def supernatural_rs():
file_config = FilesConfig(
vocab_file='twitter_hashtag/twitterhashtags.vocab',
dataset_file='DataSetsEraldo/dataSetSupernatural.txt',
task='supernatural')
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
ndy = np.array(y)
print('exemplos positivos, todo dataset')
print(ndy.sum())
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
myTuner = Tuner(c, file_config)
epochs = (100, 0)
lrs = (1e-5, 1e-1)
myTuner.random_search_cv(execs=6,
epoch_limits=epochs,
lr_limits=lrs,
cv=10,
folds=f,
freeze_epochs=True,
freeze_lr=False)
print("RS finished!\n")
def test_kfold():
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
cnn_config = TCNNConfig()
cnn_config.num_epochs = 10
file_config = FilesConfig(vocab_file='twitterhashtags.vocab',
dataset_file='DataSetsEraldo/dataSetBahia.txt')
for i in range(5):
for cf in f:
model0 = TextCNN(cnn_config)
print(c.train_distribution())
c.prepare_sample(x, y, size=300)
c.sub_sampling(size=300)
print(c.x_train.shape)
t = Trainer(corpus=cf,
model=model0,
config=cnn_config,
file_config=file_config,
verbose=True)
train_acc, train_loss, val_acc, val_loss, best_epoch = t.train()
def train_cv():
ultimos_r = []
dt = []
file_config = FilesConfig(
vocab_file='twitter_hashtag/twitterhashtags.vocab',
dataset_file='DataSetsEraldo/dataSetSupernatural.txt')
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
for cv in f:
t = Trainer(corpus=cv, file_config=file_config, verbose=True)
ultimos_r.append(t.train(dt))
print(ultimos_r)
print(':)')
def pre_rs_supernatural():
file_config = FilesConfig(
vocab_file='twitter_hashtag/twitterhashtags.vocab',
dataset_file='twitter_hashtag/out.txt',
task='supernatural')
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
myTuner = Tuner(c, file_config)
epochs = (100, 6)
lrs = (1e-5, 1e-2)
myTuner.random_search_cv(execs=1,
epoch_limits=epochs,
lr_limits=lrs,
cv=1,
folds=f,
freeze_lr=True,
freeze_epochs=True)
print("PRS finished!\n")
def supernatural_lltrain():
file_config = FilesConfig(
vocab_file='twitter_hashtag/twitterhashtags.vocab',
dataset_file='twitter_hashtag/out.txt',
task='10llsupernatural')
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
cnn_config_s = TCNNConfig()
cnn_config_s.num_classes = 2
args = [
cnn_config_s,
'../experiments/1kthashtag.2019-10-21/checkpoints/model21102019-211333epc200lr0.0001.emb',
'../experiments/1kthashtag.2019-10-21/checkpoints/model21102019-211333epc200lr0.0001.convs'
]
f = RandomSplit(corpus=c, n=10, sub=350)
f.x = x
f.y = y
t = Tuner(c, file_config, callback=model_load, args=args, rand=False)
epochs = (5, 6)
lrs = (1e-5, 1e-2)
t.random_search_rsplit(execs=4,
rsplits=f,
epoch_limits=epochs,
lr_limits=lrs,
freeze_epochs=True,
freeze_lr=False,
r=10)
print("RS finished!\n")
def test_kfold_rs():
cnn_config = TCNNConfig()
cnn_config.num_epochs = 4
file_config = FilesConfig(
vocab_file='twitter_hashtag/twitterhashtags.vocab',
dataset_file='twitter_hashtag/out.txt')
c = CorpusTE(train_file='DataSetsEraldo/dataSetSupernatural.txt',
vocab_file='twitter_hashtag/twitterhashtags.vocab')
x, y = c.prepare()
print(c.size)
f = KFold(c, 3, rand=1)
f.prepare_fold(x, y)
myTuner = Tuner(c, file_config)
epochs = (10, 30)
lrs = (0.0001, 0.01)
myTuner.random_search_cv(execs=5,
epoch_limits=epochs,
lr_limits=lrs,
cv=4,
folds=f,
freeze_lr=True)
print("RS finished!\n")
