def test_fit_2():
"""
This function tests the second way of fitting the descriptor: the data is passed by storing the compounds in the
class.
"""
test_dir = os.path.dirname(os.path.realpath(__file__))
data = np.load(test_dir + "/data/local_slatm_ch4cn_light.npz")
descriptor = data["arr_0"]
classes = data["arr_1"]
energies = data["arr_2"]
estimator = ARMP()
estimator.set_representations(representations=descriptor)
estimator.set_classes(classes=classes)
estimator.set_properties(energies)
idx = np.arange(0, 100)
estimator.fit(idx)
## ------------- ** Loading the data ** ---------------
current_dir = os.path.dirname(os.path.realpath(__file__))
data = np.load(current_dir + '/../test/data/local_slatm_ch4cn_light.npz')
descriptor = data["arr_0"]
zs = data["arr_1"]
energies = data["arr_2"]
## ------------- ** Setting up the estimator ** ---------------
estimator = ARMP(iterations=100, l2_reg=0.0)
estimator.set_representations(representations=descriptor)
estimator.set_classes(zs)
estimator.set_properties(energies)
## ------------- ** Fitting to the data ** ---------------
idx = np.arange(0, 100)
estimator.fit(idx)
## ------------- ** Predicting and scoring ** ---------------
score = estimator.score(idx)
print("The mean absolute error is %s kJ/mol." % (str(-score)))
energies_predict = estimator.predict(idx)
estimator = ARMP(
iterations=10,
l1_reg=0.0,
l2_reg=0.0,
hidden_layer_sizes=(40, 20, 10),
tensorboard=True,
store_frequency=10,
# batch_size=400,
batch_size=n_train,
learning_rate=0.1,
# scoring_function="mae",
)
estimator.set_representations(representations=X)
estimator.set_classes(Z)
estimator.set_properties(Y)
# idx = np.arange(0,100)
# estimator.fit(idx)
# score = estimator.score(idx)
# estimator.fit(x=representation, y=energies, classes=zs)
estimator.fit(x=X, y=Y, classes=Z)
## ------------- ** Predicting and scoring ** ---------------
score = estimator.score(x=X, y=Y, classes=Z)