]> git.donarmstrong.com Git - mothur.git/blobdiff - makebiomcommand.cpp
added classify.shared command and random forest files. added count file to pcr.seqs...
[mothur.git] / makebiomcommand.cpp
index 41f2316b3a036840208635d3abbacd89e59f6413..68e70ee3e48e58a89f75ef7547d7409620947cb2 100644 (file)
@@ -112,12 +112,12 @@ vector<string> MakeBiomCommand::setParameters(){
 string MakeBiomCommand::getHelpString(){       
        try {
                string helpString = "";
-               helpString += "The make.biom command parameters are shared, groups, matrixtype and label.  shared is required, unless you have a valid current file.\n";
+               helpString += "The make.biom command parameters are shared, contaxonomy, groups, matrixtype and label.  shared is required, unless you have a valid current file.\n";
                helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n";
                helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n";
                helpString += "The matrixtype parameter allows you to select what type you would like to make. Choices are sparse and dense, default is sparse.\n";
+        helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance.  ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled.\n";
                helpString += "The make.biom command should be in the following format: make.biom(shared=yourShared, groups=yourGroups, label=yourLabels).\n";
-        helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance.  ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled after the classify.otu command was run on the list and taxonomy file.\n";
                helpString += "Example make.biom(shared=abrecovery.an.shared, groups=A-B-C).\n";
                helpString += "The default value for groups is all the groups in your groupfile, and all labels in your inputfile will be used.\n";
                helpString += "The make.biom command outputs a .biom file.\n";
@@ -129,6 +129,27 @@ string MakeBiomCommand::getHelpString(){
                exit(1);
        }
 }
+//**********************************************************************************************************************
+string MakeBiomCommand::getOutputFileNameTag(string type, string inputName=""){        
+       try {
+        string outputFileName = "";
+               map<string, vector<string> >::iterator it;
+        
+        //is this a type this command creates
+        it = outputTypes.find(type);
+        if (it == outputTypes.end()) {  m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
+        else {
+            if (type == "biom")             {   outputFileName =  "biom";       }
+            else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true;  }
+        }
+        return outputFileName;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "MakeBiomCommand", "getOutputFileNameTag");
+               exit(1);
+       }
+}
+
 //**********************************************************************************************************************
 MakeBiomCommand::MakeBiomCommand(){    
        try {
@@ -165,10 +186,10 @@ MakeBiomCommand::MakeBiomCommand(string option) {
                        for (it = parameters.begin(); it != parameters.end(); it++) { 
                                if (validParameter.isValidParameter(it->first, myArray, it->second) != true) {  abort = true;  }
                        }
-                       
+
                        //initialize outputTypes
                        vector<string> tempOutNames;
-                       outputTypes["relabund"] = tempOutNames;
+                       outputTypes["biom"] = tempOutNames;
                        
                        //if the user changes the input directory command factory will send this info to us in the output parameter 
                        string inputDir = validParameter.validFile(parameters, "inputdir", false);              
@@ -328,6 +349,14 @@ int MakeBiomCommand::execute(){
                
         if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {       m->mothurRemove(outputNames[i]); }  return 0; }     
                
+        //set sabund file as new current sabundfile
+        string current = "";
+               itTypes = outputTypes.find("biom");
+               if (itTypes != outputTypes.end()) {
+                       if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setBiomFile(current); }
+               }
+
+        
                m->mothurOutEndLine();
                m->mothurOut("Output File Names: "); m->mothurOutEndLine();
                for (int i = 0; i < outputNames.size(); i++) {  m->mothurOut(outputNames[i]); m->mothurOutEndLine();    }
@@ -344,7 +373,7 @@ int MakeBiomCommand::execute(){
 int MakeBiomCommand::getBiom(vector<SharedRAbundVector*>& lookup){
        try {
         
-        string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".biom";
+        string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + "." + getOutputFileNameTag("biom");
                ofstream out;
                m->openOutputFile(outputFileName, out);
                outputNames.push_back(outputFileName); outputTypes["biom"].push_back(outputFileName);
@@ -520,15 +549,16 @@ vector<string> MakeBiomCommand::getMetaData(vector<SharedRAbundVector*>& lookup)
                 if (m->control_pressed) { return metadata; }
                 
                 //if there is a bin label use it otherwise make one
-                string binLabel = binTag;
-                string sbinNumber = otuLabels[i];
-                if (sbinNumber.length() < snumBins.length()) { 
-                    int diff = snumBins.length() - sbinNumber.length();
-                    for (int h = 0; h < diff; h++) { binLabel += "0"; }
-                }
-                binLabel += sbinNumber;
-                
-                labelTaxMap[binLabel] = taxs[i];
+                if (m->isContainingOnlyDigits(otuLabels[i])) {
+                    string binLabel = binTag;
+                    string sbinNumber = otuLabels[i];
+                    if (sbinNumber.length() < snumBins.length()) { 
+                        int diff = snumBins.length() - sbinNumber.length();
+                        for (int h = 0; h < diff; h++) { binLabel += "0"; }
+                    }
+                    binLabel += sbinNumber;
+                    labelTaxMap[binLabel] = taxs[i];
+                }else {  labelTaxMap[otuLabels[i]] = taxs[i]; }
             }
             
             
@@ -604,7 +634,7 @@ vector<string> MakeBiomCommand::parseTax(string tax, vector<string>& scores) {
                         scores.push_back(confidenceScore);
                                        }else{ scores.push_back("null"); }
                                }
-                       }
+                       }else{ scores.push_back("null"); }
                        
             //strip "" if they are there
             pos = taxon.find("\"");