def main(infile, verbose=False): lm = ngrams.build_ngram_model(jdecode.mtg_open_file( str(os.path.join(datadir, 'output.txt'))), 3, separate_lines=True, verbose=True) stats = get_statistics(infile, lm=lm, sep=True, verbose=verbose) print_statistics(stats)
def main(fname, oname, n=20, verbose=False): cbow = CBOW() realcards = jdecode.mtg_open_file(str(os.path.join(datadir, 'output.txt')), verbose=verbose) real_by_name = {c.name: c for c in realcards} lm = ngrams.build_ngram_model(realcards, 3, separate_lines=separate_lines, verbose=verbose) cards = jdecode.mtg_open_file(fname, verbose=verbose) stats = analysis.get_statistics(fname, lm=lm, sep=separate_lines, verbose=verbose) selected = [] for i in range(0, len(cards)): if select_card(cards, stats, i): selected += [(i, cards[i])] limit = 3000 random.shuffle(selected) #selected = selected[:limit] if verbose: print(('computing nearest cards for ' + str(len(selected)) + ' candindates...')) cbow_nearest = cbow.nearest_par([i_c[1] for i_c in selected]) for i in range(0, len(selected)): (j, card) = selected[i] selected[i] = (j, card, cbow_nearest[i]) if verbose: print('...done') final = [] for (i, card, nearest) in selected: for dist, rname in nearest: realcard = real_by_name[rname] if compare_to_real(card, realcard): final += [(i, card, realcard, dist)] break for (i, card, realcard, dist) in final: print('-- real --') print(realcard.format()) print('-- fake --') print(card.format()) print('-- stats --') perp_per = stats['ngram']['perp_per'][i] perp_max = stats['ngram']['perp_max'][i] print(dist) print(perp_per) print(perp_max) print('----') if not oname is None: with open(oname, 'wt') as ofile: ofile.write(utils.mse_prepend) for (i, card, realcard, dist) in final: name = realcard.name writecard(realcard, name, ofile) writecard(card, name, ofile) ofile.write('version control:\n\ttype: none\napprentice code: ') # Copy whatever output file is produced, name the copy 'set' (yes, no extension). if os.path.isfile('set'): print('ERROR: tried to overwrite existing file "set" - aborting.') return shutil.copyfile(oname, 'set') # Use the freaky mse extension instead of zip. with zipfile.ZipFile(oname+'.mse-set', mode='w') as zf: try: # Zip up the set file into oname.mse-set. zf.write('set') finally: if verbose: print('Made an MSE set file called ' + oname + '.mse-set.') # The set file is useless outside the .mse-set, delete it. os.remove('set')
def main(fname, oname, n=20, verbose=False): cbow = CBOW() realcards = jdecode.mtg_open_file(str(os.path.join(datadir, 'output.txt')), verbose=verbose) real_by_name = {c.name: c for c in realcards} lm = ngrams.build_ngram_model(realcards, 3, separate_lines=separate_lines, verbose=verbose) cards = jdecode.mtg_open_file(fname, verbose=verbose) stats = analysis.get_statistics(fname, lm=lm, sep=separate_lines, verbose=verbose) selected = [] for i in range(0, len(cards)): if select_card(cards, stats, i): selected += [(i, cards[i])] limit = 3000 random.shuffle(selected) #selected = selected[:limit] if verbose: print('computing nearest cards for ' + str(len(selected)) + ' candindates...') cbow_nearest = cbow.nearest_par(map(lambda (i, c): c, selected)) for i in range(0, len(selected)): (j, card) = selected[i] selected[i] = (j, card, cbow_nearest[i]) if verbose: print('...done') final = [] for (i, card, nearest) in selected: for dist, rname in nearest: realcard = real_by_name[rname] if compare_to_real(card, realcard): final += [(i, card, realcard, dist)] break for (i, card, realcard, dist) in final: print '-- real --' print realcard.format() print '-- fake --' print card.format() print '-- stats --' perp_per = stats['ngram']['perp_per'][i] perp_max = stats['ngram']['perp_max'][i] print dist print perp_per print perp_max print '----' if not oname is None: with open(oname, 'wt') as ofile: ofile.write(utils.mse_prepend) for (i, card, realcard, dist) in final: name = realcard.name writecard(realcard, name, ofile) writecard(card, name, ofile) ofile.write('version control:\n\ttype: none\napprentice code: ') # Copy whatever output file is produced, name the copy 'set' (yes, no extension). if os.path.isfile('set'): print 'ERROR: tried to overwrite existing file "set" - aborting.' return shutil.copyfile(oname, 'set') # Use the freaky mse extension instead of zip. with zipfile.ZipFile(oname+'.mse-set', mode='w') as zf: try: # Zip up the set file into oname.mse-set. zf.write('set') finally: if verbose: print 'Made an MSE set file called ' + oname + '.mse-set.' # The set file is useless outside the .mse-set, delete it. os.remove('set')
def main(infile, verbose = False): lm = ngrams.build_ngram_model(jdecode.mtg_open_file(str(os.path.join(datadir, 'output.txt'))), 3, separate_lines=True, verbose=True) stats = get_statistics(infile, lm=lm, sep=True, verbose=verbose) print_statistics(stats)