def fetch_dataset(molecule_type, is_triu=True, index=None):
dim = DIM[molecule_type]
def load_triu(S, P, dim):
return [extract_triu(s, dim) for s in S], [extract_triu(p, dim) for p in P]
if is_triu:
dataset, molecules = make_butadien_dataset(
np.load(
"cc2ai/" + \
molecule_type + "/molecules_" + molecule_type + "_6-31g**.npy"
),
*load_triu(*np.load(
"cc2ai/" + \
molecule_type + "/dataset_" + molecule_type + "_6-31g**.npy"
), dim),
index=index
)
else:
dataset, molecules = make_butadien_dataset(
np.load(
"cc2ai/" + \
molecule_type + "/molecules_" + molecule_type + "_6-31g**.npy"
),
*np.load(
"cc2ai/" + \
molecule_type + "/dataset_" + molecule_type + "_6-31g**.npy"
),
index=index
)
return dataset, molecules
def fetch_dataset(folder, postfix, is_triu=True, index=None, test_samples=100):
dim = DIM
if is_triu:
molecules = np.load(folder + "molecules" + postfix + ".npy")
descriptor = NonWeighted(
Gaussians(*RADIAL_GAUSSIAN_MODELS["Equidistant-Broadening_1"]),
Gaussians(*AZIMUTHAL_GAUSSIAN_MODELS["Equisitant_1"]),
Gaussians(*POLAR_GAUSSIAN_MODELS["Equisitant_1"])
)
descriptor_values = descriptor.calculate_descriptors_batch(molecules)
dataset, molecules = make_butadien_dataset(
molecules,
descriptor_values,
[extract_triu(p, DIM) for p in np.load(folder + "P" + postfix + ".npy")],
index=index,
test_samples=test_samples
)
S = np.load(folder + "S" + postfix + ".npy")
if index is None:
index = np.arange(len(S))
S_test = S[index[test_samples:]]
else:
raise NotImplementedError("Only triu networks!!")
return dataset, molecules, S_test
def prep_dataset():
"""Fetching the dataset """
def load_triu(S, P, dim):
return [extract_triu(s, dim) for s in S], [extract_triu(p, dim) for p in P]
folder = join("butadien", "data", "400")
molecules = np.load(join(folder, "molecules400.npy"))
descriptor = NonWeighted(
Gaussians(*RADIAL_GAUSSIAN_MODELS["Equidistant-Broadening_1"]),
Gaussians(*AZIMUTHAL_GAUSSIAN_MODELS["Equisitant_1"]),
Gaussians(*POLAR_GAUSSIAN_MODELS["Equisitant_1"])
)
descriptor_values = descriptor.calculate_descriptors_batch(molecules)
dataset, molecules = make_butadien_dataset(
molecules,
descriptor_values,
[extract_triu(p, DIM) for p in np.load(join(folder, "P400.npy"))],
test_samples=100
)
return dataset#, molecules
def fetch_dataset(folder, postfix, is_triu=True, index=None):
dim = DIM
def load_triu(S, P, dim):
return [extract_triu(s, dim) for s in S], [extract_triu(p, dim) for p in P]
if is_triu:
dataset, molecules = make_butadien_dataset(
np.load(
folder + "molecules" + postfix + ".npy"
),
*load_triu(
np.load(folder + "S" + postfix + ".npy"),
np.load(folder + "P" + postfix + ".npy"),
dim
),
index=index,
test_samples=100
)
else:
raise NotImplementedError("Only triu networks!!")
return dataset, molecules
def prep_dataset():
"""Fetching the dataset """
def load_triu(S, P, dim):
return [extract_triu(s, dim)
for s in S], [extract_triu(p, dim) for p in P]
folder = join("butadien", "data")
dataset, molecules = make_butadien_dataset(
np.load(join(folder, "molecules.npy")), np.load(join(folder, "S.npy")),
np.load(join(folder, "P.npy")))
return dataset #, molecules
def prep_dataset():
"""Fetching the dataset """
def load_triu(S, P, dim):
return [extract_triu(s, dim)
for s in S], [extract_triu(p, dim) for p in P]
folder = join("butadien", "data", "400")
dataset, molecules = make_butadien_dataset(
np.load(join(folder, "molecules400.npy")),
*load_triu(np.load(join(folder, "S400.npy")),
np.load(join(folder, "P400.npy")), DIM),
test_samples=100)
return dataset #, molecules
def prep_dataset(molecule_type):
"""Fetching the dataset """
def load_triu(S, P, dim):
return [extract_triu(s, dim)
for s in S], [extract_triu(p, dim) for p in P]
folder = join("cc2ai", molecule_type)
dataset, molecules = make_butadien_dataset(
np.load(
join(
folder, "molecules_" + molecule_type + "_" +
BASIS[molecule_type] + ".npy")),
*load_triu(
*np.load(
join(
folder, "dataset_" + molecule_type + "_" +
BASIS[molecule_type] + ".npy")), DIM[molecule_type]),
)
return dataset #, molecules
def main(sample_index):
msg.print_level = 2
msg.info("Hi. Measurements for butadien", 2)
#--- fetch dataset and constants ---
msg.info("Fetching sample " + str(sample_index) + " from datase", 2)
dim = DIM
molecules = np.load(
"butadien/data/molecules.npy"
)
S = np.load( "butadien/data/S.npy")
P = np.load( "butadien/data/P.npy")
dataset = make_butadien_dataset(molecules, S, P)[0]
molecule = molecules[sample_index].get_pyscf_molecule()
s = S[sample_index].reshape(dim, dim)
s_normed = dataset.inverse_input_transform(s.reshape(1, -1)).reshape(1,-1)
p = P[sample_index].reshape(dim, dim)
#---
#--- fetch network ---
msg.info("Fetching pretained network ", 2)
graph = tf.Graph()
structure, weights, biases = np.load(
"butadien/data/network.npy",
encoding="latin1"
)
with graph.as_default():
sess = tf.Session()
network = EluFixedValue(structure, weights, biases)
network.setup()
sess.run(tf.global_variables_initializer())
#---
#--- calculate guesses ---
msg.info("Calculating guesses ...",2)
msg.info("Neural network ", 1)
p_nn = network.run(sess, s_normed).reshape(dim, dim)
msg.info("McWheenys", 1)
p_mcw1 = multi_mc_wheeny(p_nn, s, n_max=1)
p_mcw5 = multi_mc_wheeny(p_nn, s, n_max=5)
msg.info("Classics", 1)
p_sap = hf.init_guess_by_atom(molecule)
p_minao = hf.init_guess_by_minao(molecule)
p_gwh = hf.init_guess_by_wolfsberg_helmholtz(molecule)
#---
#--- Measureing & print ---
outfile = "butadien/results/cube_" + str(sample_index) + "_"
msg.info("Results Converged ", 1)
cubegen.density(molecule, outfile + "converged.cube", p.astype("float64"))
msg.info("Results NN: ", 1)
cubegen.density(molecule, outfile + "nn.cube", p_nn.astype("float64"))
msg.info("Results McWheeny 1: ",1)
cubegen.density(molecule, outfile + "mcw1.cube", p_mcw1.astype("float64"))
msg.info("Results McWheeny 5: ", 1)
cubegen.density(molecule, outfile + "mcw5.cube", p_mcw5.astype("float64"))
msg.info("Results SAP: ", 1)
cubegen.density(molecule, outfile + "sap.cube", p_sap)
msg.info("Results MINAO: ", 1)
cubegen.density(molecule, outfile + "minao.cube", p_minao)
msg.info("Results GWH: ", 1)
cubegen.density(molecule, outfile + "gwh.cube", p_gwh)