def log_best(j, all_best, n_valid, seen, lggr):
if j % 50000 == 0:
lggr.info("--iteration: %d--" % j)
lggr.info("num valid (in this iteration): %d" % n_valid)
logger.info("num unique (over all iterations): %s" % len(all_best))
logger.info("num unique (in this iteration): %s" % len(seen))
log_top_best(all_best, 5, lggr)
def log_progress():
global t
logger.info("--results--")
logger.info("num valid: %d" % num_valid)
logger.info("num unique: %s" % len(all_smiles))
logger.info("num iterations: %s" % num_iterations)
log_top_best(all_smiles, 5, logger)
t = Timer(LOG_INTERVAL, log_progress)
t.start()
def log_progress():
global t
logger.info("--results--")
logger.info("num simulations: %s" % simulations)
logger.info("num valid (in this iteration): %d" % num_valid)
logger.info("num unique (over all iterations): %s" % len(all_unique))
logger.info("num unique (in this iteration): %s" % len(seen))
log_top_best(all_unique, 5, logger)
t = Timer(LOG_INTERVAL, log_progress)
t.start()
def log_best(j, all_best, n_valid, lggr):
if j % 1000 == 0:
lggr.info("--iteration: %d--" % j)
lggr.info("num valid: %d" % n_valid)
log_top_best(all_best, 5, lggr)
end = time.time()
logger.info("--done--")
logger.info("num valid: %d" % num_valid)
best = mcts.get_best_sequence()
generated_text = ''.join(best[0])
logger.info("best generated text: %s" % generated_text)
decoded = DeepSMILESLanguageModelUtils.decode(generated_text,
start='<s>',
end='</s>')
smiles = DeepSMILESLanguageModelUtils.sanitize(decoded)
logger.info("best SMILES: %s, J: %s (%s seconds)" %
(smiles, scorer.score(smiles), str((end - start))))
log_top_best(all_smiles, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
with open(dataset, 'w') as f:
for smi in list(
reversed(sorted(all_smiles.items(),
key=lambda kv: kv[1][0])))[:keep_top_n]:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
logger.info('training new LM...')
except StopTreeSearch:
pass
t.cancel()
end = time.time()
logger.info("--done--")
logger.info("num simulations: %s" % simulations)
logger.info("num valid (in this iteration): %d" % num_valid)
logger.info("num valid (over all iterations): %d" % len(all_valid))
logger.info("num unique (over all iterations): %s" % len(all_unique))
logger.info("num unique (in this iteration): %s" % len(seen))
logger.info("best SMILES: %s, J: %s (%s seconds)" %
(current_best_smiles, current_best_score, str((end - start))))
log_top_best(all_unique, 5, logger)
logger.info("writing dataset...")
name = 'molexit-%d' % n
dataset = '../models/molexit/%s.txt' % name
dataset_scores = []
with open(dataset, 'w') as f:
for smi in list(
reversed(sorted(all_unique.items(),
key=lambda kv: kv[1][0])))[:keep_top_n]:
try:
dsmi = smiles_to_deepsmiles(smi[0].strip())
tok = DeepSMILESTokenizer(dsmi)
tokens = tok.get_tokens()
f.write(' '.join([t.value for t in tokens]))
f.write("\n")
