def test_from_mvl_models(self):
with ScratchDir("."):
model = MEGNetModel.from_mvl_models("Eform_MP_2019")
li2o = self.get_structure("Li2O")
self.assertAlmostEqual(float(model.predict_structure(li2o)),
-2.0152957439422607,
places=4)
# Data preprocessing:
# Load binary compounds' formation energies example data,
# then split into training and validation subsets.
full_df = load_data("binary_e_form")
num_training = int(TRAINING_RATIO * len(full_df.index))
train_df = full_df[:num_training]
val_df = full_df[num_training:]
# 4217 training samples, 1055 validation samples.
train_structs = train_df["structure"]
val_structs = val_df["structure"]
train_targets = train_df["formation_energy_per_atom"]
val_targets = val_df["formation_energy_per_atom"]
# 1. Load MEGNetModel
meg_model = MEGNetModel.from_mvl_models("Eform_MP_2019")
# 2. Make probabilistic model
# Specify Kullback-Leibler divergence weighting in loss function:
kl_weight = BATCH_SIZE / num_training
# Then make the model:
prob_model = MEGNetProbModel(
meg_model=meg_model,
num_inducing_points=NUM_INDUCING_POINTS,
kl_weight=kl_weight,
)
def train_model():
"""Train and save the probabilistic model."""
prob_model.train(
