def train(args):
if args.task is not None:
feature_columns, label_columns, stop_metric, eval_metrics = TASKS[
args.task]
else:
raise NotImplementedError
if args.exp_dir is None:
args.exp_dir = 'autogluon_{}'.format(args.task)
model = task.fit(train_data=args.train_file,
label=label_columns,
feature_columns=feature_columns,
output_directory=args.exp_dir,
stopping_metric=stop_metric,
ngpus_per_trial=1,
eval_metric=eval_metrics)
dev_metrics_scores = model.evaluate(args.dev_file, metrics=eval_metrics)
with open(os.path.join(args.exp_dir, 'final_model_dev_score.json'),
'w') as of:
json.dump(dev_metrics_scores, of)
dev_prediction = model.predict(args.dev_file)
with open(os.path.join(args.exp_dir, 'dev_predictions.txt'), 'w') as of:
for ele in dev_prediction:
of.write(str(ele) + '\n')
model.save(os.path.join(args.exp_dir, 'saved_model'))
model = task.load(os.path.join(args.exp_dir, 'saved_model'))
test_prediction = model.predict(args.test_file)
with open(os.path.join(args.exp_dir, 'test_predictions.txt'), 'w') as of:
for ele in test_prediction:
of.write(str(ele) + '\n')
def test_mixed_column_type():
train_data = load_pd.load('https://autogluon-text.s3-accelerate.amazonaws.com/'
'glue/sts/train.parquet')
dev_data = load_pd.load('https://autogluon-text.s3-accelerate.amazonaws.com/'
'glue/sts/dev.parquet')
rng_state = np.random.RandomState(123)
train_perm = rng_state.permutation(len(train_data))
valid_perm = rng_state.permutation(len(dev_data))
train_data = train_data.iloc[train_perm[:100]]
dev_data = dev_data.iloc[valid_perm[:10]]
# Add more columns as feature
train_data = pd.DataFrame({'sentence1': train_data['sentence1'],
'sentence2': train_data['sentence2'],
'sentence3': train_data['sentence2'],
'categorical0': train_data['genre'],
'numerical0': train_data['score'],
'genre': train_data['genre'],
'score': train_data['score']})
dev_data = pd.DataFrame({'sentence1': dev_data['sentence1'],
'sentence2': dev_data['sentence2'],
'sentence3': dev_data['sentence2'],
'categorical0': dev_data['genre'],
'numerical0': dev_data['score'],
'genre': dev_data['genre'],
'score': dev_data['score']})
# Train Regression
predictor1 = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='score', num_trials=1,
verbosity=4,
ngpus_per_trial=1,
output_directory='./sts_score',
plot_results=False)
dev_rmse = predictor1.evaluate(dev_data, metrics=['rmse'])
verify_predictor_save_load(predictor1, dev_data)
# Train Classification
predictor2 = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='genre', num_trials=1,
verbosity=4,
ngpus_per_trial=1,
output_directory='./sts_genre',
plot_results=False)
dev_rmse = predictor2.evaluate(dev_data, metrics=['acc'])
verify_predictor_save_load(predictor2, dev_data, verify_proba=True)
# Specify the feature column
predictor3 = task.fit(train_data,
hyperparameters=test_hyperparameters,
feature_columns=['sentence1', 'sentence3', 'categorical0'],
label='score', num_trials=1,
verbosity=4,
ngpus_per_trial=1,
output_directory='./sts_score',
plot_results=False)
dev_rmse = predictor1.evaluate(dev_data, metrics=['rmse'])
verify_predictor_save_load(predictor3, dev_data)
def test_no_text_column_raise():
data = [('😁😁😁😁😁😁', 'grin')] * 20 + [('😃😃😃😃😃😃😃😃', 'smile')
] * 50 + [('😉😉😉', 'wink')] * 30
df = pd.DataFrame(data, columns=['data', 'label'])
with pytest.raises(NotImplementedError):
predictor = task.fit(df, label='label', verbosity=4)
def predict(args):
model = task.load(args.model_dir)
test_prediction = model.predict(args.test_file)
if args.exp_dir is None:
args.exp_dir = '.'
with open(os.path.join(args.exp_dir, 'test_predictions.txt'), 'w') as of:
for ele in test_prediction:
of.write(str(ele) + '\n')
def test_cpu_only_raise():
train_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/'
'glue/sst/train.parquet')
dev_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/'
'glue/sst/dev.parquet')
rng_state = np.random.RandomState(123)
train_perm = rng_state.permutation(len(train_data))
valid_perm = rng_state.permutation(len(dev_data))
train_data = train_data.iloc[train_perm[:100]]
dev_data = dev_data.iloc[valid_perm[:10]]
with pytest.raises(RuntimeError):
predictor = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='label',
num_trials=1,
ngpus_per_trial=0,
verbosity=4,
output_directory='./sst',
plot_results=False)
os.environ['AUTOGLUON_TEXT_TRAIN_WITHOUT_GPU'] = '1'
predictor = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='label',
num_trials=1,
ngpus_per_trial=0,
verbosity=4,
output_directory='./sst',
plot_results=False)
os.environ['AUTOGLUON_TEXT_TRAIN_WITHOUT_GPU'] = '0'
with pytest.raises(RuntimeError):
predictor = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='label',
num_trials=1,
ngpus_per_trial=0,
verbosity=4,
output_directory='./sst',
plot_results=False)
def test_no_job_finished_raise():
train_data = load_pd.load('https://autogluon-text.s3-accelerate.amazonaws.com/'
'glue/sst/train.parquet')
with pytest.raises(RuntimeError):
# Setting a very small time limits to trigger the bug
predictor = task.fit(train_data, hyperparameters=test_hyperparameters,
label='label', num_trials=1,
ngpus_per_trial=0,
verbosity=4,
time_limits=10,
output_directory='./sst_raise',
plot_results=False)
def test_emoji():
data = []
for i in range(50):
data.append(('😁' * (i + 1), 'grin'))
for i in range(30):
data.append(('😃' * (i + 1), 'smile'))
for i in range(20):
data.append(('😉' * (i + 1), 'wink'))
df = pd.DataFrame(data, columns=['data', 'label'])
predictor = task.fit(df, label='label', verbosity=3)
def test_empty_text_item():
train_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/glue/sts/train.parquet')
rng_state = np.random.RandomState(123)
train_perm = rng_state.permutation(len(train_data))
train_data = train_data.iloc[train_perm[:100]]
train_data.iat[0, 0] = None
train_data.iat[10, 0] = None
predictor = task.fit(train_data, hyperparameters=test_hyperparameters,
label='score', num_trials=1,
ngpus_per_trial=0,
verbosity=4,
output_directory='./sts_empty_text_item',
plot_results=False)
def verify_predictor_save_load(predictor, df, verify_proba=False,
verify_embedding=True):
with tempfile.TemporaryDirectory() as root:
predictor.save(root)
predictions = predictor.predict(df)
loaded_predictor = task.load(root)
predictions2 = loaded_predictor.predict(df)
npt.assert_equal(predictions, predictions2)
if verify_proba:
predictions_prob = predictor.predict_proba(df)
predictions2_prob = loaded_predictor.predict_proba(df)
npt.assert_equal(predictions_prob, predictions2_prob)
if verify_embedding:
embeddings = predictor.extract_embedding(df)
assert embeddings.shape[0] == len(df)
def test_sts():
train_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/glue/sts/train.parquet')
dev_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/glue/sts/dev.parquet')
rng_state = np.random.RandomState(123)
train_perm = rng_state.permutation(len(train_data))
valid_perm = rng_state.permutation(len(dev_data))
train_data = train_data.iloc[train_perm[:100]]
dev_data = dev_data.iloc[valid_perm[:10]]
predictor = task.fit(train_data, hyperparameters=test_hyperparameters,
label='score', num_trials=1,
verbosity=4,
ngpus_per_trial=1,
output_directory='./sts',
plot_results=False)
dev_rmse = predictor.evaluate(dev_data, metrics=['rmse'])
verify_predictor_save_load(predictor, dev_data)
def test_mrpc():
train_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/glue/mrpc/train.parquet'
)
dev_data = load_pd.load(
'https://autogluon-text.s3-accelerate.amazonaws.com/glue/mrpc/dev.parquet'
)
rng_state = np.random.RandomState(123)
train_perm = rng_state.permutation(len(train_data))
valid_perm = rng_state.permutation(len(dev_data))
train_data = train_data.iloc[train_perm[:100]]
dev_data = dev_data.iloc[valid_perm[:10]]
predictor = task.fit(train_data,
hyperparameters=test_hyperparameters,
label='label',
num_trials=1,
verbosity=4,
ngpus_per_trial=1,
output_directory='./mrpc',
plot_results=False)
dev_acc = predictor.evaluate(dev_data, metrics=['acc'])
dev_prediction = predictor.predict(dev_data)
dev_pred_prob = predictor.predict_proba(dev_data)
def __init__(self):
self.predictor_rank = task2.load(
'/content/common-alternusvera/PU/ag_predict')
self.predictor_sts = task.load(
'/content/common-alternusvera/PU/saved_dir')
