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 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 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 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(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)
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:]
print("X_train.shape, y_train.shape, X_test.shape, y_test.shape")
print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
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: "classification" for task in tasks}
model_params = {
"batch_size": None,
"data_shape": train_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=LogisticRegression())
# 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])
print("train_scores")
print(train_scores)
# Eval model on test
transformers = []
evaluator = Evaluator(model, test_dataset, transformers, verbosity=verbosity)
scores = evaluator.compute_model_performance([classification_metric])
print("scores")
print(scores)
assert scores[classification_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}
model_params = {}
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)
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 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_ECFP_regression_sharded_API(self):
"""Test of singletask RF ECFP regression API: sharded edition."""
splittype = "scaffold"
featurizer = CircularFingerprint(size=1024)
model_params = {}
tasks = ["label"]
task_type = "regression"
task_types = {task: task_type for task in tasks}
input_file = os.path.join(
self.current_dir, "../../../datasets/pdbbind_core_df.pkl.gz")
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)
# We set shard size above to force the creation of multiple shards of the data.
# pdbbind_core has ~200 examples.
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 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_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] > 0.9
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 test_sklearn_skewed_classification_overfit(self):
"""Test sklearn models can overfit 0/1 datasets with few actives."""
tasks = ["task0"]
task_types = {task: "classification" for task in tasks}
n_samples = 100
n_features = 3
n_tasks = len(tasks)
# 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 = {
"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()
# 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_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_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)
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)
# Eval model on train
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 transformer in transformers:
transformer.transform(train_dataset)
for transformer in transformers:
transformer.transform(test_dataset)
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()
train_evaluator = Evaluator(model, train_dataset, transformers, verbosity=verbosity)
train_scores = train_evaluator.compute_model_performance([regression_metric])
print("train_scores")
print(train_scores)
assert train_scores[regression_metric.name] > .5
# 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
#Append trains cores and results
predict_train = pd.DataFrame(
model.predict(train_dataset),
columns=['prediction']).to_csv(modeldir + "predict_train_" +
str(estimator) + '.csv')
predict_valid = pd.DataFrame(
model.predict(valid_dataset),
columns=['prediction']).to_csv(modeldir + "predict_validation_" +
str(estimator) + '.csv')
#Append measures
estimators = np.concatenate((estimators, [estimator, estimator]))
metrics = np.concatenate((metrics, ["r2", "mse"]))
# Fit trained model
model.save()
print("Dataframe for n_estimator selection")
df = pd.DataFrame({
'nestimators': estimators,
'train_scores': train_results,
'result_scores': test_results,
'metric': metrics
})
df.to_csv(modeldir + "RandomForestAnalysis.csv", index=False)
try:
from notifyending import *
notify_ending("Finished fitting random forest")
except:
print("Random forest")
