def test_sklearn_reload(self):
"""Test that trained model can be reloaded correctly."""
tasks = ["task0"]
task_types = {task: "classification" 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.random.randint(2, 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 = {
"batch_size": None,
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score,
verbosity=verbosity)
model = SklearnModel(tasks,
task_types,
model_params,
self.model_dir,
mode="classification",
model_instance=RandomForestClassifier())
# Fit trained model
model.fit(dataset)
model.save()
# Load trained model
reloaded_model = SklearnModel(tasks,
task_types,
model_params,
self.model_dir,
mode="classification")
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] > .9
def test_sklearn_classification_overfit(self):
"""Test that sklearn models can overfit simple classification 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.random.randint(2, size=(n_samples, n_tasks))
w = np.ones((n_samples, n_tasks))
dataset = NumpyDataset(X, y, w, ids)
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score, verbosity=verbosity)
sklearn_model = RandomForestClassifier()
model = SklearnModel(sklearn_model, self.model_dir)
# 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 model_builder(tasks, task_types, model_params, model_dir, verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_dir,
model_instance=RandomForestRegressor(n_estimators=500),
verbosity=verbosity)
def test_sklearn_regression(self):
"""Test that sklearn models can learn on simple regression datasets."""
np.random.seed(123)
dataset = sklearn.datasets.load_diabetes()
X, y = dataset.data, dataset.target
frac_train = .7
n_samples = len(X)
X_train, y_train = X[:frac_train * n_samples], y[:frac_train *
n_samples]
X_test, y_test = X[frac_train * n_samples:], y[frac_train * n_samples:]
train_dataset = Dataset.from_numpy(self.train_dir, X_train, y_train)
test_dataset = Dataset.from_numpy(self.test_dir, X_test, y_test)
tasks = train_dataset.get_task_names()
task_types = {task: "regression" for task in tasks}
model_params = {
"batch_size": None,
"data_shape": train_dataset.get_data_shape()
}
verbosity = "high"
regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
model = SklearnModel(tasks,
task_types,
model_params,
self.model_dir,
mode="regression",
model_instance=LinearRegression())
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on train
transformers = []
train_evaluator = Evaluator(model,
train_dataset,
transformers,
verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance(
[regression_metric])
print("train_scores")
print(train_scores)
# Eval model on test
transformers = []
evaluator = Evaluator(model,
test_dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
print("scores")
print(scores)
assert scores[regression_metric.name] > .5
def model_builder(tasks, task_types, model_params, model_dir, verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_dir,
model_instance=RandomForestClassifier(
class_weight="balanced", n_estimators=500),
verbosity=verbosity)
def model_builder(tasks,
task_types,
model_params,
model_builder,
verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_builder,
model_instance=LogisticRegression())
def test_singletask_sklearn_rf_ECFP_regression_API(self):
"""Test of singletask RF ECFP regression API."""
splittype = "scaffold"
featurizer = CircularFingerprint(size=1024)
model_params = {}
tasks = ["log-solubility"]
task_type = "regression"
task_types = {task: task_type for task in tasks}
input_file = os.path.join(self.current_dir, "example.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
model_params["data_shape"] = train_dataset.get_data_shape()
regression_metrics = [
Metric(metrics.r2_score),
Metric(metrics.mean_squared_error),
Metric(metrics.mean_absolute_error)
]
model = SklearnModel(tasks,
task_types,
model_params,
self.model_dir,
mode="regression",
model_instance=RandomForestRegressor())
# 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(regression_metrics)
# Eval model on test
evaluator = Evaluator(model,
test_dataset,
transformers,
verbosity=True)
_ = evaluator.compute_model_performance(regression_metrics)
def model_builder(tasks,
task_types,
model_params,
model_dir,
verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_dir,
mode="regression",
model_instance=LinearRegression(),
verbosity=verbosity)
def model_builder(tasks,
task_types,
model_params,
model_dir,
verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_dir,
mode="classification",
model_instance=RandomForestClassifier(),
verbosity=verbosity)
def rf_model_builder(tasks, task_types, params_dict, model_dir, verbosity=None):
"""Builds random forests given hyperparameters.
Last two arguments only for tensorflow models and ignored.
"""
n_estimators = params_dict["n_estimators"]
max_features = params_dict["max_features"]
return SklearnModel(
tasks, task_types, params_dict, model_dir,
mode="regression",
model_instance=RandomForestRegressor(n_estimators=n_estimators,
max_features=max_features))
def model_builder(tasks,
task_types,
model_params,
model_dir,
verbosity=None):
return SklearnModel(tasks,
task_types,
model_params,
model_dir,
mode="classification",
model_instance=LogisticRegression(),
verbosity=verbosity)
def model_builder(tasks,
task_types,
params_dict,
model_dir,
verbosity=verbosity):
n_estimators = params_dict["n_estimators"]
max_features = params_dict["max_features"]
return SklearnModel(tasks,
task_types,
params_dict,
model_dir,
model_instance=model_class(
n_estimators=n_estimators,
max_features=max_features))
def test_sklearn_transformed_regression(self):
"""Test that sklearn models can learn on simple transformed regression datasets."""
np.random.seed(123)
dataset = sklearn.datasets.load_diabetes()
X, y = dataset.data, dataset.target
frac_train = .7
n_samples = len(X)
n_train = int(frac_train * n_samples)
X_train, y_train = X[:n_train], y[:n_train]
X_test, y_test = X[n_train:], y[n_train:]
train_dataset = DiskDataset.from_numpy(self.train_dir, X_train,
y_train)
test_dataset = DiskDataset.from_numpy(self.test_dir, X_test, y_test)
# Eval model on train
transformers = [
NormalizationTransformer(transform_X=True, dataset=train_dataset),
ClippingTransformer(transform_X=True, dataset=train_dataset),
NormalizationTransformer(transform_y=True, dataset=train_dataset)
]
for data in [train_dataset, test_dataset]:
for transformer in transformers:
transformer.transform(data)
verbosity = "high"
regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
sklearn_model = LinearRegression()
model = SklearnModel(sklearn_model, self.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(
[regression_metric])
assert train_scores[regression_metric.name] > .5
# Eval model on test
evaluator = Evaluator(model,
test_dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([regression_metric])
assert scores[regression_metric.name] > .5
def test_singletask_sklearn_rf_RDKIT_descriptor_regression_API(self):
"""Test of singletask RF RDKIT-descriptor regression API."""
splittype = "scaffold"
featurizer = RDKitDescriptors()
tasks = ["log-solubility"]
task_type = "regression"
task_types = {task: task_type for task in tasks}
input_file = os.path.join(self.current_dir, "example.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 = [
NormalizationTransformer(transform_X=True, dataset=train_dataset),
ClippingTransformer(transform_X=True, dataset=train_dataset)]
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)
regression_metrics = [Metric(metrics.r2_score),
Metric(metrics.mean_squared_error),
Metric(metrics.mean_absolute_error)]
sklearn_model = RandomForestRegressor()
model = SklearnModel(sklearn_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(regression_metrics)
# Eval model on test
evaluator = Evaluator(model, test_dataset, transformers, verbosity=True)
_ = evaluator.compute_model_performance(regression_metrics)
def test_sklearn_regression_overfit(self):
"""Test that sklearn 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.random.rand(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 = {
"batch_size": None,
"data_shape": dataset.get_data_shape()
}
verbosity = "high"
regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
model = SklearnModel(tasks,
task_types,
model_params,
self.model_dir,
mode="regression",
model_instance=RandomForestRegressor())
# 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] > .7
def test_sklearn_classification(self):
"""Test that sklearn models can learn on simple classification datasets."""
np.random.seed(123)
dataset = sklearn.datasets.load_digits(n_class=2)
X, y = dataset.data, dataset.target
frac_train = .7
n_samples = len(X)
n_train = int(frac_train * n_samples)
X_train, y_train = X[:n_train], y[:n_train]
X_test, y_test = X[n_train:], y[n_train:]
train_dataset = DiskDataset.from_numpy(self.train_dir, X_train,
y_train)
test_dataset = DiskDataset.from_numpy(self.test_dir, X_test, y_test)
verbosity = "high"
classification_metric = Metric(metrics.roc_auc_score,
verbosity=verbosity)
sklearn_model = LogisticRegression()
model = SklearnModel(sklearn_model, self.model_dir)
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on train
transformers = []
train_evaluator = Evaluator(model,
train_dataset,
transformers,
verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance(
[classification_metric])
# Eval model on test
transformers = []
evaluator = Evaluator(model,
test_dataset,
transformers,
verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
assert scores[classification_metric.name] > .5
def __init__(self, pad=5):
self.pad = pad
self.convex_finder = ConvexHullPocketFinder(pad)
# Load binding pocket model
self.base_dir = tempfile.mkdtemp()
print("About to download trained model.")
# TODO(rbharath): Shift refined to full once trained.
call((
"wget -c http://deepchem.io.s3-website-us-west-1.amazonaws.com/trained_models/pocket_random_refined_RF.tar.gz"
).split())
call(("tar -zxvf pocket_random_refined_RF.tar.gz").split())
call(("mv pocket_random_refined_RF %s" % (self.base_dir)).split())
self.model_dir = os.path.join(self.base_dir, "pocket_random_refined_RF")
# Fit model on dataset
self.model = SklearnModel(model_dir=self.model_dir)
self.model.reload()
# Create featurizers
self.pocket_featurizer = BindingPocketFeaturizer()
self.ligand_featurizer = CircularFingerprint(size=1024)
pd.DataFrame(train_dataset.y,
columns=['prediction']).to_csv(modeldir + "train_original.csv")
pd.DataFrame(valid_dataset.y,
columns=['prediction']).to_csv(modeldir + "valid_original.csv")
for estimator in n_estimators:
print('n_estimators = {0}'.format(estimator))
#Create model
sklmodel = RandomForestRegressor(n_estimators=estimator,
criterion="mse",
max_features=max_features,
bootstrap=True,
oob_score=False,
n_jobs=int(cpus / 2))
model = SklearnModel(sklmodel, modeldir)
model.fit(train_dataset)
#Append trains cores and results
train_scores = model.evaluate(
train_dataset,
[metric, dc.metrics.Metric(dc.metrics.mae_score)])
train_results = np.concatenate(
(train_results, list(train_scores.values())))
valid_scores = model.evaluate(
valid_dataset,
[metric, dc.metrics.Metric(dc.metrics.mae_score)])
test_results = np.concatenate((test_results, list(valid_scores.values())))
#Append trains cores and results
predict_train = pd.DataFrame(
def model_builder(model_dir):
sklearn_model = LogisticRegression()
return SklearnModel(sklearn_model, model_dir)
pdbbind_task_types = {task: "regression" for task in pdbbind_tasks}
classification_metric = Metric(metrics.r2_score,
verbosity=verbosity,
mode="regression")
params_dict = {
"batch_size": None,
"data_shape": train_dataset.get_data_shape(),
}
if os.path.exists(model_dir):
shutil.rmtree(model_dir)
os.makedirs(model_dir)
model = SklearnModel(pdbbind_tasks,
pdbbind_task_types,
params_dict,
model_dir,
model_instance=RandomForestRegressor(n_estimators=500),
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")
# Get supports on test-set
support_generator = SupportGenerator(
test_dataset, range(len(test_dataset.get_task_names())), n_pos, n_neg,
n_trials, replace)
# Compute accuracies
task_scores = {
task: []
for task in range(len(test_dataset.get_task_names()))
}
for (task, support) in support_generator:
# Train model on support
sklearn_model = RandomForestClassifier(class_weight="balanced",
n_estimators=50)
model = SklearnModel(sklearn_model, model_dir)
model.fit(support)
# Test model
task_dataset = get_task_dataset_minus_support(test_dataset, support,
task)
y_pred = model.predict_proba(task_dataset)
score = metric.compute_metric(task_dataset.y, y_pred, task_dataset.w)
#print("Score on task %s is %s" % (str(task), str(score)))
task_scores[task].append(score)
# Join information for all tasks.
mean_task_scores = {}
for task in range(len(test_dataset.get_task_names())):
mean_task_scores[task] = np.mean(np.array(task_scores[task]))
print("Fold %s" % str(fold))
def model_builder(tasks, task_types, model_params, model_dir, verbosity=None):
return SklearnModel(tasks, task_types, model_params, model_dir,
model_instance=LogisticRegression(class_weight="balanced"),
verbosity=verbosity)
def generate_rf_model():
model_dir = "."
sklearn_model = RandomForestRegressor(n_estimators=500)
return SklearnModel(sklearn_model, model_dir)
def model_builder(model_dir): sklearn_model = RandomForestRegressor() return SklearnModel(sklearn_model, model_dir)
def model_builder(model_dir): sklearn_model = RandomForestClassifier() return SklearnModel(sklearn_model, model_dir)
def model_builder(model_dir):
sklearn_model = RandomForestRegressor(n_estimators=500)
return SklearnModel(sklearn_model, model_dir)
def model_builder(model_dir):
sklearn_model = RandomForestClassifier(
class_weight="balanced", n_estimators=500)
return SklearnModel(sklearn_model, model_dir)
def rf_model_builder(model_params, model_dir):
sklearn_model = RandomForestClassifier(**model_params)
return SklearnModel(sklearn_model, model_dir)
featurizer = deepchem.feat.WeaveFeaturizer(),
transformers = 2,
modelname = MPNNModel,
model_file = model_dir + "mpnn_model",
dataset_file = data_dir + 'To_predict.csv',
fname = 'PredictedMPNN.csv',
parentdir = data_dir,
newdir = newdir)
flag_predicted = False;
if len(models) == 0 or "RandomForest" in models:
print("-Evaluating Random Forest Model", flush = True)
predictchem.predict_csv_from_model(
featurizer = deepchem.feat.CircularFingerprint(size=1024),
transformers = 2,
modelname = SklearnModel(model_dir = model_dir + "random_forest"),
model_file = "", #No need for model_file
dataset_file = data_dir + 'To_predict.csv',
fname = 'PredictedForest.csv',
parentdir = data_dir,
newdir = newdir,
modeltype = "sklearn")
flag_predicted = False;
if len(models) == 0 or "KRR" in models:
print("-Evaluating Kernel Ridge Regression", flush = True)
predictchem.predict_csv_from_model(
featurizer = deepchem.feat.CircularFingerprint(size=1024),
transformers = 2,
modelname = SklearnModel(model_dir = model_dir + "krr_model"),
model_file = "", #No need for model_file
