def tag(self, tagger: StanfordPOSTagger = None): """ Tag the given sentence. """ tags = tagger.tag(self.raw()) for i, tag in enumerate(tags): self[i].cpostag = tag.label self[i].postag = tag.label
def evaluate_intent(filelist, classifier_path=None, eval_alignment=None, eval_ds=None, eval_posproj=None, classifier_feats=CLASS_FEATS_DEFAULT, eval_tagger=None, gold_tagmap=None, trans_tagmap=None, outpath=None): """ Given a list of files that have manual POS tags and manual alignment, evaluate the various INTENT methods on that file. :param filelist: List of paths to evaluate against. :type filelist: list[str] :param classifier_path: Path to the classifier model :type classifier_path: str :param eval_alignment: """ tagger = StanfordPOSTagger(tagger_model) outstream = sys.stdout if outpath is not None: outstream = open(outpath, mode='w', encoding='utf-8') # ============================================================================= # Set up the objects to run as "servers" # ============================================================================= classifier_obj = MalletMaxent(classifier) if classifier_path is not None: classifier_obj = MalletMaxent(classifier_path) class_matches, class_compares = 0, 0 e_tagger = None if eval_tagger is not None: e_tagger = StanfordPOSTagger(eval_tagger) mas = MultAlignScorer() ds_plma = PerLangMethodAccuracies() pos_plma= PerLangMethodAccuracies() pos_pla = POSEvalDict() pos_proj_matrix = POSMatrix() pos_class_matrix = POSMatrix() # ------------------------------------------- # If a tag map is specified, let's load it. # ------------------------------------------- g_tm = TagMap(gold_tagmap) if gold_tagmap is not None else None t_tm = TagMap(trans_tagmap) if trans_tagmap is not None else None # Go through all the files in the list... for f in filelist: outstream.write('Evaluating on file: {}\n'.format(f)) xc = xc_load(f, mode=FULL) lang = os.path.basename(f) # ------------------------------------------- # Test the classifier if evaluation is requested. # ------------------------------------------- if classifier_path is not None: matches, compares, acc = evaluate_classifier_on_instances(xc, classifier_obj, classifier_feats, pos_class_matrix, gold_tagmap=g_tm) outstream.write('{},{},{},{:.2f}\n'.format(lang, matches, compares, acc)) class_matches += matches class_compares += compares # ------------------------------------------- # Test alignment if requested. # ------------------------------------------- if eval_alignment: mas.add_corpus('gold', INTENT_ALN_MANUAL, lang, xc) EVAL_LOG.log(NORM_LEVEL, "Evaluating heuristic methods...") evaluate_heuristic_methods_on_file(f, xc, mas, classifier_obj, tagger, lang) EVAL_LOG.log(NORM_LEVEL, "Evaluating statistical methods...") evaluate_statistic_methods_on_file(f, xc, mas, classifier_obj, tagger, lang) # ------------------------------------------- # Test DS Projection if requested # ------------------------------------------- if eval_ds: evaluate_ds_projections_on_file(lang, xc, ds_plma, outstream=outstream) outstream.write('{}\n'.format(ds_plma)) # ------------------------------------------- # Test POS Projection # ------------------------------------------- if eval_posproj: evaluate_pos_projections_on_file(lang, xc, pos_plma, pos_proj_matrix, tagger, gold_tagmap=g_tm, trans_tagmap=t_tm, outstream=outstream) if e_tagger is not None: evaluate_lang_pos(lang, xc, e_tagger, pos_pla, gold_tagmap=g_tm, outstream=outstream) if eval_alignment: mas.eval_all(outstream=outstream) if eval_ds: outstream.write('{}\n'.format(ds_plma)) if e_tagger is not None: outstream.write('{},{},{},{:.2f}\n'.format(lang, pos_pla.all_matches(), pos_pla.fulltotal(), pos_pla.accuracy())) e_tagger.close() # Report the POS tagging accuracy... if classifier_path is not None: outstream.write("ALL...\n") outstream.write('{},{},{:.2f}\n'.format(class_matches, class_compares, class_matches/class_compares*100)) outstream.write('{}\n'.format(pos_class_matrix)) if eval_posproj: outstream.write('{}\n'.format(pos_proj_matrix)) outstream.close()