X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=clustercommand.cpp;h=94129654e1d2b11275e82d3a5da0382b1448efa9;hp=b46e1fb14f9aaf9c34a94216ffd5692c4f043148;hb=615301e57c25e241356a9c2380648d117709458d;hpb=9b53f130ac9af5e95444ce2e817fce25ed19ff03 diff --git a/clustercommand.cpp b/clustercommand.cpp index b46e1fb..9412965 100644 --- a/clustercommand.cpp +++ b/clustercommand.cpp @@ -17,19 +17,20 @@ //********************************************************************************************************************** vector ClusterCommand::setParameters(){ try { - CommandParameter pphylip("phylip", "InputTypes", "", "", "PhylipColumn", "PhylipColumn", "none",false,false); parameters.push_back(pphylip); - CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName",false,false); parameters.push_back(pname); - CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pcount); - CommandParameter pcolumn("column", "InputTypes", "", "", "PhylipColumn", "PhylipColumn", "ColumnName",false,false); parameters.push_back(pcolumn); - CommandParameter pcutoff("cutoff", "Number", "", "10", "", "", "",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 pshowabund("showabund", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pshowabund); - CommandParameter ptiming("timing", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(ptiming); - CommandParameter psim("sim", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psim); - CommandParameter phard("hard", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(phard); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pphylip("phylip", "InputTypes", "", "", "PhylipColumn", "PhylipColumn", "none","list",false,false,true); parameters.push_back(pphylip); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName","rabund-sabund",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pcount); + CommandParameter pcolumn("column", "InputTypes", "", "", "PhylipColumn", "PhylipColumn", "ColumnName","list",false,false,true); parameters.push_back(pcolumn); + CommandParameter pcutoff("cutoff", "Number", "", "10", "", "", "","",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,true); parameters.push_back(pmethod); + CommandParameter pshowabund("showabund", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pshowabund); + CommandParameter ptiming("timing", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(ptiming); + CommandParameter psim("sim", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psim); + CommandParameter phard("hard", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(phard); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + //CommandParameter padjust("adjust", "String", "", "F", "", "", "","",false,false); parameters.push_back(padjust); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -45,7 +46,8 @@ string ClusterCommand::getHelpString(){ try { string helpString = ""; helpString += "The cluster command parameter options are phylip, column, name, count, method, cuttoff, hard, precision, sim, showabund and timing. Phylip or column and name are required, unless you have a valid current file.\n"; - helpString += "The cluster command should be in the following format: \n"; + //helpString += "The adjust parameter is used to handle missing distances. If you set a cutoff, adjust=f by default. If not, adjust=t by default. Adjust=f, means ignore missing distances and adjust cutoff as needed with the average neighbor method. Adjust=t, will treat missing distances as 1.0. You can also set the value the missing distances should be set to, adjust=0.5 would give missing distances a value of 0.5.\n"; + helpString += "The cluster command should be in the following format: \n"; helpString += "cluster(method=yourMethod, cutoff=yourCutoff, precision=yourPrecision) \n"; helpString += "The acceptable cluster methods are furthest, nearest, average and weighted. If no method is provided then average is assumed.\n"; return helpString; @@ -56,26 +58,21 @@ string ClusterCommand::getHelpString(){ } } //********************************************************************************************************************** -string ClusterCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string ClusterCommand::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 { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "ClusterCommand", "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 { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ClusterCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** ClusterCommand::ClusterCommand(){ @@ -234,10 +231,18 @@ ClusterCommand::ClusterCommand(string option) { temp = validParameter.validFile(parameters, "sim", false); if (temp == "not found") { temp = "F"; } sim = m->isTrue(temp); + //bool cutoffSet = false; temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "10"; } + //else { cutoffSet = true; } m->mothurConvert(temp, cutoff); - cutoff += (5 / (precision * 10.0)); + cutoff += (5 / (precision * 10.0)); + + //temp = validParameter.validFile(parameters, "adjust", false); if (temp == "not found") { temp = "F"; } + //if (m->isNumeric1(temp)) { m->mothurConvert(temp, adjust); } + //else if (m->isTrue(temp)) { adjust = 1.0; } + //else { adjust = -1.0; } + adjust=-1.0; method = validParameter.validFile(parameters, "method", false); if (method == "not found") { method = "average"; } @@ -310,7 +315,7 @@ int ClusterCommand::execute(){ read->read(nameMap); }else if (countfile != "") { ct = new CountTable(); - ct->readTable(countfile); + ct->readTable(countfile, false); read->read(ct); }else { read->read(nameMap); } @@ -330,20 +335,22 @@ int ClusterCommand::execute(){ } //create cluster - if (method == "furthest") { cluster = new CompleteLinkage(rabund, list, matrix, cutoff, method); } - else if(method == "nearest"){ cluster = new SingleLinkage(rabund, list, matrix, cutoff, method); } - else if(method == "average"){ cluster = new AverageLinkage(rabund, list, matrix, cutoff, method); } - else if(method == "weighted"){ cluster = new WeightedLinkage(rabund, list, matrix, cutoff, method); } + if (method == "furthest") { cluster = new CompleteLinkage(rabund, list, matrix, cutoff, method, adjust); } + else if(method == "nearest"){ cluster = new SingleLinkage(rabund, list, matrix, cutoff, method, adjust); } + else if(method == "average"){ cluster = new AverageLinkage(rabund, list, matrix, cutoff, method, adjust); } + else if(method == "weighted"){ cluster = new WeightedLinkage(rabund, list, matrix, cutoff, method, adjust); } tag = cluster->getTag(); 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 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, sabundFile);