def sklearn_train() -> None:
"""Parses scikit-learn training arguments and trains a scikit-learn model.
This is the entry point for the command line command :code:`sklearn_train`.
"""
cross_validate(args=SklearnTrainArgs().parse_args(),
train_func=run_sklearn)
def sklearn_train() -> None:
"""Runs sklearn training."""
args = SklearnTrainArgs().parse_args()
logger = create_logger(name='sklearn-train',
save_dir=args.save_dir,
quiet=args.quiet)
cross_validate_sklearn(args, logger)
def sklearn_train() -> None:
"""Parses scikit-learn training arguments and trains a scikit-learn model.
This is the entry point for the command line command :code:`sklearn_train`.
"""
args = SklearnTrainArgs().parse_args()
logger = create_logger(name='sklearn-train',
save_dir=args.save_dir,
quiet=args.quiet)
cross_validate_sklearn(args, logger)
def predict_sklearn(args: SklearnPredictArgs):
print('Loading data')
data = get_data(path=args.test_path,
smiles_column=args.smiles_column,
target_columns=[])
print('Loading training arguments')
with open(args.checkpoint_paths[0], 'rb') as f:
model = pickle.load(f)
train_args: SklearnTrainArgs = SklearnTrainArgs().from_dict(
model.train_args, skip_unsettable=True)
print('Computing morgan fingerprints')
morgan_fingerprint = get_features_generator('morgan')
for datapoint in tqdm(data, total=len(data)):
datapoint.set_features(
morgan_fingerprint(mol=datapoint.smiles,
radius=train_args.radius,
num_bits=train_args.num_bits))
print(
f'Predicting with an ensemble of {len(args.checkpoint_paths)} models')
sum_preds = np.zeros((len(data), train_args.num_tasks))
for checkpoint_path in tqdm(args.checkpoint_paths,
total=len(args.checkpoint_paths)):
with open(checkpoint_path, 'rb') as f:
model = pickle.load(f)
model_preds = predict(model=model,
model_type=train_args.model_type,
dataset_type=train_args.dataset_type,
features=data.features())
sum_preds += np.array(model_preds)
# Ensemble predictions
avg_preds = sum_preds / len(args.checkpoint_paths)
avg_preds = avg_preds.tolist()
print(f'Saving predictions to {args.preds_path}')
assert len(data) == len(avg_preds)
makedirs(args.preds_path, isfile=True)
# Copy predictions over to data
for datapoint, preds in zip(data, avg_preds):
for pred_name, pred in zip(train_args.task_names, preds):
datapoint.row[pred_name] = pred
# Save
with open(args.preds_path, 'w') as f:
writer = csv.DictWriter(f, fieldnames=data[0].row.keys())
writer.writeheader()
for datapoint in data:
writer.writerow(datapoint.row)
def predict_sklearn(args: SklearnPredictArgs) -> None:
"""
Loads data and a trained scikit-learn model and uses the model to make predictions on the data.
:param args: A :class:`~chemprop.args.SklearnPredictArgs` object containing arguments for
loading data, loading a trained scikit-learn model, and making predictions with the model.
"""
print('Loading data')
data = get_data(path=args.test_path,
smiles_columns=args.smiles_columns,
target_columns=[],
ignore_columns=[],
store_row=True)
print('Loading training arguments')
with open(args.checkpoint_paths[0], 'rb') as f:
model = pickle.load(f)
train_args: SklearnTrainArgs = SklearnTrainArgs().from_dict(
model.train_args, skip_unsettable=True)
print('Computing morgan fingerprints')
morgan_fingerprint = get_features_generator('morgan')
for datapoint in tqdm(data, total=len(data)):
for s in datapoint.smiles:
datapoint.extend_features(
morgan_fingerprint(mol=s,
radius=train_args.radius,
num_bits=train_args.num_bits))
print(
f'Predicting with an ensemble of {len(args.checkpoint_paths)} models')
sum_preds = np.zeros((len(data), train_args.num_tasks))
for checkpoint_path in tqdm(args.checkpoint_paths,
total=len(args.checkpoint_paths)):
with open(checkpoint_path, 'rb') as f:
model = pickle.load(f)
model_preds = predict(model=model,
model_type=train_args.model_type,
dataset_type=train_args.dataset_type,
features=data.features())
sum_preds += np.array(model_preds)
# Ensemble predictions
avg_preds = sum_preds / len(args.checkpoint_paths)
avg_preds = avg_preds.tolist()
print(f'Saving predictions to {args.preds_path}')
# assert len(data) == len(avg_preds) #TODO: address with unit test later
makedirs(args.preds_path, isfile=True)
# Copy predictions over to data
for datapoint, preds in zip(data, avg_preds):
for pred_name, pred in zip(train_args.task_names, preds):
datapoint.row[pred_name] = pred
# Save
with open(args.preds_path, 'w') as f:
writer = csv.DictWriter(f, fieldnames=data[0].row.keys())
writer.writeheader()
for datapoint in data:
writer.writerow(datapoint.row)
from chemprop.args import SklearnTrainArgs
from chemprop.sklearn_train import cross_validate_sklearn
from chemprop.utils import create_logger
if __name__ == '__main__':
args = SklearnTrainArgs().parse_args()
logger = create_logger(name='sklearn-train',
save_dir=args.save_dir,
quiet=args.quiet)
if args.metric is None:
if args.dataset_type == 'regression':
args.metric = 'rmse'
elif args.dataset_type == 'classification':
args.metric = 'auc'
else:
raise ValueError(
f'Default metric not supported for dataset_type "{args.dataset_type}"'
)
cross_validate_sklearn(args, logger)