]> git.donarmstrong.com Git - mothur.git/blobdiff - summarysharedcommand.cpp
added concensus command and updated calcs
[mothur.git] / summarysharedcommand.cpp
index b9fd08debd294870af590f5be48fdc4a7c7ba890..b3e665085e701b51db3873f7e5f503112c4fc91e 100644 (file)
@@ -8,8 +8,10 @@
  */
 
 #include "summarysharedcommand.h"
+#include "sharedsobscollectsummary.h"
 #include "sharedchao1.h"
 #include "sharedace.h"
+#include "sharednseqs.h"
 #include "sharedjabund.h"
 #include "sharedsorabund.h"
 #include "sharedjclass.h"
 #include "sharedsorest.h"
 #include "sharedthetayc.h"
 #include "sharedthetan.h"
+#include "sharedkstest.h"
+#include "whittaker.h"
+#include "sharedochiai.h"
+#include "sharedanderbergs.h"
+#include "sharedkulczynski.h"
+#include "sharedkulczynskicody.h"
+#include "sharedlennon.h"
+#include "sharedmorisitahorn.h"
+#include "sharedbraycurtis.h"
+
 
 //**********************************************************************************************************************
 
 SummarySharedCommand::SummarySharedCommand(){
        try {
                globaldata = GlobalData::getInstance();
+               outputFileName = ((getRootName(globaldata->inputFileName)) + "shared.summary");
+               openOutputFile(outputFileName, outputFileHandle);
+               format = globaldata->getFormat();
+               validCalculator = new ValidCalculators();
+               util = new SharedUtil();
+               mult = false;
                
                int i;
-               for (i=0; i<globaldata->sharedSummaryEstimators.size(); i++) {
-                       if (globaldata->sharedSummaryEstimators[i] == "sharedChao") { 
-                               sumCalculators.push_back(new SharedChao1());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedAce") { 
-                               sumCalculators.push_back(new SharedAce());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedJabund") {   
-                               sumCalculators.push_back(new SharedJAbund());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorensonAbund") { 
-                               sumCalculators.push_back(new SharedSorAbund());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedJclass") { 
-                               sumCalculators.push_back(new SharedJclass());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorClass") { 
-                               sumCalculators.push_back(new SharedSorClass());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedJest") { 
-                               sumCalculators.push_back(new SharedJest());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "sharedSorEst") { 
-                               sumCalculators.push_back(new SharedSorEst());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "SharedThetaYC") { 
-                               sumCalculators.push_back(new SharedThetaYC());
-                       }else if (globaldata->sharedSummaryEstimators[i] == "SharedThetaN") { 
-                               sumCalculators.push_back(new SharedThetaN());
+               for (i=0; i<globaldata->Estimators.size(); i++) {
+                       if (validCalculator->isValidCalculator("sharedsummary", globaldata->Estimators[i]) == true) { 
+                               if (globaldata->Estimators[i] == "sharedsobs") { 
+                                       sumCalculators.push_back(new SharedSobsCS());
+                               }else if (globaldata->Estimators[i] == "sharedchao") { 
+                                       sumCalculators.push_back(new SharedChao1());
+                               }else if (globaldata->Estimators[i] == "sharedace") { 
+                                       sumCalculators.push_back(new SharedAce());
+                               }else if (globaldata->Estimators[i] == "jabund") {      
+                                       sumCalculators.push_back(new JAbund());
+                               }else if (globaldata->Estimators[i] == "sorabund") { 
+                                       sumCalculators.push_back(new SorAbund());
+                               }else if (globaldata->Estimators[i] == "jclass") { 
+                                       sumCalculators.push_back(new Jclass());
+                               }else if (globaldata->Estimators[i] == "sorclass") { 
+                                       sumCalculators.push_back(new SorClass());
+                               }else if (globaldata->Estimators[i] == "jest") { 
+                                       sumCalculators.push_back(new Jest());
+                               }else if (globaldata->Estimators[i] == "sorest") { 
+                                       sumCalculators.push_back(new SorEst());
+                               }else if (globaldata->Estimators[i] == "thetayc") { 
+                                       sumCalculators.push_back(new ThetaYC());
+                               }else if (globaldata->Estimators[i] == "thetan") { 
+                                       sumCalculators.push_back(new ThetaN());
+                               }else if (globaldata->Estimators[i] == "kstest") { 
+                                       sumCalculators.push_back(new KSTest());
+                               }else if (globaldata->Estimators[i] == "sharednseqs") { 
+                                       sumCalculators.push_back(new SharedNSeqs());
+                               }else if (globaldata->Estimators[i] == "ochiai") { 
+                                       sumCalculators.push_back(new Ochiai());
+                               }else if (globaldata->Estimators[i] == "anderberg") { 
+                                       sumCalculators.push_back(new Anderberg());
+                               }else if (globaldata->Estimators[i] == "kulczynski") { 
+                                       sumCalculators.push_back(new Kulczynski());
+                               }else if (globaldata->Estimators[i] == "kulczynskicody") { 
+                                       sumCalculators.push_back(new KulczynskiCody());
+                               }else if (globaldata->Estimators[i] == "lennon") { 
+                                       sumCalculators.push_back(new Lennon());
+                               }else if (globaldata->Estimators[i] == "morisitahorn") { 
+                                       sumCalculators.push_back(new MorHorn());
+                               }else if (globaldata->Estimators[i] == "braycurtis") { 
+                                       sumCalculators.push_back(new BrayCurtis());
+                               }else if (globaldata->Estimators[i] == "whittaker") { 
+                                       sumCalculators.push_back(new Whittaker());
+                               }
                        }
                }
+               //reset calc for next command
+               globaldata->setCalc("");
+
        }
        catch(exception& e) {
                cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function SummarySharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
@@ -64,46 +109,114 @@ SummarySharedCommand::SummarySharedCommand(){
 SummarySharedCommand::~SummarySharedCommand(){
        delete input;
        delete read;
+       delete util;
 }
 
 //**********************************************************************************************************************
 
 int SummarySharedCommand::execute(){
        try {
-               outputFileName = ((getRootName(globaldata->inputFileName)) + "sharedSummary");
-               openOutputFile(outputFileName, outputFileHandle);
-       
-               read = new ReadPhilFile(globaldata->inputFileName);     
-               read->read(&*globaldata); 
+               int count = 1;  
+               
+               //if the users entered no valid calculators don't execute command
+               if (sumCalculators.size() == 0) { return 0; }
+               //check if any calcs can do multiples
+               else{
+                       for (int i = 0; i < sumCalculators.size(); i++) {
+                               if (sumCalculators[i]->getMultiple() == true) { mult = true; }
+                       }
+               }
+               
+               if (format == "sharedfile") {
+                       read = new ReadOTUFile(globaldata->inputFileName);      
+                       read->read(&*globaldata); 
+                       
+                       input = globaldata->ginput;
+                       order = input->getSharedOrderVector();
+               }else {
+                       //you are using a list and a groupfile
+                       read = new ReadOTUFile(globaldata->inputFileName);      
+                       read->read(&*globaldata); 
+               
+                       input = globaldata->ginput;
+                       SharedList = globaldata->gSharedList;
+                       order = SharedList->getSharedOrderVector();
+               }
+               
+               //set users groups
+               util->setGroups(globaldata->Groups, globaldata->gGroupmap->namesOfGroups, "summary");
                
-               outputFileHandle << '\t' << '\t' << '\t' << '\t'; //pads file for labels and groupnames
+               //output estimator names as column headers
+               outputFileHandle << "label" <<'\t' << "comparison" << '\t'; 
                for(int i=0;i<sumCalculators.size();i++){
                        outputFileHandle << '\t' << sumCalculators[i]->getName();
                }
                outputFileHandle << endl;
                
-               list = globaldata->glist;
-               input = globaldata->ginput;
-               order = list->getSharedOrderVector();
-               getGroupComb();
+               //create file and put column headers for multiple groups file
+               if (mult = true) {
+                       outAllFileName = ((getRootName(globaldata->inputFileName)) + "sharedmultiple.summary");
+                       openOutputFile(outAllFileName, outAll);
+                       
+                       outAll << "label" <<'\t' << "comparison" << '\t'; 
+                       for(int i=0;i<sumCalculators.size();i++){
+                               if (sumCalculators[i]->getMultiple() == true) { 
+                                       outAll << '\t' << sumCalculators[i]->getName();
+                               }
+                       }
+                       outAll << endl;
+               }
                
-               int count = 1;
                while(order != NULL){
                
                        if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){                       
        
                                cout << order->getLabel() << '\t' << count << endl;
-                               getSharedVectors();  //fills group vectors from order vector.
+                               util->getSharedVectors(globaldata->Groups, lookup, order);  //fills group vectors from order vector.  //fills group vectors from order vector.
                                
-                               //randomize group order
-                               if (globaldata->getJumble() == "1") { random_shuffle(lookup.begin(), lookup.end()); }
+                               //loop through calculators and add to file all for all calcs that can do mutiple groups
+                               if (mult = true) {
+                                       //output label
+                                       outAll << order->getLabel() << '\t';
+                                       
+                                       //output groups names
+                                       string outNames = "";
+                                       for (int j = 0; j < lookup.size(); j++) {
+                                               outNames += lookup[j]->getGroup() +  "-";
+                                       }
+                                       outNames = outNames.substr(0, outNames.length()-1); //rip off extra '-';
+                                       outAll << outNames << '\t';
+                                       
+                                       for(int i=0;i<sumCalculators.size();i++){
+                                               if (sumCalculators[i]->getMultiple() == true) { 
+                                                       sumCalculators[i]->getValues(lookup);
+                                                       outAll << '\t';
+                                                       sumCalculators[i]->print(outAll);
+                                               }
+                                       }
+                                       outAll << endl;
+                               }
 
                                int n = 1; 
+                               vector<SharedRAbundVector*> subset;
                                for (int k = 0; k < (lookup.size() - 1); k++) { // pass cdd each set of groups to commpare
                                        for (int l = n; l < lookup.size(); l++) {
-                                               outputFileHandle << order->getLabel() << '\t' << groupComb[n-1] << '\t'; //print out label and group
-                                               for(int i=0;i<sumCalculators.size();i++){
-                                                       sumCalculators[i]->getValues(lookup[k], lookup[l]); //saves the calculator outputs
+                                               
+                                               outputFileHandle << order->getLabel() << '\t';
+                                               
+                                               subset.clear(); //clear out old pair of sharedrabunds
+                                               //add new pair of sharedrabunds
+                                               subset.push_back(lookup[k]); subset.push_back(lookup[l]); 
+                                               
+                                               //sort groups to be alphanumeric
+                                               if (lookup[k]->getGroup() > lookup[l]->getGroup()) {
+                                                       outputFileHandle << (lookup[l]->getGroup() +'\t' + lookup[k]->getGroup()) << '\t'; //print out groups
+                                               }else{
+                                                       outputFileHandle << (lookup[k]->getGroup() +'\t' + lookup[l]->getGroup()) << '\t'; //print out groups
+                                               }
+                                               
+                                               for(int i=0;i<sumCalculators.size();i++) {
+                                                       sumCalculators[i]->getValues(subset); //saves the calculator outputs
                                                        outputFileHandle << '\t';
                                                        sumCalculators[i]->print(outputFileHandle);
                                                }
@@ -113,15 +226,24 @@ int SummarySharedCommand::execute(){
                                }
                        }
                
-                       list = input->getListVector(); //get new list vector to process
-                       if (list != NULL) {
-                               order = list->getSharedOrderVector(); //gets new order vector with group info.
-                               count++;
+                       //get next line to process
+                       if (format == "sharedfile") {
+                               order = input->getSharedOrderVector();
                        }else {
-                               break;
+                               //you are using a list and a groupfile
+                               SharedList = input->getSharedListVector(); //get new list vector to process
+                               if (SharedList != NULL) {
+                                       order = SharedList->getSharedOrderVector(); //gets new order vector with group info.
+                               }else {
+                                       break;
+                               }
                        }
+                       count++;
                }
-       
+               
+               //reset groups parameter
+               globaldata->Groups.clear();  globaldata->setGroups("");
+
                return 0;
        }
        catch(exception& e) {
@@ -134,70 +256,4 @@ int SummarySharedCommand::execute(){
        }               
 }
 
-//**********************************************************************************************************************
-
-void SummarySharedCommand::getSharedVectors(){
-try {
-               lookup.clear();
-               //create and initialize vector of sharedvectors, one for each group
-               for (int i = 0; i < globaldata->gGroupmap->getNumGroups(); i++) { 
-                       SharedRAbundVector* temp = new SharedRAbundVector(order->getNumBins());
-                       temp->setLabel(order->getLabel());
-                       temp->setGroup(globaldata->gGroupmap->namesOfGroups[i]);
-                       lookup.push_back(temp);
-               }
-               
-               int numSeqs = order->size();
-               //sample all the members
-               for(int i=0;i<numSeqs;i++){
-                       //get first sample
-                       individual chosen = order->get(i);
-                       int abundance; 
-                                       
-                       //set info for sharedvector in chosens group
-                       for (int j = 0; j < lookup.size(); j++) { 
-                               if (chosen.group == lookup[j]->getGroup()) {
-                                        abundance = lookup[j]->getAbundance(chosen.bin);
-                                        lookup[j]->set(chosen.bin, (abundance + 1), chosen.group);
-                                        break;
-                               }
-                       }
-                       
-               }
-       }
-       catch(exception& e) {
-               cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function getSharedVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
-               exit(1);
-       }
-       catch(...) {
-               cout << "An unknown error has occurred in the SummarySharedCommand class function getSharedVectors. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
-               exit(1);
-       }
-
-}
-
-/**************************************************************************************/
-void SummarySharedCommand::getGroupComb() {
-       try {
-               string group;
-               
-               int n = 1;
-               for (int i = 0; i < (globaldata->gGroupmap->getNumGroups() - 1); i++) {
-                       for (int l = n; l < globaldata->gGroupmap->getNumGroups(); l++) {
-                               group = globaldata->gGroupmap->namesOfGroups[i] + globaldata->gGroupmap->namesOfGroups[l];
-                               groupComb.push_back(group);     
-                       }
-                       n++;
-               }
-       }
-       catch(exception& e) {
-               cout << "Standard Error: " << e.what() << " has occurred in the SummarySharedCommand class Function getGroupComb. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
-               exit(1);
-       }
-       catch(...) {
-               cout << "An unknown error has occurred in the SummarySharedCommand class function getGroupComb. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
-               exit(1);
-       }
-
-}
-
+/***********************************************************/