X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=pcoacommand.cpp;h=2043a128bd94bc755cb7ef10f5a8b8d9bdb5a6be;hb=6b32d112bb60e9f7eb6d4407a4eed4c49b67bced;hp=ee0a5462de87049f6b026546492203be630ea8d7;hpb=4956d362c5bc6a47cf7a6290258f0e763e3a406e;p=mothur.git diff --git a/pcoacommand.cpp b/pcoacommand.cpp index ee0a546..2043a12 100644 --- a/pcoacommand.cpp +++ b/pcoacommand.cpp @@ -8,70 +8,87 @@ * */ -#include "pcacommand.h" +#include "pcoacommand.h" +#include "readphylipvector.h" + //********************************************************************************************************************** -vector PCACommand::getValidParameters(){ +vector PCOACommand::setParameters(){ try { - string Array[] = {"phylip", "outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pphylip("phylip", "InputTypes", "", "", "none", "none", "none","pcoa-loadings",false,true,true); parameters.push_back(pphylip); + CommandParameter pmetric("metric", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pmetric); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + 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); } return myArray; } catch(exception& e) { - m->errorOut(e, "PCACommand", "getValidParameters"); + m->errorOut(e, "PCOACommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -PCACommand::PCACommand(){ +string PCOACommand::getHelpString(){ try { - abort = true; - //initialize outputTypes - vector tempOutNames; - outputTypes["pcoa"] = tempOutNames; - outputTypes["loadings"] = tempOutNames; + string helpString = ""; + helpString += "The pcoa command parameters are phylip and metric"; + helpString += "The phylip parameter allows you to enter your distance file."; + helpString += "The metric parameter allows indicate you if would like the pearson correlation coefficient calculated. Default=True"; + helpString += "Example pcoa(phylip=yourDistanceFile).\n"; + helpString += "Note: No spaces between parameter labels (i.e. phylip), '=' and parameters (i.e.yourDistanceFile).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "PCACommand", "PCACommand"); + m->errorOut(e, "PCOACommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector PCACommand::getRequiredParameters(){ - try { - string Array[] = {"phylip"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "PCACommand", "getRequiredParameters"); - exit(1); - } +string PCOACommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "pcoa") { pattern = "[filename],pcoa.axes"; } + else if (type == "loadings") { pattern = "[filename],pcoa.loadings"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "PCOACommand", "getOutputPattern"); + exit(1); + } } + + //********************************************************************************************************************** -vector PCACommand::getRequiredFiles(){ +PCOACommand::PCOACommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["pcoa"] = tempOutNames; + outputTypes["loadings"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "PCACommand", "getRequiredFiles"); + m->errorOut(e, "PCOACommand", "PCOACommand"); exit(1); } } //********************************************************************************************************************** -PCACommand::PCACommand(string option) { +PCOACommand::PCOACommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"phylip","outputdir", "inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser. getParameters(); @@ -105,8 +122,14 @@ PCACommand::PCACommand(string option) { //required parameters phylipfile = validParameter.validFile(parameters, "phylip", true); if (phylipfile == "not open") { abort = true; } - else if (phylipfile == "not found") { phylipfile = ""; abort = true; } - else { filename = phylipfile; } + else if (phylipfile == "not found") { + //if there is a current phylip file, use it + phylipfile = m->getPhylipFile(); + if (phylipfile != "") { m->mothurOut("Using " + phylipfile + " as input file for the phylip parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current phylip file and the phylip parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setPhylipFile(phylipfile); } + + filename = phylipfile; //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ @@ -114,34 +137,21 @@ PCACommand::PCACommand(string option) { outputDir += m->hasPath(phylipfile); //if user entered a file with a path then preserve it } - //error checking on files - if (phylipfile == "") { m->mothurOut("You must provide a distance file before running the pca command."); m->mothurOutEndLine(); abort = true; } + string temp = validParameter.validFile(parameters, "metric", false); if (temp == "not found"){ temp = "T"; } + metric = m->isTrue(temp); } } catch(exception& e) { - m->errorOut(e, "PCACommand", "PCACommand"); + m->errorOut(e, "PCOACommand", "PCOACommand"); exit(1); } } //********************************************************************************************************************** -void PCACommand::help(){ +int PCOACommand::execute(){ try { - m->mothurOut("The pca command..."); m->mothurOutEndLine(); - } - catch(exception& e) { - m->errorOut(e, "PCACommand", "help"); - exit(1); - } -} -//********************************************************************************************************************** -PCACommand::~PCACommand(){} -//********************************************************************************************************************** -int PCACommand::execute(){ - try { - - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } cout.setf(ios::fixed, ios::floatfield); cout.setf(ios::showpoint); @@ -153,7 +163,8 @@ int PCACommand::execute(){ fbase = outputDir + m->getRootName(m->getSimpleName(filename)); - read(filename, names, D); + ReadPhylipVector readFile(filename); + names = readFile.read(D); if (m->control_pressed) { return 0; } @@ -161,15 +172,14 @@ int PCACommand::execute(){ vector d; vector e; vector > G = D; - vector > copy_G; - //int rank = D.size(); - + //vector > copy_G; + m->mothurOut("\nProcessing...\n"); for(int count=0;count<2;count++){ - recenter(offset, D, G); if (m->control_pressed) { return 0; } - tred2(G, d, e); if (m->control_pressed) { return 0; } - qtli(d, e, G); if (m->control_pressed) { return 0; } + linearCalc.recenter(offset, D, G); if (m->control_pressed) { return 0; } + linearCalc.tred2(G, d, e); if (m->control_pressed) { return 0; } + linearCalc.qtli(d, e, G); if (m->control_pressed) { return 0; } offset = d[d.size()-1]; if(offset > 0.0) break; } @@ -178,7 +188,23 @@ int PCACommand::execute(){ output(fbase, names, G, d); - 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; } + + if (metric) { + + for (int i = 1; i < 4; i++) { + + vector< vector > EuclidDists = linearCalc.calculateEuclidianDistance(G, i); //G is the pcoa file + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + double corr = linearCalc.calcPearson(EuclidDists, D); //G is the pcoa file, D is the users distance matrix + + m->mothurOut("Rsq " + toString(i) + " axis: " + toString(corr * corr)); m->mothurOutEndLine(); + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + } + } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -188,373 +214,26 @@ int PCACommand::execute(){ return 0; } catch(exception& e) { - m->errorOut(e, "PCACommand", "execute"); + m->errorOut(e, "PCOACommand", "execute"); exit(1); } } /*********************************************************************************************************************************/ -inline double SIGN(const double a, const double b) -{ - return b>=0 ? (a>=0 ? a:-a) : (a>=0 ? -a:a); -} - -/*********************************************************************************************************************************/ - -void PCACommand::get_comment(istream& f, char begin, char end){ +void PCOACommand::get_comment(istream& f, char begin, char end){ try { char d=f.get(); while(d != end){ d = f.get(); } d = f.peek(); } catch(exception& e) { - m->errorOut(e, "PCACommand", "get_comment"); + m->errorOut(e, "PCOACommand", "get_comment"); exit(1); } } - -/*********************************************************************************************************************************/ - -int PCACommand::read_phylip(istream& f, int square_m, vector& name_list, vector >& d){ - try { - // int count1=0; - // int count2=0; - - int rank; - f >> rank; - - name_list.resize(rank); - d.resize(rank); - if(square_m == 1){ - for(int i=0;i> name_list[i]; - // cout << i << "\t" << name_list[i] << endl; - for(int j=0;jcontrol_pressed) { return 0; } - - f >> d[i][j]; - if (d[i][j] == -0.0000) - d[i][j] = 0.0000; - } - } - } - else if(square_m == 2){ - for(int i=0;i> name_list[0]; - for(int i=1;i> name_list[i]; - d[i][i]=0.0000; - for(int j=0;jcontrol_pressed) { return 0; } - f >> d[i][j]; - if (d[i][j] == -0.0000) - d[i][j] = 0.0000; - d[j][i]=d[i][j]; - } - } - } - - return 0; - } - catch(exception& e) { - m->errorOut(e, "PCACommand", "read_phylip"); - exit(1); - } - -} - -/*********************************************************************************************************************************/ - -void PCACommand::read(string fname, vector& names, vector >& D){ - try { - ifstream f; - m->openInputFile(fname, f); - - //check whether matrix is square - char d; - int q = 1; - int numSeqs; - string name; - - f >> numSeqs >> name; - - while((d=f.get()) != EOF){ - - //is d a number meaning its square - if(isalnum(d)){ - q = 1; - break; - } - - //is d a line return meaning its lower triangle - if(d == '\n'){ - q = 2; - break; - } - } - f.close(); - - //reopen to get back to beginning - m->openInputFile(fname, f); - read_phylip(f, q, names, D); - } - catch(exception& e) { - m->errorOut(e, "PCACommand", "read"); - exit(1); - } -} - -/*********************************************************************************************************************************/ - -double PCACommand::pythag(double a, double b) { return(pow(a*a+b*b,0.5)); } - -/*********************************************************************************************************************************/ - -void PCACommand::matrix_mult(vector > first, vector > second, vector >& product){ - try { - int first_rows = first.size(); - int first_cols = first[0].size(); - int second_cols = second[0].size(); - - product.resize(first_rows); - for(int i=0;ierrorOut(e, "PCACommand", "matrix_mult"); - exit(1); - } - -} - -/*********************************************************************************************************************************/ - -void PCACommand::recenter(double offset, vector > D, vector >& G){ - try { - int rank = D.size(); - - vector > A(rank); - vector > C(rank); - for(int i=0;ierrorOut(e, "PCACommand", "recenter"); - exit(1); - } - -} - -/*********************************************************************************************************************************/ - -// This function is taken from Numerical Recipes in C++ by Press et al., 2nd edition, pg. 479 - -void PCACommand::tred2(vector >& a, vector& d, vector& e){ - try { - double scale, hh, h, g, f; - - int n = a.size(); - - d.resize(n); - e.resize(n); - - for(int i=n-1;i>0;i--){ - int l=i-1; - h = scale = 0.0000; - if(l>0){ - for(int k=0;k= 0.0 ? -sqrt(h) : sqrt(h)); - e[i] = scale * g; - h -= f * g; - a[i][l] = f - g; - f = 0.0; - for(int j=0;jerrorOut(e, "PCACommand", "tred2"); - exit(1); - } - -} - -/*********************************************************************************************************************************/ - -// This function is taken from Numerical Recipes in C++ by Press et al., 2nd edition, pg. 479 - -void PCACommand::qtli(vector& d, vector& e, vector >& z) { - try { - int m, i, iter; - double s, r, p, g, f, dd, c, b; - - int n = d.size(); - for(int i=1;i<=n;i++){ - e[i-1] = e[i]; - } - e[n-1] = 0.0000; - - for(int l=0;l=l;i--){ - f = s * e[i]; - b = c * e[i]; - e[i+1] = (r=pythag(f,g)); - if(r==0.0){ - d[i+1] -= p; - e[m] = 0.0000; - break; - } - s = f / r; - c = g / r; - g = d[i+1] - p; - r = (d[i] - g) * s + 2.0 * c * b; - d[i+1] = g + ( p = s * r); - g = c * r - b; - for(int k=0;k= l) continue; - d[l] -= p; - e[l] = g; - e[m] = 0.0; - } - } while (m != l); - } - - int k; - for(int i=0;i= p){ - p=d[k=j]; - } - } - if(k!=i){ - d[k]=d[i]; - d[i]=p; - for(int j=0;jerrorOut(e, "PCACommand", "qtli"); - exit(1); - } -} - /*********************************************************************************************************************************/ -void PCACommand::output(string fnameRoot, vector name_list, vector > G, vector d) { +void PCOACommand::output(string fnameRoot, vector name_list, vector >& G, vector d) { try { int rank = name_list.size(); double dsum = 0.0000; @@ -566,17 +245,23 @@ void PCACommand::output(string fnameRoot, vector name_list, vector variables; + variables["[filename]"] = fnameRoot; + string pcoaDataFile = getOutputFileName("pcoa",variables); + m->openOutputFile(pcoaDataFile, pcaData); pcaData.setf(ios::fixed, ios::floatfield); pcaData.setf(ios::showpoint); - outputNames.push_back(fnameRoot+"pcoa"); - outputTypes["pcoa"].push_back(fnameRoot+"pcoa"); + outputNames.push_back(pcoaDataFile); + outputTypes["pcoa"].push_back(pcoaDataFile); - ofstream pcaLoadings((fnameRoot+"pcoa.loadings").c_str(), ios::trunc); + ofstream pcaLoadings; + string loadingsFile = getOutputFileName("loadings",variables); + m->openOutputFile(loadingsFile, pcaLoadings); pcaLoadings.setf(ios::fixed, ios::floatfield); pcaLoadings.setf(ios::showpoint); - outputNames.push_back(fnameRoot+"pcoa.loadings"); - outputTypes["loadings"].push_back(fnameRoot+"pcoa.loadings"); + outputNames.push_back(loadingsFile); + outputTypes["loadings"].push_back(loadingsFile); pcaLoadings << "axis\tloading\n"; for(int i=0;i name_list, vectorerrorOut(e, "PCACommand", "output"); + m->errorOut(e, "PCOACommand", "output"); exit(1); } }