X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=cooccurrencecommand.cpp;h=e4c915d6a14e4a9755a17d64c073fdda1440803b;hb=d205e70ae86dbee2efc2df02f2717975854de6ba;hp=f1f849af255004e901777f32fb72aa7bd5e7a129;hpb=4993ef2939f9705644a81085bbfae444af062116;p=mothur.git

diff --git a/cooccurrencecommand.cpp b/cooccurrencecommand.cpp
index f1f849a..e4c915d 100644
--- a/cooccurrencecommand.cpp
+++ b/cooccurrencecommand.cpp
@@ -180,7 +180,7 @@ int CooccurrenceCommand::execute(){
         m->openOutputFile(outputFileName, out);
         outputNames.push_back(outputFileName);  outputTypes["summary"].push_back(outputFileName);
         out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint);
-        out << "metric\tlabel\tScore\tpValue\n";
+        out << "metric\tlabel\tScore\tzScore\tstandardDeviation\n";
 
 		//as long as you are not at the end of the file or done wih the lines you want
 		while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
@@ -272,20 +272,23 @@ int CooccurrenceCommand::execute(){
 int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp, ofstream& out){
     try {
         int numOTUS = thisLookUp[0]->getNumBins();
-        vector< vector<int> > initmatrix; initmatrix.resize(thisLookUp.size());
+        
+        if(numOTUS < 2) {
+            m->mothurOut("Not enough OTUs for co-occurrence analysis, skipping"); m->mothurOutEndLine();
+            return 0;
+        }
+        
         vector< vector<int> > co_matrix; co_matrix.resize(thisLookUp[0]->getNumBins());
         for (int i = 0; i < thisLookUp[0]->getNumBins(); i++) { co_matrix[i].resize((thisLookUp.size()), 0); }
-        for (int i = 0; i < thisLookUp.size(); i++) { initmatrix[i].resize((thisLookUp[i]->getNumBins()), 0); }
         vector<int> columntotal; columntotal.resize(thisLookUp.size(), 0);
         vector<int> rowtotal; rowtotal.resize(numOTUS, 0);
         
-        for (int i = 0; i < thisLookUp.size(); i++) {
-            for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) {
+        for (int i = 0; i < thisLookUp.size(); i++) { //nrows in the shared file
+            for (int j = 0; j < thisLookUp[i]->getNumBins(); j++) { //cols of original shared file
                 if (m->control_pressed) { return 0; }
                 int abund = thisLookUp[i]->getAbundance(j);
                 
                 if(abund > 0) {
-                    initmatrix[i][j] = 1;
                     co_matrix[j][i] = 1;
                     rowtotal[j]++;
                     columntotal[i]++;
@@ -299,8 +302,6 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
         int ncols = thisLookUp.size();//groups
         double initscore = 0.0;
         
-        vector<int> columntotal; columntotal.resize(ncols, 0);
-        vector<int> rowtotal; rowtotal.resize(nrows, 0);
         vector<double> stats;
         double probabilityMatrix[ncols * nrows];
         vector<vector<int> > nullmatrix(nrows, vector<int>(ncols, 0));
@@ -322,15 +323,16 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
                 }
             }
         }
-        else if (matrix == "sim2") {
-            for(int i=0;i<nrows;i++) {
-                start = 0.0;
-                for(int j=0;j<ncols;j++) {
-                    probabilityMatrix[ncols * i + j] = start + 1/double(ncols);
-                    start = start + 1/double(ncols);
-                }
-            }
-        }
+        //don't need a prob matrix because we just shuffle the rows, may use this in the future
+        else if (matrix == "sim2") { }
+//            for(int i=0;i<nrows;i++) {
+//                start = 0.0;
+//                for(int j=0;j<ncols;j++) {
+//                    probabilityMatrix[ncols * i + j] = start + 1/double(ncols);
+//                    start = start + 1/double(ncols);
+//                }
+//            }
+//        }
         
         else if (matrix == "sim3") {
             for(int j=0;j<ncols;j++) {
@@ -389,18 +391,18 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
                 }
             }
         }
-        else if (matrix == "sim9") { }
+        else if (matrix == "sim9" || matrix == "sim2") { }
         else {
             m->mothurOut("[ERROR]: No model selected! \n");
             m->control_pressed = true;
         }
         
         
-        
-        if (metric == "cscore") { initscore = trial.calc_c_score(initmatrix, rowtotal, ncols, nrows); }
-        else if (metric == "checker") { initscore = trial.calc_checker(initmatrix, rowtotal, ncols, nrows); }
+        //co_matrix is the transposed shared file, initmatrix is the original shared file
+        if (metric == "cscore") { initscore = trial.calc_c_score(co_matrix, rowtotal, ncols, nrows); }
+        else if (metric == "checker") { initscore = trial.calc_checker(co_matrix, rowtotal, ncols, nrows); }
         else if (metric == "vratio") { initscore = trial.calc_vratio(nrows, ncols, rowtotal, columntotal); }
-        else if (metric == "combo") { initscore = trial.calc_combo(nrows, ncols, initmatrix); }
+        else if (metric == "combo") { initscore = trial.calc_combo(nrows, ncols, co_matrix); }
         else { m->mothurOut("[ERROR]: No metric selected!\n"); m->control_pressed = true; return 1; }
         
         m->mothurOut("Initial c score: " + toString(initscore)); m->mothurOutEndLine();
@@ -409,79 +411,14 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
         double current;
         double randnum;
         int count;
-        
-        //burn-in
-        for(int i=0;i<10000;i++){
-            nullmatrix.clear();
-            //zero-fill the null matrix
-            nullmatrix.assign(nrows, vector<int>(ncols, 0));
-            
-            if(matrix == "sim1" || matrix == "sim6" || matrix == "sim8" || matrix == "sim7") {
-                count = 0;
-                while(count < n) {
-                nextnum:
-                    previous = 0.0;
-                    randnum = rand() / double(RAND_MAX);
-                    for(int i=0;i<nrows;i++) {
-                        for(int j=0;j<ncols;j++) {
-                            current = probabilityMatrix[ncols * i + j];
-                            if(randnum <= current && randnum > previous) {
-                                nullmatrix[i][j] = 1;
-                                count++;
-                                if (count > n) break;
-                                else
-                                    goto nextnum;
-                            }
-                            previous = current;
-                        }
-                    }
-                }
-            }
-            
-            else if(matrix == "sim2" || matrix == "sim4") {
-                for(int i=0;i<nrows;i++) {
-                    previous = 0.0;
-                    count = 0;
-                    while(count < rowtotal[i]) {
-                        randnum = rand() / double(RAND_MAX);
-                        for(int j=0;j<ncols;j++) {
-                            current = probabilityMatrix[ncols * i + j];
-                            if(randnum <= current && randnum > previous && nullmatrix[i][j] != 1) {
-                                nullmatrix[i][j] = 1;
-                                count++;
-                                previous = 0.0;
-                                break;
-                            }
-                            previous = current;
-                        }
-                    }
-                }
-            }
-            
-            else if(matrix == "sim3" || matrix == "sim5") {
-                //columns
-                for(int j=0;j<ncols;j++) {
-                    count = 0;
-                    while(count < columntotal[j]) {
-                        randnum = rand() / double(RAND_MAX);
-                        for(int i=0;i<nrows;i++) {
-                            current = probabilityMatrix[ncols * i + j];
-                            if(randnum <= current && randnum > previous && nullmatrix[i][j] != 1) {
-                                nullmatrix[i][j] = 1;
-                                count++;
-                                previous = 0.0;
-                                break;
-                            }
-                            previous = current;
-                        }
-                    }
-                }
-            }
-            
+
+        //burn-in for sim9    
+        if(matrix == "sim9") {
+            for(int i=0;i<10000;i++) trial.swap_checkerboards (co_matrix, ncols, nrows);
         }
-        
+
         //populate null matrix from probability matrix, do this a lot.
-        for(int i=0;i<runs;i++){
+        for(int k=0;k<runs;k++){
             nullmatrix.clear();
             //zero-fill the null matrix
             nullmatrix.assign(nrows, vector<int>(ncols, 0));
@@ -489,6 +426,7 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
             if(matrix == "sim1" || matrix == "sim6" || matrix == "sim8" || matrix == "sim7") {
                 count = 0;
                 while(count < n) {
+                    if (m->control_pressed) { return 0; }
                 nextnum2:
                     previous = 0.0;
                     randnum = rand() / double(RAND_MAX);
@@ -508,11 +446,21 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
                 }
             }
             
-            else if(matrix == "sim2" || matrix == "sim4") {
+            else if (matrix == "sim2") {
+                for(int i=0;i<nrows;i++) {
+                    random_shuffle( co_matrix[i].begin(), co_matrix[i].end() ); 
+                }
+                //do this for the scoring since those all have nullmatrix as a parameter
+                //nullmatrix gets cleared at the begining of each run
+                nullmatrix = co_matrix;
+            }
+            
+            else if(matrix == "sim4") {
                 for(int i=0;i<nrows;i++) {
-                    previous = 0.0;
                     count = 0;
                     while(count < rowtotal[i]) {
+                        previous = 0.0;
+                        if (m->control_pressed) { return 0; }
                         randnum = rand() / double(RAND_MAX);
                         for(int j=0;j<ncols;j++) {
                             current = probabilityMatrix[ncols * i + j];
@@ -533,6 +481,7 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
                 for(int j=0;j<ncols;j++) {
                     count = 0;
                     while(count < columntotal[j]) {
+                        if (m->control_pressed) { return 0; }
                         randnum = rand() / double(RAND_MAX);
                         for(int i=0;i<nrows;i++) {
                             current = probabilityMatrix[ncols * i + j];
@@ -550,7 +499,8 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
             
             //swap_checkerboards takes the original matrix and swaps checkerboards
             else if(matrix == "sim9") {
-                trial.swap_checkerboards (initmatrix, rowtotal, columntotal, ncols, nrows);
+                trial.swap_checkerboards (co_matrix, ncols, nrows);
+                nullmatrix = co_matrix;
             }
             else {
                 m->mothurOut("[ERROR]: No null model selected!\n\n"); m->control_pressed = true;
@@ -586,12 +536,20 @@ int CooccurrenceCommand::getCooccurrence(vector<SharedRAbundVector*>& thisLookUp
         
         m->mothurOutEndLine(); m->mothurOut("average metric score: " + toString(nullMean)); m->mothurOutEndLine();
         
+        //calc_p_value is not a statistical p-value, it's just the average that are either > or < the initscore.
+        //All it does is show what is expected in a competitively structured community
+        //zscore is output so p-value can be looked up in a ztable
         double pvalue = 0.0;
         if (metric == "cscore" || metric == "checker") { pvalue = trial.calc_pvalue_greaterthan (stats, initscore); }
         else{ pvalue = trial.calc_pvalue_lessthan (stats, initscore); }
+
+        double sd = trial.getSD(runs, stats, nullMean);
+
+        double zscore = trial.get_zscore(sd, nullMean, initscore);
         
-        m->mothurOut("pvalue: " + toString(pvalue)); m->mothurOutEndLine();
-        out << metric << '\t' << thisLookUp[0]->getLabel() << '\t' << nullMean << '\t' << pvalue << endl;
+        m->mothurOut("zscore: " + toString(zscore)); m->mothurOutEndLine();
+        m->mothurOut("standard deviation: " + toString(sd)); m->mothurOutEndLine();
+        out << metric << '\t' << thisLookUp[0]->getLabel() << '\t' << nullMean << '\t' << zscore << '\t' << sd << endl;
         
         return 0;
     }