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)
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)
def test_ape(self):
f = AtomicPackingEfficiency()
ef = ElementFraction()
ef.set_n_jobs(1)
# Test the APE calculation routines
self.assertAlmostEqual(1.11632, f.get_ideal_radius_ratio(15))
self.assertAlmostEqual(0.154701, f.get_ideal_radius_ratio(2))
self.assertAlmostEqual(1.65915, f.get_ideal_radius_ratio(27))
self.assertAlmostEqual(15, f.find_ideal_cluster_size(1.116)[0])
self.assertAlmostEqual(3, f.find_ideal_cluster_size(0.1)[0])
self.assertAlmostEqual(24, f.find_ideal_cluster_size(2)[0])
# Test the nearest neighbor lookup tool
nn_lookup = f.create_cluster_lookup_tool(
[Element('Cu'), Element('Zr')])
# Check that the table gets the correct structures
stable_clusters = [
Composition('CuZr10'),
Composition('Cu6Zr6'),
Composition('Cu8Zr5'),
Composition('Cu13Zr1'),
Composition('Cu3Zr12'),
Composition('Cu8Zr8'),
Composition('Cu12Zr5'),
Composition('Cu17Zr')
]
ds, _ = nn_lookup.kneighbors(ef.featurize_many(stable_clusters),
n_neighbors=1)
self.assertArrayAlmostEqual([[0]] * 8, ds)
self.assertEqual(8, nn_lookup._fit_X.shape[0])
# Swap the order of the clusters, make sure it gets the same list
nn_lookup_swapped = f.create_cluster_lookup_tool(
[Element('Zr'), Element('Cu')])
self.assertArrayAlmostEqual(sorted(nn_lookup._fit_X.tolist()),
sorted(nn_lookup_swapped._fit_X.tolist()))
# Make sure we had a cache hit
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().misses)
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().hits)
# Change the tolerance, see if it changes the results properly
f.threshold = 0.002
nn_lookup = f.create_cluster_lookup_tool(
[Element('Cu'), Element('Zr')])
self.assertEqual(2, nn_lookup._fit_X.shape[0])
ds, _ = nn_lookup.kneighbors(ef.featurize_many(
[Composition('CuZr10'),
Composition('Cu3Zr12')]),
n_neighbors=1)
self.assertArrayAlmostEqual([[0]] * 2, ds)
# Make sure we had a cache miss
self.assertEqual(2, f._create_cluster_lookup_tool.cache_info().misses)
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().hits)
# Compute the distances from Cu50Zr50
mean_dists = f.compute_nearest_cluster_distance(Composition('CuZr'))
self.assertArrayAlmostEqual([0.424264, 0.667602, 0.800561],
mean_dists,
decimal=6)
# Compute the optimal APE for Cu50Zr50
self.assertArrayAlmostEqual([0.000233857, 0.003508794],
f.compute_simultaneous_packing_efficiency(
Composition('Cu50Zr50')))
# Test the dataframe calculator
df = pd.DataFrame({'comp': [Composition('CuZr')]})
df = f.featurize_dataframe(df, 'comp')
self.assertEqual(6, len(df.columns))
self.assertIn('dist from 5 clusters |APE| < 0.002', df.columns)
self.assertAlmostEqual(0.003508794,
df['mean abs simul. packing efficiency'][0])
# Make sure it works with composition that do not match any efficient clusters
feat = f.compute_nearest_cluster_distance(Composition('Al'))
self.assertArrayAlmostEqual([1] * 3, feat)
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_ape(self):
f = AtomicPackingEfficiency()
ef = ElementFraction()
ef.set_n_jobs(1)
# Test the APE calculation routines
self.assertAlmostEqual(1.11632, f.get_ideal_radius_ratio(15))
self.assertAlmostEqual(0.154701, f.get_ideal_radius_ratio(2))
self.assertAlmostEqual(1.65915, f.get_ideal_radius_ratio(27))
self.assertAlmostEqual(15, f.find_ideal_cluster_size(1.116)[0])
self.assertAlmostEqual(3, f.find_ideal_cluster_size(0.1)[0])
self.assertAlmostEqual(24, f.find_ideal_cluster_size(2)[0])
# Test the nearest neighbor lookup tool
nn_lookup = f.create_cluster_lookup_tool([Element('Cu'),
Element('Zr')])
# Check that the table gets the correct structures
stable_clusters = [Composition('CuZr10'), Composition('Cu6Zr6'),
Composition('Cu8Zr5'), Composition('Cu13Zr1'),
Composition('Cu3Zr12'), Composition('Cu8Zr8'),
Composition('Cu12Zr5'), Composition('Cu17Zr')]
ds, _ = nn_lookup.kneighbors(
ef.featurize_many(stable_clusters),
n_neighbors=1)
self.assertArrayAlmostEqual([[0]]*8, ds)
self.assertEqual(8, nn_lookup._fit_X.shape[0])
# Swap the order of the clusters, make sure it gets the same list
nn_lookup_swapped = f.create_cluster_lookup_tool([Element('Zr'),
Element('Cu')])
self.assertArrayAlmostEqual(sorted(nn_lookup._fit_X.tolist()),
sorted(nn_lookup_swapped._fit_X.tolist()))
# Make sure we had a cache hit
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().misses)
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().hits)
# Change the tolerance, see if it changes the results properly
f.threshold = 0.002
nn_lookup = f.create_cluster_lookup_tool([Element('Cu'),
Element('Zr')])
self.assertEqual(2, nn_lookup._fit_X.shape[0])
ds, _ = nn_lookup.kneighbors(
ef.featurize_many([Composition('CuZr10'), Composition('Cu3Zr12')]),
n_neighbors=1)
self.assertArrayAlmostEqual([[0]]*2, ds)
# Make sure we had a cache miss
self.assertEqual(2, f._create_cluster_lookup_tool.cache_info().misses)
self.assertEqual(1, f._create_cluster_lookup_tool.cache_info().hits)
# Compute the distances from Cu50Zr50
mean_dists = f.compute_nearest_cluster_distance(Composition('CuZr'))
self.assertArrayAlmostEqual([0.424264, 0.667602, 0.800561], mean_dists,
decimal=6)
# Compute the optimal APE for Cu50Zr50
self.assertArrayAlmostEqual([0.000233857, 0.003508794],
f.compute_simultaneous_packing_efficiency(
Composition('Cu50Zr50')
))
# Test the dataframe calculator
df = pd.DataFrame({'comp': [Composition('CuZr')]})
f.featurize_dataframe(df, 'comp')
self.assertEqual(6, len(df.columns))
self.assertIn('dist from 5 clusters |APE| < 0.002', df.columns)
self.assertAlmostEqual(0.003508794,
df['mean abs simul. packing efficiency'][0])
# Make sure it works with composition that do not match any efficient clusters
feat = f.compute_nearest_cluster_distance(Composition('Al'))
self.assertArrayAlmostEqual([1]*3, feat)