X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readdistcommand.cpp;h=f6cf5db3948ea8da4557fad5b98da360019922e7;hb=c82900be3ceed3d9bc491bdc98b1819ef85c1af7;hp=744a35d6715867e64697461d88d648982479f0f5;hpb=163b300cfd7d4ca4e70c454be20f07b1d8346650;p=mothur.git diff --git a/readdistcommand.cpp b/readdistcommand.cpp index 744a35d..f6cf5db 100644 --- a/readdistcommand.cpp +++ b/readdistcommand.cpp @@ -66,13 +66,13 @@ ReadDistCommand::ReadDistCommand(string option){ if ((phylipfile != "") && (groupfile != "")) { globaldata->setFormat("matrix"); } - if ((phylipfile == "") && (columnfile == "")) { cout << "When executing a read.dist command you must enter a phylip or a column." << endl; abort = true; } - else if ((phylipfile != "") && (columnfile != "")) { cout << "When executing a read.dist command you must enter ONLY ONE of the following: phylip or column." << endl; abort = true; } + if ((phylipfile == "") && (columnfile == "")) { mothurOut("When executing a read.dist command you must enter a phylip or a column."); mothurOutEndLine(); abort = true; } + else if ((phylipfile != "") && (columnfile != "")) { mothurOut("When executing a read.dist command you must enter ONLY ONE of the following: phylip or column."); mothurOutEndLine(); abort = true; } if (columnfile != "") { if (namefile == "") { cout << "You need to provide a namefile if you are going to use the column format." << endl; abort = true; } } - + //check for optional parameter and set defaults // ...at some point should added some additional type checking... //get user cutoff and precision or use defaults @@ -93,6 +93,7 @@ ReadDistCommand::ReadDistCommand(string option){ else if (format == "matrix") { groupMap = new GroupMap(groupfile); groupMap->readMap(); + if (globaldata->gGroupmap != NULL) { delete globaldata->gGroupmap; } globaldata->gGroupmap = groupMap; } @@ -113,11 +114,7 @@ ReadDistCommand::ReadDistCommand(string option){ } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function ReadDistCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function ReadDistCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "ReadDistCommand", "ReadDistCommand"); exit(1); } } @@ -125,32 +122,31 @@ ReadDistCommand::ReadDistCommand(string option){ void ReadDistCommand::help(){ try { - cout << "The read.dist command parameter options are phylip or column, group, name, cutoff and precision" << "\n"; - cout << "The read.dist command can be used in two ways. The first is to read a phylip or column and run the cluster command" << "\n"; - cout << "For this use the read.dist command should be in the following format: " << "\n"; - cout << "read.dist(phylip=yourDistFile, name=yourNameFile, cutoff=yourCutoff, precision=yourPrecision) " << "\n"; - cout << "The phylip or column parameter is required, but only one may be used. If you use a column file the name filename is required. " << "\n"; - cout << "If you do not provide a cutoff value 10.00 is assumed. If you do not provide a precision value then 100 is assumed." << "\n"; - cout << "The second way to use the read.dist command is to read a phylip or column and a group, so you can use the libshuff command." << "\n"; - cout << "For this use the read.dist command should be in the following format: " << "\n"; - cout << "read.dist(phylip=yourPhylipfile, group=yourGroupFile). The cutoff and precision parameters are not valid with this use. " << "\n"; - cout << "Note: No spaces between parameter labels (i.e. phylip), '=' and parameters (i.e.yourPhylipfile)." << "\n" << "\n"; + mothurOut("The read.dist command parameter options are phylip or column, group, name, cutoff and precision\n"); + mothurOut("The read.dist command can be used in two ways. The first is to read a phylip or column and run the cluster command\n"); + mothurOut("For this use the read.dist command should be in the following format: \n"); + mothurOut("read.dist(phylip=yourDistFile, name=yourNameFile, cutoff=yourCutoff, precision=yourPrecision) \n"); + mothurOut("The phylip or column parameter is required, but only one may be used. If you use a column file the name filename is required. \n"); + mothurOut("If you do not provide a cutoff value 10.00 is assumed. If you do not provide a precision value then 100 is assumed.\n"); + mothurOut("The second way to use the read.dist command is to read a phylip or column and a group, so you can use the libshuff command.\n"); + mothurOut("For this use the read.dist command should be in the following format: \n"); + mothurOut("read.dist(phylip=yourPhylipfile, group=yourGroupFile). The cutoff and precision parameters are not valid with this use. \n"); + mothurOut("Note: No spaces between parameter labels (i.e. phylip), '=' and parameters (i.e.yourPhylipfile).\n\n"); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "ReadDistCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** ReadDistCommand::~ReadDistCommand(){ if (abort == false) { - if (format != "matrix") { delete read; delete nameMap; } + if (format != "matrix") { + delete read; + delete nameMap; + } } } @@ -159,16 +155,48 @@ int ReadDistCommand::execute(){ try { if (abort == true) { return 0; } + + time_t start = time(NULL); + size_t numDists = 0; if (format == "matrix") { ifstream in; openInputFile(distFileName, in); matrix = new FullMatrix(in); //reads the matrix file in.close(); + + //if files don't match... + if (matrix->getNumSeqs() < groupMap->getNumSeqs()) { + mothurOut("Your distance file contains " + toString(matrix->getNumSeqs()) + " sequences, and your group file contains " + toString(groupMap->getNumSeqs()) + " sequences."); mothurOutEndLine(); + //create new group file + string newGroupFile = getRootName(groupfile) + "editted.groups"; + ofstream outGroups; + openOutputFile(newGroupFile, outGroups); + + for (int i = 0; i < matrix->getNumSeqs(); i++) { + Names temp = matrix->getRowInfo(i); + outGroups << temp.seqName << '\t' << temp.groupName << endl; + } + outGroups.close(); + + mothurOut(newGroupFile + " is a new group file containing only the sequence that are in your distance file. I will read this file instead."); mothurOutEndLine(); + + //read new groupfile + delete groupMap; groupMap = NULL; + groupfile = newGroupFile; + globaldata->setGroupFile(groupfile); + + groupMap = new GroupMap(groupfile); + groupMap->readMap(); + + globaldata->gGroupmap = groupMap; + } + //memory leak prevention if (globaldata->gMatrix != NULL) { delete globaldata->gMatrix; } globaldata->gMatrix = matrix; //save matrix for coverage commands - }else { + numDists = matrix->getSizes()[1]; + } else { read->read(nameMap); //to prevent memory leak @@ -177,16 +205,39 @@ int ReadDistCommand::execute(){ if (globaldata->gSparseMatrix != NULL) { delete globaldata->gSparseMatrix; } globaldata->gSparseMatrix = read->getMatrix(); + numDists = globaldata->gSparseMatrix->getNNodes(); + + int lines = cutoff / (1.0/precision); + vector dist_cutoff(lines+1,0); + for (int i = 0; i <= lines;i++) { + dist_cutoff[i] = (i + 0.5) / precision; + } + vector dist_count(lines+1,0); + list::iterator currentCell; + SparseMatrix* smatrix = globaldata->gSparseMatrix; + for (currentCell = smatrix->begin(); currentCell != smatrix->end(); currentCell++) { + for (int i = 0; i <= lines;i++) { + if (currentCell->dist < dist_cutoff[i]) { + dist_count[i]++; + break; + } + } + } + // string dist_string = "Dist:"; + // string count_string = "Count: "; + //for (int i = 0; i <= lines;i++) { + //dist_string = dist_string.append("\t").append(toString(dist_cutoff[i])); + // count_string = count_string.append("\t").append(toString(dist_count[i])); + // } + //mothurOut(dist_string); mothurOutEndLine(); mothurOut(count_string); mothurOutEndLine(); } + mothurOut("It took " + toString(time(NULL) - start) + " secs to read "); mothurOutEndLine(); return 0; + } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "ReadDistCommand", "execute"); exit(1); } }