def test_set_properties():
"""
This test checks that the set_properties function sets the correct properties.
:return:
"""
test_dir = os.path.dirname(os.path.realpath(__file__))
energies = np.loadtxt(test_dir + '/CN_isobutane/prop_kjmol_training.txt',
usecols=[1])
estimator = ARMP(representation='slatm')
assert estimator.properties == None
estimator.set_properties(energies)
assert np.all(estimator.properties == energies)
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)
def test_fit_1():
"""
This function tests the first way of fitting the descriptor: the data is passed by first creating compounds and then
the descriptors are created from the compounds.
"""
test_dir = os.path.dirname(os.path.realpath(__file__))
filenames = glob.glob(test_dir + "/CN_isobutane/*.xyz")
energies = np.loadtxt(test_dir + '/CN_isobutane/prop_kjmol_training.txt',
usecols=[1])
filenames.sort()
estimator = ARMP(representation="acsf")
estimator.generate_compounds(filenames[:50])
estimator.set_properties(energies[:50])
estimator.generate_representation()
idx = np.arange(0, 50)
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)
"eta": 30.8065
}
# Generate estimator
estimator = ARMP(iterations=10,
l1_reg=0.0001,
l2_reg=0.005,
learning_rate=0.0005,
representation_name='acsf',
representation_params=acsf_params,
tensorboard=True,
store_frequency=2,
hidden_layer_sizes=(50, 30, 10),
batch_size=200)
estimator.set_properties(ene_isopent)
estimator.generate_representation(pad_xyz, pad_zs, method='fortran')
print("Generated the representations")
print(estimator.representation.shape)
idx = list(range(n_samples))
idx_train, idx_test = modsel.train_test_split(idx,
random_state=42,
shuffle=True)
estimator.fit(idx_train)
data_squal = h5py.File(
"/Volumes/Transcend/data_sets/CN_squalane/dft/squalane_cn_dft.hdf5", "r")
"rcut": 5,
"acut": 5,
"zeta": 220.127,
"eta": 30.8065
}
estimator = ARMP(iterations=6000,
representation_name='acsf',
representation_params=acsf_params,
l1_reg=0.0,
l2_reg=0.0,
scoring_function="rmse",
tensorboard=False,
store_frequency=10,
learning_rate=0.075)
estimator.set_properties(energies[:100])
estimator.generate_compounds(filenames[:100])
estimator.generate_representation(method="tf")
print(estimator.representation.shape)
idx = list(range(100))
idx_train, idx_test = modsel.train_test_split(idx,
test_size=0,
random_state=42,
shuffle=True)
estimator.fit(idx_train)
score = estimator.score(idx_train)
print("The RMSE is %s kcal/mol." % (str(score)))
from qml.aglaia.aglaia import ARMP
import glob
import numpy as np
from sklearn import model_selection as modsel
test_dir = "/Volumes/Transcend/repositories/my_qml_fork/qml/test/"
filenames = glob.glob(test_dir + "/qm7/*.xyz")
energies = np.loadtxt(test_dir + '/data/hof_qm7.txt', usecols=[1])
filenames.sort()
n_samples = 500
estimator = ARMP(representation_name="acsf", iterations=100)
estimator.generate_compounds(filenames[:n_samples])
estimator.set_properties(energies[:n_samples])
estimator.generate_representation(method="fortran")
idx = np.arange(0, n_samples)
idx_train, idx_test = modsel.train_test_split(idx,
random_state=42,
shuffle=True,
test_size=0.1)
estimator.fit(idx_train)
estimator.score(idx_train)
"radial_rs": np.arange(0, 10, 0.5),
"angular_rs": np.arange(0, 10, 0.5),
"theta_s": np.arange(0, 3.14, 0.25)
}
estimator = ARMP(iterations=2000,
batch_size=256,
l1_reg=0.0001,
l2_reg=0.005,
learning_rate=0.00015,
representation='acsf',
representation_params=acsf_params,
tensorboard=True,
store_frequency=50)
estimator.set_properties(ene)
estimator.generate_representation(xyz, zs)
idx = list(range(n_samples))
idx_train, idx_test = modsel.train_test_split(idx,
test_size=0.15,
random_state=42,
shuffle=True)
all_scores = []
for lr in learning_rate:
for l1 in l1_reg:
for l2 in l2_reg:
estimator.fit(idx_train)
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)
print("The mean absolute error is %s kJ/mol." % (str(-score)))
"eta": 39.81824764370754
}
estimator = ARMP(iterations=2633,
batch_size=22,
l1_reg=1.46e-05,
l2_reg=0.0001,
learning_rate=0.0013,
representation_name='acsf',
representation_params=acsf_params,
tensorboard=True,
store_frequency=25,
hidden_layer_sizes=(185, ))
# Loading the model previously trained
estimator.load_nn("../trained_nn/vr-nn")
estimator.set_properties(ene_surface)
# Generating the representation
start = time.time()
estimator.generate_representation(xyz_surface, zs_surface, method="fortran")
end = time.time()
print("The time taken to generate the representations is %s s" %
(str(end - start)))
print("The shape of the representations is %s" %
(str(estimator.representation.shape)))
# Predicting the energies
idx = list(range(n_samples))
predictions = estimator.predict(idx)
# Printing the mean absolute error
xyz = np.array([[[0, 1, 0], [0, 1, 1], [1, 0, 1]],
[[1, 2, 2], [3, 1, 2], [1, 3, 4]],
[[4, 1, 2], [0.5, 5, 6], [-1, 2, 3]]])
zs = np.array([[1, 2, 3],
[1, 2, 3],
[1, 2, 3]])
ene_true = np.array([0.5, 0.9, 1.0])
estimator = ARMP(iterations=10, l1_reg=0.0001, l2_reg=0.005, learning_rate=0.0005, representation='acsf',
representation_params={"radial_rs": np.arange(0, 10, 5), "angular_rs": np.arange(0, 10, 5),
"theta_s": np.arange(0, 3.14, 3)},
tensorboard=True, store_frequency=10
)
estimator.set_properties(ene_true)
estimator.generate_representation(xyz, zs)
idx = list(range(xyz.shape[0]))
estimator.fit(idx)
estimator.save_nn(save_dir="temp")
pred1 = estimator.predict(idx)
estimator.loaded_model = True
estimator.fit(idx)
pred2 = estimator.predict(idx)
estimator.session.close()