def _parse_criteria(self, criteria):
"""
Internal method to perform mapping of criteria to proper mongo queries
using aliases, as well as some useful sanitization. For example, string
formulas such as "Fe2O3" are auto-converted to proper mongo queries of
{"Fe":2, "O":3}.
If 'criteria' is None, returns an empty dict. Putting this logic here
simplifies callers and allows subclasses to insert something even
when there are no criteria.
"""
if criteria is None:
return dict()
parsed_crit = dict()
for k, v in self.default_criteria.items():
if k not in criteria:
parsed_crit[self.aliases.get(k, k)] = v
for key, crit in list(criteria.items()):
if key in ["normalized_formula", "reduced_cell_formula"]:
comp = Composition(crit)
parsed_crit["pretty_formula"] = comp.reduced_formula
elif key == "unit_cell_formula":
comp = Composition(crit)
crit = comp.as_dict()
for el, amt in crit.items():
parsed_crit["{}.{}".format(self.aliases[key], el)] = amt
parsed_crit["nelements"] = len(crit)
parsed_crit['pretty_formula'] = comp.reduced_formula
elif key in ["$or", "$and"]:
parsed_crit[key] = [self._parse_criteria(m) for m in crit]
else:
parsed_crit[self.aliases.get(key, key)] = crit
return parsed_crit
def _parse_criteria(self, criteria):
"""
Internal method to perform mapping of criteria to proper mongo queries
using aliases, as well as some useful sanitization. For example, string
formulas such as "Fe2O3" are auto-converted to proper mongo queries of
{"Fe":2, "O":3}.
If 'criteria' is None, returns an empty dict. Putting this logic here
simplifies callers and allows subclasses to insert something even
when there are no criteria.
"""
if criteria is None:
return dict()
parsed_crit = dict()
for k, v in self.defaults.items():
if k not in criteria:
parsed_crit[self.aliases.get(k, k)] = v
for key, crit in list(criteria.items()):
if key in ["normalized_formula", "reduced_cell_formula"]:
comp = Composition(crit)
parsed_crit["pretty_formula"] = comp.reduced_formula
elif key == "unit_cell_formula":
comp = Composition(crit)
crit = comp.as_dict()
for el, amt in crit.items():
parsed_crit["{}.{}".format(self.aliases[key], el)] = amt
parsed_crit["nelements"] = len(crit)
parsed_crit['pretty_formula'] = comp.reduced_formula
elif key in ["$or", "$and"]:
parsed_crit[key] = [self._parse_criteria(m) for m in crit]
else:
parsed_crit[self.aliases.get(key, key)] = crit
return parsed_crit
def id_mobile_ion(formula):
"""id_mobile_ion
Given a formula, identifies the mobile ion present, if any.
:param formula: Formula to fetch working ion from.
"""
c = Composition(formula)
wi = [el for el in c.as_dict() if el in mobile_ion]
return wi[0]
def get_composition_from_string(comp_str):
"""validate and return composition from string `comp_str`."""
from pymatgen import Composition, Element
comp = Composition(comp_str)
for element in comp.elements:
Element(element)
formula = comp.get_integer_formula_and_factor()[0]
comp = Composition(formula)
return ''.join([
'{}{}'.format(key, int(value) if value > 1 else '')
for key, value in comp.as_dict().items()
])
def get_composition_from_string(comp_str):
"""validate and return composition from string `comp_str`."""
from pymatgen import Composition, Element
comp = Composition(comp_str)
for element in comp.elements:
Element(element)
formula = comp.get_integer_formula_and_factor()[0]
comp = Composition(formula)
return ''.join([
'{}{}'.format(key,
int(value) if value > 1 else '')
for key, value in comp.as_dict().items()
])
def get_qmpy_formation_energy(total_e, formula, n_atoms):
"""
Helper function to computer qmpy-compatible formation
energy using reference energies extracted from OQMD
Args:
total_e (float): total energy
formula (str): chemical formula
n_atoms (int): number of atoms
Returns:
(float): qmpy-compatible formation energy
"""
composition = Composition(formula).fractional_composition
energy = total_e / n_atoms
for element, weight in composition.as_dict().items():
energy -= QMPY_REFERENCES[element] * weight
if (element in QMPY_REFERENCES_HUBBARD) and ("O" in composition):
energy -= QMPY_REFERENCES_HUBBARD[element] * weight
return energy
def compute_corrections(self, exp_entries: list,
calc_entries: dict) -> dict:
"""
Computes the corrections and fills in correction, corrections_std_error, and corrections_dict.
Args:
exp_entries: list of dictionary objects with the following keys/values:
{"formula": chemical formula, "exp energy": formation energy in eV/formula unit,
"uncertainty": uncertainty in formation energy}
calc_entries: dictionary of computed entries, of the form {chemical formula: ComputedEntry}
Raises:
ValueError: calc_compounds is missing an entry
"""
self.exp_compounds = exp_entries
self.calc_compounds = calc_entries
self.names: List[str] = []
self.diffs: List[float] = []
self.coeff_mat: List[List[float]] = []
self.exp_uncer: List[float] = []
# remove any corrections in calc_compounds
for entry in self.calc_compounds.values():
entry.correction = 0
for cmpd_info in self.exp_compounds:
# to get consistent element ordering in formula
name = Composition(cmpd_info["formula"]).reduced_formula
allow = True
compound = self.calc_compounds.get(name, None)
if not compound:
warnings.warn(
"Compound {} is not found in provided computed entries and is excluded from the fit"
.format(name))
continue
# filter out compounds with large uncertainties
relative_uncertainty = abs(cmpd_info["uncertainty"] /
cmpd_info["exp energy"])
if relative_uncertainty > self.max_error:
allow = False
warnings.warn(
"Compound {} is excluded from the fit due to high experimental uncertainty ({}%)"
.format(name, relative_uncertainty))
# filter out compounds containing certain polyanions
for anion in self.exclude_polyanions:
if anion in name or anion in cmpd_info["formula"]:
allow = False
warnings.warn(
"Compound {} contains the polyanion {} and is excluded from the fit"
.format(name, anion))
break
# filter out compounds that are unstable
if isinstance(self.allow_unstable, float):
try:
eah = compound.data["e_above_hull"]
except KeyError:
raise ValueError("Missing e above hull data")
if eah > self.allow_unstable:
allow = False
warnings.warn(
"Compound {} is unstable and excluded from the fit (e_above_hull = {})"
.format(name, eah))
if allow:
comp = Composition(name)
elems = list(comp.as_dict())
reactants = []
for elem in elems:
try:
elem_name = Composition(elem).reduced_formula
reactants.append(self.calc_compounds[elem_name])
except KeyError:
raise ValueError("Computed entries missing " + elem)
rxn = ComputedReaction(reactants, [compound])
rxn.normalize_to(comp)
energy = rxn.calculated_reaction_energy
coeff = []
for specie in self.species:
if specie == "oxide":
if compound.data["oxide_type"] == "oxide":
coeff.append(comp["O"])
self.oxides.append(name)
else:
coeff.append(0)
elif specie == "peroxide":
if compound.data["oxide_type"] == "peroxide":
coeff.append(comp["O"])
self.peroxides.append(name)
else:
coeff.append(0)
elif specie == "superoxide":
if compound.data["oxide_type"] == "superoxide":
coeff.append(comp["O"])
self.superoxides.append(name)
else:
coeff.append(0)
elif specie == "S":
if Element("S") in comp:
sf_type = "sulfide"
if compound.data.get("sulfide_type"):
sf_type = compound.data["sulfide_type"]
elif hasattr(compound, "structure"):
sf_type = sulfide_type(compound.structure)
if sf_type == "sulfide":
coeff.append(comp["S"])
self.sulfides.append(name)
else:
coeff.append(0)
else:
coeff.append(0)
else:
try:
coeff.append(comp[specie])
except ValueError:
raise ValueError(
"We can't detect this specie: {}".format(
specie))
self.names.append(name)
self.diffs.append(
(cmpd_info["exp energy"] - energy) / comp.num_atoms)
self.coeff_mat.append([i / comp.num_atoms for i in coeff])
self.exp_uncer.append(
(cmpd_info["uncertainty"]) / comp.num_atoms)
# for any exp entries with no uncertainty value, assign average uncertainty value
sigma = np.array(self.exp_uncer)
sigma[sigma == 0] = np.nan
with warnings.catch_warnings():
warnings.simplefilter(
"ignore", category=RuntimeWarning
) # numpy raises warning if the entire array is nan values
mean_uncer = np.nanmean(sigma)
sigma = np.where(np.isnan(sigma), mean_uncer, sigma)
if np.isnan(mean_uncer):
# no uncertainty values for any compounds, don't try to weight
popt, self.pcov = curve_fit(_func,
self.coeff_mat,
self.diffs,
p0=np.ones(len(self.species)))
else:
popt, self.pcov = curve_fit(
_func,
self.coeff_mat,
self.diffs,
p0=np.ones(len(self.species)),
sigma=sigma,
absolute_sigma=True,
)
self.corrections = popt.tolist()
self.corrections_std_error = np.sqrt(np.diag(self.pcov)).tolist()
for i in range(len(self.species)):
self.corrections_dict[self.species[i]] = (
round(self.corrections[i], 3),
round(self.corrections_std_error[i], 4),
)
return self.corrections_dict
#bandgap_str = formula+','+str(bandgap[0])
out = list(out)
#print(out)
df_avial["Eg"]=out
df_avial.to_csv("roost_screening_result_exp1_208_m9.csv", index=False, header=True)
df_bandgap = pd.read_csv('./roost_screening_result_exp2_127_m211.csv')
"""
3. discard item whose band gap value < 6
"""
df_filtered = df_bandgap[df_bandgap["Eg"] >= 6]
num_atom_l = []
num_elements_l = []
for c in df_filtered["composition"]:
c = Composition(c)
num_elements = len(c.as_dict())
num_atom = c.num_atoms
num_atom_l.append(num_atom)
num_elements_l.append(num_elements)
df_filtered["num_atom"] = num_atom_l
df_filtered["# of elements"] = num_elements_l
df_filtered = df_filtered[df_filtered["num_atom"] < 8]
df_filtered = df_filtered[df_filtered["# of elements"] < 4]
df_filtered.to_csv("roost_simple_candidate_exp1_M9.csv", index=False, header=True)
print('success!')
def get_qmpy_formation_energy(total_e, formula, n_atoms):
mus = {
u'Ac': -4.1060035325,
u'Ag': -2.8217729525,
u'Al': -3.74573946,
u'Ar': -0.00636995,
u'As': -4.651918435,
u'Au': -3.26680174,
u'B': -6.67796758,
u'Ba': -1.92352708,
u'Be': -3.75520865,
u'Bi': -4.038931855,
u'Br': -1.31759562258416,
u'C': -9.2170759925,
u'Ca': -1.977817,
u'Cd': -0.90043514,
u'Ce': -4.7771708225,
u'Cl': -1.47561368438088,
u'Co': -7.089565,
u'Cr': -9.50844998,
u'Cs': -0.85462775,
u'Cu': -3.7159594,
u'Dy': -4.60150328333333,
u'Er': -4.56334055,
u'Eu': -1.8875732,
u'F': -1.45692429086889,
u'Fe': -8.3078978,
u'Ga': -3.031846515,
u'Gd': -4.6550712925,
u'Ge': -4.623692585,
u'H': -3.38063384781582,
u'He': -0.004303435,
u'Hf': -9.955368785,
u'Hg': -0.358963825033731,
u'Ho': -4.57679364666667,
u'I': -1.35196205757168,
u'In': -2.71993876,
u'Ir': -8.8549203,
u'K': -1.096699335,
u'Kr': -0.004058825,
u'La': -4.93543556,
u'Li': -1.89660627,
u'Lu': -4.524181525,
u'Mg': -1.54251595083333,
u'Mn': -9.0269032462069,
u'Mo': -10.8480839,
u'N': -8.11974103465649,
u'Na': -1.19920373914835,
u'Nb': -10.09391206,
u'Nd': -4.762916335,
u'Ne': -0.02931791,
u'Ni': -5.56661952,
u'Np': -12.94027372125,
u'O': -4.52329546412125,
u'Os': -11.22597601,
u'P': -5.15856496104006,
u'Pa': -9.49577589,
u'Pb': -3.70396484,
u'Pd': -5.17671826,
u'Pm': -4.7452352875,
u'Pr': -4.7748066125,
u'Pt': -6.05575959,
u'Pu': -14.29838348,
u'Rb': -0.9630733,
u'Re': -12.422818875,
u'Rh': -7.26940476,
u'Ru': -9.2019888,
u'S': -3.83888286598664,
u'Sb': -4.117563025,
u'Sc': -6.328367185,
u'Se': -3.48117276,
u'Si': -5.424892535,
u'Sm': -4.7147675825,
u'Sn': -3.9140929231488,
u'Sr': -1.6829138,
u'Ta': -11.85252937,
u'Tb': -5.28775675533333,
u'Tc': -10.360747885,
u'Te': -3.14184237666667,
u'Th': -7.41301719,
u'Ti': -7.69805778621374,
u'Tl': -2.359420025,
u'Tm': -4.47502416,
u'U': -11.292348705,
u'V': -8.94097896,
u'W': -12.96020695,
u'Xe': 0.00306349,
u'Y': -6.464420635,
u'Yb': -1.51277545,
u'Zn': -1.2660268,
u'Zr': -8.54717235
}
hubbard_mus = {
u'Co': 2.0736240219357,
u'Cr': 2.79591214925926,
u'Cu': 1.457571831687,
u'Fe': 2.24490453841424,
u'Mn': 2.08652912841877,
u'Ni': 2.56766185643768,
u'Np': 2.77764768949249,
u'Pu': 2.2108747749433,
u'Th': 1.06653674624248,
u'U': 2.57513786752409,
u'V': 2.67812162528461
}
from pymatgen import Composition
c = Composition(formula).fractional_composition
e = total_e / n_atoms
for k, v in c.as_dict().items():
e -= mus[k] * v
if (k in hubbard_mus) and ('O' in c):
e -= hubbard_mus[k] * v
return e
