def randomvalidate(model, lm, emissions, cfd):
args = Namespace()
args.targetlang="gn"
## args.sourcetext="/space/Europarl_Intersection_preprocessed/intersection.en.txt.ascii.taggedlemmas"
## args.targettext="/space/Europarl_Intersection_preprocessed/intersection.es.txt.lemmas"
## args.alignments="/space/output_en_es/training.align"
args.sourcetext="/space/es_gn_bibles/bible.es.txt"
args.targettext="/space/es_gn_bibles/bible.gn.txt"
args.alignments="/space/output_es_gn/training.align"
args.fast=False
triple_sentences = learn.load_bitext(args)
tl_sentences = learn.get_target_language_sentences(triple_sentences)
sl_sentences = [source for (source,target,align) in triple_sentences]
sentence_pairs = list(zip(sl_sentences, tl_sentences))
hmmparts = HMMParts(lm, emissions, cfd)
totalcorrect = 0
totalwords = 0
for lineid in guarani.testset:
(ss, ts) = sentence_pairs[lineid]
print(" ".join(ss))
if model == "unigram":
tagged = skinnyhmm.mfs(cfd, ss)
if model == "bigram":
tagged = skinnyhmm.viterbi(lm, emissions, cfd, ss)
elif model == "trigram":
tagged = searches.beam(lm, emissions, cfd, ss, beamwidth=BEAMWIDTH)
elif model == "memm":
tagged = searches.beam_memm(ss, hmmparts, beamwidth=BEAMWIDTH)
print("ORIGINAL:", list(zip(ss,ts)))
print("TAGGED:", tagged)
predicted = [t for (s,t) in tagged]
correct = 0
print(list(zip(ts, predicted)))
for actual, pred in zip(ts, predicted):
if actual == UNTRANSLATED: continue
totalwords += 1
if actual == pred:
correct += 1
totalcorrect += 1
print("sentence accuracy:", correct / len(ss))
print("considered words:", len(ss))
accuracy = (totalcorrect / totalwords)
print("accuracy:", accuracy)
print("considered words:", totalwords)
