#include "unifracunweightedcommand.h"
+//**********************************************************************************************************************
+vector<string> UnifracUnweightedCommand::getValidParameters(){
+ try {
+ string Array[] = {"groups","iters","distance","random", "processors","outputdir","inputdir"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracUnweightedCommand", "getValidParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+UnifracUnweightedCommand::UnifracUnweightedCommand(){
+ try {
+ globaldata = GlobalData::getInstance();
+ abort = true;
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["unweighted"] = tempOutNames;
+ outputTypes["uwsummary"] = tempOutNames;
+ outputTypes["phylip"] = tempOutNames;
+ outputTypes["column"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracUnweightedCommand", "UnifracUnweightedCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> UnifracUnweightedCommand::getRequiredParameters(){
+ try {
+ vector<string> myArray;
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracUnweightedCommand", "getRequiredParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<string> UnifracUnweightedCommand::getRequiredFiles(){
+ try {
+ string Array[] = {"tree","group"};
+ vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracUnweightedCommand", "getRequiredFiles");
+ exit(1);
+ }
+}
/***********************************************************/
UnifracUnweightedCommand::UnifracUnweightedCommand(string option) {
try {
else {
//valid paramters for this command
- string Array[] = {"groups","iters","distance","random", "outputdir","inputdir"};
+ string Array[] = {"groups","iters","distance","random", "processors","outputdir","inputdir"};
vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
OptionParser parser(option);
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
+ //initialize outputTypes
+ vector<string> tempOutNames;
+ outputTypes["unweighted"] = tempOutNames;
+ outputTypes["uwsummary"] = tempOutNames;
+ outputTypes["phylip"] = tempOutNames;
+ outputTypes["column"] = tempOutNames;
+
if (globaldata->gTree.size() == 0) {//no trees were read
m->mothurOut("You must execute the read.tree command, before you may execute the unifrac.unweighted command."); m->mothurOutEndLine(); abort = true; }
itersString = validParameter.validFile(parameters, "iters", false); if (itersString == "not found") { itersString = "1000"; }
convert(itersString, iters);
- string temp = validParameter.validFile(parameters, "distance", false); if (temp == "not found") { temp = "false"; }
- phylip = m->isTrue(temp);
+ string temp = validParameter.validFile(parameters, "distance", false);
+ if (temp == "not found") { phylip = false; outputForm = ""; }
+ else{
+ if ((temp == "lt") || (temp == "column") || (temp == "square")) { phylip = true; outputForm = temp; }
+ else { m->mothurOut("Options for distance are: lt, square, or column. Using lt."); m->mothurOutEndLine(); phylip = true; outputForm = "lt"; }
+ }
temp = validParameter.validFile(parameters, "random", false); if (temp == "not found") { temp = "f"; }
random = m->isTrue(temp);
+ temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; }
+ convert(temp, processors);
+
if (!random) { iters = 0; } //turn off random calcs
//if user selects distance = true and no groups it won't calc the pairwise
T = globaldata->gTree;
tmap = globaldata->gTreemap;
sumFile = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".uwsummary";
- outputNames.push_back(sumFile);
+ outputNames.push_back(sumFile); outputTypes["uwsummary"].push_back(sumFile);
m->openOutputFile(sumFile, outSum);
util = new SharedUtil();
void UnifracUnweightedCommand::help(){
try {
m->mothurOut("The unifrac.unweighted command can only be executed after a successful read.tree command.\n");
- m->mothurOut("The unifrac.unweighted command parameters are groups, iters, distance and random. No parameters are required.\n");
+ m->mothurOut("The unifrac.unweighted command parameters are groups, iters, distance, processors and random. No parameters are required.\n");
m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 1 valid group.\n");
m->mothurOut("The group names are separated by dashes. The iters parameter allows you to specify how many random trees you would like compared to your tree.\n");
- m->mothurOut("The distance parameter allows you to create a distance file from the results. The default is false.\n");
+ m->mothurOut("The distance parameter allows you to create a distance file from the results. The default is false. You may set distance to lt, square or column.\n");
m->mothurOut("The random parameter allows you to shut off the comparison to random trees. The default is false, meaning compare don't your trees with randomly generated trees.\n");
+ m->mothurOut("The processors parameter allows you to specify the number of processors to use. The default is 1.\n");
m->mothurOut("The unifrac.unweighted command should be in the following format: unifrac.unweighted(groups=yourGroups, iters=yourIters).\n");
m->mothurOut("Example unifrac.unweighted(groups=A-B-C, iters=500).\n");
m->mothurOut("The default value for groups is all the groups in your groupfile, and iters is 1000.\n");
if (random) {
output = new ColumnFile(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString);
outputNames.push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted");
+ outputTypes["unweighted"].push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted");
}
utreeScores.resize(numComp);
UWScoreSig.resize(numComp);
- userData = unweighted->getValues(T[i]); //userData[0] = unweightedscore
-
- if (m->control_pressed) {
- if (random) { delete output; }
- outSum.close();
- for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }
- return 0;
- }
+ userData = unweighted->getValues(T[i], processors, outputDir); //userData[0] = unweightedscore
+
+ if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }return 0; }
//output scores for each combination
for(int k = 0; k < numComp; k++) {
//add users score to validscores
validScores[userData[k]] = userData[k];
}
-
+
//get unweighted scores for random trees - if random is false iters = 0
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], "", "");
+ randomData = unweighted->getValues(T[i], "", "", processors, outputDir);
- if (m->control_pressed) {
- 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) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
for(int k = 0; k < numComp; k++) {
//add trees unweighted score to map of scores
//add randoms score to validscores
validScores[randomData[k]] = randomData[k];
}
+
+ //report progress
+ m->mothurOut("Iter: " + toString(j+1)); m->mothurOutEndLine();
}
for(int a = 0; a < numComp; a++) {
}
-
- if (m->control_pressed) {
- 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) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
//print output files
printUWSummaryFile(i);
if (UWScoreSig[a][0] > (1/(float)iters)) {
outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl;
cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl;
- m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t" + toString(UWScoreSig[a][0])); m->mothurOutEndLine();
+ m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t" + toString(UWScoreSig[a][0])+ "\n");
}else {
outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl;
cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl;
- m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t<" + toString((1/float(iters)))); 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"); m->mothurOutEndLine();
+ m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t0.00\n");
}
}
/***********************************************************/
void UnifracUnweightedCommand::createPhylipFile(int i) {
try {
- string phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist";
- outputNames.push_back(phylipFileName);
+ string phylipFileName;
+ if ((outputForm == "lt") || (outputForm == "square")) {
+ phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.phylip.dist";
+ outputNames.push_back(phylipFileName); outputTypes["phylip"].push_back(phylipFileName);
+ }else { //column
+ phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.column.dist";
+ outputNames.push_back(phylipFileName); outputTypes["column"].push_back(phylipFileName);
+ }
ofstream out;
m->openOutputFile(phylipFileName, out);
-
- //output numSeqs
- out << globaldata->Groups.size() << endl;
-
+
+ if ((outputForm == "lt") || (outputForm == "square")) {
+ //output numSeqs
+ out << globaldata->Groups.size() << endl;
+ }
+
//make matrix with scores in it
vector< vector<float> > dists; dists.resize(globaldata->Groups.size());
for (int i = 0; i < globaldata->Groups.size(); i++) {
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 < r; l++) { out << dists[r][l] << '\t'; }
- out << endl;
+ if (outputForm == "lt") {
+ out << name << '\t';
+
+ //output distances
+ for (int l = 0; l < r; l++) { out << dists[r][l] << '\t'; }
+ out << endl;
+ }else if (outputForm == "square") {
+ out << name << '\t';
+
+ //output distances
+ for (int l = 0; l < globaldata->Groups.size(); l++) { out << dists[r][l] << '\t'; }
+ out << endl;
+ }else{
+ //output distances
+ for (int l = 0; l < r; l++) {
+ string otherName = globaldata->Groups[l];
+ if (otherName.length() < 10) { //pad with spaces to make compatible
+ while (otherName.length() < 10) { otherName += " "; }
+ }
+
+ out << name << '\t' << otherName << dists[r][l] << endl;
+ }
+ }
}
out.close();
}