def run_sklearn(args: SklearnTrainArgs,
data: MoleculeDataset,
logger: Logger = None) -> Dict[str, List[float]]:
"""
Loads data, trains a scikit-learn model, and returns test scores for the model checkpoint with the highest validation score.
:param args: A :class:`~chemprop.args.SklearnTrainArgs` object containing arguments for
loading data and training the scikit-learn model.
:param data: A :class:`~chemprop.data.MoleculeDataset` containing the data.
:param logger: A logger to record output.
:return: A dictionary mapping each metric in :code:`metrics` to a list of values for each task.
"""
if logger is not None:
debug, info = logger.debug, logger.info
else:
debug = info = print
debug(pformat(vars(args)))
debug('Loading data')
data = get_data(path=args.data_path,
smiles_columns=args.smiles_columns,
target_columns=args.target_columns)
args.task_names = get_task_names(path=args.data_path,
smiles_columns=args.smiles_columns,
target_columns=args.target_columns,
ignore_columns=args.ignore_columns)
if args.model_type == 'svm' and data.num_tasks() != 1:
raise ValueError(
f'SVM can only handle single-task data but found {data.num_tasks()} tasks'
)
debug(f'Splitting data with seed {args.seed}')
# Need to have val set so that train and test sets are the same as when doing MPN
train_data, _, test_data = split_data(data=data,
split_type=args.split_type,
seed=args.seed,
sizes=args.split_sizes,
num_folds=args.num_folds,
args=args)
if args.save_smiles_splits:
save_smiles_splits(
data_path=args.data_path,
save_dir=args.save_dir,
task_names=args.task_names,
features_path=args.features_path,
train_data=train_data,
test_data=test_data,
smiles_columns=args.smiles_columns,
)
debug(
f'Total size = {len(data):,} | train size = {len(train_data):,} | test size = {len(test_data):,}'
)
debug('Computing morgan fingerprints')
morgan_fingerprint = get_features_generator('morgan')
for dataset in [train_data, test_data]:
for datapoint in tqdm(dataset, total=len(dataset)):
for s in datapoint.smiles:
datapoint.extend_features(
morgan_fingerprint(mol=s,
radius=args.radius,
num_bits=args.num_bits))
debug('Building model')
if args.dataset_type == 'regression':
if args.model_type == 'random_forest':
model = RandomForestRegressor(n_estimators=args.num_trees,
n_jobs=-1,
random_state=args.seed)
elif args.model_type == 'svm':
model = SVR()
else:
raise ValueError(f'Model type "{args.model_type}" not supported')
elif args.dataset_type == 'classification':
if args.model_type == 'random_forest':
model = RandomForestClassifier(n_estimators=args.num_trees,
n_jobs=-1,
class_weight=args.class_weight)
elif args.model_type == 'svm':
model = SVC()
else:
raise ValueError(f'Model type "{args.model_type}" not supported')
else:
raise ValueError(f'Dataset type "{args.dataset_type}" not supported')
debug(model)
model.train_args = args.as_dict()
debug('Training')
if args.single_task:
scores = single_task_sklearn(model=model,
train_data=train_data,
test_data=test_data,
metrics=args.metrics,
args=args,
logger=logger)
else:
scores = multi_task_sklearn(model=model,
train_data=train_data,
test_data=test_data,
metrics=args.metrics,
args=args,
logger=logger)
for metric in args.metrics:
info(f'Test {metric} = {np.nanmean(scores[metric])}')
return scores
def run_sklearn(args: SklearnTrainArgs, logger: Logger = None) -> List[float]:
if logger is not None:
debug, info = logger.debug, logger.info
else:
debug = info = print
debug(pformat(vars(args)))
metric_func = get_metric_func(args.metric)
debug('Loading data')
data = get_data(path=args.data_path,
smiles_column=args.smiles_column,
target_columns=args.target_columns)
args.task_names = get_task_names(path=args.data_path,
smiles_column=args.smiles_column,
target_columns=args.target_columns,
ignore_columns=args.ignore_columns)
if args.model_type == 'svm' and data.num_tasks() != 1:
raise ValueError(
f'SVM can only handle single-task data but found {data.num_tasks()} tasks'
)
debug(f'Splitting data with seed {args.seed}')
# Need to have val set so that train and test sets are the same as when doing MPN
train_data, _, test_data = split_data(data=data,
split_type=args.split_type,
seed=args.seed,
sizes=args.split_sizes,
args=args)
debug(
f'Total size = {len(data):,} | train size = {len(train_data):,} | test size = {len(test_data):,}'
)
debug('Computing morgan fingerprints')
morgan_fingerprint = get_features_generator('morgan')
for dataset in [train_data, test_data]:
for datapoint in tqdm(dataset, total=len(dataset)):
datapoint.set_features(
morgan_fingerprint(mol=datapoint.smiles,
radius=args.radius,
num_bits=args.num_bits))
debug('Building model')
if args.dataset_type == 'regression':
if args.model_type == 'random_forest':
model = RandomForestRegressor(n_estimators=args.num_trees,
n_jobs=-1)
elif args.model_type == 'svm':
model = SVR()
else:
raise ValueError(f'Model type "{args.model_type}" not supported')
elif args.dataset_type == 'classification':
if args.model_type == 'random_forest':
model = RandomForestClassifier(n_estimators=args.num_trees,
n_jobs=-1,
class_weight=args.class_weight)
elif args.model_type == 'svm':
model = SVC()
else:
raise ValueError(f'Model type "{args.model_type}" not supported')
else:
raise ValueError(f'Dataset type "{args.dataset_type}" not supported')
debug(model)
model.train_args = args.as_dict()
debug('Training')
if args.single_task:
scores = single_task_sklearn(model=model,
train_data=train_data,
test_data=test_data,
metric_func=metric_func,
args=args,
logger=logger)
else:
scores = multi_task_sklearn(model=model,
train_data=train_data,
test_data=test_data,
metric_func=metric_func,
args=args,
logger=logger)
info(f'Test {args.metric} = {np.nanmean(scores)}')
return scores