "boneh") {
                                                cDisplays.push_back(new CollectDisplay(new Boneh(size), new OneColumnFile(fileNameRoot+"boneh")));
+                                               outputNames.push_back(fileNameRoot+"boneh");
                                        }else if (Estimators[i] == "solow") {
                                                cDisplays.push_back(new CollectDisplay(new Solow(size), new OneColumnFile(fileNameRoot+"solow")));
+                                               outputNames.push_back(fileNameRoot+"solow");
                                        }else if (Estimators[i] == "shen") {
                                                cDisplays.push_back(new CollectDisplay(new Shen(size, abund), new OneColumnFile(fileNameRoot+"shen")));
+                                               outputNames.push_back(fileNameRoot+"shen");
                                        }
                                }
                        }
                
-                       
                        //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); 
-                               
+               
                        order = globaldata->gorder;
                        string lastLabel = order->getLabel();
                        input = globaldata->ginput;
@@ -209,16 +254,42 @@ int CollectCommand::execute(){
                        //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->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;
+                       }
+
 
                        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);
                                        cCurve->getCurve(freq);
                                        delete cCurve;
                                        
-                                       mothurOut(order->getLabel()); mothurOutEndLine();
                                        processedLabels.insert(order->getLabel());
                                        userLabels.erase(order->getLabel());
                                        
@@ -231,11 +302,12 @@ int CollectCommand::execute(){
                                        delete order;
                                        order = (input->getOrderVector(lastLabel));
                                        
+                                       m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                        cCurve = new Collect(order, cDisplays);
                                        cCurve->getCurve(freq);
                                        delete cCurve;
                                        
-                                       mothurOut(order->getLabel()); mothurOutEndLine();
+                                       
                                        processedLabels.insert(order->getLabel());
                                        userLabels.erase(order->getLabel());
                                        
@@ -249,16 +321,28 @@ 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;
                        for (it = userLabels.begin(); it != userLabels.end(); it++) {  
-                               mothurOut("Your file does not include the label " + *it); 
+                               m->mothurOut("Your file does not include the label " + *it); 
                                if (processedLabels.count(lastLabel) != 1) {
-                                       mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine();
+                                       m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine();
                                        needToRun = true;
                                }else {
-                                       mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine();
+                                       m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine();
                                }
                        }
                        
@@ -267,11 +351,23 @@ int CollectCommand::execute(){
                                if (order != NULL) {    delete order;   }
                                order = (input->getOrderVector(lastLabel));
                                
-                               mothurOut(order->getLabel()); mothurOutEndLine();
+                               m->mothurOut(order->getLabel()); m->mothurOutEndLine();
                                
                                cCurve = new Collect(order, cDisplays);
                                cCurve->getCurve(freq);
                                delete cCurve;
+                               
+                               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;
                        }
                        
@@ -283,12 +379,21 @@ 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();    }
+               m->mothurOutEndLine();
+
                
                return 0;
        }
        catch(exception& e) {
-               errorOut(e, "CollectCommand", "execute");
+               m->errorOut(e, "CollectCommand", "execute");
                exit(1);
        }
 }
@@ -348,7 +453,7 @@ vector<string> CollectCommand::parseSharedFile(string filename) {
                return filenames;
        }
        catch(exception& e) {
-               errorOut(e, "CollectCommand", "parseSharedFile");
+               m->errorOut(e, "CollectCommand", "parseSharedFile");
                exit(1);
        }
 }