def get_structure_properties(structure: Structure, mode: str = 'all') -> dict:
if mode == 'all':
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset(
'CoordinationNumber_ward-prb-2017'),
StructuralHeterogeneity(),
ChemicalOrdering(),
DensityFeatures(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
'LocalPropertyDifference_ward-prb-2017'),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
else:
# Calculate only those which do not need a Voronoi tesselation
featurizer = MultipleFeaturizer([
DensityFeatures(),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
X = featurizer.featurize(structure)
matminer_dict = dict(list(zip(featurizer.feature_labels(), X)))
matminer_dict['volume'] = structure.volume
return matminer_dict
def featurize_structures(self, featurizer=None, **kwargs):
"""
Featurizes the hypothetical structures available from
hypo_structures method. Hypothetical structures for which
featurization fails are removed and valid structures are
made available as valid_structures
Args:
featurizer (Featurizer): A MatMiner Featurizer.
Defaults to MultipleFeaturizer with PRB Ward
Voronoi descriptors.
**kwargs (dict): kwargs passed to featurize_many
method of featurizer.
Returns:
(pandas.DataFrame): features
"""
# Note the redundancy here is for pandas to work
if self.hypo_structures is None:
warnings.warn("No structures available. Generating structures.")
self.get_structures()
print("Generating features")
featurizer = featurizer if featurizer else MultipleFeaturizer([
SiteStatsFingerprint.from_preset("CoordinationNumber_ward-prb-2017"),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset("LocalPropertyDifference_ward-prb-2017"),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=['frac'])),
StructureComposition(IonProperty(fast=True))
])
features = featurizer.featurize_many(
self.hypo_structures['structure'],
ignore_errors=True, **kwargs)
n_species, formula = [], []
for s in self.hypo_structures['structure']:
n_species.append(len(s.composition.elements))
formula.append(s.composition.formula)
self._features_df = pd.DataFrame.from_records(
features, columns=featurizer.feature_labels())
self._features_df.index = self.hypo_structures.index
self._features_df['N_species'] = n_species
self._features_df['Composition'] = formula
self._features_df['structure'] = self.hypo_structures['structure']
self.features = self._features_df.dropna(axis=0, how='any')
self.features = self.features.reindex(sorted(self.features.columns), axis=1)
self._valid_structure_labels = list(self.features.index)
self.valid_structures = self.hypo_structures.loc[self._valid_structure_labels]
print("{} out of {} structures were successfully featurized.".format(
self.features.shape[0], self._features_df.shape[0]))
return self.features
def featurize_composition(df: pd.DataFrame) -> pd.DataFrame:
""" Decorate input `pandas.DataFrame` of structures with composition
features from matminer.
Currently applies the set of all matminer composition features.
Args:
df (pandas.DataFrame): the input dataframe with `"structure"`
column containing `pymatgen.Structure` objects.
Returns:
pandas.DataFrame: the decorated DataFrame.
"""
logging.info("Applying composition featurizers...")
df = df.copy()
df['composition'] = df['structure'].apply(lambda s: s.composition)
featurizer = MultipleFeaturizer([ElementProperty.from_preset("magpie"),
AtomicOrbitals(),
BandCenter(),
# ElectronAffinity(), - This descriptor was not used in the paper preset
Stoichiometry(),
ValenceOrbital(),
IonProperty(),
ElementFraction(),
TMetalFraction(),
# CohesiveEnergy(), - This descriptor was not used in the paper preset
Miedema(),
YangSolidSolution(),
AtomicPackingEfficiency(),
])
df = featurizer.featurize_dataframe(df, "composition", multiindex=True, ignore_errors=True)
df.columns = df.columns.map('|'.join).str.strip('|')
ox_featurizer = MultipleFeaturizer([OxidationStates(),
ElectronegativityDiff()
])
df = CompositionToOxidComposition().featurize_dataframe(df, "Input Data|composition")
df = ox_featurizer.featurize_dataframe(df, "composition_oxid", multiindex=True, ignore_errors=True)
df = df.rename(columns={'Input Data': ''})
df.columns = df.columns.map('|'.join).str.strip('|')
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df['AtomicOrbitals|HOMO_character'] = df['AtomicOrbitals|HOMO_character'].map(_orbitals)
df['AtomicOrbitals|LUMO_character'] = df['AtomicOrbitals|LUMO_character'].map(_orbitals)
df['AtomicOrbitals|HOMO_element'] = df['AtomicOrbitals|HOMO_element'].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z
)
df['AtomicOrbitals|LUMO_element'] = df['AtomicOrbitals|LUMO_element'].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z
)
df = df.replace([np.inf, -np.inf, np.nan], 0)
return clean_df(df)
def similarity(_parents, target):
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset("CoordinationNumber_ward-prb-2017"),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
"LocalPropertyDifference_ward-prb-2017"),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=["frac"])),
StructureComposition(IonProperty(fast=True)),
])
# HACK celery doesn't work with multiprocessing (used by matminer)
try:
from celery import current_task
if current_task:
featurizer.set_n_jobs(1)
except ImportError:
pass
x_target = pd.DataFrame.from_records([featurizer.featurize(target)],
columns=featurizer.feature_labels())
x_parent = pd.DataFrame.from_records(
featurizer.featurize_many(_parents, ignore_errors=True, pbar=False),
columns=featurizer.feature_labels(),
)
nulls = x_parent[x_parent.isnull().any(axis=1)].index.values
x_parent.fillna(100000, inplace=True)
x_target = x_target.reindex(sorted(x_target.columns), axis=1)
x_parent = x_parent.reindex(sorted(x_parent.columns), axis=1)
with open(os.path.join(settings.rxn_files, "scaler2.pickle"), "rb") as f:
scaler = pickle.load(f)
with open(os.path.join(settings.rxn_files, "quantiles.pickle"), "rb") as f:
quantiles = pickle.load(f)
X = scaler.transform(x_parent.append(x_target))
D = [pairwise_distances(np.array([row, X[-1]]))[0, 1] for row in X[:-1]]
_res = []
for d in D:
_res.append(np.linspace(0, 1, 101)[np.abs(quantiles - d).argmin()])
_res = np.array(_res)
_res[nulls] = -1
return _res
def test_stoich(self):
featurizer = Stoichiometry(num_atoms=True)
df_stoich = Stoichiometry(num_atoms=True).featurize_dataframe(self.df, col_id="composition")
self.assertAlmostEqual(df_stoich["num atoms"][0], 5)
self.assertAlmostEqual(df_stoich["0-norm"][0], 2)
self.assertAlmostEqual(df_stoich["7-norm"][0], 0.604895199)
# Test whether the number of formula units affects result
original_value = featurizer.featurize(Composition("FeO"))
self.assertArrayAlmostEqual(featurizer.featurize(Composition("Fe0.5O0.5")), original_value)
self.assertArrayAlmostEqual(featurizer.featurize(Composition("Fe2O2")), original_value)
class DeBreuck2020Featurizer(modnet.featurizers.MODFeaturizer):
""" Featurizer presets used for the paper 'Machine learning
materials properties for small datasets' by Pierre-Paul De Breuck,
Geoffroy Hautier & Gian-Marco Rignanese, arXiv:2004.14766 (2020).
Uses most of the featurizers implemented by matminer at the time of
writing with their default hyperparameters and presets.
"""
from matminer.featurizers.composition import (
AtomicOrbitals,
AtomicPackingEfficiency,
BandCenter,
# CohesiveEnergy, - This descriptor was not used in the paper preset
# ElectronAffinity, - This descriptor was not used in the paper preset
ElectronegativityDiff,
ElementFraction,
ElementProperty,
IonProperty,
Miedema,
OxidationStates,
Stoichiometry,
TMetalFraction,
ValenceOrbital,
YangSolidSolution,
)
from matminer.featurizers.structure import (
# BagofBonds, - This descriptor was not used in the paper preset
BondFractions,
ChemicalOrdering,
CoulombMatrix,
DensityFeatures,
EwaldEnergy,
GlobalSymmetryFeatures,
MaximumPackingEfficiency,
# PartialRadialDistributionFunction,
RadialDistributionFunction,
SineCoulombMatrix,
StructuralHeterogeneity,
XRDPowderPattern,
)
from matminer.featurizers.site import (
AGNIFingerprints,
AverageBondAngle,
AverageBondLength,
BondOrientationalParameter,
ChemEnvSiteFingerprint,
CoordinationNumber,
CrystalNNFingerprint,
GaussianSymmFunc,
GeneralizedRadialDistributionFunction,
LocalPropertyDifference,
OPSiteFingerprint,
VoronoiFingerprint,
)
composition_featurizers = (
AtomicOrbitals(),
AtomicPackingEfficiency(),
BandCenter(),
ElementFraction(),
ElementProperty.from_preset("magpie"),
IonProperty(),
Miedema(),
Stoichiometry(),
TMetalFraction(),
ValenceOrbital(),
YangSolidSolution(),
)
oxide_composition_featurizers = (
ElectronegativityDiff(),
OxidationStates(),
)
structure_featurizers = (
DensityFeatures(),
GlobalSymmetryFeatures(),
RadialDistributionFunction(),
CoulombMatrix(),
# PartialRadialDistributionFunction(),
SineCoulombMatrix(),
EwaldEnergy(),
BondFractions(),
StructuralHeterogeneity(),
MaximumPackingEfficiency(),
ChemicalOrdering(),
XRDPowderPattern(),
# BagofBonds(),
)
site_featurizers = (
AGNIFingerprints(),
AverageBondAngle(VoronoiNN()),
AverageBondLength(VoronoiNN()),
BondOrientationalParameter(),
ChemEnvSiteFingerprint.from_preset("simple"),
CoordinationNumber(),
CrystalNNFingerprint.from_preset("ops"),
GaussianSymmFunc(),
GeneralizedRadialDistributionFunction.from_preset("gaussian"),
LocalPropertyDifference(),
OPSiteFingerprint(),
VoronoiFingerprint(),
)
def featurize_composition(self, df):
""" Applies the preset composition featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_composition(df)
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df['AtomicOrbitals|HOMO_character'] = df[
'AtomicOrbitals|HOMO_character'].map(_orbitals)
df['AtomicOrbitals|LUMO_character'] = df[
'AtomicOrbitals|LUMO_character'].map(_orbitals)
df['AtomicOrbitals|HOMO_element'] = df[
'AtomicOrbitals|HOMO_element'].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z)
df['AtomicOrbitals|LUMO_element'] = df[
'AtomicOrbitals|LUMO_element'].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z)
df = df.replace([np.inf, -np.inf, np.nan], 0)
return modnet.featurizers.clean_df(df)
def featurize_structure(self, df):
""" Applies the preset structural featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_structure(df)
dist = df[
"RadialDistributionFunction|radial distribution function"].iloc[0][
'distances'][:50]
for i, d in enumerate(dist):
_rdf_key = "RadialDistributionFunction|radial distribution function|d_{:.2f}".format(
d)
df[_rdf_key] = df[
"RadialDistributionFunction|radial distribution function"].apply(
lambda x: x['distribution'][i])
df = df.drop("RadialDistributionFunction|radial distribution function",
axis=1)
_crystal_system = {
"cubic": 1,
"tetragonal": 2,
"orthorombic": 3,
"hexagonal": 4,
"trigonal": 5,
"monoclinic": 6,
"triclinic": 7
}
def _int_map(x):
if x == np.nan:
return 0
elif x:
return 1
else:
return 0
df["GlobalSymmetryFeatures|crystal_system"] = df[
"GlobalSymmetryFeatures|crystal_system"].map(_crystal_system)
df["GlobalSymmetryFeatures|is_centrosymmetric"] = df[
"GlobalSymmetryFeatures|is_centrosymmetric"].map(_int_map)
return modnet.featurizers.clean_df(df)
def featurize_site(self, df):
""" Applies the preset site featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
# rename some features for backwards compatibility with pretrained models
aliases = {
"GeneralizedRadialDistributionFunction": "GeneralizedRDF",
"AGNIFingerprints": "AGNIFingerPrint",
"BondOrientationalParameter": "BondOrientationParameter",
"GaussianSymmFunc": "ChemEnvSiteFingerprint|GaussianSymmFunc",
}
df = super().featurize_site(df, aliases=aliases)
df = df.loc[:, (df != 0).any(axis=0)]
return modnet.featurizers.clean_df(df)
class FUTURE_PROSPECTS_2021(featurizer.extendedMODFeaturizer):
from matminer.featurizers.composition import (
AtomicOrbitals,
AtomicPackingEfficiency,
BandCenter,
CohesiveEnergy,
ElectronAffinity,
ElectronegativityDiff,
ElementFraction,
ElementProperty,
IonProperty,
Miedema,
OxidationStates,
Stoichiometry,
TMetalFraction,
ValenceOrbital,
YangSolidSolution,
)
from matminer.featurizers.structure import (
BagofBonds,
BondFractions,
ChemicalOrdering,
CoulombMatrix,
DensityFeatures,
EwaldEnergy,
GlobalSymmetryFeatures,
MaximumPackingEfficiency,
PartialRadialDistributionFunction,
RadialDistributionFunction,
SineCoulombMatrix,
StructuralHeterogeneity,
XRDPowderPattern,
)
from matminer.featurizers.site import (
AGNIFingerprints,
AverageBondAngle,
AverageBondLength,
BondOrientationalParameter,
ChemEnvSiteFingerprint,
CoordinationNumber,
CrystalNNFingerprint,
GaussianSymmFunc,
GeneralizedRadialDistributionFunction,
LocalPropertyDifference,
OPSiteFingerprint,
VoronoiFingerprint,
)
from matminer.featurizers.dos import (
DOSFeaturizer,
SiteDOS,
Hybridization,
DosAsymmetry,
)
from matminer.featurizers.bandstructure import (
BandFeaturizer,
BranchPointEnergy
)
composition_featurizers = (
AtomicOrbitals(),
AtomicPackingEfficiency(),
BandCenter(),
ElementFraction(),
ElementProperty.from_preset("magpie"),
IonProperty(),
Miedema(),
Stoichiometry(),
TMetalFraction(),
ValenceOrbital(),
YangSolidSolution(),
)
oxid_composition_featurizers = (
ElectronegativityDiff(),
OxidationStates(),
)
structure_featurizers = (
DensityFeatures(),
GlobalSymmetryFeatures(),
RadialDistributionFunction(),
CoulombMatrix(),
#PartialRadialDistributionFunction(), #Introduces a large amount of features
SineCoulombMatrix(),
EwaldEnergy(),
BondFractions(),
StructuralHeterogeneity(),
MaximumPackingEfficiency(),
ChemicalOrdering(),
XRDPowderPattern(),
)
site_featurizers = (
AGNIFingerprints(),
AverageBondAngle(VoronoiNN()),
AverageBondLength(VoronoiNN()),
BondOrientationalParameter(),
ChemEnvSiteFingerprint.from_preset("simple"),
CoordinationNumber(),
CrystalNNFingerprint.from_preset("ops"),
GaussianSymmFunc(),
GeneralizedRadialDistributionFunction.from_preset("gaussian"),
LocalPropertyDifference(),
OPSiteFingerprint(),
VoronoiFingerprint(),
)
dos_featurizers = (
DOSFeaturizer(),
SiteDOS(),
Hybridization()
)
band_featurizers = (
BandFeaturizer(),
BranchPointEnergy()
)
def __init__(self, n_jobs=None):
self._n_jobs = n_jobs
def featurize_composition(self, df):
"""Applies the preset composition featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_composition(df)
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df["AtomicOrbitals|HOMO_character"] = df["AtomicOrbitals|HOMO_character"].map(
_orbitals
)
df["AtomicOrbitals|LUMO_character"] = df["AtomicOrbitals|LUMO_character"].map(
_orbitals
)
df["AtomicOrbitals|HOMO_element"] = df["AtomicOrbitals|HOMO_element"].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z
)
df["AtomicOrbitals|LUMO_element"] = df["AtomicOrbitals|LUMO_element"].apply(
lambda x: -1 if not isinstance(x, str) else Element(x).Z
)
return clean_df(df)
def featurize_structure(self, df):
"""Applies the preset structural featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_structure(df)
dist = df["RadialDistributionFunction|radial distribution function"].iloc[0][
"distances"
][:50]
for i, d in enumerate(dist):
_rdf_key = "RadialDistributionFunction|radial distribution function|d_{:.2f}".format(
d
)
df[_rdf_key] = df[
"RadialDistributionFunction|radial distribution function"
].apply(lambda x: x["distribution"][i])
df = df.drop("RadialDistributionFunction|radial distribution function", axis=1)
_crystal_system = {
"cubic": 1,
"tetragonal": 2,
"orthorombic": 3,
"hexagonal": 4,
"trigonal": 5,
"monoclinic": 6,
"triclinic": 7,
}
def _int_map(x):
if x == np.nan:
return 0
elif x:
return 1
else:
return 0
df["GlobalSymmetryFeatures|crystal_system"] = df[
"GlobalSymmetryFeatures|crystal_system"
].map(_crystal_system)
df["GlobalSymmetryFeatures|is_centrosymmetric"] = df[
"GlobalSymmetryFeatures|is_centrosymmetric"
].map(_int_map)
return clean_df(df)
def featurize_dos(self, df):
"""Applies the presetdos featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_dos(df)
hotencodeColumns = ["DOSFeaturizer|vbm_specie_1","DOSFeaturizer|cbm_specie_1"]
one_hot = pd.get_dummies(df[hotencodeColumns])
df = df.drop(hotencodeColumns, axis = 1).join(one_hot)
_orbitals = {"s": 1, "p": 2, "d": 3, "f": 4}
df["DOSFeaturizer|vbm_character_1"] = df[
"DOSFeaturizer|vbm_character_1"
].map(_orbitals)
df["DOSFeaturizer|cbm_character_1"] = df[
"DOSFeaturizer|cbm_character_1"
].map(_orbitals)
# Splitting one feature into several floating features
# e.g. number;number;number into three columns
splitColumns = ["DOSFeaturizer|cbm_location_1", "DOSFeaturizer|vbm_location_1"]
for column in splitColumns:
try:
newColumns = df[column].str.split(";", n = 2, expand = True)
for i in range(0,3):
df[column + "_" + str(i)] = np.array(newColumns[i]).astype(np.float)
except:
continue
df = df.drop(splitColumns, axis=1)
df = df.drop(["dos"], axis=1)
return clean_df(df)
def featurize_bandstructure(self, df):
"""Applies the preset band structure featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
df = super().featurize_bandstructure(df)
def _int_map(x):
if str(x) == "False":
return 0
elif str(x) == "True":
return 1
df["BandFeaturizer|is_gap_direct"] = df[
"BandFeaturizer|is_gap_direct"
].map(_int_map)
df = df.drop(["bandstructure"], axis=1)
return clean_df(df)
def featurize_site(self, df):
"""Applies the preset site featurizers to the input dataframe,
renames some fields and cleans the output dataframe.
"""
aliases = {
"GeneralizedRadialDistributionFunction": "GeneralizedRDF",
"AGNIFingerprints": "AGNIFingerPrint",
"BondOrientationalParameter": "BondOrientationParameter",
"GaussianSymmFunc": "ChemEnvSiteFingerprint|GaussianSymmFunc",
}
df = super().featurize_site(df, aliases=aliases)
df = df.loc[:, (df != 0).any(axis=0)]
return clean_df(df)
def predict_log10_eps(
target: Union[Structure, Composition],
dielectric_type: str,
model_type: str,
) -> float:
"""
:param target: structure or composition to predict dielectric constants
:param dielectric_type: "el" or "ion"
:param model_type: "comp" or "comp_st"
:return: Descriptor vector
"""
if dielectric_type not in ["el", "ion"]:
raise ValueError(
f'Specify dielectric type "el" or "ion"\nInput: {dielectric_type}')
if model_type not in ["comp", "comp_st"]:
raise ValueError(
f'Specify regression_type "comp" or "comp_st"\nInput: {model_type}'
)
if model_type == "comp":
if isinstance(target, Structure):
comp = target.composition
else:
comp = target
comp_oxi = comp.add_charges_from_oxi_state_guesses()
if dielectric_type == "el":
ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"),
comp)
valence = ScalarFeaturizer(ValenceOrbital(), comp)
ion_prop = ScalarFeaturizer(IonProperty(), comp)
en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi)
oxi_state = ScalarFeaturizer(OxidationStates.from_preset("deml"),
comp_oxi)
atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp)
descriptor = [
ep.get_from_label("PymatgenData minimum X"),
ep.get_from_label("PymatgenData range X"),
ep.get_from_label("PymatgenData std_dev X"),
ep.get_from_label("PymatgenData mean row"),
ep.get_from_label("PymatgenData std_dev row"),
ep.get_from_label("PymatgenData mean group"),
ep.get_from_label("PymatgenData mean block"),
ep.get_from_label("PymatgenData std_dev block"),
ep.get_from_label("PymatgenData mean atomic_mass"),
ep.get_from_label("PymatgenData std_dev atomic_mass"),
ep.get_from_label("PymatgenData std_dev atomic_radius"),
ep.get_from_label("PymatgenData minimum mendeleev_no"),
ep.get_from_label("PymatgenData range mendeleev_no"),
ep.get_from_label("PymatgenData std_dev mendeleev_no"),
ep.get_from_label("PymatgenData mean thermal_conductivity"),
ep.get_from_label("PymatgenData std_dev thermal_conductivity"),
ep.get_from_label("PymatgenData mean melting_point"),
ep.get_from_label("PymatgenData std_dev melting_point"),
valence.get_from_label("avg s valence electrons"),
valence.get_from_label("avg d valence electrons"),
valence.get_from_label("frac s valence electrons"),
valence.get_from_label("frac p valence electrons"),
valence.get_from_label("frac d valence electrons"),
ion_prop.get_from_label("avg ionic char"),
TMetalFraction().featurize(comp)[0],
en_diff.get_from_label("maximum EN difference"),
en_diff.get_from_label("range EN difference"),
en_diff.get_from_label("mean EN difference"),
en_diff.get_from_label("std_dev EN difference"),
BandCenter().featurize(comp)[0],
oxi_state.get_from_label("std_dev oxidation state"),
atomic_orbital.get_from_label("HOMO_energy"),
atomic_orbital.get_from_label("LUMO_energy"),
atomic_orbital.get_from_label("gap_AO"),
]
elif dielectric_type == "ion":
stoich = ScalarFeaturizer(Stoichiometry(), comp)
ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"),
comp)
valence = ScalarFeaturizer(ValenceOrbital(), comp)
ion_prop = ScalarFeaturizer(IonProperty(), comp)
en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi)
oxi_state = ScalarFeaturizer(OxidationStates.from_preset("deml"),
comp_oxi)
atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp)
at_pack_eff = ScalarFeaturizer(AtomicPackingEfficiency(), comp)
descriptor = [
stoich.get_from_label("3-norm"),
stoich.get_from_label("5-norm"),
ep.get_from_label("PymatgenData mean X"),
ep.get_from_label("PymatgenData mean row"),
ep.get_from_label("PymatgenData std_dev row"),
ep.get_from_label("PymatgenData std_dev group"),
ep.get_from_label("PymatgenData mean block"),
ep.get_from_label("PymatgenData std_dev block"),
ep.get_from_label("PymatgenData maximum atomic_mass"),
ep.get_from_label("PymatgenData range atomic_mass"),
ep.get_from_label("PymatgenData mean atomic_mass"),
ep.get_from_label("PymatgenData std_dev atomic_mass"),
ep.get_from_label("PymatgenData maximum atomic_radius"),
ep.get_from_label("PymatgenData range atomic_radius"),
ep.get_from_label("PymatgenData mean atomic_radius"),
ep.get_from_label("PymatgenData std_dev atomic_radius"),
ep.get_from_label("PymatgenData minimum mendeleev_no"),
ep.get_from_label("PymatgenData mean mendeleev_no"),
ep.get_from_label("PymatgenData std_dev mendeleev_no"),
ep.get_from_label("PymatgenData mean thermal_conductivity"),
ep.get_from_label("PymatgenData std_dev thermal_conductivity"),
ep.get_from_label("PymatgenData mean melting_point"),
ep.get_from_label("PymatgenData std_dev melting_point"),
valence.get_from_label("avg s valence electrons"),
valence.get_from_label("frac s valence electrons"),
valence.get_from_label("frac p valence electrons"),
valence.get_from_label("frac d valence electrons"),
ion_prop.get_from_label("avg ionic char"),
TMetalFraction().featurize(comp)[0],
en_diff.get_from_label("minimum EN difference"),
en_diff.get_from_label("range EN difference"),
en_diff.get_from_label("mean EN difference"),
en_diff.get_from_label("std_dev EN difference"),
oxi_state.get_from_label("range oxidation state"),
oxi_state.get_from_label("std_dev oxidation state"),
atomic_orbital.get_from_label("LUMO_energy"),
atomic_orbital.get_from_label("gap_AO"),
at_pack_eff.get_from_label("mean simul. packing efficiency"),
at_pack_eff.get_from_label(
"mean abs simul. packing efficiency"),
at_pack_eff.get_from_label(
"dist from 1 clusters |APE| < 0.010"),
at_pack_eff.get_from_label(
"dist from 3 clusters |APE| < 0.010"),
at_pack_eff.get_from_label(
"dist from 5 clusters |APE| < 0.010"),
]
elif model_type == "comp_st":
if isinstance(target, Composition):
raise ValueError(
'comp_st (Using compositional and structural descriptor) is specified, '
'but target is composition')
comp: Composition = target.composition
comp_oxi = comp.add_charges_from_oxi_state_guesses()
target_orig = deepcopy(target)
target.add_oxidation_state_by_guess()
if dielectric_type == "el":
ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"),
comp)
valence = ScalarFeaturizer(ValenceOrbital(), comp)
en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi)
atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp)
density = ScalarFeaturizer(DensityFeatures(), target)
dist_btw_nn = MinimumRelativeDistances().featurize(target_orig)
opsf = SiteFeaturizer(OPSiteFingerprint(), target)
voro_fp = SiteFeaturizer(VoronoiFingerprint(use_symm_weights=True),
target)
gsf = SiteFeaturizer(GaussianSymmFunc(), target)
lpd = SiteFeaturizer(
LocalPropertyDifference.from_preset("ward-prb-2017"), target)
descriptor = [
ep.get_from_label("PymatgenData std_dev X"),
ep.get_from_label("PymatgenData mean block"),
ep.get_from_label("PymatgenData std_dev atomic_mass"),
valence.get_from_label("frac d valence electrons"),
TMetalFraction().featurize(comp)[0],
en_diff.get_from_label("maximum EN difference"),
en_diff.get_from_label("mean EN difference"),
atomic_orbital.get_from_label("HOMO_energy"),
atomic_orbital.get_from_label("LUMO_energy"),
density.get_from_label("density"),
np.mean(dist_btw_nn),
np.std(dist_btw_nn),
opsf.get_from_label_func("tetrahedral CN_4", np.max),
opsf.get_from_label_func("rectangular see-saw-like CN_4",
np.max),
np.max([
EwaldSiteEnergy(accuracy=4).featurize(target, i)
for i in range(target.num_sites)
]),
voro_fp.get_from_label_func("Voro_area_std_dev", np.max),
voro_fp.get_from_label_func("Voro_area_std_dev", np.mean),
voro_fp.get_from_label_func("Voro_dist_minimum", np.min),
voro_fp.get_from_label_func("Voro_dist_minimum", np.std),
gsf.get_from_label_func("G2_20.0", np.std),
gsf.get_from_label_func("G2_80.0", np.max),
gsf.get_from_label_func("G4_0.005_4.0_-1.0", np.mean),
lpd.get_from_label_func("local difference in NdValence",
np.mean),
lpd.get_from_label_func("local difference in NValence",
np.min),
lpd.get_from_label_func("local difference in NValence",
np.std),
lpd.get_from_label_func("local difference in NdUnfilled",
np.mean),
lpd.get_from_label_func("local difference in NUnfilled",
np.min),
lpd.get_from_label_func("local difference in NUnfilled",
np.mean),
lpd.get_from_label_func("local difference in GSmagmom",
np.mean)
]
elif dielectric_type == "ion":
ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"),
comp)
atomic_orbitals = ScalarFeaturizer(AtomicOrbitals(), comp)
density = ScalarFeaturizer(DensityFeatures(), target)
str_het = ScalarFeaturizer(StructuralHeterogeneity(), target)
opsf = SiteFeaturizer(OPSiteFingerprint(), target)
voro_fp = SiteFeaturizer(VoronoiFingerprint(use_symm_weights=True),
target)
gsf = SiteFeaturizer(GaussianSymmFunc(), target)
lpd = SiteFeaturizer(
LocalPropertyDifference.from_preset("ward-prb-2017"), target)
descriptor = [
ep.get_from_label("PymatgenData std_dev row"),
ep.get_from_label("PymatgenData mean thermal_conductivity"),
ep.get_from_label("PymatgenData std_dev melting_point"),
TMetalFraction().featurize(comp)[0],
atomic_orbitals.get_from_label("gap_AO"),
density.get_from_label("density"),
density.get_from_label("packing fraction"),
str_het.get_from_label("mean neighbor distance variation"),
str_het.get_from_label("avg_dev neighbor distance variation"),
opsf.get_from_label_func("sgl_bd CN_1", np.mean),
opsf.get_from_label_func("bent 150 degrees CN_2", np.mean),
opsf.get_from_label_func("linear CN_2", np.mean),
opsf.get_from_label_func("trigonal planar CN_3", np.mean),
opsf.get_from_label_func("pentagonal planar CN_5", np.std),
opsf.get_from_label_func("octahedral CN_6", np.max),
opsf.get_from_label_func("octahedral CN_6", np.std),
opsf.get_from_label_func("q6 CN_12", np.mean),
np.max([
EwaldSiteEnergy(accuracy=4).featurize(target, i)
for i in range(target.num_sites)
]),
voro_fp.get_from_label_func("Symmetry_weighted_index_4",
np.std),
voro_fp.get_from_label_func("Voro_vol_maximum", np.mean),
voro_fp.get_from_label_func("Voro_area_std_dev", np.mean),
voro_fp.get_from_label_func("Voro_area_minimum", np.std),
voro_fp.get_from_label_func("Voro_area_maximum", np.min),
voro_fp.get_from_label_func("Voro_dist_std_dev", np.mean),
gsf.get_from_label_func("G2_80.0", np.min),
gsf.get_from_label_func("G4_0.005_4.0_1.0", np.std),
lpd.get_from_label_func("local difference in Number", np.max),
lpd.get_from_label_func("local difference in MendeleevNumber",
np.max),
lpd.get_from_label_func("local difference in MendeleevNumber",
np.min),
lpd.get_from_label_func("local difference in AtomicWeight",
np.max),
lpd.get_from_label_func("local difference in AtomicWeight",
np.mean),
lpd.get_from_label_func("local difference in MeltingT",
np.mean),
lpd.get_from_label_func("local difference in Row", np.max),
lpd.get_from_label_func(
"local difference in Electronegativity", np.min),
lpd.get_from_label_func("local difference in NValence",
np.std),
lpd.get_from_label_func("local difference in NsUnfilled",
np.mean),
lpd.get_from_label_func("local difference in NdUnfilled",
np.max),
lpd.get_from_label_func("local difference in NdUnfilled",
np.std),
lpd.get_from_label_func("local difference in NUnfilled",
np.max),
lpd.get_from_label_func("local difference in NUnfilled",
np.min),
lpd.get_from_label_func("local difference in NUnfilled",
np.mean),
lpd.get_from_label_func("local difference in NUnfilled",
np.std),
lpd.get_from_label_func("local difference in GSvolume_pa",
np.max),
lpd.get_from_label_func("local difference in GSvolume_pa",
np.min),
lpd.get_from_label_func("local difference in SpaceGroupNumber",
np.max),
]
with open(
f"{os.path.dirname(__file__)}/{dielectric_type}_{model_type}.joblib",
"rb") as fr:
model: RandomForestRegressor = joblib.load(fr)
with open(
f"{os.path.dirname(__file__)}/{dielectric_type}_{model_type}_scaler.joblib",
"rb") as fr:
scaler: StandardScaler = joblib.load(fr)
descriptor = scaler.transform([descriptor])
return model.predict(descriptor)[0]
def test_stoich(self):
df_stoich = Stoichiometry(num_atoms=True).featurize_dataframe(
self.df, col_id="composition")
self.assertAlmostEqual(df_stoich["num atoms"][0], 5)
self.assertAlmostEqual(df_stoich["0-norm"][0], 2)
self.assertAlmostEqual(df_stoich["7-norm"][0], 0.604895199)
'MeltingT', 'NsValence', 'NpValence', 'NdValence',
'NfValence', 'NValence', 'NsUnfilled', 'NpUnfilled',
'NdUnfilled', 'NfUnfilled', 'NUnfilled', 'GSvolume_pa',
'SpaceGroupNumber', 'GSbandgap', 'GSmagmom')
#The following features will be created by using matminer package.
featurizer = MultipleFeaturizer([
SiteStatsFingerprint(CoordinationNumber().from_preset('VoronoiNN'),
stats=('mean', 'std_dev', 'minimum', 'maximum')),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint(
LocalPropertyDifference(properties=element_properties),
stats=('mean', 'std_dev', 'minimum', 'maximum', 'range')),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=['frac'])),
StructureComposition(IonProperty(fast=True))
])
#Generate VT based features from the material's crystal lat_params.
feature_data = featurizer.featurize_dataframe(df,
col_id=['structure'],
ignore_errors=True)
#"lat_params","compound possible" and "material_id" are not resonable physical features, so we drop these three columns
feature_data = feature_data.drop(
["structure", "compound possible", "material_id"], axis=1)
#write the data into a csv file for later use
feature_data.to_csv("data_delta_e_data.csv", index=False)
from sklearn.model_selection import KFold, cross_val_score