def run_languages(args):
languages, token_map, data_split, concept_ids, ipa_to_concept = read_info()
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
results = [[
'lang', 'avg_len', 'shannon', 'test_shannon', 'test_loss', 'test_acc',
'val_loss', 'val_acc'
]]
for i, lang in enumerate(languages):
print()
print('Lang:', i, end=' ')
if args.opt:
avg_len, shannon, test_shannon, test_loss, \
test_acc, val_loss, val_acc = run_opt_language_cv(lang, token_map, concept_ids, ipa_to_concept, args)
else:
avg_len, shannon, test_shannon, test_loss, \
test_acc, val_loss, val_acc = run_language_cv(lang, token_map, concept_ids, ipa_to_concept, args)
results += [[
lang, avg_len, shannon, test_shannon, test_loss, test_acc,
val_loss, val_acc
]]
write_csv(results, '%s/%s__results.csv' % (args.rfolder, args.model))
write_csv(results, '%s/%s__results-final.csv' % (args.rfolder, args.model))
def run_languages_cv(args):
print('------------------- Start -------------------')
_, token_map, data_split, _, _ = read_info()
languages = get_languages(is_devoicing=args.is_devoicing)
token_map = add_new_symbols_to_vocab(token_map)
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
max_order = 3
results = [[
'lang', 'artificial', 'full_avg_len', 'avg_len', 'test_loss',
'val_loss'
]]
for i, lang in enumerate(languages):
for artificial in [True, False]:
print()
print(i, end=' ')
full_avg_len, avg_len, test_loss, val_loss = run_artificial_language_cv(
lang,
token_map,
args,
artificial=artificial,
max_order=max_order)
results += [[
lang, artificial, full_avg_len, avg_len, test_loss, val_loss
]]
write_csv(
results,
'%s/artificial__%s__results.csv' % (args.rfolder, args.model))
write_csv(
results,
'%s/artificial__%s__results-final.csv' % (args.rfolder, args.model))
def run_languages(args):
print('------------------- Start -------------------')
_, token_map, data_split, concept_ids, ipa_to_concepts = read_info()
languages = get_languages(is_devoicing=args.is_devoicing)
token_map = add_new_symbols_to_vocab(token_map)
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
results = [[
'lang', 'avg_len', 'test_shannon', 'test_loss', 'test_acc', 'val_loss',
'val_acc'
]]
for i, lang in enumerate(languages):
for artificial in [True, False]:
print()
print('%d. %s %s' %
(i, lang, 'artificial' if artificial else 'default'))
avg_len, shannon, test_shannon, test_loss, \
test_acc, best_epoch, val_loss, val_acc = run_artificial_language(
lang, args.is_devoicing, token_map, concept_ids, ipa_to_concepts, args, artificial=artificial)
results += [[
'%s %s' % (lang, 'art' if artificial else 'norm'), avg_len,
shannon, test_shannon, test_loss, test_acc, best_epoch,
val_loss, val_acc
]]
write_csv(
results,
'%s/artificial__%s__results.csv' % (args.rfolder, args.model))
write_csv(
results,
'%s/artificial__%s__results-final.csv' % (args.rfolder, args.model))
def run_languages_cv(args):
print('------------------- Start -------------------')
_, token_map, data_split, concept_ids, ipa_to_concepts = read_info()
languages = get_languages(is_devoicing=args.is_devoicing)
token_map = add_new_symbols_to_vocab(token_map)
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
results = [[
'lang', 'artificial', 'avg_len', 'shannon', 'test_shannon',
'test_loss', 'test_acc', 'best_epoch', 'val_loss', 'val_acc'
]]
for i, lang in enumerate(languages):
for artificial in [True, False]:
print()
print('%d. %s %s' %
(i, lang, 'artificial' if artificial else 'default'))
embedding_size, hidden_size, nlayers, dropout = \
opt_params.get_artificial_opt_params(args.model, lang, artificial, args.artificial_type, args.data)
avg_len, shannon, test_shannon, test_loss, \
test_acc, val_loss, val_acc = run_artificial_language_cv(
lang, args.is_devoicing, token_map, concept_ids, ipa_to_concepts, args,
artificial=artificial, embedding_size=embedding_size,
hidden_size=hidden_size, nlayers=nlayers, dropout=dropout)
results += [[
lang, artificial, avg_len, shannon, test_shannon, test_loss,
test_acc, val_loss, val_acc
]]
write_csv(
results,
'%s/artificial__%s__results.csv' % (args.rfolder, args.model))
write_csv(
results,
'%s/artificial__%s__results-final.csv' % (args.rfolder, args.model))
def optimize_languages(args):
print('------------------- Start -------------------')
_, token_map, data_split, concept_ids, ipa_to_concepts = read_info()
languages = get_languages(is_devoicing=args.is_devoicing)
token_map = add_new_symbols_to_vocab(token_map)
print('Model %s' % args.model)
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
n_iters = 45
bounds = np.array([[4, 256], [32, 256], [1, 2.95], [0.0, 0.5]])
n_pre_samples = 5
opt_results = [[
'lang', 'artificial', 'avg_len', 'shannon', 'test_shannon',
'test_loss', 'test_acc', 'best_epoch', 'val_loss', 'val_acc',
'embedding_size', 'hidden_size', 'nlayers', 'dropout'
]]
for i, lang in enumerate(languages):
for artificial in [True, False]:
print()
print('%d. %s %s' %
(i, lang, 'artificial' if artificial else 'default'))
sample_loss = sample_loss_getter(lang,
args.is_devoicing,
token_map,
ipa_to_concepts,
args,
artificial=artificial)
xp, yp = bayesian_optimisation(n_iters,
sample_loss,
bounds,
n_pre_samples=n_pre_samples)
opt_results += [
get_optimal_loss(lang, args.is_devoicing, artificial,
token_map, concept_ids, ipa_to_concepts, xp,
yp, args)
]
write_csv(
results, '%s/artificial__%s__baysian-results.csv' %
(args.rfolder, args.model))
write_csv(
opt_results, '%s/artificial__%s__opt-results.csv' %
(args.rfolder, args.model))
write_csv(
results, '%s/artificial__%s__baysian-results-final.csv' %
(args.rfolder, args.model))
def get_data_loaders(ffolder,
lang,
is_devoicing,
token_map,
args,
artificial=True):
_, _, data_split, _, _ = read_info()
return _get_data_loaders(data_split,
ffolder,
lang,
is_devoicing,
token_map,
args,
artificial=artificial)
def run_languages(args):
print('------------------- Start -------------------')
languages, token_map, data_split, concept_ids, _ = read_info()
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
results = [['lang', 'full_avg_len', 'avg_len', 'test_loss', 'val_loss']]
for i, lang in enumerate(languages):
print()
print('%d Language %s' % (i, lang))
full_avg_len, avg_len, test_loss, val_loss = run_language_cv(
lang, token_map, concept_ids, args)
results += [[lang, full_avg_len, avg_len, test_loss, val_loss]]
write_csv(results, '%s/unigram.csv' % (args.rfolder))
write_csv(results, '%s/unigram-final.csv' % (args.rfolder))
def run_languages(args):
print('------------------- Start -------------------')
languages, token_map, data_split, concept_ids, _ = read_info()
print('Train %d, Val %d, Test %d' %
(len(data_split[0]), len(data_split[1]), len(data_split[2])))
max_order = 3
results = [['lang', 'full_avg_len', 'avg_len', 'test_loss', 'val_loss'] +
['param_%d' % i for i in range(max_order)]]
for i, lang in enumerate(languages):
print()
print('%d Language %s' % (i, lang))
full_avg_len, avg_len, test_loss, val_loss = \
run_language_cv(lang, token_map, concept_ids, args, max_order=max_order)
results += [[lang, full_avg_len, avg_len, test_loss,
val_loss]] # + opt_params.tolist()]
write_csv(results, '%s/ngram.csv' % (args.rfolder))
write_csv(results, '%s/ngram-final.csv' % (args.rfolder))
def get_data(lang, token_map, args, artificial=True):
_, _, data_split, _, _ = read_info()
return _get_data(data_split, lang, token_map, args, artificial=artificial)
def get_data_split_cv(fold, nfolds, verbose=True):
_, _, data_split, _, _ = read_info()
concepts = [y for x in data_split for y in x]
return _get_data_split_cv(fold, nfolds, concepts, verbose=verbose)