def test_train_small_bootstrap_presets(small_moddata, tf_session):
"""Tests the `fit_preset()` method."""
from modnet.model_presets import gen_presets
from modnet.models import EnsembleMODNetModel
modified_presets = gen_presets(100, 100)[:2]
for ind, preset in enumerate(modified_presets):
modified_presets[ind]["epochs"] = 2
data = small_moddata
# set 'optimal' features manually
data.optimal_features = [
col for col in data.df_featurized.columns
if col.startswith("ElementProperty")
]
model = EnsembleMODNetModel(
[[["eform", "egap"]]],
weights={
"eform": 1,
"egap": 1
},
num_neurons=[[4], [2], [2], [2]],
n_feat=3,
n_models=2,
bootstrap=True,
)
# nested=0/False -> no inner loop, so only 1 model
# nested=1/True -> inner loop, but default n_folds so 5
for num_nested, nested_option in zip([2, 1], [2, 0]):
results = model.fit_preset(
data,
presets=modified_presets,
nested=nested_option,
val_fraction=0.2,
n_jobs=2,
)
models = results[0]
assert len(models) == len(modified_presets)
assert len(models[0]) == num_nested
num_generations=10,
n_jobs=16,
early_stopping=True,
refit=True,
)
else:
# ... a list of presets (kind of dynamic grid search)
(
models,
val_losses,
best_learning_curve,
learning_curves,
best_presets,
) = model.fit_preset(
train_data,
classification=classification,
nested=5,
n_jobs=16,
)
# Load and featurize test dataset
test_df = task.get_test_data(fold, include_target=False, as_type="df")
try:
materials = test_df[
"structure"] if "structure" in test_df.columns else train_df[
"composition"].map(Composition)
except KeyError:
raise RuntimeError(
f"Could not find any materials data dataset for task {task!r}!"
)