5 * Created by Sarah Westcott on 1/2/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "collectcommand.h"
15 #include "bootstrap.h"
17 #include "npshannon.h"
19 #include "jackknife.h"
23 #include "bergerparker.h"
25 #include "goodscoverage.h"
33 //**********************************************************************************************************************
34 CollectCommand::CollectCommand(string option){
36 globaldata = GlobalData::getInstance();
42 //allow user to run help
43 if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; }
46 //valid paramters for this command
47 string Array[] = {"freq","label","calc","abund","size"};
48 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
50 OptionParser parser(option);
51 map<string,string> parameters = parser.getParameters();
53 ValidParameters validParameter;
55 //check to make sure all parameters are valid for command
56 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
57 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
60 //make sure the user has already run the read.otu command
61 if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { mothurOut("You must read a list, sabund, rabund or shared file before you can use the collect.single command."); mothurOutEndLine(); abort = true; }
63 //check for optional parameter and set defaults
64 // ...at some point should added some additional type checking...
65 label = validParameter.validFile(parameters, "label", false);
66 if (label == "not found") { label = ""; }
68 if(label != "all") { splitAtDash(label, labels); allLines = 0; }
69 else { allLines = 1; }
72 //if the user has not specified any labels use the ones from read.otu
74 allLines = globaldata->allLines;
75 labels = globaldata->labels;
78 calc = validParameter.validFile(parameters, "calc", false);
79 if (calc == "not found") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
81 if (calc == "default") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; }
83 splitAtDash(calc, Estimators);
86 temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; }
89 temp = validParameter.validFile(parameters, "abund", false); if (temp == "not found") { temp = "10"; }
92 temp = validParameter.validFile(parameters, "size", false); if (temp == "not found") { temp = "0"; }
98 errorOut(e, "CollectCommand", "CollectCommand");
102 //**********************************************************************************************************************
104 void CollectCommand::help(){
106 mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n");
107 mothurOut("The collect.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n");
108 mothurOut("The collect.single command parameters are label, freq, calc and abund. No parameters are required. \n");
109 mothurOut("The collect.single command should be in the following format: \n");
110 mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n");
111 mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n");
112 mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n");
113 validCalculator->printCalc("single", cout);
114 mothurOut("The label parameter is used to analyze specific labels in your input.\n");
115 mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n");
117 catch(exception& e) {
118 errorOut(e, "CollectCommand", "help");
123 //**********************************************************************************************************************
125 CollectCommand::~CollectCommand(){}
127 //**********************************************************************************************************************
129 int CollectCommand::execute(){
132 if (abort == true) { return 0; }
134 if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); }
135 else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); }
137 for (int p = 0; p < inputFileNames.size(); p++) {
139 string fileNameRoot = getRootName(inputFileNames[p]);
140 globaldata->inputFileName = inputFileNames[p];
142 if (inputFileNames.size() > 1) {
143 mothurOutEndLine(); mothurOut("Processing group " + groups[p]); mothurOutEndLine(); mothurOutEndLine();
146 validCalculator = new ValidCalculators();
148 for (int i=0; i<Estimators.size(); i++) {
149 if (validCalculator->isValidCalculator("single", Estimators[i]) == true) {
150 if (Estimators[i] == "sobs") {
151 cDisplays.push_back(new CollectDisplay(new Sobs(), new OneColumnFile(fileNameRoot+"sobs")));
152 }else if (Estimators[i] == "chao") {
153 cDisplays.push_back(new CollectDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"chao")));
154 }else if (Estimators[i] == "nseqs") {
155 cDisplays.push_back(new CollectDisplay(new NSeqs(), new OneColumnFile(fileNameRoot+"nseqs")));
156 }else if (Estimators[i] == "coverage") {
157 cDisplays.push_back(new CollectDisplay(new Coverage(), new OneColumnFile(fileNameRoot+"coverage")));
158 }else if (Estimators[i] == "ace") {
159 cDisplays.push_back(new CollectDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"ace")));
160 }else if (Estimators[i] == "jack") {
161 cDisplays.push_back(new CollectDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"jack")));
162 }else if (Estimators[i] == "shannon") {
163 cDisplays.push_back(new CollectDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"shannon")));
164 }else if (Estimators[i] == "npshannon") {
165 cDisplays.push_back(new CollectDisplay(new NPShannon(), new OneColumnFile(fileNameRoot+"np_shannon")));
166 }else if (Estimators[i] == "simpson") {
167 cDisplays.push_back(new CollectDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"simpson")));
168 }else if (Estimators[i] == "bootstrap") {
169 cDisplays.push_back(new CollectDisplay(new Bootstrap(), new OneColumnFile(fileNameRoot+"bootstrap")));
170 }else if (Estimators[i] == "geometric") {
171 cDisplays.push_back(new CollectDisplay(new Geom(), new OneColumnFile(fileNameRoot+"geometric")));
172 }else if (Estimators[i] == "qstat") {
173 cDisplays.push_back(new CollectDisplay(new QStat(), new OneColumnFile(fileNameRoot+"qstat")));
174 }else if (Estimators[i] == "logseries") {
175 cDisplays.push_back(new CollectDisplay(new LogSD(), new OneColumnFile(fileNameRoot+"logseries")));
176 }else if (Estimators[i] == "bergerparker") {
177 cDisplays.push_back(new CollectDisplay(new BergerParker(), new OneColumnFile(fileNameRoot+"bergerparker")));
178 }else if (Estimators[i] == "bstick") {
179 cDisplays.push_back(new CollectDisplay(new BStick(), new ThreeColumnFile(fileNameRoot+"bstick")));
180 }else if (Estimators[i] == "goodscoverage") {
181 cDisplays.push_back(new CollectDisplay(new GoodsCoverage(), new OneColumnFile(fileNameRoot+"goodscoverage")));
182 }else if (Estimators[i] == "efron") {
183 cDisplays.push_back(new CollectDisplay(new Efron(size), new OneColumnFile(fileNameRoot+"efron")));
184 }else if (Estimators[i] == "boneh") {
185 cDisplays.push_back(new CollectDisplay(new Boneh(size), new OneColumnFile(fileNameRoot+"boneh")));
186 }else if (Estimators[i] == "solow") {
187 cDisplays.push_back(new CollectDisplay(new Solow(size), new OneColumnFile(fileNameRoot+"solow")));
188 }else if (Estimators[i] == "shen") {
189 cDisplays.push_back(new CollectDisplay(new Shen(size, abund), new OneColumnFile(fileNameRoot+"shen")));
195 //if the users entered no valid calculators don't execute command
196 if (cDisplays.size() == 0) { return 0; }
198 read = new ReadOTUFile(inputFileNames[p]);
199 read->read(&*globaldata);
201 order = globaldata->gorder;
202 string lastLabel = order->getLabel();
203 input = globaldata->ginput;
205 //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
206 set<string> processedLabels;
207 set<string> userLabels = labels;
209 while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) {
211 if(allLines == 1 || labels.count(order->getLabel()) == 1){
213 cCurve = new Collect(order, cDisplays);
214 cCurve->getCurve(freq);
217 mothurOut(order->getLabel()); mothurOutEndLine();
218 processedLabels.insert(order->getLabel());
219 userLabels.erase(order->getLabel());
223 //you have a label the user want that is smaller than this label and the last label has not already been processed
224 if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
225 string saveLabel = order->getLabel();
228 order = (input->getOrderVector(lastLabel));
230 cCurve = new Collect(order, cDisplays);
231 cCurve->getCurve(freq);
234 mothurOut(order->getLabel()); mothurOutEndLine();
235 processedLabels.insert(order->getLabel());
236 userLabels.erase(order->getLabel());
238 //restore real lastlabel to save below
239 order->setLabel(saveLabel);
242 lastLabel = order->getLabel();
245 order = (input->getOrderVector());
248 //output error messages about any remaining user labels
249 set<string>::iterator it;
250 bool needToRun = false;
251 for (it = userLabels.begin(); it != userLabels.end(); it++) {
252 mothurOut("Your file does not include the label " + *it);
253 if (processedLabels.count(lastLabel) != 1) {
254 mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine();
257 mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine();
261 //run last label if you need to
262 if (needToRun == true) {
263 if (order != NULL) { delete order; }
264 order = (input->getOrderVector(lastLabel));
266 mothurOut(order->getLabel()); mothurOutEndLine();
268 cCurve = new Collect(order, cDisplays);
269 cCurve->getCurve(freq);
274 for(int i=0;i<cDisplays.size();i++){ delete cDisplays[i]; }
276 delete input; globaldata->ginput = NULL;
278 globaldata->gorder = NULL;
279 delete validCalculator;
286 catch(exception& e) {
287 errorOut(e, "CollectCommand", "execute");
292 //**********************************************************************************************************************
293 vector<string> CollectCommand::parseSharedFile(string filename) {
295 vector<string> filenames;
297 map<string, ofstream*> filehandles;
298 map<string, ofstream*>::iterator it3;
302 read = new ReadOTUFile(filename);
303 read->read(&*globaldata);
305 input = globaldata->ginput;
306 vector<SharedRAbundVector*> lookup = input->getSharedRAbundVectors();
308 string sharedFileRoot = getRootName(filename);
310 //clears file before we start to write to it below
311 for (int i=0; i<lookup.size(); i++) {
312 remove((sharedFileRoot + lookup[i]->getGroup() + ".rabund").c_str());
313 filenames.push_back((sharedFileRoot + lookup[i]->getGroup() + ".rabund"));
317 for (int i=0; i<lookup.size(); i++) {
319 filehandles[lookup[i]->getGroup()] = temp;
320 groups.push_back(lookup[i]->getGroup());
323 while(lookup[0] != NULL) {
325 for (int i = 0; i < lookup.size(); i++) {
326 RAbundVector rav = lookup[i]->getRAbundVector();
327 openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()]));
328 rav.print(*(filehandles[lookup[i]->getGroup()]));
329 (*(filehandles[lookup[i]->getGroup()])).close();
332 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
333 lookup = input->getSharedRAbundVectors();
337 for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) {
342 globaldata->ginput = NULL;
346 catch(exception& e) {
347 errorOut(e, "CollectCommand", "parseSharedFile");
351 //**********************************************************************************************************************