def test_tf_classification_overfit(self):
"""Test that tensorflow models can overfit simple classification datasets."""
n_samples = 10
n_features = 3
n_tasks = 1
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
classification_metric = Metric(metrics.accuracy_score, verbosity=verbosity)
tensorflow_model = TensorflowMultiTaskClassifier(
n_tasks, n_features, self.model_dir, dropouts=[0.],
learning_rate=0.0003, weight_init_stddevs=[.1],
batch_size=n_samples, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(dataset, nb_epoch=100)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .9
def test_tf_regression_overfit(self):
"""Test that TensorFlow models can overfit simple regression datasets."""
n_samples = 10
n_features = 3
n_tasks = 1
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
regression_metric = Metric(metrics.mean_squared_error, verbosity=verbosity)
# TODO(rbharath): This breaks with optimizer="momentum". Why?
tensorflow_model = TensorflowMultiTaskRegressor(
n_tasks, n_features, self.model_dir, dropouts=[0.],
learning_rate=0.003, weight_init_stddevs=[np.sqrt(6)/np.sqrt(1000)],
batch_size=n_samples, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(dataset, nb_epoch=100)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
assert scores[regression_metric.name] < .1
def test_tf_multitask_regression_overfit(self):
"""Test tf multitask overfits tiny data."""
n_tasks = 10
n_samples = 10
n_features = 3
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
regression_metric = Metric(metrics.mean_squared_error, verbosity=verbosity,
task_averager=np.mean, mode="regression")
tensorflow_model = TensorflowMultiTaskRegressor(
n_tasks, n_features, self.model_dir, dropouts=[0.],
learning_rate=0.0003, weight_init_stddevs=[.1],
batch_size=n_samples, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(dataset, nb_epoch=50)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
assert scores[regression_metric.name] < .1
def test_tf_skewed_classification_overfit(self):
"""Test tensorflow models can overfit 0/1 datasets with few actives."""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
#n_samples = 100
n_samples = 100
n_features = 3
n_tasks = len(tasks)
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
p = .05
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.binomial(1, p, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1500],
"dropouts": [.0],
"learning_rate": 0.003,
"momentum": .9,
"batch_size": n_samples,
"num_classification_tasks": 1,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [1.],
"bias_init_consts": [1.],
"nb_epoch": 200,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score,
verbosity=verbosity)
model = TensorflowModel(tasks,
task_types,
model_params,
self.model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model,
dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .8
def test_tf_multitask_classification_overfit(self):
"""Test tf multitask overfits tiny data."""
n_tasks = 10
tasks = ["task%d" % task for task in range(n_tasks)]
task_types = {task: "classification" for task in tasks}
n_samples = 10
n_features = 3
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
#y = np.random.randint(n_classes, size=(n_samples, n_tasks))
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1000],
"dropouts": [.0],
"learning_rate": 0.0003,
"momentum": .9,
"batch_size": n_samples,
"num_classification_tasks": n_tasks,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [.1],
"bias_init_consts": [1.],
"nb_epoch": 100,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.accuracy_score,
verbosity=verbosity)
model = TensorflowModel(tasks,
task_types,
model_params,
self.model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model,
dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .9
def test_tf_reload(self):
"""Test that tensorflow models can overfit simple classification datasets."""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
n_samples = 10
n_features = 3
n_tasks = len(tasks)
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.randint(n_classes, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1000],
"dropouts": [0.0],
"learning_rate": 0.003,
"momentum": 0.9,
"batch_size": n_samples,
"num_classification_tasks": 1,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [1.0],
"bias_init_consts": [1.0],
"nb_epoch": 100,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape(),
}
verbosity = "high"
classification_metric = Metric(metrics.accuracy_score, verbosity=verbosity)
model = TensorflowModel(
tasks, task_types, model_params, self.model_dir, tf_class=TensorflowMultiTaskClassifier, verbosity=verbosity
)
# Fit trained model
model.fit(dataset)
model.save()
# Load trained model
reloaded_model = TensorflowModel(
tasks, task_types, model_params, self.model_dir, tf_class=TensorflowMultiTaskClassifier, verbosity=verbosity
)
reloaded_model.reload()
assert reloaded_model.eval_model._restored_model
# Eval model on train
transformers = []
evaluator = Evaluator(reloaded_model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > 0.9
def test_tf_regression_overfit(self):
"""Test that TensorFlow models can overfit simple regression datasets."""
tasks = ["task0"]
task_types = {task: "regression" for task in tasks}
n_samples = 10
n_features = 3
n_tasks = len(tasks)
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1000],
"dropouts": [.0],
"learning_rate": 0.003,
"momentum": .9,
"batch_size": n_samples,
"num_regression_tasks": 1,
"num_features": n_features,
"weight_init_stddevs": [np.sqrt(6) / np.sqrt(1000)],
"bias_init_consts": [1.],
"nb_epoch": 100,
"penalty": 0.0,
"optimizer": "momentum",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
regression_metric = Metric(metrics.mean_squared_error,
verbosity=verbosity)
model = TensorflowModel(tasks,
task_types,
model_params,
self.model_dir,
tf_class=TensorflowMultiTaskRegressor,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model,
dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
assert scores[regression_metric.name] < .1
def test_tf_skewed_classification_overfit(self):
"""Test tensorflow models can overfit 0/1 datasets with few actives."""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
#n_samples = 100
n_samples = 100
n_features = 3
n_tasks = len(tasks)
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
p = .05
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.binomial(1, p, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1500],
"dropouts": [.0],
"learning_rate": 0.003,
"momentum": .9,
"batch_size": n_samples,
"num_classification_tasks": 1,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [1.],
"bias_init_consts": [1.],
"nb_epoch": 200,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score, verbosity=verbosity)
model = TensorflowModel(
tasks, task_types, model_params, self.model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .8
def test_tf_multitask_regression_overfit(self):
"""Test tf multitask overfits tiny data."""
n_tasks = 10
tasks = ["task%d" % task for task in range(n_tasks)]
task_types = {task: "regression" for task in tasks}
n_samples = 10
n_features = 3
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
#y = np.random.randint(n_classes, size=(n_samples, n_tasks))
y = np.zeros((n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1000],
"dropouts": [.0],
"learning_rate": 0.0003,
"momentum": .9,
"batch_size": n_samples,
"num_regression_tasks": n_tasks,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [.1],
"bias_init_consts": [1.],
"nb_epoch": 100,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
model = TensorflowModel(
tasks, task_types, model_params, self.model_dir,
tf_class=TensorflowMultiTaskRegressor,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
assert scores[regression_metric.name] > .9
def test_tf_reload(self):
"""Test that tensorflow models can overfit simple classification datasets."""
n_samples = 10
n_features = 3
n_tasks = 1
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.randint(n_classes, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
classification_metric = Metric(metrics.accuracy_score,
verbosity=verbosity)
tensorflow_model = TensorflowMultiTaskClassifier(n_tasks,
n_features,
self.model_dir,
dropouts=[0.],
verbosity=verbosity)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(dataset)
model.save()
# Load trained model
reloaded_tensorflow_model = TensorflowMultiTaskClassifier(
n_tasks,
n_features,
self.model_dir,
dropouts=[0.],
verbosity=verbosity)
reloaded_model = TensorflowModel(reloaded_tensorflow_model,
self.model_dir)
reloaded_model.reload()
# Eval model on train
transformers = []
evaluator = Evaluator(reloaded_model,
dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .6
def test_tf_skewed_missing_classification_overfit(self):
"""TF, skewed data, few actives
Test tensorflow models overfit 0/1 datasets with missing data and few
actives. This is intended to be as close to singletask MUV datasets as
possible.
"""
n_samples = 5120
n_features = 6
n_tasks = 1
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
p = .002
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.binomial(1, p, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
y_flat, w_flat = np.squeeze(y), np.squeeze(w)
y_nonzero = y_flat[w_flat != 0]
num_nonzero = np.count_nonzero(y_nonzero)
weight_nonzero = len(y_nonzero)/num_nonzero
w_flat[y_flat != 0] = weight_nonzero
w = np.reshape(w_flat, (n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score, verbosity=verbosity)
tensorflow_model = TensorflowMultiTaskClassifier(
n_tasks, n_features, self.model_dir, dropouts=[0.],
learning_rate=0.003, weight_init_stddevs=[1.],
batch_size=n_samples, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(dataset, nb_epoch=50)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .8
def test_singletask_tf_mlp_ECFP_classification_API(self):
"""Straightforward test of Tensorflow singletask deepchem classification API."""
n_features = 1024
featurizer = CircularFingerprint(size=n_features)
tasks = ["outcome"]
input_file = os.path.join(self.current_dir, "example_classification.csv")
loader = DataLoader(tasks=tasks,
smiles_field=self.smiles_field,
featurizer=featurizer,
verbosity="low")
dataset = loader.featurize(input_file, self.data_dir)
splitter = ScaffoldSplitter()
train_dataset, test_dataset = splitter.train_test_split(
dataset, self.train_dir, self.test_dir)
transformers = [
NormalizationTransformer(transform_y=True, dataset=train_dataset)]
for dataset in [train_dataset, test_dataset]:
for transformer in transformers:
transformer.transform(dataset)
classification_metrics = [Metric(metrics.roc_auc_score),
Metric(metrics.matthews_corrcoef),
Metric(metrics.recall_score),
Metric(metrics.accuracy_score)]
tensorflow_model = TensorflowMultiTaskClassifier(
len(tasks), n_features, self.model_dir)
model = TensorflowModel(tensorflow_model, self.model_dir)
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on train
evaluator = Evaluator(model, train_dataset, transformers, verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)
# Eval model on test
evaluator = Evaluator(model, test_dataset, transformers, verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)
def test_singletask_tf_mlp_ECFP_classification_API(self):
"""Straightforward test of Tensorflow singletask deepchem classification API."""
splittype = "scaffold"
output_transformers = []
input_transformers = []
task_type = "classification"
featurizer = CircularFingerprint(size=1024)
tasks = ["outcome"]
task_type = "classification"
task_types = {task: task_type for task in tasks}
input_file = os.path.join(self.current_dir,
"example_classification.csv")
loader = DataLoader(tasks=tasks,
smiles_field=self.smiles_field,
featurizer=featurizer,
verbosity="low")
dataset = loader.featurize(input_file, self.data_dir)
splitter = ScaffoldSplitter()
train_dataset, test_dataset = splitter.train_test_split(
dataset, self.train_dir, self.test_dir)
input_transformers = []
output_transformers = [
NormalizationTransformer(transform_y=True, dataset=train_dataset)
]
transformers = input_transformers + output_transformers
for dataset in [train_dataset, test_dataset]:
for transformer in transformers:
transformer.transform(dataset)
model_params = {
"batch_size": 2,
"num_classification_tasks": 1,
"num_features": 1024,
"layer_sizes": [1024],
"weight_init_stddevs": [1.],
"bias_init_consts": [0.],
"dropouts": [.5],
"num_classes": 2,
"nb_epoch": 1,
"penalty": 0.0,
"optimizer": "adam",
"learning_rate": .001,
"data_shape": train_dataset.get_data_shape()
}
classification_metrics = [
Metric(metrics.roc_auc_score),
Metric(metrics.matthews_corrcoef),
Metric(metrics.recall_score),
Metric(metrics.accuracy_score)
]
model = TensorflowModel(tasks,
task_types,
model_params,
self.model_dir,
tf_class=TensorflowMultiTaskClassifier)
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on train
evaluator = Evaluator(model,
train_dataset,
transformers,
verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)
# Eval model on test
evaluator = Evaluator(model,
test_dataset,
transformers,
verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)
train_dataset = DiskDataset.from_numpy(train_dir, X_train, y_train,
w_train, ids_train, pdbbind_tasks)
valid_dataset = DiskDataset.from_numpy(valid_dir, X_valid, y_valid,
w_valid, ids_valid, pdbbind_tasks)
classification_metric = Metric(metrics.pearson_r2_score, verbosity=verbosity,
mode="regression")
n_features = dataset.get_data_shape()[0]
tensorflow_model = TensorflowMultiTaskRegressor(
len(pdbbind_tasks), n_features, model_dir, dropouts=[.25],
learning_rate=0.0003, weight_init_stddevs=[.1],
batch_size=64, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, model_dir)
# Fit trained model
model.fit(train_dataset, nb_epoch=20)
model.save()
train_evaluator = Evaluator(model, train_dataset, transformers, verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance([classification_metric])
print("Train scores")
print(train_scores)
valid_evaluator = Evaluator(model, valid_dataset, transformers, verbosity=verbosity)
valid_scores = valid_evaluator.compute_model_performance([classification_metric])
print("Validation scores")
print(valid_scores)
def test_tf_skewed_missing_classification_overfit(self):
"""TF, skewed data, few actives
Test tensorflow models overfit 0/1 datasets with missing data and few
actives. This is intended to be as close to singletask MUV datasets as
possible.
"""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
n_samples = 5120
n_features = 6
n_tasks = len(tasks)
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
p = .002
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.binomial(1, p, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
print("np.count_nonzero(y)")
print(np.count_nonzero(y))
##### DEBUG
y_flat, w_flat = np.squeeze(y), np.squeeze(w)
y_nonzero = y_flat[w_flat != 0]
num_nonzero = np.count_nonzero(y_nonzero)
weight_nonzero = len(y_nonzero) / num_nonzero
print("weight_nonzero")
print(weight_nonzero)
w_flat[y_flat != 0] = weight_nonzero
w = np.reshape(w_flat, (n_samples, n_tasks))
print("np.amin(w), np.amax(w)")
print(np.amin(w), np.amax(w))
##### DEBUG
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1200],
"dropouts": [.0],
"learning_rate": 0.003,
"momentum": .9,
"batch_size": 75,
"num_classification_tasks": 1,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [1.],
"bias_init_consts": [1.],
"nb_epoch": 250,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score,
verbosity=verbosity)
model = TensorflowModel(tasks,
task_types,
model_params,
self.model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model,
dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .8
# Do train/valid split.
train_dataset, valid_dataset = tox21_datasets
# Fit models
classification_metric = Metric(metrics.roc_auc_score, np.mean,
verbosity=verbosity,
mode="classification")
tensorflow_model = TensorflowMultiTaskClassifier(
len(tox21_tasks), n_features, model_dir, dropouts=[.25],
learning_rate=0.0003, weight_init_stddevs=[1.],
batch_size=32, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, model_dir)
# Fit trained model
model.fit(train_dataset)
model.save()
train_evaluator = Evaluator(model, train_dataset, transformers,
verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance(
[classification_metric])
print("Train scores")
print(train_scores)
valid_evaluator = Evaluator(model, valid_dataset, transformers,
verbosity=verbosity)
valid_scores = valid_evaluator.compute_model_performance([classification_metric])
print("Validation scores")
def test_tf_skewed_missing_classification_overfit(self):
"""TF, skewed data, few actives
Test tensorflow models overfit 0/1 datasets with missing data and few
actives. This is intended to be as close to singletask MUV datasets as
possible.
"""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
n_samples = 5120
n_features = 6
n_tasks = len(tasks)
n_classes = 2
# Generate dummy dataset
np.random.seed(123)
p = .002
ids = np.arange(n_samples)
X = np.random.rand(n_samples, n_features)
y = np.random.binomial(1, p, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
y_flat, w_flat = np.squeeze(y), np.squeeze(w)
y_nonzero = y_flat[w_flat != 0]
num_nonzero = np.count_nonzero(y_nonzero)
weight_nonzero = len(y_nonzero)/num_nonzero
w_flat[y_flat != 0] = weight_nonzero
w = np.reshape(w_flat, (n_samples, n_tasks))
dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)
model_params = {
"layer_sizes": [1200],
"dropouts": [.0],
"learning_rate": 0.003,
"momentum": .9,
"batch_size": 75,
"num_classification_tasks": 1,
"num_classes": n_classes,
"num_features": n_features,
"weight_init_stddevs": [1.],
"bias_init_consts": [1.],
"nb_epoch": 250,
"penalty": 0.0,
"optimizer": "adam",
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score, verbosity=verbosity)
model = TensorflowModel(
tasks, task_types, model_params, self.model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(dataset)
model.save()
# Eval model on train
transformers = []
evaluator = Evaluator(model, dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .8
train_dataset = DiskDataset.from_numpy(train_dir, X_train, y_train,
w_train, ids_train, pdbbind_tasks)
valid_dataset = DiskDataset.from_numpy(valid_dir, X_valid, y_valid,
w_valid, ids_valid, pdbbind_tasks)
classification_metric = Metric(metrics.pearson_r2_score, verbosity=verbosity,
mode="regression")
n_features = dataset.get_data_shape()[0]
tensorflow_model = TensorflowMultiTaskRegressor(
len(pdbbind_tasks), n_features, model_dir, dropouts=[.25],
learning_rate=0.0003, weight_init_stddevs=[.1],
batch_size=64, verbosity=verbosity)
model = TensorflowModel(tensorflow_model, model_dir)
# Fit trained model
model.fit(train_dataset, nb_epoch=20)
model.save()
train_evaluator = Evaluator(model, train_dataset, transformers, verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance([classification_metric])
print("Train scores")
print(train_scores)
valid_evaluator = Evaluator(model, valid_dataset, transformers, verbosity=verbosity)
valid_scores = valid_evaluator.compute_model_performance([classification_metric])
print("Validation scores")
print(valid_scores)
"num_classes": 2,
"penalty": .0,
"optimizer": "momentum",
"learning_rate": .001,
"momentum": .9,
}
if os.path.exists(model_dir):
shutil.rmtree(model_dir)
os.makedirs(model_dir)
model = TensorflowModel(pcba_tasks, pcba_task_types, params_dict, model_dir,
tf_class=TensorflowMultiTaskClassifier,
verbosity=verbosity)
# Fit trained model
model.fit(train_dataset)
model.save()
train_evaluator = Evaluator(model, train_dataset, transformers, verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance([classification_metric])
print("Train scores")
print(train_scores)
valid_evaluator = Evaluator(model, valid_dataset, transformers, verbosity=verbosity)
valid_scores = valid_evaluator.compute_model_performance([classification_metric])
print("Validation scores")
print(valid_scores)
def test_singletask_tf_mlp_ECFP_classification_API(self):
"""Straightforward test of Tensorflow singletask deepchem classification API."""
splittype = "scaffold"
output_transformers = []
input_transformers = []
task_type = "classification"
featurizer = CircularFingerprint(size=1024)
tasks = ["outcome"]
task_type = "classification"
task_types = {task: task_type for task in tasks}
input_file = os.path.join(self.current_dir, "example_classification.csv")
loader = DataLoader(tasks=tasks,
smiles_field=self.smiles_field,
featurizer=featurizer,
verbosity="low")
dataset = loader.featurize(input_file, self.data_dir)
splitter = ScaffoldSplitter()
train_dataset, test_dataset = splitter.train_test_split(
dataset, self.train_dir, self.test_dir)
input_transformers = []
output_transformers = [
NormalizationTransformer(transform_y=True, dataset=train_dataset)]
transformers = input_transformers + output_transformers
for dataset in [train_dataset, test_dataset]:
for transformer in transformers:
transformer.transform(dataset)
model_params = {
"batch_size": 2,
"num_classification_tasks": 1,
"num_features": 1024,
"layer_sizes": [1024],
"weight_init_stddevs": [1.],
"bias_init_consts": [0.],
"dropouts": [.5],
"num_classes": 2,
"nb_epoch": 1,
"penalty": 0.0,
"optimizer": "adam",
"learning_rate": .001,
"data_shape": train_dataset.get_data_shape()
}
classification_metrics = [Metric(metrics.roc_auc_score),
Metric(metrics.matthews_corrcoef),
Metric(metrics.recall_score),
Metric(metrics.accuracy_score)]
model = TensorflowModel(
tasks, task_types, model_params, self.model_dir,
tf_class=TensorflowMultiTaskClassifier)
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on train
evaluator = Evaluator(model, train_dataset, transformers, verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)
# Eval model on test
evaluator = Evaluator(model, test_dataset, transformers, verbosity=True)
_ = evaluator.compute_model_performance(classification_metrics)