def init_guess_by_minao(mf, mol=None, ao2sub=None):
if mol is None: mol = mf.mol
if ao2sub is None: ao2sub = mf.ao2sub
dm_ao = hf.init_guess_by_minao(mol)
s = hf.get_ovlp(mol)
dm_sub = tools.dm_ao2loc(dm_ao, s, ao2sub)
return dm_sub
def init_guess_by_minao(mol):
'''Generate initial guess density matrix based on ANO basis, then project
the density matrix to the basis set defined by ``mol``
Returns:
Density matrices, a list of 2D ndarrays for alpha and beta spins
'''
dm = hf.init_guess_by_minao(mol)
return numpy.array((dm * .5, dm * .5))
def init_guess_by_minao(mol):
'''Generate initial guess density matrix based on ANO basis, then project
the density matrix to the basis set defined by ``mol``
Returns:
Density matrices, a list of 2D ndarrays for alpha and beta spins
'''
dm = hf.init_guess_by_minao(mol)
return numpy.array((dm*.5,dm*.5))
def get_init_guess(self, key=None):
""" Compute an initial guess for the density matrix. ???? """
from pyscf.scf.hf import init_guess_by_minao
if hasattr(self, 'mol'):
dm = init_guess_by_minao(self.mol)
else:
dm = self.comp_dm() # the loaded ks orbitals will be used
if dm.shape[0:2]==(1,1) and dm.shape[4]==1 : dm = dm.reshape((self.norbs,self.norbs))
return dm
def get_init_guess(self, key=None):
""" Compute an initial guess for the density matrix. """
from pyscf.scf.hf import init_guess_by_minao
if hasattr(self, 'mol'):
dm = init_guess_by_minao(self.mol)
else:
dm = self.comp_dm() # the loaded ks orbitals will be used
if dm.shape[0:2] == (1, 1) and dm.shape[4] == 1:
dm = dm.reshape((self.norbs, self.norbs))
return dm
def init_guess_by_minao(mol, breaksym=BREAKSYM):
'''Generate initial guess density matrix based on ANO basis, then project
the density matrix to the basis set defined by ``mol``
Returns:
Density matrices, a list of 2D ndarrays for alpha and beta spins
'''
dm = hf.init_guess_by_minao(mol)
dma = dmb = dm*.5
if breaksym:
dma, dmb = _break_dm_spin_symm(mol, (dma, dmb))
return numpy.array((dma,dmb))
def nn_guess(mol, S, P0=None):
"""This method returns a guess for the density matrix of a molecule
that can be used as input for scf calculations. Until now only the diagonal
elements are estimated by the network, while the rest is
Args:
- atoms <list<str>>: a list of chemical symbols for the atoms in the
molecule
- S <np.array>: the density matrix of the molecule
- P0 <np.array>: a (cheap) initial guess in which the network guess
(which calculates only the diagonal) shall be placed.
Returns:
- <np.array>: a matrix containing the initial guess for the density
matrix
"""
atoms = mol.species
sess = tf.Session()
#--- acquire model and setup graph ---
model_database = normpath("./models")
networks = {}
for species in list(set(atoms)):
model = np.load(join(model_database, species + ".npy"), encoding="bytes")
nn = EluFixedValue(*model)
nn.setup()
networks[species] = nn
sess.run(tf.global_variables_initializer())
#---
# if no init guess is given used pyscf default guess
if P0 is None:
P0 = init_guess_by_minao(mol.get_pyscf_molecule())
dm = []
for atom_index, atom in enumerate(atoms):
inputs = [Descriptor.values(S, atoms, atom_index)]
dm += (list(networks[atom].run(sess, inputs)))
# overwrite the diag of P0
np.fill_diagonal(P0, dm)
return P0
def init_guess_by_minao(mol, breaksym=BREAKSYM):
'''Generate initial guess density matrix based on ANO basis, then project
the density matrix to the basis set defined by ``mol``
Returns:
Density matrices, a list of 2D ndarrays for alpha and beta spins
'''
dm = hf.init_guess_by_minao(mol)
dma = dmb = dm*.5
if breaksym:
#remove off-diagonal part of beta DM
dmb = numpy.zeros_like(dma)
for b0, b1, p0, p1 in mol.aoslice_by_atom():
dmb[p0:p1,p0:p1] = dma[p0:p1,p0:p1]
return numpy.array((dma,dmb))
def init_guess_by_minao(mol, breaksym=BREAKSYM):
'''Generate initial guess density matrix based on ANO basis, then project
the density matrix to the basis set defined by ``mol``
Returns:
Density matrices, a list of 2D ndarrays for alpha and beta spins
'''
dm = hf.init_guess_by_minao(mol)
dma = dmb = dm*.5
if breaksym:
#remove off-diagonal part of beta DM
dmb = numpy.zeros_like(dma)
for b0, b1, p0, p1 in mol.aoslice_by_atom():
dmb[p0:p1,p0:p1] = dma[p0:p1,p0:p1]
return numpy.array((dma,dmb))
def do_analysis(dataset, molecules, s_raw, log_file):
#--- calculate guesses ---
msg.info("Calculating guesses ...",2)
p_1e = np.array([
hf.init_guess_by_1e(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_sap = np.array([
hf.init_guess_by_atom(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_minao = np.array([
hf.init_guess_by_minao(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_gwh = np.array([
hf.init_guess_by_wolfsberg_helmholtz(mol.get_pyscf_molecule()) for mol in molecules[1]
])
#---
with open(log_file, "a+") as f:
f.write("\n\n+++++ H_Core +++++\n")
msg.info("Results H_Core: ", 1)
measure_and_display(
p_1e.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ SAP +++++\n")
msg.info("Results SAP: ", 1)
measure_and_display(
p_sap.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ MINAO +++++\n")
msg.info("Results MINAO: ", 1)
measure_and_display(
p_minao.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ GWH +++++\n")
msg.info("Results GWH: ", 1)
measure_and_display(
p_gwh.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
def init_guess_by_minao(mol):
'''Initial guess in terms of the overlap to minimal basis.'''
dm = hf.init_guess_by_minao(mol)
return _proj_dmll(mol, dm, mol)
def init_guess_by_minao(mol):
dm = hf.init_guess_by_minao(mol)
return numpy.array((dm*.5, dm*.5))
def init_guess_by_minao(mol):
'''Initial guess in terms of the overlap to minimal basis.'''
dm = hf.init_guess_by_minao(mol)
return _proj_dmll(mol, dm, mol)
def not_used():
msg.info("Netowrk Analysis!", 2)
#--- fetching the molecules ---
msg.info("Fetching the molecules", 2)
def grep_molecule(input_file):
import re
with open(input_file) as f:
molecule = re.search(r"\$molecule.*\$end", f.read(), re.DOTALL)
if molecule is None:
raise ValueError("No molecule found in " + f.name)
else:
molecule = molecule.group(0)
# cut out geometries
geometries = molecule.splitlines()[2:-1]
# from geometries take the species and positions
species, positions = [], []
for line in geometries:
splits = line.split()
species.append(splits[0])
positions.append(splits[1:])
return species, positions
def fetch_molecules(folder):
files = [file for file in listdir(folder) if ".inp" in file]
for i, file in enumerate(files):
msg.info("Fetching: " + str(i + 1) + "/" + str(len(files)))
mol = Molecule(*grep_molecule(join(folder, file)))
mol.basis = "sto-3g"
yield mol
molecules = list(fetch_molecules("butadien/data"))
#---
#--- do scf ---
msg.info("Running the SCF calculations", 2)
iterations = []
for i, molecule in enumerate(molecules):
mol = molecule.get_pyscf_molecule()
msg.info("Calculating: " + str(i + 1) + "/200.")
# assemble pyscf initial guesses
P_1e = hf.init_guess_by_1e(mol)
P_atom = hf.init_guess_by_atom(mol)
P_minao = hf.init_guess_by_minao(mol)
# nn guess
S = hf.get_ovlp(mol).reshape(1, dim**2)
P_NN = network.run(sess, S).reshape(dim, dim)
iterations_molecule = []
for guess in [P_1e, P_atom, P_minao, P_NN]: #, P_NN]:
mf = hf.RHF(mol)
mf.verbose = 1
mf.kernel(dm0=guess)
iterations_molecule.append(mf.iterations)
iterations.append(iterations_molecule)
iterations = np.array(iterations)
#---
#--- statistics ---
fig, axes = plt.subplots(2, 2)
bins = 1 # todo hier kann man auch ein array angeben
for i, name in enumerate(['1e', 'atom', 'P_minao']):
hist, bins = np.histogram(iterations[:, i])
center = (bins[:-1] + bins[1:]) / 2
axes[i].bar(center, hist, label=name)
plt.legend()
plt.show()
def init_guess_by_minao(mol):
dm = hf.init_guess_by_minao(mol)
return numpy.array((dm*.5, dm*.5))
def main(molecule_type):
msg.print_level = 2
msg.info("Hi. Measurements for " + molecule_type, 2)
#--- fetch dataset and constants ---
msg.info("Fetching dataset", 2)
dataset_triu, molecules = fetch_dataset(molecule_type, True)
dataset, _ = fetch_dataset(molecule_type, False)
dim = DIM[molecule_type]
#---
#--- fetch network ---
msg.info("Fetching pretained network ", 2)
graph = tf.Graph()
structure, weights, biases = np.load(
"cc2ai/" + molecule_type + "/network_" + molecule_type + ".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)
s_raw = make_matrix_batch(dataset_triu.inverse_input_transform(dataset_triu.testing[0]), dim, True)
msg.info("Neural network ", 1)
p_nn = network.run(sess, dataset_triu.testing[0])
msg.info("McWheenys", 1)
p_batch = make_matrix_batch(p_nn, dim, True)
p_mcw1 = np.array(list(map(lambda x: multi_mc_wheeny(x[0], x[1], n_max=1), zip(p_batch, s_raw))))
p_mcw5 = np.array(list(map(lambda x: multi_mc_wheeny(x[0], x[1], n_max=5), zip (p_batch, s_raw))))
msg.info("Classics", 1)
p_1e = np.array([
hf.init_guess_by_1e(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_sap = np.array([
hf.init_guess_by_atom(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_minao = np.array([
hf.init_guess_by_minao(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_gwh = np.array([
hf.init_guess_by_wolfsberg_helmholtz(mol.get_pyscf_molecule()) for mol in molecules[1]
])
#---
#--- Measureing & print ---
log_file = "cc2ai/" + molecule_type + "/pretrained_" + str(date.today()) + ".log"
with open(log_file, "a+") as f:
f.write("##### Analysis of " + str(datetime.now()) + " #####\n")
msg.info("Results NN: ", 1)
with open(log_file, "a+") as f:
f.write("\n+++++ Plain NN +++++\n")
measure_and_display(
p_nn, dataset_triu, molecules, molecule_type, True, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ McW 1 +++++\n")
msg.info("Results McWheeny 1: ",1)
measure_and_display(
p_mcw1.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ McW 5 +++++\n")
msg.info("Results McWheeny 5: ", 1)
measure_and_display(
p_mcw5.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ H_Core +++++\n")
msg.info("Results H_Core: ", 1)
measure_and_display(
p_1e.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ SAP +++++\n")
msg.info("Results SAP: ", 1)
measure_and_display(
p_sap.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ MINAO +++++\n")
msg.info("Results MINAO: ", 1)
measure_and_display(
p_minao.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ GWH +++++\n")
msg.info("Results GWH: ", 1)
measure_and_display(
p_gwh.reshape(-1, dim**2), dataset, molecules, molecule_type, False, log_file
)
#---
#--- do scf ---
msg.info("Running the SCF calculations", 2)
iterations = []
for i, molecule in enumerate(molecules):
mol = molecule.get_pyscf_molecule()
msg.info("Calculating: " + str(i + 1) + "/200.")
# assemble pyscf initial guesses
P_1e = hf.init_guess_by_1e(mol)
P_atom = hf.init_guess_by_atom(mol)
P_minao = hf.init_guess_by_minao(mol)
print("die normalen sind fertig")
# nn guess
S = hf.get_ovlp(mol).reshape(1, dim**2)
P_NN = network.run(sess, S).reshape(dim, dim).astype('float64')
print("P_NN fertig")
iterations_molecule = []
for guess in [P_1e, P_atom, P_minao, P_NN]:#, P_NN]:
print("SCF")
mf = hf.RHF(mol)
mf.verbose = 1
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)
def do_analysis(network_path, dataset, molecules, s_raw, log_file):
#--- fetch network ---
msg.info("Fetching pretained network ", 2)
graph = tf.Graph()
structure, weights, biases = np.load(
network_path,
encoding="latin1"
)[:3]
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, dataset.testing[0])
msg.info("McWheenys", 1)
p_batch = make_matrix_batch(p_nn, DIM, True)
p_mcw1 = np.array(list(map(lambda x: multi_mc_wheeny(x[0], x[1], n_max=1), zip(p_batch, s_raw))))
p_mcw5 = np.array(list(map(lambda x: multi_mc_wheeny(x[0], x[1], n_max=5), zip (p_batch, s_raw))))
msg.info("Classics", 1)
p_1e = np.array([
hf.init_guess_by_1e(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_sap = np.array([
hf.init_guess_by_atom(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_minao = np.array([
hf.init_guess_by_minao(mol.get_pyscf_molecule()) for mol in molecules[1]
])
p_gwh = np.array([
hf.init_guess_by_wolfsberg_helmholtz(mol.get_pyscf_molecule()) for mol in molecules[1]
])
#---
msg.info("Results NN: ", 1)
with open(log_file, "a+") as f:
f.write("\n+++++ Plain NN +++++\n")
measure_and_display(
p_nn, dataset, molecules, True, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ McW 1 +++++\n")
msg.info("Results McWheeny 1: ",1)
measure_and_display(
p_mcw1.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ McW 5 +++++\n")
msg.info("Results McWheeny 5: ", 1)
measure_and_display(
p_mcw5.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ H_Core +++++\n")
msg.info("Results H_Core: ", 1)
measure_and_display(
p_1e.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ SAP +++++\n")
msg.info("Results SAP: ", 1)
measure_and_display(
p_sap.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ MINAO +++++\n")
msg.info("Results MINAO: ", 1)
measure_and_display(
p_minao.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)
with open(log_file, "a+") as f:
f.write("\n\n+++++ GWH +++++\n")
msg.info("Results GWH: ", 1)
measure_and_display(
p_gwh.reshape(-1, DIM**2), dataset, molecules, False, log_file, s=s_raw
)