OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
- ValidParameters validParameter;
+ ValidParameters validParameter("cluster.split");
//check to make sure all parameters are valid for command
map<string,string>::iterator it;
it = parameters.find("phylip");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["phylip"] = inputDir + it->second; }
}
it = parameters.find("column");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["column"] = inputDir + it->second; }
}
it = parameters.find("name");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["name"] = inputDir + it->second; }
}
it = parameters.find("taxonomy");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
}
it = parameters.find("fasta");
//user has given a template file
if(it != parameters.end()){
- path = hasPath(it->second);
+ path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["fasta"] = inputDir + it->second; }
}
convert(temp, precision);
temp = validParameter.validFile(parameters, "hard", false); if (temp == "not found") { temp = "F"; }
- hard = isTrue(temp);
+ hard = m->isTrue(temp);
temp = validParameter.validFile(parameters, "large", false); if (temp == "not found") { temp = "F"; }
- large = isTrue(temp);
+ large = m->isTrue(temp);
temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; }
convert(temp, processors);
m->mothurOut("The cluster.split command can split your files in 3 ways. Splitting by distance file, by classification, or by classification also using a fasta file. \n");
m->mothurOut("For the distance file method, you need only provide your distance file and mothur will split the file into distinct groups. \n");
m->mothurOut("For the classification method, you need to provide your distance file and taxonomy file, and set the splitmethod to classify. \n");
- m->mothurOut("You will also need to set the taxlevel you want to split by. mothur will split the sequence into distinct taxonomy groups, and split the distance file based on those groups. \n");
+ m->mothurOut("You will also need to set the taxlevel you want to split by. mothur will split the sequences into distinct taxonomy groups, and split the distance file based on those groups. \n");
m->mothurOut("For the classification method using a fasta file, you need to provide your fasta file, names file and taxonomy file. \n");
m->mothurOut("You will also need to set the taxlevel you want to split by. mothur will split the sequence into distinct taxonomy groups, and create distance files for each grouping. \n");
m->mothurOut("The phylip and column parameter allow you to enter your distance file. \n");
m->mothurOut("The method allows you to specify what clustering algorythm you want to use, default=furthest, option furthest, nearest, or average. \n");
m->mothurOut("The splitmethod parameter allows you to specify how you want to split your distance file before you cluster, default=distance, options distance, classify or fasta. \n");
m->mothurOut("The taxonomy parameter allows you to enter the taxonomy file for your sequences, this is only valid if you are using splitmethod=classify. Be sure your taxonomy file does not include the probability scores. \n");
- m->mothurOut("The taxlevel parameter allows you to specify the taxonomy level you want to use to split the distance file, default=1. \n");
+ m->mothurOut("The taxlevel parameter allows you to specify the taxonomy level you want to use to split the distance file, default=1, meaning use the first taxon in each list. \n");
m->mothurOut("The large parameter allows you to indicate that your distance matrix is too large to fit in RAM. The default value is false.\n");
#ifdef USE_MPI
m->mothurOut("When using MPI, the processors parameter is set to the number of MPI processes running. \n");
if (namefile == "") { //you need to make a namefile for split matrix
ofstream out;
namefile = phylipfile + ".names";
- openOutputFile(namefile, out);
+ m->openOutputFile(namefile, out);
for (int i = 0; i < listToMakeNameFile->getNumBins(); i++) {
string bin = listToMakeNameFile->get(i);
out << bin << '\t' << bin << endl;
for(int i=0;i<processors;i++){
string filename = toString(processIDS[i]) + ".temp";
ifstream in;
- openInputFile(filename, in);
+ m->openInputFile(filename, in);
- in >> tag; gobble(in);
+ in >> tag; m->gobble(in);
while(!in.eof()) {
string tempName;
- in >> tempName; gobble(in);
+ in >> tempName; m->gobble(in);
listFileNames.push_back(tempName);
}
in.close();
//get labels
filename = toString(processIDS[i]) + ".temp.labels";
ifstream in2;
- openInputFile(filename, in2);
+ m->openInputFile(filename, in2);
float tempCutoff;
- in2 >> tempCutoff; gobble(in2);
+ in2 >> tempCutoff; m->gobble(in2);
if (tempCutoff < cutoff) { cutoff = tempCutoff; }
while(!in2.eof()) {
string tempName;
- in2 >> tempName; gobble(in2);
+ in2 >> tempName; m->gobble(in2);
if (labels.count(tempName) == 0) { labels.insert(tempName); }
}
in2.close();
//read in singletons
if (singleton != "none") {
ifstream in;
- openInputFile(singleton, in);
+ m->openInputFile(singleton, in);
string firstCol, secondCol;
listSingle = new ListVector();
while (!in.eof()) {
- in >> firstCol >> secondCol; gobble(in);
+ in >> firstCol >> secondCol; m->gobble(in);
listSingle->push_back(secondCol);
}
in.close();
string filledInList = listNames[k] + "filledInTemp";
ofstream outFilled;
- openOutputFile(filledInList, outFilled);
+ m->openOutputFile(filledInList, outFilled);
//for each label needed
for(int l = 0; l < orderFloat.size(); l++){
//**********************************************************************************************************************
int ClusterSplitCommand::mergeLists(vector<string> listNames, map<float, int> userLabels, ListVector* listSingle){
try {
- if (outputDir == "") { outputDir += hasPath(distfile); }
- fileroot = outputDir + getRootName(getSimpleName(distfile));
+ if (outputDir == "") { outputDir += m->hasPath(distfile); }
+ fileroot = outputDir + m->getRootName(m->getSimpleName(distfile));
- openOutputFile(fileroot+ tag + ".sabund", outSabund);
- openOutputFile(fileroot+ tag + ".rabund", outRabund);
- openOutputFile(fileroot+ tag + ".list", outList);
+ m->openOutputFile(fileroot+ tag + ".sabund", outSabund);
+ m->openOutputFile(fileroot+ tag + ".rabund", outRabund);
+ m->openOutputFile(fileroot+ tag + ".list", outList);
outputNames.push_back(fileroot+ tag + ".sabund");
outputNames.push_back(fileroot+ tag + ".rabund");
if (listSingle != NULL) {
for (int j = 0; j < listSingle->getNumBins(); j++) {
outList << listSingle->get(j) << '\t';
- rabund->push_back(getNumNames(listSingle->get(j)));
+ rabund->push_back(m->getNumNames(listSingle->get(j)));
}
}
else {
for (int j = 0; j < list->getNumBins(); j++) {
outList << list->get(j) << '\t';
- rabund->push_back(getNumNames(list->get(j)));
+ rabund->push_back(m->getNumNames(list->get(j)));
}
delete list;
}
RAbundVector oldRAbund = oldList->getRAbundVector();
oldRAbund.setLabel(label);
- if (isTrue(showabund)) {
+ if (m->isTrue(showabund)) {
oldRAbund.getSAbundVector().print(cout);
}
oldRAbund.print(outRabund);
//write out names to file
string filename = toString(getpid()) + ".temp";
ofstream out;
- openOutputFile(filename, out);
+ m->openOutputFile(filename, out);
out << tag << endl;
for (int j = 0; j < listFileNames.size(); j++) { out << listFileNames[j] << endl; }
out.close();
//print out labels
ofstream outLabels;
filename = toString(getpid()) + ".temp.labels";
- openOutputFile(filename, outLabels);
+ m->openOutputFile(filename, outLabels);
outLabels << cutoff << endl;
for (set<string>::iterator it = labels.begin(); it != labels.end(); it++) {
else if(method == "average"){ cluster = new AverageLinkage(rabund, list, matrix, cutoff, method); }
tag = cluster->getTag();
- if (outputDir == "") { outputDir += hasPath(thisDistFile); }
- fileroot = outputDir + getRootName(getSimpleName(thisDistFile));
+ if (outputDir == "") { outputDir += m->hasPath(thisDistFile); }
+ fileroot = outputDir + m->getRootName(m->getSimpleName(thisDistFile));
ofstream listFile;
- openOutputFile(fileroot+ tag + ".list", listFile);
+ m->openOutputFile(fileroot+ tag + ".list", listFile);
listFileNames.push_back(fileroot+ tag + ".list");
float dist = matrix->getSmallDist();
float rndDist;
if (hard) {
- rndDist = ceilDist(dist, precision);
+ rndDist = m->ceilDist(dist, precision);
}else{
- rndDist = roundDist(dist, precision);
+ rndDist = m->roundDist(dist, precision);
}
if(previousDist <= 0.0000 && dist != previousDist){
remove(thisDistFile.c_str());
remove(thisNamefile.c_str());
- if (saveCutoff != cutoff) { m->mothurOut("Cutoff was " + toString(cutoff) + " changed cutoff to " + toString(saveCutoff)); m->mothurOutEndLine(); }
+ if (saveCutoff != cutoff) {
+ if (hard) { saveCutoff = m->ceilDist(saveCutoff, precision); }
+ else { saveCutoff = m->roundDist(saveCutoff, precision); }
+
+ m->mothurOut("Cutoff was " + toString(cutoff) + " changed cutoff to " + toString(saveCutoff)); m->mothurOutEndLine();
+ }
if (saveCutoff < smallestCutoff) { smallestCutoff = saveCutoff; }
}
projects / mothur.git / blobdiff