def psi4_clean():
"""Function to put Psi4 back to a clean state. In particular deletes
scratch files and resets Psi variables. Call as last part of the real
deriv call to Psi4.
"""
psi4.clean_variables()
psi4.clean()
def _clean_psi_environ(do_clean: bool):
"""Reset work environment to new Psi4 instance state.
This includes global variables (P::e.globals, P::e.arrays, P::e.options) and any
non-explicitly-retained PSIO-managed scratch files.
"""
if do_clean:
core.clean_variables()
core.clean_options()
core.clean()
def nbody_gufunc(func, method_string, **kwargs):
"""
Computes the nbody interaction energy, gradient, or Hessian depending on input.
This is a generalized univeral function for computing interaction and total quantities.
:returns: *return type of func* |w--w| The data.
:returns: (*float*, :py:class:`~psi4.core.Wavefunction`) |w--w| data and wavefunction with energy/gradient/hessian set appropriately when **return_wfn** specified.
:type func: function
:param func: ``energy`` || etc.
Python function that accepts method_string and a molecule. Returns a
energy, gradient, or Hessian as requested.
:type method_string: string
:param method_string: ``'scf'`` || ``'mp2'`` || ``'ci5'`` || etc.
First argument, lowercase and usually unlabeled. Indicates the computational
method to be passed to func.
:type molecule: :ref:`molecule <op_py_molecule>`
:param molecule: ``h2o`` || etc.
The target molecule, if not the last molecule defined.
:type return_wfn: :ref:`boolean <op_py_boolean>`
:param return_wfn: ``'on'`` || |dl| ``'off'`` |dr|
Indicate to additionally return the :py:class:`~psi4.core.Wavefunction`
calculation result as the second element of a tuple.
:type bsse_type: string or list
:param bsse_type: ``'cp'`` || ``['nocp', 'vmfc']`` || |dl| ``None`` |dr| || etc.
Type of BSSE correction to compute: CP, NoCP, or VMFC. The first in this
list is returned by this function. By default, this function is not called.
:type max_nbody: int
:param max_nbody: ``3`` || etc.
Maximum n-body to compute, cannot exceed the number of fragments in the moleucle.
:type ptype: string
:param ptype: ``'energy'`` || ``'gradient'`` || ``'hessian'``
Type of the procedure passed in.
:type return_total_data: :ref:`boolean <op_py_boolean>`
:param return_total_data: ``'on'`` || |dl| ``'off'`` |dr|
If True returns the total data (energy/gradient/etc) of the system,
otherwise returns interaction data.
:type levels: dict
:param levels: ``{1: 'ccsd(t)', 2: 'mp2', 'supersystem': 'scf'}`` || ``{1: 2, 2: 'ccsd(t)', 3: 'mp2'}`` || etc
Dictionary of different levels of theory for different levels of expansion
Note that method_string is not used in this case.
supersystem computes all higher order n-body effects up to nfragments.
:type embedding_charges: dict
:param embedding_charges: ``{1: [-0.834, 0.417, 0.417], ..}``
Dictionary of atom-centered point charges. keys: 1-based index of fragment, values: list of charges for each fragment.
:type charge_method: string
:param charge_method: ``scf/6-31g`` || ``b3lyp/6-31g*`` || etc
Method to compute point charges for monomers. Overridden by embedding_charges if both are provided.
:type charge_type: string
:param charge_type: ``MULLIKEN_CHARGES`` || ``LOWDIN_CHARGES``
Default is ``MULLIKEN_CHARGES``
"""
# Initialize dictionaries for easy data passing
metadata, component_results, nbody_results = {}, {}, {}
# Parse some kwargs
kwargs = p4util.kwargs_lower(kwargs)
if kwargs.get('levels', False):
return driver_nbody_helper.multi_level(func, **kwargs)
metadata['ptype'] = kwargs.pop('ptype', None)
metadata['return_wfn'] = kwargs.pop('return_wfn', False)
metadata['return_total_data'] = kwargs.pop('return_total_data', False)
metadata['molecule'] = kwargs.pop('molecule', core.get_active_molecule())
metadata['molecule'].update_geometry()
metadata['molecule'].fix_com(True)
metadata['molecule'].fix_orientation(True)
metadata['embedding_charges'] = kwargs.get('embedding_charges', False)
metadata['kwargs'] = kwargs
core.clean_variables()
if metadata['ptype'] not in ['energy', 'gradient', 'hessian']:
raise ValidationError("""N-Body driver: The ptype '%s' is not regonized.""" % metadata['ptype'])
# Parse bsse_type, raise exception if not provided or unrecognized
metadata['bsse_type_list'] = kwargs.pop('bsse_type')
if metadata['bsse_type_list'] is None:
raise ValidationError("N-Body GUFunc: Must pass a bsse_type")
if not isinstance(metadata['bsse_type_list'], list):
metadata['bsse_type_list'] = [metadata['bsse_type_list']]
for num, btype in enumerate(metadata['bsse_type_list']):
metadata['bsse_type_list'][num] = btype.lower()
if btype.lower() not in ['cp', 'nocp', 'vmfc']:
raise ValidationError("N-Body GUFunc: bsse_type '%s' is not recognized" % btype.lower())
metadata['max_nbody'] = kwargs.get('max_nbody', -1)
metadata['max_frag'] = metadata['molecule'].nfragments()
if metadata['max_nbody'] == -1:
metadata['max_nbody'] = metadata['molecule'].nfragments()
else:
metadata['max_nbody'] = min(metadata['max_nbody'], metadata['max_frag'])
# Flip this off for now, needs more testing
# If we are doing CP lets save them integrals
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# # Set to save RI integrals for repeated full-basis computations
# ri_ints_io = core.get_global_option('DF_INTS_IO')
# # inquire if above at all applies to dfmp2 or just scf
# core.set_global_option('DF_INTS_IO', 'SAVE')
# psioh = core.IOManager.shared_object()
# psioh.set_specific_retention(97, True)
bsse_str = metadata['bsse_type_list'][0]
if len(metadata['bsse_type_list']) > 1:
bsse_str = str(metadata['bsse_type_list'])
core.print_out("\n\n")
core.print_out(" ===> N-Body Interaction Abacus <===\n")
core.print_out(" BSSE Treatment: %s\n" % bsse_str)
# Get compute list
metadata = build_nbody_compute_list(metadata)
# Compute N-Body components
component_results = compute_nbody_components(func, method_string, metadata)
# Assemble N-Body quantities
nbody_results = assemble_nbody_components(metadata, component_results)
# Build wfn and bind variables
wfn = core.Wavefunction.build(metadata['molecule'], 'def2-svp')
dicts = [
'energies', 'ptype', 'intermediates', 'energy_body_dict', 'gradient_body_dict', 'hessian_body_dict', 'nbody',
'cp_energy_body_dict', 'nocp_energy_body_dict', 'vmfc_energy_body_dict'
]
if metadata['ptype'] == 'gradient':
wfn.set_gradient(nbody_results['ret_ptype'])
nbody_results['gradient_body_dict'] = nbody_results['ptype_body_dict']
elif metadata['ptype'] == 'hessian':
nbody_results['hessian_body_dict'] = nbody_results['ptype_body_dict']
wfn.set_hessian(nbody_results['ret_ptype'])
component_results_gradient = component_results.copy()
component_results_gradient['ptype'] = component_results_gradient['gradients']
metadata['ptype'] = 'gradient'
nbody_results_gradient = assemble_nbody_components(metadata, component_results_gradient)
wfn.set_gradient(nbody_results_gradient['ret_ptype'])
nbody_results['gradient_body_dict'] = nbody_results_gradient['ptype_body_dict']
for r in [component_results, nbody_results]:
for d in r:
if d in dicts:
for var, value in r[d].items():
try:
wfn.set_scalar_variable(str(var), value)
core.set_scalar_variable(str(var), value)
except:
wfn.set_array_variable(d.split('_')[0].upper() + ' ' + str(var), core.Matrix.from_array(value))
core.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
wfn.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
if metadata['return_wfn']:
return (nbody_results['ret_ptype'], wfn)
else:
return nbody_results['ret_ptype']
def nbody_gufunc(func: Union[str, Callable], method_string: str, **kwargs):
"""
Computes the nbody interaction energy, gradient, or Hessian depending on input.
This is a generalized univeral function for computing interaction and total quantities.
:returns: *return type of func* |w--w| The data.
:returns: (*float*, :py:class:`~psi4.core.Wavefunction`) |w--w| data and wavefunction with energy/gradient/hessian set appropriately when **return_wfn** specified.
:type func: Callable
:param func: ``energy`` || etc.
Python function that accepts method_string and a molecule. Returns a
energy, gradient, or Hessian as requested.
:type method_string: str
:param method_string: ``'scf'`` || ``'mp2'`` || ``'ci5'`` || etc.
First argument, lowercase and usually unlabeled. Indicates the computational
method to be passed to func.
:type molecule: :ref:`molecule <op_py_molecule>`
:param molecule: ``h2o`` || etc.
The target molecule, if not the last molecule defined.
:type return_wfn: :ref:`boolean <op_py_boolean>`
:param return_wfn: ``'on'`` || |dl| ``'off'`` |dr|
Indicate to additionally return the :py:class:`~psi4.core.Wavefunction`
calculation result as the second element of a tuple.
:type bsse_type: str or list
:param bsse_type: ``'cp'`` || ``['nocp', 'vmfc']`` || |dl| ``None`` |dr| || etc.
Type of BSSE correction to compute: CP, NoCP, or VMFC. The first in this
list is returned by this function. By default, this function is not called.
:type max_nbody: int
:param max_nbody: ``3`` || etc.
Maximum n-body to compute, cannot exceed the number of fragments in the moleucle.
:type ptype: str
:param ptype: ``'energy'`` || ``'gradient'`` || ``'hessian'``
Type of the procedure passed in.
:type return_total_data: :ref:`boolean <op_py_boolean>`
:param return_total_data: ``'on'`` || |dl| ``'off'`` |dr|
If True returns the total data (energy/gradient/etc) of the system,
otherwise returns interaction data.
:type levels: dict
:param levels: ``{1: 'ccsd(t)', 2: 'mp2', 'supersystem': 'scf'}`` || ``{1: 2, 2: 'ccsd(t)', 3: 'mp2'}`` || etc
Dictionary of different levels of theory for different levels of expansion
Note that method_string is not used in this case.
supersystem computes all higher order n-body effects up to nfragments.
:type embedding_charges: dict
:param embedding_charges: ``{1: [-0.834, 0.417, 0.417], ..}``
Dictionary of atom-centered point charges. keys: 1-based index of fragment, values: list of charges for each fragment.
:type charge_method: str
:param charge_method: ``scf/6-31g`` || ``b3lyp/6-31g*`` || etc
Method to compute point charges for monomers. Overridden by embedding_charges if both are provided.
:type charge_type: str
:param charge_type: ``MULLIKEN_CHARGES`` || ``LOWDIN_CHARGES``
Default is ``MULLIKEN_CHARGES``
"""
# Initialize dictionaries for easy data passing
metadata, component_results, nbody_results = {}, {}, {}
# Parse some kwargs
kwargs = p4util.kwargs_lower(kwargs)
if kwargs.get('levels', False):
return driver_nbody_helper.multi_level(func, **kwargs)
metadata['ptype'] = kwargs.pop('ptype', None)
metadata['return_wfn'] = kwargs.pop('return_wfn', False)
metadata['return_total_data'] = kwargs.pop('return_total_data', False)
metadata['molecule'] = kwargs.pop('molecule', core.get_active_molecule())
metadata['molecule'].update_geometry()
metadata['molecule'].fix_com(True)
metadata['molecule'].fix_orientation(True)
metadata['embedding_charges'] = kwargs.get('embedding_charges', False)
metadata['kwargs'] = kwargs
core.clean_variables()
if metadata['ptype'] not in ['energy', 'gradient', 'hessian']:
raise ValidationError(
"""N-Body driver: The ptype '%s' is not regonized.""" %
metadata['ptype'])
# Parse bsse_type, raise exception if not provided or unrecognized
metadata['bsse_type_list'] = kwargs.pop('bsse_type')
if metadata['bsse_type_list'] is None:
raise ValidationError("N-Body GUFunc: Must pass a bsse_type")
if not isinstance(metadata['bsse_type_list'], list):
metadata['bsse_type_list'] = [metadata['bsse_type_list']]
for num, btype in enumerate(metadata['bsse_type_list']):
metadata['bsse_type_list'][num] = btype.lower()
if btype.lower() not in ['cp', 'nocp', 'vmfc']:
raise ValidationError(
"N-Body GUFunc: bsse_type '%s' is not recognized" %
btype.lower())
metadata['max_nbody'] = kwargs.get('max_nbody', -1)
if metadata['molecule'].nfragments() == 1:
raise ValidationError(
"N-Body requires active molecule to have more than 1 fragment.")
metadata['max_frag'] = metadata['molecule'].nfragments()
if metadata['max_nbody'] == -1:
metadata['max_nbody'] = metadata['molecule'].nfragments()
else:
metadata['max_nbody'] = min(metadata['max_nbody'],
metadata['max_frag'])
# Flip this off for now, needs more testing
# If we are doing CP lets save them integrals
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# # Set to save RI integrals for repeated full-basis computations
# ri_ints_io = core.get_global_option('DF_INTS_IO')
# # inquire if above at all applies to dfmp2 or just scf
# core.set_global_option('DF_INTS_IO', 'SAVE')
# psioh = core.IOManager.shared_object()
# psioh.set_specific_retention(97, True)
bsse_str = metadata['bsse_type_list'][0]
if len(metadata['bsse_type_list']) > 1:
bsse_str = str(metadata['bsse_type_list'])
core.print_out("\n\n")
core.print_out(" ===> N-Body Interaction Abacus <===\n")
core.print_out(" BSSE Treatment: %s\n" %
bsse_str)
# Get compute list
metadata = build_nbody_compute_list(metadata)
# Compute N-Body components
component_results = compute_nbody_components(func, method_string, metadata)
# Assemble N-Body quantities
nbody_results = assemble_nbody_components(metadata, component_results)
# Build wfn and bind variables
wfn = core.Wavefunction.build(metadata['molecule'], 'def2-svp')
dicts = [
'energies', 'ptype', 'intermediates', 'energy_body_dict',
'gradient_body_dict', 'hessian_body_dict', 'nbody',
'cp_energy_body_dict', 'nocp_energy_body_dict', 'vmfc_energy_body_dict'
]
if metadata['ptype'] == 'gradient':
wfn.set_gradient(nbody_results['ret_ptype'])
nbody_results['gradient_body_dict'] = nbody_results['ptype_body_dict']
elif metadata['ptype'] == 'hessian':
nbody_results['hessian_body_dict'] = nbody_results['ptype_body_dict']
wfn.set_hessian(nbody_results['ret_ptype'])
component_results_gradient = component_results.copy()
component_results_gradient['ptype'] = component_results_gradient[
'gradients']
metadata['ptype'] = 'gradient'
nbody_results_gradient = assemble_nbody_components(
metadata, component_results_gradient)
wfn.set_gradient(nbody_results_gradient['ret_ptype'])
nbody_results['gradient_body_dict'] = nbody_results_gradient[
'ptype_body_dict']
for r in [component_results, nbody_results]:
for d in r:
if d in dicts:
for var, value in r[d].items():
try:
wfn.set_scalar_variable(str(var), value)
core.set_scalar_variable(str(var), value)
except:
wfn.set_array_variable(
d.split('_')[0].upper() + ' ' + str(var),
core.Matrix.from_array(value))
core.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
wfn.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
if metadata['ptype'] == 'gradient':
core.set_variable("CURRENT GRADIENT", nbody_results['ret_ptype'])
elif metadata['ptype'] == 'hessian':
core.set_variable("CURRENT HESSIAN", nbody_results['ret_ptype'])
if metadata['return_wfn']:
return (nbody_results['ret_ptype'], wfn)
else:
return nbody_results['ret_ptype']
def _clean_psi_environ(do_clean):
if do_clean:
core.clean_variables()
core.clean_options()
core.clean()
def nbody_gufunc(func, method_string, **kwargs):
"""
Computes the nbody interaction energy, gradient, or Hessian depending on input.
This is a generalized univeral function for computing interaction quantities.
:returns: *return type of func* |w--w| The interaction data.
:returns: (*float*, :ref:`Wavefunction<sec:psimod_Wavefunction>`) |w--w| interaction data and wavefunction with energy/gradient/hessian set appropriately when **return_wfn** specified.
:type func: function
:param func: ``energy`` || etc.
Python function that accepts method_string and a molecule. Returns a
energy, gradient, or Hessian as requested.
:type method_string: string
:param method_string: ``'scf'`` || ``'mp2'`` || ``'ci5'`` || etc.
First argument, lowercase and usually unlabeled. Indicates the computational
method to be passed to func.
:type molecule: :ref:`molecule <op_py_molecule>`
:param molecule: ``h2o`` || etc.
The target molecule, if not the last molecule defined.
:type return_wfn: :ref:`boolean <op_py_boolean>`
:param return_wfn: ``'on'`` || |dl| ``'off'`` |dr|
Indicate to additionally return the :ref:`Wavefunction<sec:psimod_Wavefunction>`
calculation result as the second element of a tuple.
:type bsse_type: string or list
:param bsse_type: ``'cp'`` || ``['nocp', 'vmfc']`` || |dl| ``None`` |dr| || etc.
Type of BSSE correction to compute: CP, NoCP, or VMFC. The first in this
list is returned by this function. By default, this function is not called.
:type max_nbody: int
:param max_nbody: ``3`` || etc.
Maximum n-body to compute, cannot exceed the number of fragments in the moleucle.
:type ptype: string
:param ptype: ``'energy'`` || ``'gradient'`` || ``'hessian'``
Type of the procedure passed in.
:type return_total_data: :ref:`boolean <op_py_boolean>`
:param return_total_data: ``'on'`` || |dl| ``'off'`` |dr|
If True returns the total data (energy/gradient/etc) of the system,
otherwise returns interaction data.
"""
### ==> Parse some kwargs <==
kwargs = p4util.kwargs_lower(kwargs)
return_wfn = kwargs.pop('return_wfn', False)
ptype = kwargs.pop('ptype', None)
return_total_data = kwargs.pop('return_total_data', False)
molecule = kwargs.pop('molecule', core.get_active_molecule())
molecule.update_geometry()
core.clean_variables()
if ptype not in ['energy', 'gradient', 'hessian']:
raise ValidationError(
"""N-Body driver: The ptype '%s' is not regonized.""" % ptype)
# Figure out BSSE types
do_cp = False
do_nocp = False
do_vmfc = False
return_method = False
# Must be passed bsse_type
bsse_type_list = kwargs.pop('bsse_type')
if bsse_type_list is None:
raise ValidationError("N-Body GUFunc: Must pass a bsse_type")
if not isinstance(bsse_type_list, list):
bsse_type_list = [bsse_type_list]
for num, btype in enumerate(bsse_type_list):
if btype.lower() == 'cp':
do_cp = True
if (num == 0): return_method = 'cp'
elif btype.lower() == 'nocp':
do_nocp = True
if (num == 0): return_method = 'nocp'
elif btype.lower() == 'vmfc':
do_vmfc = True
if (num == 0): return_method = 'vmfc'
else:
raise ValidationError(
"N-Body GUFunc: bsse_type '%s' is not recognized" %
btype.lower())
max_nbody = kwargs.get('max_nbody', -1)
max_frag = molecule.nfragments()
if max_nbody == -1:
max_nbody = molecule.nfragments()
else:
max_nbody = min(max_nbody, max_frag)
# What levels do we need?
nbody_range = range(1, max_nbody + 1)
fragment_range = range(1, max_frag + 1)
# Flip this off for now, needs more testing
# If we are doing CP lets save them integrals
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# # Set to save RI integrals for repeated full-basis computations
# ri_ints_io = core.get_global_option('DF_INTS_IO')
# # inquire if above at all applies to dfmp2 or just scf
# core.set_global_option('DF_INTS_IO', 'SAVE')
# psioh = core.IOManager.shared_object()
# psioh.set_specific_retention(97, True)
bsse_str = bsse_type_list[0]
if len(bsse_type_list) > 1:
bsse_str = str(bsse_type_list)
core.print_out("\n\n")
core.print_out(" ===> N-Body Interaction Abacus <===\n")
core.print_out(" BSSE Treatment: %s\n" %
bsse_str)
cp_compute_list = {x: set() for x in nbody_range}
nocp_compute_list = {x: set() for x in nbody_range}
vmfc_compute_list = {x: set() for x in nbody_range}
vmfc_level_list = {x: set()
for x in nbody_range
} # Need to sum something slightly different
# Build up compute sets
if do_cp:
# Everything is in dimer basis
basis_tuple = tuple(fragment_range)
for nbody in nbody_range:
for x in it.combinations(fragment_range, nbody):
cp_compute_list[nbody].add((x, basis_tuple))
if do_nocp:
# Everything in monomer basis
for nbody in nbody_range:
for x in it.combinations(fragment_range, nbody):
nocp_compute_list[nbody].add((x, x))
if do_vmfc:
# Like a CP for all combinations of pairs or greater
for nbody in nbody_range:
for cp_combos in it.combinations(fragment_range, nbody):
basis_tuple = tuple(cp_combos)
for interior_nbody in nbody_range:
for x in it.combinations(cp_combos, interior_nbody):
combo_tuple = (x, basis_tuple)
vmfc_compute_list[interior_nbody].add(combo_tuple)
vmfc_level_list[len(basis_tuple)].add(combo_tuple)
# Build a comprehensive compute_range
compute_list = {x: set() for x in nbody_range}
for n in nbody_range:
compute_list[n] |= cp_compute_list[n]
compute_list[n] |= nocp_compute_list[n]
compute_list[n] |= vmfc_compute_list[n]
core.print_out(" Number of %d-body computations: %d\n" %
(n, len(compute_list[n])))
# Build size and slices dictionaries
fragment_size_dict = {
frag: molecule.extract_subsets(frag).natom()
for frag in range(1, max_frag + 1)
}
start = 0
fragment_slice_dict = {}
for k, v in fragment_size_dict.items():
fragment_slice_dict[k] = slice(start, start + v)
start += v
molecule_total_atoms = sum(fragment_size_dict.values())
# Now compute the energies
energies_dict = {}
ptype_dict = {}
for n in compute_list.keys():
core.print_out(
"\n ==> N-Body: Now computing %d-body complexes <==\n\n" % n)
print("\n ==> N-Body: Now computing %d-body complexes <==\n" % n)
total = len(compute_list[n])
for num, pair in enumerate(compute_list[n]):
core.print_out(
"\n N-Body: Computing complex (%d/%d) with fragments %s in the basis of fragments %s.\n\n"
% (num + 1, total, str(pair[0]), str(pair[1])))
ghost = list(set(pair[1]) - set(pair[0]))
current_mol = molecule.extract_subsets(list(pair[0]), ghost)
ptype_dict[pair] = func(method_string,
molecule=current_mol,
**kwargs)
energies_dict[pair] = core.get_variable("CURRENT ENERGY")
core.print_out(
"\n N-Body: Complex Energy (fragments = %s, basis = %s: %20.14f)\n"
% (str(pair[0]), str(pair[1]), energies_dict[pair]))
# Flip this off for now, needs more testing
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# core.set_global_option('DF_INTS_IO', 'LOAD')
core.clean()
# Final dictionaries
cp_energy_by_level = {n: 0.0 for n in nbody_range}
nocp_energy_by_level = {n: 0.0 for n in nbody_range}
cp_energy_body_dict = {n: 0.0 for n in nbody_range}
nocp_energy_body_dict = {n: 0.0 for n in nbody_range}
vmfc_energy_body_dict = {n: 0.0 for n in nbody_range}
# Build out ptype dictionaries if needed
if ptype != 'energy':
if ptype == 'gradient':
arr_shape = (molecule_total_atoms, 3)
elif ptype == 'hessian':
arr_shape = (molecule_total_atoms * 3, molecule_total_atoms * 3)
else:
raise KeyError("N-Body: ptype '%s' not recognized" % ptype)
cp_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
nocp_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
vmfc_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
cp_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
nocp_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
vmfc_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
else:
cp_ptype_by_level, cp_ptype_body_dict = None, None
nocp_ptype_by_level, nocp_ptype_body_dict = None, None
vmfc_ptype_body_dict = None
# Sum up all of the levels
for n in nbody_range:
# Energy
cp_energy_by_level[n] = sum(energies_dict[v]
for v in cp_compute_list[n])
nocp_energy_by_level[n] = sum(energies_dict[v]
for v in nocp_compute_list[n])
# Special vmfc case
if n > 1:
vmfc_energy_body_dict[n] = vmfc_energy_body_dict[n - 1]
for tup in vmfc_level_list[n]:
vmfc_energy_body_dict[n] += (
(-1)**(n - len(tup[0]))) * energies_dict[tup]
# Do ptype
if ptype != 'energy':
_sum_cluster_ptype_data(ptype, ptype_dict, cp_compute_list[n],
fragment_slice_dict, fragment_size_dict,
cp_ptype_by_level[n])
_sum_cluster_ptype_data(ptype, ptype_dict, nocp_compute_list[n],
fragment_slice_dict, fragment_size_dict,
nocp_ptype_by_level[n])
_sum_cluster_ptype_data(ptype,
ptype_dict,
vmfc_level_list[n],
fragment_slice_dict,
fragment_size_dict,
vmfc_ptype_by_level[n],
vmfc=True)
# Compute cp energy and ptype
if do_cp:
for n in nbody_range:
if n == max_frag:
cp_energy_body_dict[n] = cp_energy_by_level[n]
if ptype != 'energy':
cp_ptype_body_dict[n][:] = cp_ptype_by_level[n]
continue
for k in range(1, n + 1):
take_nk = nCr(max_frag - k - 1, n - k)
sign = ((-1)**(n - k))
value = cp_energy_by_level[k]
cp_energy_body_dict[n] += take_nk * sign * value
if ptype != 'energy':
value = cp_ptype_by_level[k]
cp_ptype_body_dict[n] += take_nk * sign * value
_print_nbody_energy(cp_energy_body_dict, "Counterpoise Corrected (CP)")
cp_interaction_energy = cp_energy_body_dict[
max_nbody] - cp_energy_body_dict[1]
core.set_variable('Counterpoise Corrected Total Energy',
cp_energy_body_dict[max_nbody])
core.set_variable('Counterpoise Corrected Interaction Energy',
cp_interaction_energy)
for n in nbody_range[1:]:
var_key = 'CP-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(var_key,
cp_energy_body_dict[n] - cp_energy_body_dict[1])
# Compute nocp energy and ptype
if do_nocp:
for n in nbody_range:
if n == max_frag:
nocp_energy_body_dict[n] = nocp_energy_by_level[n]
if ptype != 'energy':
nocp_ptype_body_dict[n][:] = nocp_ptype_by_level[n]
continue
for k in range(1, n + 1):
take_nk = nCr(max_frag - k - 1, n - k)
sign = ((-1)**(n - k))
value = nocp_energy_by_level[k]
nocp_energy_body_dict[n] += take_nk * sign * value
if ptype != 'energy':
value = nocp_ptype_by_level[k]
nocp_ptype_body_dict[n] += take_nk * sign * value
_print_nbody_energy(nocp_energy_body_dict,
"Non-Counterpoise Corrected (NoCP)")
nocp_interaction_energy = nocp_energy_body_dict[
max_nbody] - nocp_energy_body_dict[1]
core.set_variable('Non-Counterpoise Corrected Total Energy',
nocp_energy_body_dict[max_nbody])
core.set_variable('Non-Counterpoise Corrected Interaction Energy',
nocp_interaction_energy)
for n in nbody_range[1:]:
var_key = 'NOCP-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(
var_key, nocp_energy_body_dict[n] - nocp_energy_body_dict[1])
# Compute vmfc energy and ptype
if do_vmfc:
_print_nbody_energy(vmfc_energy_body_dict,
"Valiron-Mayer Function Couterpoise (VMFC)")
vmfc_interaction_energy = vmfc_energy_body_dict[
max_nbody] - vmfc_energy_body_dict[1]
core.set_variable('Valiron-Mayer Function Couterpoise Total Energy',
vmfc_energy_body_dict[max_nbody])
core.set_variable(
'Valiron-Mayer Function Couterpoise Interaction Energy',
vmfc_interaction_energy)
for n in nbody_range[1:]:
var_key = 'VMFC-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(
var_key, vmfc_energy_body_dict[n] - vmfc_energy_body_dict[1])
if return_method == 'cp':
ptype_body_dict = cp_ptype_body_dict
energy_body_dict = cp_energy_body_dict
elif return_method == 'nocp':
ptype_body_dict = nocp_ptype_body_dict
energy_body_dict = nocp_energy_body_dict
elif return_method == 'vmfc':
ptype_body_dict = vmfc_ptype_body_dict
energy_body_dict = vmfc_energy_body_dict
else:
raise ValidationError(
"N-Body Wrapper: Invalid return type. Should never be here, please post this error on github."
)
# Figure out and build return types
if return_total_data:
ret_energy = energy_body_dict[max_nbody]
else:
ret_energy = energy_body_dict[max_nbody]
ret_energy -= energy_body_dict[1]
if ptype != 'energy':
if return_total_data:
np_final_ptype = ptype_body_dict[max_nbody].copy()
else:
np_final_ptype = ptype_body_dict[max_nbody].copy()
np_final_ptype -= ptype_body_dict[1]
ret_ptype = core.Matrix.from_array(np_final_ptype)
else:
ret_ptype = ret_energy
# Build and set a wavefunction
wfn = core.Wavefunction.build(molecule, 'sto-3g')
wfn.cdict["nbody_energy"] = energies_dict
wfn.cdict["nbody_ptype"] = ptype_dict
wfn.cdict["nbody_body_energy"] = energy_body_dict
wfn.cdict["nbody_body_ptype"] = ptype_body_dict
if ptype == 'gradient':
wfn.set_gradient(ret_ptype)
elif ptype == 'hessian':
wfn.set_hessian(ret_ptype)
core.set_variable("CURRENT ENERGY", ret_energy)
if return_wfn:
return (ret_ptype, wfn)
else:
return ret_ptype
def nbody_gufunc(func, method_string, **kwargs):
"""
Computes the nbody interaction energy, gradient, or Hessian depending on input.
This is a generalized univeral function for computing interaction quantities.
:returns: *return type of func* |w--w| The interaction data.
:returns: (*float*, :py:class:`~psi4.core.Wavefunction`) |w--w| interaction data and wavefunction with energy/gradient/hessian set appropriately when **return_wfn** specified.
:type func: function
:param func: ``energy`` || etc.
Python function that accepts method_string and a molecule. Returns a
energy, gradient, or Hessian as requested.
:type method_string: string
:param method_string: ``'scf'`` || ``'mp2'`` || ``'ci5'`` || etc.
First argument, lowercase and usually unlabeled. Indicates the computational
method to be passed to func.
:type molecule: :ref:`molecule <op_py_molecule>`
:param molecule: ``h2o`` || etc.
The target molecule, if not the last molecule defined.
:type return_wfn: :ref:`boolean <op_py_boolean>`
:param return_wfn: ``'on'`` || |dl| ``'off'`` |dr|
Indicate to additionally return the :py:class:`~psi4.core.Wavefunction`
calculation result as the second element of a tuple.
:type bsse_type: string or list
:param bsse_type: ``'cp'`` || ``['nocp', 'vmfc']`` || |dl| ``None`` |dr| || etc.
Type of BSSE correction to compute: CP, NoCP, or VMFC. The first in this
list is returned by this function. By default, this function is not called.
:type max_nbody: int
:param max_nbody: ``3`` || etc.
Maximum n-body to compute, cannot exceed the number of fragments in the moleucle.
:type ptype: string
:param ptype: ``'energy'`` || ``'gradient'`` || ``'hessian'``
Type of the procedure passed in.
:type return_total_data: :ref:`boolean <op_py_boolean>`
:param return_total_data: ``'on'`` || |dl| ``'off'`` |dr|
If True returns the total data (energy/gradient/etc) of the system,
otherwise returns interaction data.
"""
### ==> Parse some kwargs <==
kwargs = p4util.kwargs_lower(kwargs)
return_wfn = kwargs.pop('return_wfn', False)
ptype = kwargs.pop('ptype', None)
return_total_data = kwargs.pop('return_total_data', False)
molecule = kwargs.pop('molecule', core.get_active_molecule())
molecule.update_geometry()
core.clean_variables()
if ptype not in ['energy', 'gradient', 'hessian']:
raise ValidationError("""N-Body driver: The ptype '%s' is not regonized.""" % ptype)
# Figure out BSSE types
do_cp = False
do_nocp = False
do_vmfc = False
return_method = False
# Must be passed bsse_type
bsse_type_list = kwargs.pop('bsse_type')
if bsse_type_list is None:
raise ValidationError("N-Body GUFunc: Must pass a bsse_type")
if not isinstance(bsse_type_list, list):
bsse_type_list = [bsse_type_list]
for num, btype in enumerate(bsse_type_list):
if btype.lower() == 'cp':
do_cp = True
if (num == 0): return_method = 'cp'
elif btype.lower() == 'nocp':
do_nocp = True
if (num == 0): return_method = 'nocp'
elif btype.lower() == 'vmfc':
do_vmfc = True
if (num == 0): return_method = 'vmfc'
else:
raise ValidationError("N-Body GUFunc: bsse_type '%s' is not recognized" % btype.lower())
max_nbody = kwargs.get('max_nbody', -1)
max_frag = molecule.nfragments()
if max_nbody == -1:
max_nbody = molecule.nfragments()
else:
max_nbody = min(max_nbody, max_frag)
# What levels do we need?
nbody_range = range(1, max_nbody + 1)
fragment_range = range(1, max_frag + 1)
# Flip this off for now, needs more testing
# If we are doing CP lets save them integrals
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# # Set to save RI integrals for repeated full-basis computations
# ri_ints_io = core.get_global_option('DF_INTS_IO')
# # inquire if above at all applies to dfmp2 or just scf
# core.set_global_option('DF_INTS_IO', 'SAVE')
# psioh = core.IOManager.shared_object()
# psioh.set_specific_retention(97, True)
bsse_str = bsse_type_list[0]
if len(bsse_type_list) >1:
bsse_str = str(bsse_type_list)
core.print_out("\n\n")
core.print_out(" ===> N-Body Interaction Abacus <===\n")
core.print_out(" BSSE Treatment: %s\n" % bsse_str)
cp_compute_list = {x:set() for x in nbody_range}
nocp_compute_list = {x:set() for x in nbody_range}
vmfc_compute_list = {x:set() for x in nbody_range}
vmfc_level_list = {x:set() for x in nbody_range} # Need to sum something slightly different
# Build up compute sets
if do_cp:
# Everything is in dimer basis
basis_tuple = tuple(fragment_range)
for nbody in nbody_range:
for x in it.combinations(fragment_range, nbody):
cp_compute_list[nbody].add( (x, basis_tuple) )
if do_nocp:
# Everything in monomer basis
for nbody in nbody_range:
for x in it.combinations(fragment_range, nbody):
nocp_compute_list[nbody].add( (x, x) )
if do_vmfc:
# Like a CP for all combinations of pairs or greater
for nbody in nbody_range:
for cp_combos in it.combinations(fragment_range, nbody):
basis_tuple = tuple(cp_combos)
for interior_nbody in nbody_range:
for x in it.combinations(cp_combos, interior_nbody):
combo_tuple = (x, basis_tuple)
vmfc_compute_list[interior_nbody].add( combo_tuple )
vmfc_level_list[len(basis_tuple)].add( combo_tuple )
# Build a comprehensive compute_range
compute_list = {x:set() for x in nbody_range}
for n in nbody_range:
compute_list[n] |= cp_compute_list[n]
compute_list[n] |= nocp_compute_list[n]
compute_list[n] |= vmfc_compute_list[n]
core.print_out(" Number of %d-body computations: %d\n" % (n, len(compute_list[n])))
# Build size and slices dictionaries
fragment_size_dict = {frag: molecule.extract_subsets(frag).natom() for
frag in range(1, max_frag+1)}
start = 0
fragment_slice_dict = {}
for k, v in fragment_size_dict.items():
fragment_slice_dict[k] = slice(start, start + v)
start += v
molecule_total_atoms = sum(fragment_size_dict.values())
# Now compute the energies
energies_dict = {}
ptype_dict = {}
for n in compute_list.keys():
core.print_out("\n ==> N-Body: Now computing %d-body complexes <==\n\n" % n)
total = len(compute_list[n])
for num, pair in enumerate(compute_list[n]):
core.print_out("\n N-Body: Computing complex (%d/%d) with fragments %s in the basis of fragments %s.\n\n" %
(num + 1, total, str(pair[0]), str(pair[1])))
ghost = list(set(pair[1]) - set(pair[0]))
current_mol = molecule.extract_subsets(list(pair[0]), ghost)
ptype_dict[pair] = func(method_string, molecule=current_mol, **kwargs)
energies_dict[pair] = core.get_variable("CURRENT ENERGY")
core.print_out("\n N-Body: Complex Energy (fragments = %s, basis = %s: %20.14f)\n" %
(str(pair[0]), str(pair[1]), energies_dict[pair]))
# Flip this off for now, needs more testing
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# core.set_global_option('DF_INTS_IO', 'LOAD')
core.clean()
# Final dictionaries
cp_energy_by_level = {n: 0.0 for n in nbody_range}
nocp_energy_by_level = {n: 0.0 for n in nbody_range}
cp_energy_body_dict = {n: 0.0 for n in nbody_range}
nocp_energy_body_dict = {n: 0.0 for n in nbody_range}
vmfc_energy_body_dict = {n: 0.0 for n in nbody_range}
# Build out ptype dictionaries if needed
if ptype != 'energy':
if ptype == 'gradient':
arr_shape = (molecule_total_atoms, 3)
elif ptype == 'hessian':
arr_shape = (molecule_total_atoms * 3, molecule_total_atoms * 3)
else:
raise KeyError("N-Body: ptype '%s' not recognized" % ptype)
cp_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
nocp_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
vmfc_ptype_by_level = {n: np.zeros(arr_shape) for n in nbody_range}
cp_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
nocp_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
vmfc_ptype_body_dict = {n: np.zeros(arr_shape) for n in nbody_range}
else:
cp_ptype_by_level, cp_ptype_body_dict = None, None
nocp_ptype_by_level, nocp_ptype_body_dict = None, None
vmfc_ptype_body_dict = None
# Sum up all of the levels
for n in nbody_range:
# Energy
cp_energy_by_level[n] = sum(energies_dict[v] for v in cp_compute_list[n])
nocp_energy_by_level[n] = sum(energies_dict[v] for v in nocp_compute_list[n])
# Special vmfc case
if n > 1:
vmfc_energy_body_dict[n] = vmfc_energy_body_dict[n - 1]
for tup in vmfc_level_list[n]:
vmfc_energy_body_dict[n] += ((-1) ** (n - len(tup[0]))) * energies_dict[tup]
# Do ptype
if ptype != 'energy':
_sum_cluster_ptype_data(ptype, ptype_dict, cp_compute_list[n],
fragment_slice_dict, fragment_size_dict,
cp_ptype_by_level[n])
_sum_cluster_ptype_data(ptype, ptype_dict, nocp_compute_list[n],
fragment_slice_dict, fragment_size_dict,
nocp_ptype_by_level[n])
_sum_cluster_ptype_data(ptype, ptype_dict, vmfc_level_list[n],
fragment_slice_dict, fragment_size_dict,
vmfc_ptype_by_level[n], vmfc=True)
# Compute cp energy and ptype
if do_cp:
for n in nbody_range:
if n == max_frag:
cp_energy_body_dict[n] = cp_energy_by_level[n]
if ptype != 'energy':
cp_ptype_body_dict[n][:] = cp_ptype_by_level[n]
continue
for k in range(1, n + 1):
take_nk = nCr(max_frag - k - 1, n - k)
sign = ((-1) ** (n - k))
value = cp_energy_by_level[k]
cp_energy_body_dict[n] += take_nk * sign * value
if ptype != 'energy':
value = cp_ptype_by_level[k]
cp_ptype_body_dict[n] += take_nk * sign * value
_print_nbody_energy(cp_energy_body_dict, "Counterpoise Corrected (CP)")
cp_interaction_energy = cp_energy_body_dict[max_nbody] - cp_energy_body_dict[1]
core.set_variable('Counterpoise Corrected Total Energy', cp_energy_body_dict[max_nbody])
core.set_variable('Counterpoise Corrected Interaction Energy', cp_interaction_energy)
for n in nbody_range[1:]:
var_key = 'CP-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(var_key, cp_energy_body_dict[n] - cp_energy_body_dict[1])
# Compute nocp energy and ptype
if do_nocp:
for n in nbody_range:
if n == max_frag:
nocp_energy_body_dict[n] = nocp_energy_by_level[n]
if ptype != 'energy':
nocp_ptype_body_dict[n][:] = nocp_ptype_by_level[n]
continue
for k in range(1, n + 1):
take_nk = nCr(max_frag - k - 1, n - k)
sign = ((-1) ** (n - k))
value = nocp_energy_by_level[k]
nocp_energy_body_dict[n] += take_nk * sign * value
if ptype != 'energy':
value = nocp_ptype_by_level[k]
nocp_ptype_body_dict[n] += take_nk * sign * value
_print_nbody_energy(nocp_energy_body_dict, "Non-Counterpoise Corrected (NoCP)")
nocp_interaction_energy = nocp_energy_body_dict[max_nbody] - nocp_energy_body_dict[1]
core.set_variable('Non-Counterpoise Corrected Total Energy', nocp_energy_body_dict[max_nbody])
core.set_variable('Non-Counterpoise Corrected Interaction Energy', nocp_interaction_energy)
for n in nbody_range[1:]:
var_key = 'NOCP-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(var_key, nocp_energy_body_dict[n] - nocp_energy_body_dict[1])
# Compute vmfc energy and ptype
if do_vmfc:
_print_nbody_energy(vmfc_energy_body_dict, "Valiron-Mayer Function Couterpoise (VMFC)")
vmfc_interaction_energy = vmfc_energy_body_dict[max_nbody] - vmfc_energy_body_dict[1]
core.set_variable('Valiron-Mayer Function Couterpoise Total Energy', vmfc_energy_body_dict[max_nbody])
core.set_variable('Valiron-Mayer Function Couterpoise Interaction Energy', vmfc_interaction_energy)
for n in nbody_range[1:]:
var_key = 'VMFC-CORRECTED %d-BODY INTERACTION ENERGY' % n
core.set_variable(var_key, vmfc_energy_body_dict[n] - vmfc_energy_body_dict[1])
if return_method == 'cp':
ptype_body_dict = cp_ptype_body_dict
energy_body_dict = cp_energy_body_dict
elif return_method == 'nocp':
ptype_body_dict = nocp_ptype_body_dict
energy_body_dict = nocp_energy_body_dict
elif return_method == 'vmfc':
ptype_body_dict = vmfc_ptype_body_dict
energy_body_dict = vmfc_energy_body_dict
else:
raise ValidationError("N-Body Wrapper: Invalid return type. Should never be here, please post this error on github.")
# Figure out and build return types
if return_total_data:
ret_energy = energy_body_dict[max_nbody]
else:
ret_energy = energy_body_dict[max_nbody]
ret_energy -= energy_body_dict[1]
if ptype != 'energy':
if return_total_data:
np_final_ptype = ptype_body_dict[max_nbody].copy()
else:
np_final_ptype = ptype_body_dict[max_nbody].copy()
np_final_ptype -= ptype_body_dict[1]
ret_ptype = core.Matrix.from_array(np_final_ptype)
else:
ret_ptype = ret_energy
# Build and set a wavefunction
wfn = core.Wavefunction.build(molecule, 'sto-3g')
wfn.nbody_energy = energies_dict
wfn.nbody_ptype = ptype_dict
wfn.nbody_body_energy = energy_body_dict
wfn.nbody_body_ptype = ptype_body_dict
if ptype == 'gradient':
wfn.set_gradient(ret_ptype)
elif ptype == 'hessian':
wfn.set_hessian(ret_ptype)
core.set_variable("CURRENT ENERGY", ret_energy)
if return_wfn:
return (ret_ptype, wfn)
else:
return ret_ptype
def nbody_gufunc(func, method_string, **kwargs):
"""
Computes the nbody interaction energy, gradient, or Hessian depending on input.
This is a generalized univeral function for computing interaction quantities.
:returns: *return type of func* |w--w| The interaction data.
:returns: (*float*, :py:class:`~psi4.core.Wavefunction`) |w--w| interaction data and wavefunction with energy/gradient/hessian set appropriately when **return_wfn** specified.
:type func: function
:param func: ``energy`` || etc.
Python function that accepts method_string and a molecule. Returns a
energy, gradient, or Hessian as requested.
:type method_string: string
:param method_string: ``'scf'`` || ``'mp2'`` || ``'ci5'`` || etc.
First argument, lowercase and usually unlabeled. Indicates the computational
method to be passed to func.
:type molecule: :ref:`molecule <op_py_molecule>`
:param molecule: ``h2o`` || etc.
The target molecule, if not the last molecule defined.
:type return_wfn: :ref:`boolean <op_py_boolean>`
:param return_wfn: ``'on'`` || |dl| ``'off'`` |dr|
Indicate to additionally return the :py:class:`~psi4.core.Wavefunction`
calculation result as the second element of a tuple.
:type bsse_type: string or list
:param bsse_type: ``'cp'`` || ``['nocp', 'vmfc']`` || |dl| ``None`` |dr| || etc.
Type of BSSE correction to compute: CP, NoCP, or VMFC. The first in this
list is returned by this function. By default, this function is not called.
:type max_nbody: int
:param max_nbody: ``3`` || etc.
Maximum n-body to compute, cannot exceed the number of fragments in the moleucle.
:type ptype: string
:param ptype: ``'energy'`` || ``'gradient'`` || ``'hessian'``
Type of the procedure passed in.
:type return_total_data: :ref:`boolean <op_py_boolean>`
:param return_total_data: ``'on'`` || |dl| ``'off'`` |dr|
If True returns the total data (energy/gradient/etc) of the system,
otherwise returns interaction data.
"""
# Initialize dictionaries for easy data passing
metadata, component_results, nbody_results = {}, {}, {}
# Parse some kwargs
kwargs = p4util.kwargs_lower(kwargs)
metadata['ptype'] = kwargs.pop('ptype', None)
metadata['return_wfn'] = kwargs.pop('return_wfn', False)
metadata['return_total_data'] = kwargs.pop('return_total_data', False)
metadata['molecule'] = kwargs.pop('molecule', core.get_active_molecule())
metadata['molecule'].update_geometry()
metadata['kwargs'] = kwargs
core.clean_variables()
if metadata['ptype'] not in ['energy', 'gradient', 'hessian']:
raise ValidationError("""N-Body driver: The ptype '%s' is not regonized.""" % metadata['ptype'])
# Parse bsse_type, raise exception if not provided or unrecognized
metadata['bsse_type_list'] = kwargs.pop('bsse_type')
if metadata['bsse_type_list'] is None:
raise ValidationError("N-Body GUFunc: Must pass a bsse_type")
if not isinstance(metadata['bsse_type_list'], list):
metadata['bsse_type_list'] = [metadata['bsse_type_list']]
for num, btype in enumerate(metadata['bsse_type_list']):
metadata['bsse_type_list'][num] = btype.lower()
if btype.lower() not in ['cp', 'nocp', 'vmfc']:
raise ValidationError("N-Body GUFunc: bsse_type '%s' is not recognized" % btype.lower())
metadata['max_nbody'] = kwargs.get('max_nbody', -1)
metadata['max_frag'] = metadata['molecule'].nfragments()
if metadata['max_nbody'] == -1:
metadata['max_nbody'] = metadata['molecule'].nfragments()
else:
metadata['max_nbody'] = min(metadata['max_nbody'], metadata['max_frag'])
# Flip this off for now, needs more testing
# If we are doing CP lets save them integrals
#if 'cp' in bsse_type_list and (len(bsse_type_list) == 1):
# # Set to save RI integrals for repeated full-basis computations
# ri_ints_io = core.get_global_option('DF_INTS_IO')
# # inquire if above at all applies to dfmp2 or just scf
# core.set_global_option('DF_INTS_IO', 'SAVE')
# psioh = core.IOManager.shared_object()
# psioh.set_specific_retention(97, True)
bsse_str = metadata['bsse_type_list'][0]
if len(metadata['bsse_type_list']) > 1:
bsse_str = str(metadata['bsse_type_list'])
core.print_out("\n\n")
core.print_out(" ===> N-Body Interaction Abacus <===\n")
core.print_out(" BSSE Treatment: %s\n" % bsse_str)
# Get compute list
metadata = build_nbody_compute_list(metadata)
# Compute N-Body components
component_results = compute_nbody_components(func, method_string, metadata)
# Assemble N-Body quantities
nbody_results = assemble_nbody_components(metadata, component_results)
# Figure out returns
if metadata['ptype'] != 'energy':
if metadata['return_total_data']:
np_final_ptype = nbody_results['ptype_body_dict'][metadata['max_nbody']].copy()
else:
np_final_ptype = nbody_results['ptype_body_dict'][metadata['max_nbody']].copy()
np_final_ptype -= ptype_body_dict[1]
nbody_results['ret_ptype'] = core.Matrix.from_array(np_final_ptype)
else:
nbody_results['ret_ptype'] = nbody_results['ret_energy']
# Build wfn and bind variables
wfn = core.Wavefunction.build(metadata['molecule'], 'def2-svp')
dicts = ['energies', 'ptype', 'intermediates', 'energy_body_dict', 'ptype_body_dict', 'nbody']
for r in [component_results, nbody_results]:
for d in r:
if d in dicts:
for var, value in r[d].items():
wfn.set_variable(str(var), value)
core.set_variable(str(var), value)
if metadata['ptype'] == 'gradient':
wfn.set_gradient(ret_ptype)
elif metadata['ptype'] == 'hessian':
wfn.set_hessian(ret_ptype)
core.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
wfn.set_variable("CURRENT ENERGY", nbody_results['ret_energy'])
if metadata['return_wfn']:
return (nbody_results['ret_ptype'], wfn)
else:
return nbody_results['ret_ptype']
def database(name, db_name, **kwargs):
r"""Function to access the molecule objects and reference energies of
popular chemical databases.
:aliases: db()
:returns: (*float*) Mean absolute deviation of the database in kcal/mol
:PSI variables:
.. hlist::
:columns: 1
* :psivar:`db_name DATABASE MEAN SIGNED DEVIATION`
* :psivar:`db_name DATABASE MEAN ABSOLUTE DEVIATION`
* :psivar:`db_name DATABASE ROOT-MEAN-SQUARE DEVIATION`
* Python dictionaries of results accessible as ``DB_RGT`` and ``DB_RXN``.
.. note:: It is very easy to make a database from a collection of xyz files
using the script :source:`psi4/share/psi4/scripts/ixyz2database.py`.
See :ref:`sec:createDatabase` for details.
.. caution:: Some features are not yet implemented. Buy a developer some coffee.
- In sow/reap mode, use only global options (e.g., the local option set by ``set scf scf_type df`` will not be respected).
.. note:: To access a database that is not embedded in a |PSIfour|
distribution, add the path to the directory containing the database
to the environment variable :envvar:`PYTHONPATH`.
:type name: str
:param name: ``'scf'`` || ``'sapt0'`` || ``'ccsd(t)'`` || etc.
First argument, usually unlabeled. Indicates the computational method
to be applied to the database. May be any valid argument to
:py:func:`psi4.driver.energy`.
:type db_name: str
:param db_name: ``'BASIC'`` || ``'S22'`` || ``'HTBH'`` || etc.
Second argument, usually unlabeled. Indicates the requested database
name, matching (case insensitive) the name of a python file in
``psi4/share/databases`` or :envvar:`PYTHONPATH`. Consult that
directory for available databases and literature citations.
:type func: :ref:`function <op_py_function>`
:param func: |dl| ``energy`` |dr| || ``optimize`` || ``cbs``
Indicates the type of calculation to be performed on each database
member. The default performs a single-point ``energy('name')``, while
``optimize`` perfoms a geometry optimization on each reagent, and
``cbs`` performs a compound single-point energy. If a nested series
of python functions is intended (see :ref:`sec:intercalls`), use
keyword ``db_func`` instead of ``func``.
:type mode: str
:param mode: |dl| ``'continuous'`` |dr| || ``'sow'`` || ``'reap'``
Indicates whether the calculations required to complete the
database are to be run in one file (``'continuous'``) or are to be
farmed out in an embarrassingly parallel fashion
(``'sow'``/``'reap'``). For the latter, run an initial job with
``'sow'`` and follow instructions in its output file.
:type cp: :ref:`boolean <op_py_boolean>`
:param cp: ``'on'`` || |dl| ``'off'`` |dr|
Indicates whether counterpoise correction is employed in computing
interaction energies. Use this option and NOT the ``bsse_type="cp"``
function for BSSE correction in database(). Option available
(See :ref:`sec:availableDatabases`) only for databases of bimolecular complexes.
:type rlxd: :ref:`boolean <op_py_boolean>`
:param rlxd: ``'on'`` || |dl| ``'off'`` |dr|
Indicates whether correction for deformation energy is
employed in computing interaction energies. Option available
(See :ref:`sec:availableDatabases`) only for databases of bimolecular complexes
with non-frozen monomers, e.g., HBC6.
:type symm: :ref:`boolean <op_py_boolean>`
:param symm: |dl| ``'on'`` |dr| || ``'off'``
Indicates whether the native symmetry of the database reagents is
employed (``'on'``) or whether it is forced to :math:`C_1` symmetry
(``'off'``). Some computational methods (e.g., SAPT) require no
symmetry, and this will be set by database().
:type zpe: :ref:`boolean <op_py_boolean>`
:param zpe: ``'on'`` || |dl| ``'off'`` |dr|
Indicates whether zero-point-energy corrections are appended to
single-point energy values. Option valid only for certain
thermochemical databases. Disabled until Hessians ready.
:type benchmark: str
:param benchmark: |dl| ``'default'`` |dr| || ``'S22A'`` || etc.
Indicates whether a non-default set of reference energies, if
available (See :ref:`sec:availableDatabases`), are employed for the
calculation of error statistics.
:type tabulate: List[str]
:param tabulate: |dl| ``[]`` |dr| || ``['scf total energy', 'natom']`` || etc.
Indicates whether to form tables of variables other than the
primary requested energy. Available for any PSI variable.
:type subset: Union[str, List[str]]
:param subset:
Indicates a subset of the full database to run. This is a very
flexible option and can be used in three distinct ways, outlined
below. Note that two take a string and the last takes an array.
See :ref:`sec:availableDatabases` for available values.
* ``'small'`` || ``'large'`` || ``'equilibrium'``
Calls predefined subsets of the requested database, either
``'small'``, a few of the smallest database members,
``'large'``, the largest of the database members, or
``'equilibrium'``, the equilibrium geometries for a database
composed of dissociation curves.
* ``'BzBz_S'`` || ``'FaOOFaON'`` || ``'ArNe'`` || ``'HB'`` || etc.
For databases composed of dissociation curves, or otherwise
divided into subsets, individual curves and subsets can be
called by name. Consult the database python files for available
molecular systems (case insensitive).
* ``[1,2,5]`` || ``['1','2','5']`` || ``['BzMe-3.5', 'MeMe-5.0']`` || etc.
Specify a list of database members to run. Consult the
database python files for available molecular systems. This
is the only portion of database input that is case sensitive;
choices for this keyword must match the database python file.
:examples:
>>> # [1] Two-stage SCF calculation on short, equilibrium, and long helium dimer
>>> db('scf','RGC10',cast_up='sto-3g',subset=['HeHe-0.85','HeHe-1.0','HeHe-1.5'], tabulate=['scf total energy','natom'])
>>> # [2] Counterpoise-corrected interaction energies for three complexes in S22
>>> # Error statistics computed wrt an old benchmark, S22A
>>> database('mp2','S22',cp=1,subset=[16,17,8],benchmark='S22A')
>>> # [3] SAPT0 on the neon dimer dissociation curve
>>> db('sapt0',subset='NeNe',cp=0,symm=0,db_name='RGC10')
>>> # [4] Optimize system 1 in database S22, producing tables of scf and mp2 energy
>>> db('mp2','S22',db_func=optimize,subset=[1], tabulate=['mp2 total energy','current energy'])
>>> # [5] CCSD on the smallest systems of HTBH, a hydrogen-transfer database
>>> database('ccsd','HTBH',subset='small', tabulate=['ccsd total energy', 'mp2 total energy'])
"""
lowername = name #TODO
kwargs = p4util.kwargs_lower(kwargs)
# Wrap any positional arguments into kwargs (for intercalls among wrappers)
if not ('name' in kwargs) and name:
kwargs['name'] = name #.lower()
if not ('db_name' in kwargs) and db_name:
kwargs['db_name'] = db_name
# Establish function to call
func = kwargs.pop('db_func', kwargs.pop('func', energy))
kwargs['db_func'] = func
# Bounce to CP if bsse kwarg (someday)
if kwargs.get('bsse_type', None) is not None:
raise ValidationError(
"""Database: Cannot specify bsse_type for database. Use the cp keyword withing database instead."""
)
allowoptexceeded = kwargs.get('allowoptexceeded', False)
optstash = p4util.OptionsState(['WRITER_FILE_LABEL'], ['SCF', 'REFERENCE'])
# Wrapper wholly defines molecule. discard any passed-in
kwargs.pop('molecule', None)
# Paths to search for database files: here + PSIPATH + library + PYTHONPATH
db_paths = []
db_paths.append(os.getcwd())
db_paths.extend(os.environ.get('PSIPATH', '').split(os.path.pathsep))
db_paths.append(os.path.join(core.get_datadir(), 'databases'))
db_paths.append(os.path.dirname(__file__))
db_paths = list(map(os.path.abspath, db_paths))
sys.path[1:1] = db_paths
# TODO this should be modernized a la interface_cfour
# Define path and load module for requested database
database = p4util.import_ignorecase(db_name)
if database is None:
core.print_out('\nPython module for database %s failed to load\n\n' %
(db_name))
core.print_out('\nSearch path that was tried:\n')
core.print_out(", ".join(map(str, sys.path)))
raise ValidationError("Python module loading problem for database " +
str(db_name))
else:
dbse = database.dbse
HRXN = database.HRXN
ACTV = database.ACTV
RXNM = database.RXNM
BIND = database.BIND
TAGL = database.TAGL
GEOS = database.GEOS
try:
DATA = database.DATA
except AttributeError:
DATA = {}
user_writer_file_label = core.get_global_option('WRITER_FILE_LABEL')
user_reference = core.get_global_option('REFERENCE')
# Configuration based upon e_name & db_name options
# Force non-supramolecular if needed
if not hasattr(lowername, '__call__') and re.match(r'^.*sapt', lowername):
try:
database.ACTV_SA
except AttributeError:
raise ValidationError(
'Database %s not suitable for non-supramolecular calculation.'
% (db_name))
else:
ACTV = database.ACTV_SA
# Force open-shell if needed
openshell_override = 0
if user_reference in ['RHF', 'RKS']:
try:
database.isOS
except AttributeError:
pass
else:
if p4util.yes.match(str(database.isOS)):
openshell_override = 1
core.print_out(
'\nSome reagents in database %s require an open-shell reference; will be reset to UHF/UKS as needed.\n'
% (db_name))
# Configuration based upon database keyword options
# Option symmetry- whether symmetry treated normally or turned off (currently req'd for dfmp2 & dft)
db_symm = kwargs.get('symm', True)
symmetry_override = 0
if db_symm is False:
symmetry_override = 1
elif db_symm is True:
pass
else:
raise ValidationError("""Symmetry mode '%s' not valid.""" % (db_symm))
# Option mode of operation- whether db run in one job or files farmed out
db_mode = kwargs.pop('db_mode', kwargs.pop('mode', 'continuous')).lower()
kwargs['db_mode'] = db_mode
if db_mode == 'continuous':
pass
elif db_mode == 'sow':
pass
elif db_mode == 'reap':
db_linkage = kwargs.get('linkage', None)
if db_linkage is None:
raise ValidationError(
"""Database execution mode 'reap' requires a linkage option."""
)
else:
raise ValidationError("""Database execution mode '%s' not valid.""" %
(db_mode))
# Option counterpoise- whether for interaction energy databases run in bsse-corrected or not
db_cp = kwargs.get('cp', False)
if db_cp is True:
try:
database.ACTV_CP
except AttributeError:
raise ValidationError(
"""Counterpoise correction mode 'yes' invalid for database %s."""
% (db_name))
else:
ACTV = database.ACTV_CP
elif db_cp is False:
pass
else:
raise ValidationError(
"""Counterpoise correction mode '%s' not valid.""" % (db_cp))
# Option relaxed- whether for non-frozen-monomer interaction energy databases include deformation correction or not?
db_rlxd = kwargs.get('rlxd', False)
if db_rlxd is True:
if db_cp is True:
try:
database.ACTV_CPRLX
database.RXNM_CPRLX
except AttributeError:
raise ValidationError(
'Deformation and counterpoise correction mode \'yes\' invalid for database %s.'
% (db_name))
else:
ACTV = database.ACTV_CPRLX
RXNM = database.RXNM_CPRLX
elif db_cp is False:
try:
database.ACTV_RLX
except AttributeError:
raise ValidationError(
'Deformation correction mode \'yes\' invalid for database %s.'
% (db_name))
else:
ACTV = database.ACTV_RLX
elif db_rlxd is False:
#elif no.match(str(db_rlxd)):
pass
else:
raise ValidationError('Deformation correction mode \'%s\' not valid.' %
(db_rlxd))
# Option zero-point-correction- whether for thermochem databases jobs are corrected by zpe
db_zpe = kwargs.get('zpe', False)
if db_zpe is True:
raise ValidationError(
'Zero-point-correction mode \'yes\' not yet implemented.')
elif db_zpe is False:
pass
else:
raise ValidationError('Zero-point-correction \'mode\' %s not valid.' %
(db_zpe))
# Option benchmark- whether error statistics computed wrt alternate reference energies
db_benchmark = 'default'
if 'benchmark' in kwargs:
db_benchmark = kwargs['benchmark']
if db_benchmark.lower() == 'default':
pass
else:
BIND = p4util.getattr_ignorecase(database, 'BIND_' + db_benchmark)
if BIND is None:
raise ValidationError(
'Special benchmark \'%s\' not available for database %s.' %
(db_benchmark, db_name))
# Option tabulate- whether tables of variables other than primary energy method are formed
# TODO db(func=cbs,tabulate=[non-current-energy]) # broken
db_tabulate = []
if 'tabulate' in kwargs:
db_tabulate = kwargs['tabulate']
# Option subset- whether all of the database or just a portion is run
db_subset = HRXN
if 'subset' in kwargs:
db_subset = kwargs['subset']
if isinstance(db_subset, (str, bytes)):
if db_subset.lower() == 'small':
try:
database.HRXN_SM
except AttributeError:
raise ValidationError(
"""Special subset 'small' not available for database %s."""
% (db_name))
else:
HRXN = database.HRXN_SM
elif db_subset.lower() == 'large':
try:
database.HRXN_LG
except AttributeError:
raise ValidationError(
"""Special subset 'large' not available for database %s."""
% (db_name))
else:
HRXN = database.HRXN_LG
elif db_subset.lower() == 'equilibrium':
try:
database.HRXN_EQ
except AttributeError:
raise ValidationError(
"""Special subset 'equilibrium' not available for database %s."""
% (db_name))
else:
HRXN = database.HRXN_EQ
else:
HRXN = p4util.getattr_ignorecase(database, db_subset)
if HRXN is None:
HRXN = p4util.getattr_ignorecase(database, 'HRXN_' + db_subset)
if HRXN is None:
raise ValidationError(
"""Special subset '%s' not available for database %s."""
% (db_subset, db_name))
else:
temp = []
for rxn in db_subset:
if rxn in HRXN:
temp.append(rxn)
else:
raise ValidationError(
"""Subset element '%s' not a member of database %s.""" %
(str(rxn), db_name))
HRXN = temp
temp = []
for rxn in HRXN:
temp.append(ACTV['%s-%s' % (dbse, rxn)])
HSYS = p4util.drop_duplicates(sum(temp, []))
# Sow all the necessary reagent computations
core.print_out("\n\n")
p4util.banner(("Database %s Computation" % (db_name)))
core.print_out("\n")
# write index of calcs to output file
instructions = """\n The database single-job procedure has been selected through mode='continuous'.\n"""
instructions += """ Calculations for the reagents will proceed in the order below and will be followed\n"""
instructions += """ by summary results for the database.\n\n"""
for rgt in HSYS:
instructions += """ %-s\n""" % (rgt)
core.print_out(instructions)
# Loop through chemical systems
ERGT = {}
ERXN = {}
VRGT = {}
VRXN = {}
for rgt in HSYS:
VRGT[rgt] = {}
core.print_out('\n')
p4util.banner(' Database {} Computation: Reagent {} \n {}'.format(
db_name, rgt, TAGL[rgt]))
core.print_out('\n')
molecule = core.Molecule.from_dict(GEOS[rgt].to_dict())
molecule.set_name(rgt)
molecule.update_geometry()
if symmetry_override:
molecule.reset_point_group('c1')
molecule.fix_orientation(True)
molecule.fix_com(True)
molecule.update_geometry()
if (openshell_override) and (molecule.multiplicity() != 1):
if user_reference == 'RHF':
core.set_global_option('REFERENCE', 'UHF')
elif user_reference == 'RKS':
core.set_global_option('REFERENCE', 'UKS')
core.set_global_option(
'WRITER_FILE_LABEL', user_writer_file_label +
('' if user_writer_file_label == '' else '-') + rgt)
if allowoptexceeded:
try:
ERGT[rgt] = func(molecule=molecule, **kwargs)
except ConvergenceError:
core.print_out(f"Optimization exceeded cycles for {rgt}")
ERGT[rgt] = 0.0
else:
ERGT[rgt] = func(molecule=molecule, **kwargs)
core.print_variables()
core.print_out(" Database Contributions Map:\n {}\n".format('-' *
75))
for rxn in HRXN:
db_rxn = dbse + '-' + str(rxn)
if rgt in ACTV[db_rxn]:
core.print_out(
' reagent {} contributes by {:.4f} to reaction {}\n'.
format(rgt, RXNM[db_rxn][rgt], db_rxn))
core.print_out('\n')
for envv in db_tabulate:
VRGT[rgt][envv.upper()] = core.variable(envv)
core.set_global_option("REFERENCE", user_reference)
core.clean()
#core.opt_clean()
core.clean_variables()
# Reap all the necessary reaction computations
core.print_out("\n")
p4util.banner(("Database %s Results" % (db_name)))
core.print_out("\n")
maxactv = []
for rxn in HRXN:
maxactv.append(len(ACTV[dbse + '-' + str(rxn)]))
maxrgt = max(maxactv)
table_delimit = '-' * (62 + 20 * maxrgt)
tables = ''
# find any reactions that are incomplete
FAIL = collections.defaultdict(int)
for rxn in HRXN:
db_rxn = dbse + '-' + str(rxn)
for i in range(len(ACTV[db_rxn])):
if abs(ERGT[ACTV[db_rxn][i]]) < 1.0e-12:
if not allowoptexceeded:
FAIL[rxn] = 1
# tabulate requested process::environment variables
tables += """ For each VARIABLE requested by tabulate, a 'Reaction Value' will be formed from\n"""
tables += """ 'Reagent' values according to weightings 'Wt', as for the REQUESTED ENERGY below.\n"""
tables += """ Depending on the nature of the variable, this may or may not make any physical sense.\n"""
for rxn in HRXN:
db_rxn = dbse + '-' + str(rxn)
VRXN[db_rxn] = {}
for envv in db_tabulate:
envv = envv.upper()
tables += """\n ==> %s <==\n\n""" % (envv.title())
tables += _tblhead(maxrgt, table_delimit, 2)
for rxn in HRXN:
db_rxn = dbse + '-' + str(rxn)
if FAIL[rxn]:
tables += """\n%23s %8s %8s %8s %8s""" % (db_rxn, '', '****',
'', '')
for i in range(len(ACTV[db_rxn])):
tables += """ %16.8f %2.0f""" % (VRGT[
ACTV[db_rxn][i]][envv], RXNM[db_rxn][ACTV[db_rxn][i]])
else:
VRXN[db_rxn][envv] = 0.0
for i in range(len(ACTV[db_rxn])):
VRXN[db_rxn][envv] += VRGT[
ACTV[db_rxn][i]][envv] * RXNM[db_rxn][ACTV[db_rxn][i]]
tables += """\n%23s %16.8f """ % (
db_rxn, VRXN[db_rxn][envv])
for i in range(len(ACTV[db_rxn])):
tables += """ %16.8f %2.0f""" % (VRGT[
ACTV[db_rxn][i]][envv], RXNM[db_rxn][ACTV[db_rxn][i]])
tables += """\n %s\n""" % (table_delimit)
# tabulate primary requested energy variable with statistics
count_rxn = 0
minDerror = 100000.0
maxDerror = 0.0
MSDerror = 0.0
MADerror = 0.0
RMSDerror = 0.0
tables += """\n ==> %s <==\n\n""" % ('Requested Energy')
tables += _tblhead(maxrgt, table_delimit, 1)
for rxn in HRXN:
db_rxn = dbse + '-' + str(rxn)
if FAIL[rxn]:
tables += """\n%23s %8.4f %8s %10s %10s""" % (
db_rxn, BIND[db_rxn], '****', '****', '****')
for i in range(len(ACTV[db_rxn])):
tables += """ %16.8f %2.0f""" % (ERGT[ACTV[db_rxn][i]],
RXNM[db_rxn][ACTV[db_rxn][i]])
else:
ERXN[db_rxn] = 0.0
for i in range(len(ACTV[db_rxn])):
ERXN[db_rxn] += ERGT[ACTV[db_rxn][i]] * RXNM[db_rxn][
ACTV[db_rxn][i]]
error = constants.hartree2kcalmol * ERXN[db_rxn] - BIND[db_rxn]
tables += """\n%23s %8.4f %8.4f %10.4f %10.4f""" % (
db_rxn, BIND[db_rxn], constants.hartree2kcalmol * ERXN[db_rxn],
error, error * constants.cal2J)
for i in range(len(ACTV[db_rxn])):
tables += """ %16.8f %2.0f""" % (ERGT[ACTV[db_rxn][i]],
RXNM[db_rxn][ACTV[db_rxn][i]])
if abs(error) < abs(minDerror):
minDerror = error
if abs(error) > abs(maxDerror):
maxDerror = error
MSDerror += error
MADerror += abs(error)
RMSDerror += error * error
count_rxn += 1
tables += """\n %s\n""" % (table_delimit)
if count_rxn:
MSDerror /= float(count_rxn)
MADerror /= float(count_rxn)
RMSDerror = math.sqrt(RMSDerror / float(count_rxn))
tables += """%23s %19s %10.4f %10.4f\n""" % (
'Minimal Dev', '', minDerror, minDerror * constants.cal2J)
tables += """%23s %19s %10.4f %10.4f\n""" % (
'Maximal Dev', '', maxDerror, maxDerror * constants.cal2J)
tables += """%23s %19s %10.4f %10.4f\n""" % (
'Mean Signed Dev', '', MSDerror, MSDerror * constants.cal2J)
tables += """%23s %19s %10.4f %10.4f\n""" % (
'Mean Absolute Dev', '', MADerror, MADerror * constants.cal2J)
tables += """%23s %19s %10.4f %10.4f\n""" % (
'RMS Dev', '', RMSDerror, RMSDerror * constants.cal2J)
tables += """ %s\n""" % (table_delimit)
core.set_variable('%s DATABASE MEAN SIGNED DEVIATION' % (db_name),
MSDerror)
core.set_variable('%s DATABASE MEAN ABSOLUTE DEVIATION' % (db_name),
MADerror)
core.set_variable('%s DATABASE ROOT-MEAN-SQUARE DEVIATION' % (db_name),
RMSDerror)
core.print_out(tables)
finalenergy = MADerror
else:
finalenergy = 0.0
optstash.restore()
DB_RGT.clear()
DB_RGT.update(VRGT)
DB_RXN.clear()
DB_RXN.update(VRXN)
return finalenergy
