def __init__(self, materials, site_descriptors, query=None, **kwargs):
"""
Calculates site descriptors for materials
Args:
materials (Store): Store of materials documents
site_descriptors (Store): Store of site-descriptors data such as tetrahedral order parameter or percentage of 8-fold coordination
query (dict): dictionary to limit materials to be analyzed
"""
self.materials = materials
self.site_descriptors = site_descriptors
self.query = query if query else {}
# Set up all targeted site descriptors.
self.sds = {}
for nn in NearNeighbors.__subclasses__():
nn_ = getattr(pymatgen.analysis.local_env, nn.__name__)
t = nn.__name__ if nn.__name__ \
not in cls_to_abbrev.keys() \
else cls_to_abbrev[nn.__name__]
k = 'cn_{}'.format(t)
self.sds[k] = CoordinationNumber(nn_(), use_weights=False)
k = 'cn_wt_{}'.format(t)
self.sds[k] = CoordinationNumber(nn_(), use_weights=True)
self.sds['opsf'] = OPSiteFingerprint()
#self.sds['csf'] = CrystalSiteFingerprint.from_preset('ops')
super().__init__(sources=[materials],
targets=[site_descriptors],
**kwargs)
def __init__(self, materials, descriptors, **kwargs):
"""
Calculates site-based descriptors (e.g., coordination numbers
with different near-neighbor finding approaches) for materials and
runs statistics analysis on selected descriptor types
(order parameter-based site fingerprints). The latter is
useful as a definition of a structure fingerprint
on the basis of local coordination information.
Furthermore, composition descriptors are calculated
(Magpie element property vector).
Args:
materials (Store): Store of materials documents.
descriptors (Store): Store of composition, site, and
structure descriptor data such
as tetrahedral order parameter or
fraction of being 8-fold coordinated.
mat_query (dict): dictionary to limit materials to be analyzed.
"""
self.materials = materials
self.descriptors = descriptors
# Set up all targeted site descriptors.
self.sds = {}
for nn in nn_target_classes:
nn_ = getattr(local_env, nn)
k = "cn_{}".format(nn)
self.sds[k] = CoordinationNumber(nn_(), use_weights="none")
k = "cn_wt_{}".format(nn)
self.sds[k] = CoordinationNumber(nn_(), use_weights="sum")
self.all_output_pieces = {"site_descriptors": [k for k in self.sds.keys()]}
self.sds["csf"] = CrystalNNFingerprint.from_preset("ops",
distance_cutoffs=None,
x_diff_weight=None)
self.all_output_pieces["statistics"] = ["csf"]
# Set up all targeted composition descriptors.
self.cds = {}
self.cds["magpie"] = ElementProperty.from_preset("magpie")
self.all_output_pieces["composition_descriptors"] = ["magpie"]
self.all_output_pieces["meta"] = ["atomate"]
super().__init__(source=materials,
target=descriptors,
ufn=self.calc,
projection=["structure"],
**kwargs)
def get_fps(structure, cutoff=10.0, processes=8):
all_descrs = []
try:
coordination_number_ = CoordinationNumber.from_preset('VoronoiNN')
voronoi_fps_ = VoronoiFingerprintModified(
cutoff=cutoff).featurize_structure(structure)
crystal_nn_fingerprint_ = CrystalNNFingerprint.from_preset('cn')
op_site_fingerprint_ = OPSiteFingerprint()
agni_fingerprints_ = AGNIFingerprints()
gaussian_symm_func_fps_ = GaussianSymmFuncModified(
).featurize_structure(structure)
pymatgen_data_ = PymatgenData()
magpie_data_ = MagpieData()
data_list = [[
structure, i, site, coordination_number_, voronoi_fps_,
crystal_nn_fingerprint_, op_site_fingerprint_, agni_fingerprints_,
gaussian_symm_func_fps_, pymatgen_data_, magpie_data_
] for i, site in enumerate(structure)]
pool = multiprocessing.Pool(processes=processes)
all_descrs = np.array(pool.map(get_all_site_descrs, data_list))
except (AttributeError, IndexError) as error:
pass
return all_descrs
def __init__(self, materials, descriptors, mat_query=None, **kwargs):
"""
Calculates site-based descriptors (e.g., coordination numbers
with different near-neighbor finding approaches) for materials and
runs statistics analysis on selected descriptor types
(order parameter-based site fingerprints). The latter is
useful as a definition of a structure fingerprint
on the basis of local coordination information.
Furthermore, composition descriptors are calculated
(Magpie element property vector).
Args:
materials (Store): Store of materials documents.
descriptors (Store): Store of composition, site, and
structure descriptor data such
as tetrahedral order parameter or
fraction of being 8-fold coordinated.
mat_query (dict): dictionary to limit materials to be analyzed.
"""
self.materials = materials
self.descriptors = descriptors
self.mat_query = mat_query if mat_query else {}
# Set up all targeted site descriptors.
self.sds = {}
for nn in nn_target_classes:
nn_ = getattr(pymatgen.analysis.local_env, nn)
k = 'cn_{}'.format(nn)
self.sds[k] = CoordinationNumber(nn_(), use_weights='none')
k = 'cn_wt_{}'.format(nn)
self.sds[k] = CoordinationNumber(nn_(), use_weights='sum')
self.all_output_pieces = {
'site_descriptors': [k for k in self.sds.keys()]
}
self.sds['csf'] = CrystalNNFingerprint.from_preset(
'ops', distance_cutoffs=None, x_diff_weight=None)
self.all_output_pieces['statistics'] = ['csf']
# Set up all targeted composition descriptors.
self.cds = {}
self.cds["magpie"] = ElementProperty.from_preset('magpie')
self.all_output_pieces['composition_descriptors'] = ['magpie']
self.all_output_pieces['meta'] = ['atomate']
super().__init__(sources=[materials], targets=[descriptors], **kwargs)
def __init__(self, materials, site_descriptors, mat_query=None, **kwargs):
"""
Calculates site-based descriptors (e.g., coordination numbers
with different near-neighbor finding approaches) for materials and
runs statistics analysis on selected descriptor types
(order parameter-based site fingerprints). The latter is
useful as a definition of a structure fingerprint
on the basis of local coordination information.
Args:
materials (Store): Store of materials documents.
site_descriptors (Store): Store of site-descriptors data such
as tetrahedral order parameter or
fraction of being 8-fold coordinated.
mat_query (dict): dictionary to limit materials to be analyzed.
"""
self.materials = materials
self.site_descriptors = site_descriptors
self.mat_query = mat_query if mat_query else {}
# Set up all targeted site descriptors.
self.sds = {}
for nn in NearNeighbors.__subclasses__():
nn_ = getattr(pymatgen.analysis.local_env, nn.__name__)
t = nn.__name__
k = 'cn_{}'.format(t)
self.sds[k] = CoordinationNumber(nn_(), use_weights='none')
k = 'cn_wt_{}'.format(t)
self.sds[k] = CoordinationNumber(nn_(), use_weights='sum')
self.all_output_pieces = {
'site_descriptors': [k for k in self.sds.keys()]
}
self.sds['opsf'] = OPSiteFingerprint()
self.sds['csf'] = CrystalSiteFingerprint.from_preset('ops')
self.all_output_pieces['statistics'] = ['opsf', 'csf']
super().__init__(sources=[materials],
targets=[site_descriptors],
**kwargs)
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_cns(self):
cnv = CoordinationNumber.from_preset('VoronoiNN')
self.assertEqual(len(cnv.feature_labels()), 1)
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 14)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 14)
self.assertEqual(len(cnv.citations()), 2)
cnv = CoordinationNumber(VoronoiNN(), use_weights='sum')
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 9.2584516)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 9.2584516)
self.assertEqual(len(cnv.citations()), 2)
cnv = CoordinationNumber(VoronoiNN(), use_weights='effective')
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 11.648923254)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 11.648923254)
self.assertEqual(len(cnv.citations()), 2)
cnj = CoordinationNumber.from_preset('JmolNN')
self.assertEqual(cnj.feature_labels()[0], 'CN_JmolNN')
self.assertAlmostEqual(cnj.featurize(self.sc, 0)[0], 0)
self.assertAlmostEqual(cnj.featurize(self.cscl, 0)[0], 0)
self.assertAlmostEqual(cnj.featurize(self.cscl, 1)[0], 0)
self.assertEqual(len(cnj.citations()), 1)
jmnn = JmolNN(el_radius_updates={"Al": 1.55, "Cl": 1.7, "Cs": 1.7})
cnj = CoordinationNumber(jmnn)
self.assertEqual(cnj.feature_labels()[0], 'CN_JmolNN')
self.assertAlmostEqual(cnj.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnj.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnj.featurize(self.cscl, 1)[0], 8)
self.assertEqual(len(cnj.citations()), 1)
cnmd = CoordinationNumber.from_preset('MinimumDistanceNN')
self.assertEqual(cnmd.feature_labels()[0], 'CN_MinimumDistanceNN')
self.assertAlmostEqual(cnmd.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmd.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmd.featurize(self.cscl, 1)[0], 8)
self.assertEqual(len(cnmd.citations()), 1)
cnmok = CoordinationNumber.from_preset('MinimumOKeeffeNN')
self.assertEqual(cnmok.feature_labels()[0], 'CN_MinimumOKeeffeNN')
self.assertAlmostEqual(cnmok.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmok.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmok.featurize(self.cscl, 1)[0], 6)
self.assertEqual(len(cnmok.citations()), 2)
cnmvire = CoordinationNumber.from_preset('MinimumVIRENN')
self.assertEqual(cnmvire.feature_labels()[0], 'CN_MinimumVIRENN')
self.assertAlmostEqual(cnmvire.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmvire.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmvire.featurize(self.cscl, 1)[0], 14)
self.assertEqual(len(cnmvire.citations()), 2)
self.assertEqual(len(cnmvire.implementors()), 2)
self.assertEqual(cnmvire.implementors()[0], 'Nils E. R. Zimmermann')
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 test_cns(self):
cnv = CoordinationNumber.from_preset('VoronoiNN')
self.assertEqual(len(cnv.feature_labels()), 1)
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 14)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 14)
self.assertEqual(len(cnv.citations()), 2)
cnv = CoordinationNumber(VoronoiNN(), use_weights='sum')
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 9.2584516)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 9.2584516)
self.assertEqual(len(cnv.citations()), 2)
cnv = CoordinationNumber(VoronoiNN(), use_weights='effective')
self.assertEqual(cnv.feature_labels()[0], 'CN_VoronoiNN')
self.assertAlmostEqual(cnv.featurize(self.cscl, 0)[0], 11.648923254)
self.assertAlmostEqual(cnv.featurize(self.cscl, 1)[0], 11.648923254)
self.assertEqual(len(cnv.citations()), 2)
cnj = CoordinationNumber.from_preset('JmolNN')
self.assertEqual(cnj.feature_labels()[0], 'CN_JmolNN')
self.assertAlmostEqual(cnj.featurize(self.sc, 0)[0], 0)
self.assertAlmostEqual(cnj.featurize(self.cscl, 0)[0], 0)
self.assertAlmostEqual(cnj.featurize(self.cscl, 1)[0], 0)
self.assertEqual(len(cnj.citations()), 1)
jmnn = JmolNN(el_radius_updates={"Al": 1.55, "Cl": 1.7, "Cs": 1.7})
cnj = CoordinationNumber(jmnn)
self.assertEqual(cnj.feature_labels()[0], 'CN_JmolNN')
self.assertAlmostEqual(cnj.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnj.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnj.featurize(self.cscl, 1)[0], 8)
self.assertEqual(len(cnj.citations()), 1)
cnmd = CoordinationNumber.from_preset('MinimumDistanceNN')
self.assertEqual(cnmd.feature_labels()[0], 'CN_MinimumDistanceNN')
self.assertAlmostEqual(cnmd.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmd.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmd.featurize(self.cscl, 1)[0], 8)
self.assertEqual(len(cnmd.citations()), 1)
cnmok = CoordinationNumber.from_preset('MinimumOKeeffeNN')
self.assertEqual(cnmok.feature_labels()[0], 'CN_MinimumOKeeffeNN')
self.assertAlmostEqual(cnmok.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmok.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmok.featurize(self.cscl, 1)[0], 6)
self.assertEqual(len(cnmok.citations()), 2)
cnmvire = CoordinationNumber.from_preset('MinimumVIRENN')
self.assertEqual(cnmvire.feature_labels()[0], 'CN_MinimumVIRENN')
self.assertAlmostEqual(cnmvire.featurize(self.sc, 0)[0], 6)
self.assertAlmostEqual(cnmvire.featurize(self.cscl, 0)[0], 8)
self.assertAlmostEqual(cnmvire.featurize(self.cscl, 1)[0], 14)
self.assertEqual(len(cnmvire.citations()), 2)
self.assertEqual(len(cnmvire.implementors()), 2)
self.assertEqual(cnmvire.implementors()[0], 'Nils E. R. Zimmermann')
def from_preset(preset, **kwargs):
"""
Create a SiteStatsFingerprint class according to a preset
Args:
preset (str) - Name of preset
kwargs - Options for SiteStatsFingerprint
"""
if preset == "CrystalNNFingerprint_cn":
return SiteStatsFingerprint(
CrystalNNFingerprint.from_preset("cn", cation_anion=False),
**kwargs)
elif preset == "CrystalNNFingerprint_cn_cation_anion":
return SiteStatsFingerprint(
CrystalNNFingerprint.from_preset("cn", cation_anion=True),
**kwargs)
elif preset == "CrystalNNFingerprint_ops":
return SiteStatsFingerprint(
CrystalNNFingerprint.from_preset("ops", cation_anion=False),
**kwargs)
elif preset == "CrystalNNFingerprint_ops_cation_anion":
return SiteStatsFingerprint(
CrystalNNFingerprint.from_preset("ops", cation_anion=True),
**kwargs)
elif preset == "OPSiteFingerprint":
return SiteStatsFingerprint(OPSiteFingerprint(), **kwargs)
elif preset == "LocalPropertyDifference_ward-prb-2017":
return SiteStatsFingerprint(
LocalPropertyDifference.from_preset("ward-prb-2017"),
stats=["minimum", "maximum", "range", "mean", "avg_dev"])
elif preset == "CoordinationNumber_ward-prb-2017":
return SiteStatsFingerprint(
CoordinationNumber(nn=VoronoiNN(weight='area'),
use_weights="effective"),
stats=["minimum", "maximum", "range", "mean", "avg_dev"])
elif preset == "Composition-dejong2016_AD":
return SiteStatsFingerprint(
LocalPropertyDifference(properties=[
"Number", "AtomicWeight", "Column", "Row",
"CovalentRadius", "Electronegativity"
],
signed=False),
stats=['holder_mean::%d' % d
for d in range(0, 4 + 1)] + ['std_dev'],
)
elif preset == "Composition-dejong2016_SD":
return SiteStatsFingerprint(
LocalPropertyDifference(properties=[
"Number", "AtomicWeight", "Column", "Row",
"CovalentRadius", "Electronegativity"
],
signed=True),
stats=['holder_mean::%d' % d for d in [1, 2, 4]] + ['std_dev'],
)
elif preset == "BondLength-dejong2016":
return SiteStatsFingerprint(
AverageBondLength(VoronoiNN()),
stats=['holder_mean::%d' % d for d in range(-4, 4 + 1)] +
['std_dev', 'geom_std_dev'])
elif preset == "BondAngle-dejong2016":
return SiteStatsFingerprint(
AverageBondAngle(VoronoiNN()),
stats=['holder_mean::%d' % d for d in range(-4, 4 + 1)] +
['std_dev', 'geom_std_dev'])
else:
# TODO: Why assume coordination number? Should this just raise an error? - lw
# One of the various Coordination Number presets:
# MinimumVIRENN, MinimumDistanceNN, JmolNN, VoronoiNN, etc.
try:
return SiteStatsFingerprint(
CoordinationNumber.from_preset(preset), **kwargs)
except:
pass
raise ValueError("Unrecognized preset!")
def AddFeatures(df): # Add features by Matminer
from matminer.featurizers.conversions import StrToComposition
df = StrToComposition().featurize_dataframe(df, "formula")
from matminer.featurizers.composition import ElementProperty
ep_feat = ElementProperty.from_preset(preset_name="magpie")
df = ep_feat.featurize_dataframe(
df, col_id="composition"
) # input the "composition" column to the featurizer
from matminer.featurizers.conversions import CompositionToOxidComposition
from matminer.featurizers.composition import OxidationStates
df = CompositionToOxidComposition().featurize_dataframe(df, "composition")
os_feat = OxidationStates()
df = os_feat.featurize_dataframe(df, "composition_oxid")
from matminer.featurizers.composition import ElectronAffinity
ea_feat = ElectronAffinity()
df = ea_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import BandCenter
bc_feat = BandCenter()
df = bc_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import CohesiveEnergy
ce_feat = CohesiveEnergy()
df = ce_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import Miedema
m_feat = Miedema()
df = m_feat.featurize_dataframe(df, "composition_oxid", ignore_errors=True)
from matminer.featurizers.composition import TMetalFraction
tmf_feat = TMetalFraction()
df = tmf_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import ValenceOrbital
vo_feat = ValenceOrbital()
df = vo_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import YangSolidSolution
yss_feat = YangSolidSolution()
df = yss_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.structure import GlobalSymmetryFeatures
# This is the border between compositional features and structural features. Comment out the following featurizers to use only compostional features.
gsf_feat = GlobalSymmetryFeatures()
df = gsf_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralComplexity
sc_feat = StructuralComplexity()
df = sc_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import ChemicalOrdering
co_feat = ChemicalOrdering()
df = co_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MaximumPackingEfficiency
mpe_feat = MaximumPackingEfficiency()
df = mpe_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MinimumRelativeDistances
mrd_feat = MinimumRelativeDistances()
df = mrd_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralHeterogeneity
sh_feat = StructuralHeterogeneity()
df = sh_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import SiteStatsFingerprint
from matminer.featurizers.site import AverageBondLength
from pymatgen.analysis.local_env import CrystalNN
bl_feat = SiteStatsFingerprint(
AverageBondLength(CrystalNN(search_cutoff=20)))
df = bl_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import AverageBondAngle
ba_feat = SiteStatsFingerprint(
AverageBondAngle(CrystalNN(search_cutoff=20)))
df = ba_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import BondOrientationalParameter
bop_feat = SiteStatsFingerprint(BondOrientationalParameter())
df = bop_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import CoordinationNumber
cn_feat = SiteStatsFingerprint(CoordinationNumber())
df = cn_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, "structure", ignore_errors=True)
return (df)
def structure_to_convmol(structure,
properties=ELEMENTAL_PROPERTIES,
max_atoms=200,
max_features=41,
tolerance_distance=0.25):
atomic_radii = {
'At': 1.50,
'Bk': 1.70,
'Cm': 1.74,
'Fr': 2.60,
'He': 0.28,
'Kr': 1.16,
'Lr': 1.71,
'Md': 1.94,
'Ne': 0.58,
'No': 1.97,
'Rn': 1.50,
'Xe': 1.40,
}
distance_matrix = structure.distance_matrix
for index, x in np.ndenumerate(distance_matrix):
radius_1 = Element(structure._sites[
index[0]].specie).atomic_radius or atomic_radii[str(
structure._sites[index[0]].specie)]
radius_2 = Element(structure._sites[
index[1]].specie).atomic_radius or atomic_radii[str(
structure._sites[index[1]].specie)]
max_distance = radius_1 + radius_2 + tolerance_distance
if x > max_distance:
distance_matrix[index] = 0
else:
distance_matrix[index] = 1
np.fill_diagonal(distance_matrix, 1)
atom_features = []
for i, site in enumerate(structure._sites):
atom_feature_vector = []
for atom_property in properties:
min_value = np.nanmin(
np.array(list(atom_property.values()), dtype=float))
max_value = np.nanmax(
np.array(list(atom_property.values()), dtype=float))
if atom_property[str(Element(site.specie))] is not None:
atom_feature_vector.append(
(atom_property[str(Element(site.specie))] - min_value) /
(max_value - min_value))
else:
atom_feature_vector.append(None)
voronoi_min = np.array([
0.0, 10.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 0.0, 1.0,
1.0
])
voronoi_max = np.array([
120.0, 135.0, 11.0, 3.0, 11.0, 12.0, 18.0, 7.0, 17.0, 17.0, 6.0,
2.0, 6.0, 7.0
])
voronoi_fps = VoronoiFingerprint().featurize(structure, i)
i_fold_symmetry_indices = voronoi_fps[8:16]
voronoi_stats = (np.array(voronoi_fps[16:]) -
voronoi_min) / (voronoi_max - voronoi_min)
atom_feature_vector.extend(i_fold_symmetry_indices +
voronoi_stats.tolist())
coord_min = np.array([1])
coord_max = np.array([36])
coord_fps = (
(CoordinationNumber.from_preset("MinimumDistanceNN").featurize(
structure, i) - coord_min) / (coord_max - coord_min)).tolist()
atom_feature_vector.extend(coord_fps)
atom_features.append(atom_feature_vector)
atom_features = np.array(atom_features, dtype=np.float)
if np.isnan(atom_features).any():
raise ValueError('feature vector contains nan value')
return (zfill(distance_matrix, max_atoms,
max_atoms), zfill(atom_features, max_atoms,
max_features), len(structure.sites))
StructureComposition,
MaximumPackingEfficiency)
from matminer.featurizers.composition import ElementProperty, Stoichiometry, ValenceOrbital, IonProperty
from matminer.featurizers.site import CoordinationNumber, LocalPropertyDifference
from matminer.utils.data import MagpieData
element_properties = ('Electronegativity', 'Row', 'Column', 'Number',
'MendeleevNumber', 'AtomicWeight', 'CovalentRadius',
'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,
def featurize_site(df: pd.DataFrame, site_stats=("mean", "std_dev")) -> pd.DataFrame:
""" Decorate input `pandas.DataFrame` of structures with site
features from matminer.
Currently creates the set of all matminer structure features with
the `matminer.featurizers.structure.SiteStatsFingerprint`.
Args:
df (pandas.DataFrame): the input dataframe with `"structure"`
column containing `pymatgen.Structure` objects.
site_stats (Tuple[str]): the matminer site stats to use in the
`SiteStatsFingerprint` for all features.
Returns:
pandas.DataFrame: the decorated DataFrame.
"""
logging.info("Applying site featurizers...")
df = df.copy()
df.columns = ["Input data|" + x for x in df.columns]
site_fingerprints = (
AGNIFingerprints(),
GeneralizedRadialDistributionFunction.from_preset("gaussian"),
OPSiteFingerprint(),
CrystalNNFingerprint.from_preset("ops"),
VoronoiFingerprint(),
GaussianSymmFunc(),
ChemEnvSiteFingerprint.from_preset("simple"),
CoordinationNumber(),
LocalPropertyDifference(),
BondOrientationalParameter(),
AverageBondLength(VoronoiNN()),
AverageBondAngle(VoronoiNN())
)
for fingerprint in site_fingerprints:
site_stats_fingerprint = SiteStatsFingerprint(
fingerprint,
stats=site_stats
)
df = site_stats_fingerprint.featurize_dataframe(
df,
"Input data|structure",
multiindex=False,
ignore_errors=True
)
fingerprint_name = fingerprint.__class__.__name__
# rename some features for backwards compatibility with pretrained models
if fingerprint_name == "GeneralizedRadialDistributionFunction":
fingerprint_name = "GeneralizedRDF"
elif fingerprint_name == "AGNIFingerprints":
fingerprint_name = "AGNIFingerPrint"
elif fingerprint_name == "BondOrientationalParameter":
fingerprint_name = "BondOrientationParameter"
elif fingerprint_name == "GaussianSymmFunc":
fingerprint_name = "ChemEnvSiteFingerprint|GaussianSymmFunc"
if "|" not in fingerprint_name:
fingerprint_name += "|"
df.columns = [f"{fingerprint_name}{x}" if "|" not in x else x for x in df.columns]
df = df.loc[:, (df != 0).any(axis=0)]
return clean_df(df)
