if 'pickle' in filename_wordsX:
wordsX = IO.readPickledWords(filename_wordsX)
wordsY = IO.readPickledWords(filename_wordsY)
else:
wordsX = IO.readWords(filename_wordsX)
wordsY = IO.readWords(filename_wordsY)
if filename_lexicon == 'None': # we don't have a lexicon. assume identity.
log(100, 'Using identity lexicon')
lex = None
gold_lex = dict() #
for w in wordsX.words:
gold_lex[w] = [w]
log(100, gold_lex)
else:
lex = BilexiconUtil.readLexicon(filename_lexicon)
(gold_lex, times) = BilexiconUtil.filterLexicon(lex, wordsX.words, wordsY.words)
log(100, 'Done filtering gold lexicon')
seed = []
used_targets = set()
for source_word in wordsX.words: # go over source
if source_word in gold_lex: # check source in lexicon
translations = gold_lex[source_word] # get translations of source
for translation in translations: # then, append translations for non-translated sources.
if translation in wordsY.words and translation not in used_targets:
seed.append((source_word, translation))
used_targets.add(translation)
print "%s,%s" % (source_word, translation)
break
else:
# cmd line args
filename_wordsX = sys.argv[1]
filename_wordsY = sys.argv[2]
filename_seed = sys.argv[3]
options = parseOptions()
# read input files
wordsX, wordsY, seed_list = readInput(options, filename_wordsX, filename_wordsY, filename_seed)
N = len(wordsX.words)
options.matchingFilename = "results/matching_N=%d_expid=%d_alpha=%2.2f_T=%d.txt" % (
N,
options.exp_id,
options.alpha,
options.T,
)
NSeed = len(seed_list.X)
if options.filename_lexicon is not None:
lex = BU.readLexicon(options.filename_lexicon)
(gold_lex, times) = BU.filterLexicon(lex, wordsX.words[:-NSeed], wordsY.words[:-NSeed])
options.gold_lex = gold_lex
print "Gold lexicon contains", len(gold_lex), "pairs."
else:
options.gold_lex = None
print colored("WARNING: No gold lexicon", "red")
print >> sys.stderr, "==============#########=========="
print >> sys.stderr, "Starting mCCA:"
print >> sys.stderr, NSeed, "seed pairs:", zip(seed_list.X, seed_list.Y)
(wordsX, wordsY, edge_cost, cost) = mcca(options, wordsX, wordsY, seed_list)
log(0, "hamming distance:", perm.hamming(wordsX.words, wordsY.words))
bell()
