*/
#include "unifracunweightedcommand.h"
+#include "treereader.h"
//**********************************************************************************************************************
vector<string> UnifracUnweightedCommand::setParameters(){
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
+ else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
vector<string> myArray = setParameters();
}
}
- m->runParse = true;
-
- //check for required parameters
+ //check for required parameters
treefile = validParameter.validFile(parameters, "tree", true);
if (treefile == "not open") { abort = true; }
else if (treefile == "not found") { //if there is a current design file, use it
treefile = m->getTreeFile();
if (treefile != "") { m->mothurOut("Using " + treefile + " as input file for the tree parameter."); m->mothurOutEndLine(); }
else { m->mothurOut("You have no current tree file and the tree parameter is required."); m->mothurOutEndLine(); abort = true; }
- }
+ }else { m->setTreeFile(treefile); }
//check for required parameters
groupfile = validParameter.validFile(parameters, "group", true);
if (groupfile == "not open") { abort = true; }
else if (groupfile == "not found") { groupfile = ""; }
+ else { m->setGroupFile(groupfile); }
namefile = validParameter.validFile(parameters, "name", true);
- if (namefile == "not open") { abort = true; }
+ if (namefile == "not open") { namefile = ""; abort = true; }
else if (namefile == "not found") { namefile = ""; }
+ else { m->setNameFile(namefile); }
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
if (groups == "not found") { groups = ""; }
else {
m->splitAtDash(groups, Groups);
- m->Groups = Groups;
+ m->setGroups(Groups);
}
itersString = validParameter.validFile(parameters, "iters", false); if (itersString == "not found") { itersString = "1000"; }
- convert(itersString, iters);
+ m->mothurConvert(itersString, iters);
string temp = validParameter.validFile(parameters, "distance", false);
if (temp == "not found") { phylip = false; outputForm = ""; }
temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
m->setProcessors(temp);
- convert(temp, processors);
+ m->mothurConvert(temp, processors);
if (!random) { iters = 0; } //turn off random calcs
if ((phylip) && (Groups.size() == 0)) {
groups = "all";
m->splitAtDash(groups, Groups);
- m->Groups = Groups;
+ m->setGroups(Groups);
+ }
+
+ if (namefile == "") {
+ vector<string> files; files.push_back(treefile);
+ parser.getNameFile(files);
}
}
if (abort == true) { if (calledHelp) { return 0; } return 2; }
- if (groupfile != "") {
- //read in group map info.
- tmap = new TreeMap(groupfile);
- tmap->readMap();
- }else{ //fake out by putting everyone in one group
- Tree* tree = new Tree(treefile); delete tree; //extracts names from tree to make faked out groupmap
- tmap = new TreeMap();
-
- for (int i = 0; i < m->Treenames.size(); i++) { tmap->addSeq(m->Treenames[i], "Group1"); }
- }
-
- if (namefile != "") { readNamesFile(); }
-
- read = new ReadNewickTree(treefile);
- int readOk = read->read(tmap);
-
- if (readOk != 0) { m->mothurOut("Read Terminated."); m->mothurOutEndLine(); delete tmap; delete read; return 0; }
-
- read->AssembleTrees();
- T = read->getTrees();
- delete read;
+ m->setTreeFile(treefile);
- //make sure all files match
- //if you provide a namefile we will use the numNames in the namefile as long as the number of unique match the tree names size.
- int numNamesInTree;
- if (namefile != "") {
- if (numUniquesInName == m->Treenames.size()) { numNamesInTree = nameMap.size(); }
- else { numNamesInTree = m->Treenames.size(); }
- }else { numNamesInTree = m->Treenames.size(); }
-
-
- //output any names that are in group file but not in tree
- if (numNamesInTree < tmap->getNumSeqs()) {
- for (int i = 0; i < tmap->namesOfSeqs.size(); i++) {
- //is that name in the tree?
- int count = 0;
- for (int j = 0; j < m->Treenames.size(); j++) {
- if (tmap->namesOfSeqs[i] == m->Treenames[j]) { break; } //found it
- count++;
- }
-
- if (m->control_pressed) {
- delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; }
- for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear();
- m->Groups.clear();
- return 0;
- }
-
- //then you did not find it so report it
- if (count == m->Treenames.size()) {
- //if it is in your namefile then don't remove
- map<string, string>::iterator it = nameMap.find(tmap->namesOfSeqs[i]);
-
- if (it == nameMap.end()) {
- m->mothurOut(tmap->namesOfSeqs[i] + " is in your groupfile and not in your tree. It will be disregarded."); m->mothurOutEndLine();
- tmap->removeSeq(tmap->namesOfSeqs[i]);
- i--; //need this because removeSeq removes name from namesOfSeqs
- }
- }
- }
- }
-
+ TreeReader* reader = new TreeReader(treefile, groupfile, namefile);
+ T = reader->getTrees();
+ tmap = T[0]->getTreeMap();
+ map<string, string> nameMap = reader->getNameMap();
+ delete reader;
+
sumFile = outputDir + m->getSimpleName(treefile) + ".uwsummary";
outputNames.push_back(sumFile); outputTypes["uwsummary"].push_back(sumFile);
m->openOutputFile(sumFile, outSum);
- util = new SharedUtil();
- util->setGroups(m->Groups, tmap->namesOfGroups, allGroups, numGroups, "unweighted"); //sets the groups the user wants to analyze
- util->getCombos(groupComb, m->Groups, numComp);
- delete util;
+ SharedUtil util;
+ Groups = m->getGroups();
+ vector<string> namesGroups = tmap->getNamesOfGroups();
+ util.setGroups(Groups, namesGroups, allGroups, numGroups, "unweighted"); //sets the groups the user wants to analyze
+ util.getCombos(groupComb, Groups, numComp);
+ m->setGroups(Groups);
if (numGroups == 1) { numComp++; groupComb.push_back(allGroups); }
- unweighted = new Unweighted(tmap, includeRoot);
+ Unweighted unweighted(includeRoot);
int start = time(NULL);
if (numComp < processors) { processors = numComp; }
- outSum << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" <<'\t' << "UWSig" << endl;
- m->mothurOut("Tree#\tGroups\tUWScore\tUWSig"); m->mothurOutEndLine();
+ outSum << "Tree#" << '\t' << "Groups" << '\t' << "UWScore" <<'\t';
+ m->mothurOut("Tree#\tGroups\tUWScore\t");
+ if (random) { outSum << "UWSig"; m->mothurOut("UWSig"); }
+ outSum << endl; m->mothurOutEndLine();
//get pscores for users trees
for (int i = 0; i < T.size(); i++) {
if (m->control_pressed) {
- delete tmap; delete unweighted;
+ delete tmap;
for (int i = 0; i < T.size(); i++) { delete T[i]; }
outSum.close();
- for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); }
return 0;
}
utreeScores.resize(numComp);
UWScoreSig.resize(numComp);
- userData = unweighted->getValues(T[i], processors, outputDir); //userData[0] = unweightedscore
+ userData = unweighted.getValues(T[i], processors, outputDir); //userData[0] = unweightedscore
- if (m->control_pressed) { delete tmap; delete unweighted;
- for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }return 0; }
+ if (m->control_pressed) { delete tmap;
+ for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); }return 0; }
//output scores for each combination
for(int k = 0; k < numComp; k++) {
for (int j = 0; j < iters; j++) {
//we need a different getValues because when we swap the labels we only want to swap those in each pairwise comparison
- randomData = unweighted->getValues(T[i], "", "", processors, outputDir);
+ randomData = unweighted.getValues(T[i], "", "", processors, outputDir);
- if (m->control_pressed) { delete tmap; delete unweighted;
- for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete tmap;
+ for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
for(int k = 0; k < numComp; k++) {
//add trees unweighted score to map of scores
}
- if (m->control_pressed) { delete tmap; delete unweighted;
- for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { delete tmap;
+ for (int i = 0; i < T.size(); i++) { delete T[i]; }if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
//print output files
printUWSummaryFile(i);
outSum.close();
- m->Groups.clear();
- delete tmap; delete unweighted;
+ delete tmap;
for (int i = 0; i < T.size(); i++) { delete T[i]; }
- if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run unifrac.unweighted."); m->mothurOutEndLine();
m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t<" + toString((1/float(iters))) + "\n");
}
}else{
- outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl;
- cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl;
- m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t0.00\n");
+ outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << endl;
+ cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << endl;
+ m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\n");
}
}
if ((outputForm == "lt") || (outputForm == "square")) {
//output numSeqs
- out << m->Groups.size() << endl;
+ out << m->getNumGroups() << endl;
}
//make matrix with scores in it
- vector< vector<float> > dists; dists.resize(m->Groups.size());
- for (int i = 0; i < m->Groups.size(); i++) {
- dists[i].resize(m->Groups.size(), 0.0);
+ vector< vector<float> > dists; dists.resize(m->getNumGroups());
+ for (int i = 0; i < m->getNumGroups(); i++) {
+ dists[i].resize(m->getNumGroups(), 0.0);
}
//flip it so you can print it
int count = 0;
- for (int r=0; r<m->Groups.size(); r++) {
+ for (int r=0; r<m->getNumGroups(); r++) {
for (int l = 0; l < r; l++) {
dists[r][l] = utreeScores[count][0];
dists[l][r] = utreeScores[count][0];
}
//output to file
- for (int r=0; r<m->Groups.size(); r++) {
+ for (int r=0; r<m->getNumGroups(); r++) {
//output name
- string name = m->Groups[r];
+ string name = (m->getGroups())[r];
if (name.length() < 10) { //pad with spaces to make compatible
while (name.length() < 10) { name += " "; }
}
out << name << '\t';
//output distances
- for (int l = 0; l < m->Groups.size(); l++) { out << dists[r][l] << '\t'; }
+ for (int l = 0; l < m->getNumGroups(); l++) { out << dists[r][l] << '\t'; }
out << endl;
}else{
//output distances
for (int l = 0; l < r; l++) {
- string otherName = m->Groups[l];
+ string otherName = (m->getGroups())[l];
if (otherName.length() < 10) { //pad with spaces to make compatible
while (otherName.length() < 10) { otherName += " "; }
}
m->errorOut(e, "UnifracUnweightedCommand", "createPhylipFile");
exit(1);
}
-}/*****************************************************************/
-int UnifracUnweightedCommand::readNamesFile() {
- try {
- m->names.clear();
- numUniquesInName = 0;
-
- ifstream in;
- m->openInputFile(namefile, in);
-
- string first, second;
- map<string, string>::iterator itNames;
-
- while(!in.eof()) {
- in >> first >> second; m->gobble(in);
-
- numUniquesInName++;
-
- itNames = m->names.find(first);
- if (itNames == m->names.end()) {
- m->names[first] = second;
-
- //we need a list of names in your namefile to use above when removing extra seqs above so we don't remove them
- vector<string> dupNames;
- m->splitAtComma(second, dupNames);
-
- for (int i = 0; i < dupNames.size(); i++) {
- nameMap[dupNames[i]] = dupNames[i];
- if ((groupfile == "") && (i != 0)) { tmap->addSeq(dupNames[i], "Group1"); }
- }
- }else { m->mothurOut(first + " has already been seen in namefile, disregarding names file."); m->mothurOutEndLine(); in.close(); m->names.clear(); namefile = ""; return 1; }
- }
- in.close();
-
- return 0;
- }
- catch(exception& e) {
- m->errorOut(e, "UnifracUnweightedCommand", "readNamesFile");
- exit(1);
- }
}
/***********************************************************/