]> git.donarmstrong.com Git - mothur.git/blobdiff - clustersplitcommand.cpp
projects / mothur.git / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
paralellized parsimony, unifrac.unweighted, phylo.diversity, indicator commands for...
[mothur.git] / clustersplitcommand.cpp
diff --git a/clustersplitcommand.cpp b/clustersplitcommand.cpp
index 277e4a248374e596f61fa2f976c1b25696495a9d..74867ebdeb0ec271d07d727b7cf9c8d19aa13284 100644 (file)
--- a/clustersplitcommand.cpp
+++ b/clustersplitcommand.cpp
@@ -13,26 +13,26 @@
 //**********************************************************************************************************************
 vector<string> ClusterSplitCommand::setParameters(){   
        try {
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FastaTaxName",false,false); parameters.push_back(ptaxonomy);
-               CommandParameter pphylip("phylip", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "none",false,false); parameters.push_back(pphylip);
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "FastaTaxName",false,false); parameters.push_back(pfasta);
-               CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName-FastaTaxName",false,false); parameters.push_back(pname);
-        CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "",false,false); parameters.push_back(pcount);
-               CommandParameter pcolumn("column", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "ColumnName",false,false); parameters.push_back(pcolumn);
-               CommandParameter ptaxlevel("taxlevel", "Number", "", "3", "", "", "",false,false); parameters.push_back(ptaxlevel);
-               CommandParameter psplitmethod("splitmethod", "Multiple", "classify-fasta-distance", "distance", "", "", "",false,false); parameters.push_back(psplitmethod);
-               CommandParameter plarge("large", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(plarge);
-               CommandParameter pshowabund("showabund", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pshowabund);
-        CommandParameter pcluster("cluster", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pcluster);
-               CommandParameter ptiming("timing", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(ptiming);
-               CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
-               CommandParameter pcutoff("cutoff", "Number", "", "0.25", "", "", "",false,false); parameters.push_back(pcutoff);
-               CommandParameter pprecision("precision", "Number", "", "100", "", "", "",false,false); parameters.push_back(pprecision);
-               CommandParameter pmethod("method", "Multiple", "furthest-nearest-average-weighted", "average", "", "", "",false,false); parameters.push_back(pmethod);
-               CommandParameter phard("hard", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(phard);
-        CommandParameter pclassic("classic", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pclassic);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FastaTaxName","",false,false,true); parameters.push_back(ptaxonomy);
+               CommandParameter pphylip("phylip", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "none","list",false,false,true); parameters.push_back(pphylip);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "FastaTaxName","list",false,false,true); parameters.push_back(pfasta);
+               CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName-FastaTaxName","rabund-sabund",false,false,true); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "","",false,false,true); parameters.push_back(pcount);
+               CommandParameter pcolumn("column", "InputTypes", "", "", "PhylipColumnFasta", "PhylipColumnFasta", "ColumnName","list",false,false,true); parameters.push_back(pcolumn);
+               CommandParameter ptaxlevel("taxlevel", "Number", "", "3", "", "", "","",false,false,true); parameters.push_back(ptaxlevel);
+               CommandParameter psplitmethod("splitmethod", "Multiple", "classify-fasta-distance", "distance", "", "", "","",false,false,true); parameters.push_back(psplitmethod);
+               CommandParameter plarge("large", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(plarge);
+               CommandParameter pshowabund("showabund", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pshowabund);
+        CommandParameter pcluster("cluster", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pcluster);
+               CommandParameter ptiming("timing", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(ptiming);
+               CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors);
+               CommandParameter pcutoff("cutoff", "Number", "", "0.25", "", "", "","",false,false,true); parameters.push_back(pcutoff);
+               CommandParameter pprecision("precision", "Number", "", "100", "", "", "","",false,false); parameters.push_back(pprecision);
+               CommandParameter pmethod("method", "Multiple", "furthest-nearest-average-weighted", "average", "", "", "","",false,false); parameters.push_back(pmethod);
+               CommandParameter phard("hard", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(phard);
+        CommandParameter pclassic("classic", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pclassic);
+               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
+               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
                        
                vector<string> myArray;
                for (int i = 0; i < parameters.size(); i++) {   myArray.push_back(parameters[i].name);          }
@@ -81,27 +81,22 @@ string ClusterSplitCommand::getHelpString(){
        }
 }
 //**********************************************************************************************************************
-string ClusterSplitCommand::getOutputFileNameTag(string type, string inputName=""){    
-       try {
-        string outputFileName = "";
-               map<string, vector<string> >::iterator it;
+string ClusterSplitCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
         
-        //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 == "list") {  outputFileName =  "list"; }
-            else if (type == "rabund") {  outputFileName =  "rabund"; }
-            else if (type == "sabund") {  outputFileName =  "sabund"; }
-            else if (type == "column") {  outputFileName =  "dist"; }
-            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, "ClusterSplitCommand", "getOutputFileNameTag");
-               exit(1);
-       }
+        if (type == "list") {  pattern = "[filename],[clustertag],list-[filename],[clustertag],[tag2],list"; } 
+        else if (type == "rabund") {  pattern = "[filename],[clustertag],rabund"; } 
+        else if (type == "sabund") {  pattern = "[filename],[clustertag],sabund"; }
+        else if (type == "column") {  pattern = "[filename],dist"; }
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "ClusterSplitCommand", "getOutputPattern");
+        exit(1);
+    }
 }
 //**********************************************************************************************************************
 ClusterSplitCommand::ClusterSplitCommand(){    
@@ -444,19 +439,18 @@ int ClusterSplitCommand::execute(){
                vector< map<string, string> > distName = split->getDistanceFiles();  //returns map of distance files -> namefile sorted by distance file size
                delete split;
                
+        if (m->debug) { m->mothurOut("[DEBUG]: distName.size() = " + toString(distName.size()) + ".\n"); }
+                
                //output a merged distance file
-               if (splitmethod == "fasta")             { createMergedDistanceFile(distName); }
-                       
+               //if (splitmethod == "fasta")           { createMergedDistanceFile(distName); }
                                
                if (m->control_pressed) { return 0; }
                
                m->mothurOut("It took " + toString(time(NULL) - estart) + " seconds to split the distance file."); m->mothurOutEndLine();
                estart = time(NULL);
-                
+              
         if (!runCluster) { 
-#ifdef USE_MPI
-    }
-#endif 
+
                 m->mothurOutEndLine();
                 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
                 for (int i = 0; i < distName.size(); i++) {    m->mothurOut(distName[i].begin()->first); m->mothurOutEndLine(); m->mothurOut(distName[i].begin()->second); m->mothurOutEndLine();      }
@@ -464,7 +458,7 @@ int ClusterSplitCommand::execute(){
                 return 0;
                 
         }
-                
+   
                //****************** break up files between processes and cluster each file set ******************************//
        #ifdef USE_MPI
                        ////you are process 0 from above////
@@ -821,11 +815,13 @@ int ClusterSplitCommand::mergeLists(vector<string> listNames, map<float, int> us
                if (outputDir == "") { outputDir += m->hasPath(distfile); }
                fileroot = outputDir + m->getRootName(m->getSimpleName(distfile));
                
-        string sabundFileName = fileroot+ tag + "." + getOutputFileNameTag("sabund");
-        string rabundFileName = fileroot+ tag + "." + getOutputFileNameTag("rabund");
-        string listFileName = fileroot+ tag + ".";
-        if (countfile != "") { listFileName += "unique_"; }
-        listFileName += getOutputFileNameTag("list");
+        map<string, string> variables; 
+        variables["[filename]"] = fileroot;
+        variables["[clustertag]"] = tag;
+        string sabundFileName = getOutputFileName("sabund", variables);
+        string rabundFileName = getOutputFileName("rabund", variables);
+        if (countfile != "") { variables["[tag2]"] = "unique_list"; }
+        string listFileName = getOutputFileName("list", variables);
         
         if (countfile == "") {
             m->openOutputFile(sabundFileName,  outSabund);
@@ -950,7 +946,7 @@ vector<string>  ClusterSplitCommand::createProcesses(vector< map<string, string>
             if ((processToAssign-1) == 1) { m->mothurOut(distName[i].begin()->first + "\n"); }
         }
         
-        //not lets reverse the order of ever other process, so we balance big files running with little ones
+        //now lets reverse the order of ever other process, so we balance big files running with little ones
         for (int i = 0; i < processors; i++) {
             //cout << i << endl;
             int remainder = ((i+1) % processors);
@@ -1172,7 +1168,7 @@ string ClusterSplitCommand::clusterClassicFile(string thisDistFile, string thisN
             cluster->readPhylipFile(thisDistFile, nameMap);
                }else if (countfile != "") {
             ct = new CountTable();
-            ct->readTable(thisNamefile);
+            ct->readTable(thisNamefile, false);
             cluster->readPhylipFile(thisDistFile, ct);
         }
         tag = cluster->getTag();
@@ -1300,7 +1296,7 @@ string ClusterSplitCommand::clusterFile(string thisDistFile, string thisNamefile
             read->read(nameMap);
                }else if (countfile != "") {
             ct = new CountTable();
-            ct->readTable(thisNamefile);
+            ct->readTable(thisNamefile, false);
             read->read(ct);
         }else { read->read(nameMap); }
                
@@ -1440,7 +1436,9 @@ int ClusterSplitCommand::createMergedDistanceFile(vector< map<string, string> >
                
                string thisOutputDir = outputDir;
                if (outputDir == "") { thisOutputDir = m->hasPath(fastafile); }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("column");
+        map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile));
+               string outputFileName = getOutputFileName("column", variables);
                m->mothurRemove(outputFileName);
                
                
Mothur--16S microbiota sequencing software; mirror of main repository with my branches