def fit_model(model_name, model_params, model_dir, data_dir):
"""Builds model from featurized data."""
task_type = Model.get_task_type(model_name)
train_dir = os.path.join(data_dir, "train-data")
train = Dataset(train_dir)
task_types = {task: task_type for task in train.get_task_names()}
model_params["data_shape"] = train.get_data_shape()
model = Model.model_builder(model_name, task_types, model_params)
model.fit(train)
model.save(model_dir)
def featurize_and_split(input_file, feature_dir, samples_dir, train_dir,
test_dir, splittype, feature_types, input_transforms,
output_transforms, tasks, feature_files=None):
"""Featurize inputs with NNScore and do train-test split."""
loader = DataLoader(tasks=tasks,
smiles_field="smiles",
protein_pdb_field="protein_pdb",
ligand_pdb_field="ligand_pdb",
verbose=True)
if feature_files is None:
print("About to featurize.")
samples = loader.featurize(input_file, feature_dir,
samples_dir, shard_size=8)
print("Completed Featurization")
else:
# Transform data into arrays for ML
samples = FeaturizedSamples(samples_dir, feature_files,
reload_data=False)
# Split into train/test
train_samples, test_samples = samples.train_test_split(
splittype, train_dir, test_dir)
print("Finished train test split.")
train_dataset = Dataset(train_dir, train_samples, feature_types)
test_dataset = Dataset(test_dir, test_samples, feature_types)
print("Finished creating train test datasets")
# Transforming train/test data
train_dataset.transform(input_transforms, output_transforms)
test_dataset.transform(input_transforms, output_transforms)
print("Finished Transforming train test data.")
return train_dataset, test_dataset
def _featurize_train_test_split(self,
splittype,
compound_featurizers,
complex_featurizers,
input_transforms,
output_transforms,
input_file,
tasks,
protein_pdb_field=None,
ligand_pdb_field=None,
user_specified_features=None,
shard_size=100):
# Featurize input
featurizers = compound_featurizers + complex_featurizers
input_file = os.path.join(self.current_dir, input_file)
featurizer = DataFeaturizer(
tasks=tasks,
smiles_field=self.smiles_field,
protein_pdb_field=protein_pdb_field,
ligand_pdb_field=ligand_pdb_field,
compound_featurizers=compound_featurizers,
complex_featurizers=complex_featurizers,
user_specified_features=user_specified_features,
verbose=True)
#Featurizes samples and transforms them into NumPy arrays suitable for ML.
#returns an instance of class FeaturizedSamples()
samples = featurizer.featurize(input_file,
self.feature_dir,
self.samples_dir,
shard_size=shard_size)
# Splits featurized samples into train/test
train_samples, test_samples = samples.train_test_split(
splittype, self.train_dir, self.test_dir)
use_user_specified_features = False
if user_specified_features is not None:
use_user_specified_features = True
train_dataset = Dataset(
data_dir=self.train_dir,
samples=train_samples,
featurizers=featurizers,
tasks=tasks,
use_user_specified_features=use_user_specified_features)
test_dataset = Dataset(
data_dir=self.test_dir,
samples=test_samples,
featurizers=featurizers,
tasks=tasks,
use_user_specified_features=use_user_specified_features)
# Transforming train/test data
train_dataset.transform(input_transforms, output_transforms)
test_dataset.transform(input_transforms, output_transforms)
return train_dataset, test_dataset
def train_test_split(input_transforms, output_transforms, feature_types, splittype, data_dir):
"""Saves transformed model."""
samples_dir = os.path.join(data_dir, "samples")
samples = FeaturizedSamples(samples_dir, reload_data=True)
print("Split data into train/test")
train_samples_dir = os.path.join(data_dir, "train-samples")
test_samples_dir = os.path.join(data_dir, "test-samples")
train_samples, test_samples = samples.train_test_split(splittype, train_samples_dir, test_samples_dir)
train_data_dir = os.path.join(data_dir, "train-data")
test_data_dir = os.path.join(data_dir, "test-data")
print("Generating train dataset.")
train_dataset = Dataset(train_data_dir, train_samples, feature_types)
print("Generating test dataset.")
test_dataset = Dataset(test_data_dir, test_samples, feature_types)
print("Transforming train data.")
train_dataset.transform(input_transforms, output_transforms)
print("Transforming test data.")
test_dataset.transform(input_transforms, output_transforms)
def test_API(self):
"""Straightforward test of multitask deepchem classification API."""
splittype = "scaffold"
feature_types = ["ECFP"]
output_transforms = []
input_transforms = []
task_type = "classification"
# TODO(rbharath): There should be some automatic check to ensure that all
# required model_params are specified.
model_params = {"nb_hidden": 10, "activation": "relu",
"dropout": .5, "learning_rate": .01,
"momentum": .9, "nesterov": False,
"decay": 1e-4, "batch_size": 5,
"nb_epoch": 2}
model_name = "multitask_deep_classifier"
# Featurize input
featurizer = DataFeaturizer(tasks=self.tasks,
smiles_field=self.smiles_field,
verbose=True)
feature_files = featurizer.featurize(self.input_file, feature_types, self.feature_dir)
# Transform data into arrays for ML
samples = FeaturizedSamples(self.samplesdir, feature_files,
reload_data=False)
# Split into train/test
train_samples, test_samples = samples.train_test_split(
splittype, self.train_dir, self.test_dir)
train_dataset = Dataset(self.train_dir, train_samples, feature_types)
test_dataset = Dataset(self.test_dir, test_samples, feature_types)
# Transforming train/test data
train_dataset.transform(input_transforms, output_transforms)
test_dataset.transform(input_transforms, output_transforms)
# Fit model
task_types = {task: task_type for task in self.tasks}
model_params["data_shape"] = train_dataset.get_data_shape()
model = Model.model_builder(model_name, task_types, model_params)
model.fit(train_dataset)
model.save(self.model_dir)
# Eval model on train
evaluator = Evaluator(model, test_dataset, verbose=True)
with tempfile.NamedTemporaryFile() as test_csv_out:
with tempfile.NamedTemporaryFile() as test_stats_out:
evaluator.compute_model_performance(test_csv_out, test_stats_out)
def _create_model(self, splittype, feature_types, input_transforms,
output_transforms, task_type, model_params, model_name,
input_file, tasks, protein_pdb_field=None, ligand_pdb_field=None):
"""Helper method to create model for test."""
# Featurize input
input_file = os.path.join(self.current_dir, input_file)
featurizer = DataFeaturizer(tasks=tasks,
smiles_field=self.smiles_field,
protein_pdb_field=protein_pdb_field,
ligand_pdb_field=ligand_pdb_field,
verbose=True)
feature_files = featurizer.featurize(input_file, feature_types, self.feature_dir)
# Transform data into arrays for ML
samples = FeaturizedSamples(self.samplesdir, feature_files,
reload_data=False)
# Split into train/test
train_samples, test_samples = samples.train_test_split(
splittype, self.train_dir, self.test_dir)
train_dataset = Dataset(self.train_dir, train_samples, feature_types)
test_dataset = Dataset(self.test_dir, test_samples, feature_types)
# Transforming train/test data
train_dataset.transform(input_transforms, output_transforms)
test_dataset.transform(input_transforms, output_transforms)
# Fit model
task_types = {task: task_type for task in tasks}
model_params["data_shape"] = train_dataset.get_data_shape()
model = Model.model_builder(model_name, task_types, model_params)
model.fit(train_dataset)
model.save(self.model_dir)
# Eval model on train
evaluator = Evaluator(model, test_dataset, verbose=True)
with tempfile.NamedTemporaryFile() as test_csv_out:
with tempfile.NamedTemporaryFile() as test_stats_out:
_, _ = evaluator.compute_model_performance(
test_csv_out, test_stats_out)
def create_model(args):
"""Creates a model"""
model_name = args.model
if args.base_dir is not None:
feature_dir = os.path.join(args.base_dir, "features")
data_dir = os.path.join(args.base_dir, "data")
model_dir = os.path.join(args.base_dir, "model")
ensure_exists([args.base_dir, feature_dir, data_dir, model_dir])
else:
if args.model_dir is None or args.data_dir is None or args.feature_dir is None:
raise ValueError("If base-dir not specified, must specify " "feature-dir, data-dir, model-dir.")
feature_dir, model_dir, data_dir = (args.feature_dir, args.model_dir, args.data_dir)
ensure_exists([feature_dir, data_dir, model_dir])
if args.featurize:
print("+++++++++++++++++++++++++++++++++")
print("Perform featurization")
featurize_inputs(
feature_dir,
data_dir,
args.input_files,
args.user_specified_features,
args.tasks,
args.smiles_field,
args.split_field,
args.id_field,
args.threshold,
args.protein_pdb_field,
args.ligand_pdb_field,
args.ligand_mol2_field,
)
if args.generate_dataset:
print("+++++++++++++++++++++++++++++++++")
print("Generate dataset for featurized samples")
samples_dir = os.path.join(data_dir, "samples")
samples = FeaturizedSamples(samples_dir, reload_data=True)
print("Generating dataset.")
full_data_dir = os.path.join(data_dir, "full-data")
full_dataset = Dataset(full_data_dir, samples, args.feature_types)
print("Transform data.")
full_dataset.transform(args.input_transforms, args.output_transforms)
if args.train_test_split:
print("+++++++++++++++++++++++++++++++++")
print("Perform train-test split")
train_test_split(args.input_transforms, args.output_transforms, args.feature_types, args.splittype, data_dir)
if args.fit:
print("+++++++++++++++++++++++++++++++++")
print("Fit model")
model_params = extract_model_params(args)
fit_model(model_name, model_params, model_dir, data_dir)
if args.eval:
print("+++++++++++++++++++++++++++++++++")
print("Eval Model on Train")
print("-------------------")
train_dir = os.path.join(data_dir, "train-data")
csv_out_train = os.path.join(data_dir, "train.csv")
stats_out_train = os.path.join(data_dir, "train-stats.txt")
eval_trained_model(model_name, model_dir, train_dir, csv_out_train, stats_out_train)
print("Eval Model on Test")
print("------------------")
test_dir = os.path.join(data_dir, "test-data")
csv_out_test = os.path.join(data_dir, "test.csv")
stats_out_test = os.path.join(data_dir, "test-stats.txt")
eval_trained_model(model_name, model_dir, test_dir, csv_out_test, stats_out_test)
if args.eval_full:
print("+++++++++++++++++++++++++++++++++")
print("Eval Model on Full Dataset")
print("--------------------------")
full_data_dir = os.path.join(data_dir, "full-data")
csv_out_full = os.path.join(data_dir, "full.csv")
stats_out_full = os.path.join(data_dir, "full-stats.txt")
eval_trained_model(model_name, model_dir, full_data_dir, csv_out_full, stats_out_full)
