2 * collectsharedcommand.cpp
5 * Created by Sarah Westcott on 1/2/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "collectsharedcommand.h"
11 #include "sharedsobscollectsummary.h"
12 #include "sharedchao1.h"
13 #include "sharedace.h"
14 #include "sharedjabund.h"
15 #include "sharedsorabund.h"
16 #include "sharedjclass.h"
17 #include "sharedsorclass.h"
18 #include "sharedjest.h"
19 #include "sharedsorest.h"
20 #include "sharedthetayc.h"
21 #include "sharedthetan.h"
22 #include "sharedkstest.h"
23 #include "whittaker.h"
24 #include "sharednseqs.h"
25 #include "sharedochiai.h"
26 #include "sharedanderbergs.h"
27 #include "sharedkulczynski.h"
28 #include "sharedkulczynskicody.h"
29 #include "sharedlennon.h"
30 #include "sharedmorisitahorn.h"
31 #include "sharedbraycurtis.h"
32 #include "sharedjackknife.h"
33 #include "whittaker.h"
37 //**********************************************************************************************************************
39 CollectSharedCommand::CollectSharedCommand(string option){
41 globaldata = GlobalData::getInstance();
48 //allow user to run help
49 if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; }
52 //valid paramters for this command
53 string Array[] = {"freq","line","label","calc","groups"};
54 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
56 OptionParser parser(option);
57 map<string,string> parameters=parser.getParameters();
59 ValidParameters validParameter;
61 //check to make sure all parameters are valid for command
62 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
63 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
66 //make sure the user has already run the read.otu command
67 if (globaldata->getSharedFile() == "") {
68 if (globaldata->getListFile() == "") { cout << "You must read a list and a group, or a shared before you can use the collect.shared command." << endl; abort = true; }
69 else if (globaldata->getGroupFile() == "") { cout << "You must read a list and a group, or a shared before you can use the collect.shared command." << endl; abort = true; }
73 //check for optional parameter and set defaults
74 // ...at some point should added some additional type checking...
75 line = validParameter.validFile(parameters, "line", false);
76 if (line == "not found") { line = ""; }
78 if(line != "all") { splitAtDash(line, lines); allLines = 0; }
79 else { allLines = 1; }
82 label = validParameter.validFile(parameters, "label", false);
83 if (label == "not found") { label = ""; }
85 if(label != "all") { splitAtDash(label, labels); allLines = 0; }
86 else { allLines = 1; }
89 //make sure user did not use both the line and label parameters
90 if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; }
91 //if the user has not specified any line or labels use the ones from read.otu
92 else if((line == "") && (label == "")) {
93 allLines = globaldata->allLines;
94 labels = globaldata->labels;
95 lines = globaldata->lines;
98 calc = validParameter.validFile(parameters, "calc", false);
99 if (calc == "not found") { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
101 if (calc == "default") { calc = "sharedsobs-sharedchao-sharedace-jabund-sorabund-jclass-sorclass-jest-sorest-thetayc-thetan"; }
103 splitAtDash(calc, Estimators);
105 groups = validParameter.validFile(parameters, "groups", false);
106 if (groups == "not found") { groups = ""; }
108 splitAtDash(groups, Groups);
109 globaldata->Groups = Groups;
113 temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; }
116 if (abort == false) {
118 string fileNameRoot = getRootName(globaldata->inputFileName);
119 // format = globaldata->getFormat();
122 validCalculator = new ValidCalculators();
123 util = new SharedUtil();
125 for (i=0; i<Estimators.size(); i++) {
126 if (validCalculator->isValidCalculator("shared", Estimators[i]) == true) {
127 if (Estimators[i] == "sharedchao") {
128 cDisplays.push_back(new CollectDisplay(new SharedChao1(), new SharedOneColumnFile(fileNameRoot+"shared.chao")));
129 }else if (Estimators[i] == "sharedsobs") {
130 cDisplays.push_back(new CollectDisplay(new SharedSobsCS(), new SharedOneColumnFile(fileNameRoot+"shared.sobs")));
131 }else if (Estimators[i] == "sharedace") {
132 cDisplays.push_back(new CollectDisplay(new SharedAce(), new SharedOneColumnFile(fileNameRoot+"shared.ace")));
133 }else if (Estimators[i] == "jabund") {
134 cDisplays.push_back(new CollectDisplay(new JAbund(), new SharedOneColumnFile(fileNameRoot+"jabund")));
135 }else if (Estimators[i] == "sorabund") {
136 cDisplays.push_back(new CollectDisplay(new SorAbund(), new SharedOneColumnFile(fileNameRoot+"sorabund")));
137 }else if (Estimators[i] == "jclass") {
138 cDisplays.push_back(new CollectDisplay(new Jclass(), new SharedOneColumnFile(fileNameRoot+"jclass")));
139 }else if (Estimators[i] == "sorclass") {
140 cDisplays.push_back(new CollectDisplay(new SorClass(), new SharedOneColumnFile(fileNameRoot+"sorclass")));
141 }else if (Estimators[i] == "jest") {
142 cDisplays.push_back(new CollectDisplay(new Jest(), new SharedOneColumnFile(fileNameRoot+"jest")));
143 }else if (Estimators[i] == "sorest") {
144 cDisplays.push_back(new CollectDisplay(new SorEst(), new SharedOneColumnFile(fileNameRoot+"sorest")));
145 }else if (Estimators[i] == "thetayc") {
146 cDisplays.push_back(new CollectDisplay(new ThetaYC(), new SharedOneColumnFile(fileNameRoot+"thetayc")));
147 }else if (Estimators[i] == "thetan") {
148 cDisplays.push_back(new CollectDisplay(new ThetaN(), new SharedOneColumnFile(fileNameRoot+"thetan")));
149 }else if (Estimators[i] == "kstest") {
150 cDisplays.push_back(new CollectDisplay(new KSTest(), new SharedOneColumnFile(fileNameRoot+"kstest")));
151 }else if (Estimators[i] == "whittaker") {
152 cDisplays.push_back(new CollectDisplay(new Whittaker(), new SharedOneColumnFile(fileNameRoot+"whittaker")));
153 }else if (Estimators[i] == "sharednseqs") {
154 cDisplays.push_back(new CollectDisplay(new SharedNSeqs(), new SharedOneColumnFile(fileNameRoot+"shared.nseqs")));
155 }else if (Estimators[i] == "ochiai") {
156 cDisplays.push_back(new CollectDisplay(new Ochiai(), new SharedOneColumnFile(fileNameRoot+"ochiai")));
157 }else if (Estimators[i] == "anderberg") {
158 cDisplays.push_back(new CollectDisplay(new Anderberg(), new SharedOneColumnFile(fileNameRoot+"anderberg")));
159 }else if (Estimators[i] == "skulczynski") {
160 cDisplays.push_back(new CollectDisplay(new Kulczynski(), new SharedOneColumnFile(fileNameRoot+"kulczynski")));
161 }else if (Estimators[i] == "kulczynskicody") {
162 cDisplays.push_back(new CollectDisplay(new KulczynskiCody(), new SharedOneColumnFile(fileNameRoot+"kulczynskicody")));
163 }else if (Estimators[i] == "lennon") {
164 cDisplays.push_back(new CollectDisplay(new Lennon(), new SharedOneColumnFile(fileNameRoot+"lennon")));
165 }else if (Estimators[i] == "morisitahorn") {
166 cDisplays.push_back(new CollectDisplay(new MorHorn(), new SharedOneColumnFile(fileNameRoot+"morisitahorn")));
167 }else if (Estimators[i] == "braycurtis") {
168 cDisplays.push_back(new CollectDisplay(new BrayCurtis(), new SharedOneColumnFile(fileNameRoot+"braycurtis")));
176 catch(exception& e) {
177 cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function CollectSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
181 cout << "An unknown error has occurred in the CollectSharedCommand class function CollectSharedCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
186 //**********************************************************************************************************************
188 void CollectSharedCommand::help(){
190 cout << "The collect.shared command can only be executed after a successful read.otu command." << "\n";
191 cout << "The collect.shared command parameters are label, line, freq, calc and groups. No parameters are required, but you may not use " << "\n";
192 cout << "both the line and label parameters at the same time. The collect.shared command should be in the following format: " << "\n";
193 cout << "collect.shared(label=yourLabel, line=yourLines, freq=yourFreq, calc=yourEstimators, groups=yourGroups)." << "\n";
194 cout << "Example collect.shared(label=unique-.01-.03, line=0-5-10, freq=10, groups=B-C, calc=sharedchao-sharedace-jabund-sorensonabund-jclass-sorclass-jest-sorest-thetayc-thetan)." << "\n";
195 cout << "The default values for freq is 100 and calc are sharedsobs-sharedchao-sharedace-jabund-sorensonabund-jclass-sorclass-jest-sorest-thetayc-thetan." << "\n";
196 cout << "The default value for groups is all the groups in your groupfile." << "\n";
197 validCalculator->printCalc("shared", cout);
198 cout << "The label and line parameters are used to analyze specific lines in your input." << "\n";
199 cout << "The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 2 valid groups." << "\n";
200 cout << "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile)." << "\n" << "\n";
203 catch(exception& e) {
204 cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
208 cout << "An unknown error has occurred in the CollectSharedCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
213 //**********************************************************************************************************************
215 CollectSharedCommand::~CollectSharedCommand(){
221 delete validCalculator;
224 //**********************************************************************************************************************
226 int CollectSharedCommand::execute(){
229 if (abort == true) { return 0; }
233 //if the users entered no valid calculators don't execute command
234 if (cDisplays.size() == 0) { return 0; }
236 read = new ReadOTUFile(globaldata->inputFileName);
237 read->read(&*globaldata);
239 input = globaldata->ginput;
240 order = input->getSharedOrderVector();
241 SharedOrderVector* lastOrder = order;
243 //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
244 set<string> processedLabels;
245 set<string> userLabels = globaldata->labels;
246 set<int> userLines = globaldata->lines;
249 util->setGroups(globaldata->Groups, globaldata->gGroupmap->namesOfGroups, "collect");
250 util->updateGroupIndex(globaldata->Groups, globaldata->gGroupmap->groupIndex);
252 while((order != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) {
254 if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(order->getLabel()) == 1){
256 //create collectors curve
257 cCurve = new Collect(order, cDisplays);
258 cCurve->getSharedCurve(freq);
261 cout << order->getLabel() << '\t' << count << endl;
262 processedLabels.insert(order->getLabel());
263 userLabels.erase(order->getLabel());
264 userLines.erase(count);
266 //you have a label the user want that is smaller than this line and the last line has not already been processed
269 if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastOrder->getLabel()) != 1)) {
270 //create collectors curve
271 cCurve = new Collect(lastOrder, cDisplays);
272 cCurve->getSharedCurve(freq);
275 cout << lastOrder->getLabel() << '\t' << count << endl;
276 processedLabels.insert(lastOrder->getLabel());
277 userLabels.erase(lastOrder->getLabel());
280 if (count != 1) { delete lastOrder; }
283 //get next line to process
284 order = input->getSharedOrderVector();
288 //output error messages about any remaining user labels
289 set<string>::iterator it;
290 bool needToRun = false;
291 for (it = userLabels.begin(); it != userLabels.end(); it++) {
292 cout << "Your file does not include the label "<< *it;
293 if (processedLabels.count(lastOrder->getLabel()) != 1) {
294 cout << ". I will use " << lastOrder->getLabel() << "." << endl;
297 cout << ". Please refer to " << lastOrder->getLabel() << "." << endl;
301 //run last line if you need to
302 if (needToRun == true) {
303 cCurve = new Collect(lastOrder, cDisplays);
304 cCurve->getCurve(freq);
307 cout << lastOrder->getLabel() << '\t' << count << endl;
311 for(int i=0;i<cDisplays.size();i++){ delete cDisplays[i]; }
313 //reset groups parameter
314 globaldata->Groups.clear();
318 catch(exception& e) {
319 cout << "Standard Error: " << e.what() << " has occurred in the CollectSharedCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
323 cout << "An unknown error has occurred in the CollectSharedCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
328 /***********************************************************/