bool processmodel(const string & inputmodelfile, int inputmodeltype, const string & outputmodelfile, int outputmodeltype, const string & corpusfile, PatternSetModel * constrainbymodel, IndexedCorpus * corpus, PatternModelOptions & options, bool continued, bool expand, int firstsentence, bool ignoreerrors, string inputmodelfile2, ClassDecoder * classdecoder, ClassEncoder * classencoder, bool print, bool report, bool nocoverage, bool histogram , bool query, string dorelations, bool doinstantiate, bool info, bool printreverseindex, int cooc, double coocthreshold, bool flexfromskip, const vector<string> & querypatterns) {
if (!(print || report || histogram || query || info || cooc || printreverseindex || (dorelations != "") || (!querypatterns.empty()) || (!outputmodelfile.empty()) )) {
cerr << "Ooops... You didn't really give me anything to do...that can't be right.. Please study the usage options (-h) again! Did you perhaps forget a --print or --outputmodel? " << endl;
return false;
}
ModelType * inputmodel;
string outputqualifier = "";
if ((outputmodeltype == UNINDEXEDPATTERNMODEL) || (outputmodeltype == UNINDEXEDPATTERNPOINTERMODEL)) {
outputqualifier += " unindexed";
}
if ((outputmodeltype == INDEXEDPATTERNPOINTERMODEL) || (outputmodeltype == UNINDEXEDPATTERNPOINTERMODEL)) {
outputqualifier += " pointer";
}
if (inputmodelfile.empty()) {
//train model from scratch
inputmodel = new ModelType(corpus);
cerr << "Training" << outputqualifier << " model on " << corpusfile <<endl;
inputmodel->train(corpusfile, options, constrainbymodel, NULL, continued,firstsentence,ignoreerrors);
if (constrainbymodel) {
cerr << "Unloading constraint model" << endl;
delete constrainbymodel;
constrainbymodel = NULL;
}
if (options.DOSKIPGRAMS) {
if ((inputmodeltype == UNINDEXEDPATTERNMODEL) || (inputmodeltype == UNINDEXEDPATTERNPOINTERMODEL)) {
cerr << "WARNING: Can't compute skipgrams non-exhaustively on unindexed model" << endl;
if (flexfromskip) cerr << "WARNING: Can't compute flexgrams from skipgrams on unindexed model" << endl;
} else {
if (!inputmodelfile2.empty()) cerr << "WARNING: Can not compute skipgrams constrained by " << inputmodelfile2 << "!" << endl;
if (!inputmodel->hasskipgrams) {
cerr << "Computing skipgrams" << endl;
inputmodel->trainskipgrams(options);
}
if (flexfromskip) {
cerr << "Computing flexgrams from skipgrams" << corpusfile <<endl;
int found = inputmodel->computeflexgrams_fromskipgrams();
cerr << found << " flexgrams found" << corpusfile <<endl;
}
}
}
} else {
//load model
cerr << "Loading pattern model " << inputmodelfile << " as" << outputqualifier << " model..."<<endl;
inputmodel = new ModelType(inputmodelfile, options, (PatternModelInterface*) constrainbymodel, corpus);
if ((corpus != NULL) && (inputmodel->hasskipgrams)) {
cerr << "Filtering skipgrams..." << endl;
inputmodel->pruneskipgrams(options.MINTOKENS, options.MINSKIPTYPES);
}
if ((!corpusfile.empty()) && (expand)) {
cerr << "Expanding model on " << corpusfile <<endl;
inputmodel->train(corpusfile, options, constrainbymodel,NULL, continued,firstsentence,ignoreerrors);
if (constrainbymodel) {
cerr << "Unloading constraint model" << endl;
delete constrainbymodel;
constrainbymodel = NULL;
}
} else if (options.DOSKIPGRAMS) {
if (constrainbymodel) {
cerr << "Unloading constraint model" << endl;
delete constrainbymodel;
constrainbymodel = NULL;
}
cerr << "Computing skipgrams" << endl;
if (!inputmodelfile2.empty()) cerr << "WARNING: Can not compute skipgrams constrained by " << inputmodelfile2 << "!" << endl;
inputmodel->trainskipgrams(options);
if (flexfromskip) {
cerr << "Computing flexgrams from skipgrams" << corpusfile <<endl;
int found = inputmodel->computeflexgrams_fromskipgrams();
cerr << found << " flexgrams found" << corpusfile <<endl;
}
} else {
if (constrainbymodel) {
cerr << "Unloading constraint model" << endl;
delete constrainbymodel;
constrainbymodel = NULL;
}
}
}
if (!outputmodelfile.empty()) {
cerr << "Writing model to " << outputmodelfile << endl;
inputmodel->write(outputmodelfile);
}
viewmodel<ModelType>(*inputmodel, classdecoder, classencoder, print, report, nocoverage, histogram, query, dorelations, doinstantiate, info, printreverseindex, cooc, coocthreshold);
if (!querypatterns.empty()) {
processquerypatterns<ModelType>(*inputmodel, classencoder, classdecoder, querypatterns, dorelations, doinstantiate);
}
delete inputmodel;
return true;
}
void writeResults(ModelType& model, double* counts) {
double denom;
char outF[STRLEN];
FILE *fo;
sprintf(modelF, "%s.model", statName);
model.write(modelF);
//calculate tau values
double *tau = new double[M + 1];
memset(tau, 0, sizeof(double) * (M + 1));
denom = 0.0;
for (int i = 1; i <= M; i++)
if (eel[i] >= EPSILON) {
tau[i] = theta[i] / eel[i];
denom += tau[i];
}
general_assert(denom > 0, "No alignable reads?!");
for (int i = 1; i <= M; i++) {
tau[i] /= denom;
}
//isoform level results
sprintf(outF, "%s.iso_res", imdName);
fo = fopen(outF, "w");
for (int i = 1; i <= M; i++) {
const Transcript& transcript = transcripts.getTranscriptAt(i);
fprintf(fo, "%s%c", transcript.getTranscriptID().c_str(), (i < M ? '\t' : '\n'));
}
for (int i = 1; i <= M; i++)
fprintf(fo, "%.2f%c", counts[i], (i < M ? '\t' : '\n'));
for (int i = 1; i <= M; i++)
fprintf(fo, "%.15g%c", tau[i], (i < M ? '\t' : '\n'));
for (int i = 1; i <= M; i++) {
const Transcript& transcript = transcripts.getTranscriptAt(i);
fprintf(fo, "%s%c", transcript.getGeneID().c_str(), (i < M ? '\t' : '\n'));
}
fclose(fo);
//gene level results
sprintf(outF, "%s.gene_res", imdName);
fo = fopen(outF, "w");
for (int i = 0; i < m; i++) {
const string& gene_id = transcripts.getTranscriptAt(gi.spAt(i)).getGeneID();
fprintf(fo, "%s%c", gene_id.c_str(), (i < m - 1 ? '\t' : '\n'));
}
for (int i = 0; i < m; i++) {
double sumC = 0.0; // sum of counts
int b = gi.spAt(i), e = gi.spAt(i + 1);
for (int j = b; j < e; j++) sumC += counts[j];
fprintf(fo, "%.2f%c", sumC, (i < m - 1 ? '\t' : '\n'));
}
for (int i = 0; i < m; i++) {
double sumT = 0.0; // sum of tau values
int b = gi.spAt(i), e = gi.spAt(i + 1);
for (int j = b; j < e; j++) sumT += tau[j];
fprintf(fo, "%.15g%c", sumT, (i < m - 1 ? '\t' : '\n'));
}
for (int i = 0; i < m; i++) {
int b = gi.spAt(i), e = gi.spAt(i + 1);
for (int j = b; j < e; j++) {
fprintf(fo, "%s%c", transcripts.getTranscriptAt(j).getTranscriptID().c_str(), (j < e - 1 ? ',' : (i < m - 1 ? '\t' :'\n')));
}
}
fclose(fo);
delete[] tau;
if (verbose) { printf("Expression Results are written!\n"); }
}
void writeResults(ModelType& model, double* counts) {
sprintf(modelF, "%s.model", statName);
model.write(modelF);
writeResultsEM(M, refName, imdName, transcripts, theta, eel, countvs[0]);
}
