def test_simple_cubic(self):
"""Test with an easy structure"""
# Make sure direction-dependent fingerprints are zero
agni = AGNIFingerprints(directions=['x', 'y', 'z'])
features = agni.featurize(self.sc, 0)
self.assertEqual(8 * 3, len(features))
self.assertEqual(8 * 3, len(set(agni.feature_labels())))
self.assertArrayAlmostEqual([
0,
] * 24, features)
# Compute the "atomic fingerprints"
agni.directions = [None]
agni.cutoff = 3.75 # To only get 6 neighbors to deal with
features = agni.featurize(self.sc, 0)
self.assertEqual(8, len(features))
self.assertEqual(8, len(set(agni.feature_labels())))
self.assertEqual(0.8, agni.etas[0])
self.assertAlmostEqual(
6 * np.exp(-(3.52 / 0.8)**2) * 0.5 *
(np.cos(np.pi * 3.52 / 3.75) + 1), features[0])
self.assertAlmostEqual(
6 * np.exp(-(3.52 / 16)**2) * 0.5 *
(np.cos(np.pi * 3.52 / 3.75) + 1), features[-1])
# Test that passing etas to constructor works
new_etas = np.logspace(-4, 2, 6)
agni = AGNIFingerprints(directions=['x', 'y', 'z'], etas=new_etas)
self.assertArrayAlmostEqual(new_etas, agni.etas)
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 test_dataframe(self):
data = pd.DataFrame({
'strc': [self.cscl, self.cscl, self.sc],
'site': [0, 1, 0]
})
agni = AGNIFingerprints()
agni.featurize_dataframe(data, ['strc', 'site'])
def test_off_center_cscl(self):
agni = AGNIFingerprints(directions=[None, 'x', 'y', 'z'], cutoff=4)
# Compute the features on both sites
site1 = agni.featurize(self.cscl, 0)
site2 = agni.featurize(self.cscl, 1)
# The atomic attributes should be equal
self.assertArrayAlmostEqual(site1[:8], site2[:8])
# The direction-dependent ones should be equal and opposite in sign
self.assertArrayAlmostEqual(-1 * site1[8:], site2[8:])
# Make sure the site-ones are as expected.
right_dist = 4.209 * np.sqrt(0.45 ** 2 + 2 * 0.5 ** 2)
right_xdist = 4.209 * 0.45
left_dist = 4.209 * np.sqrt(0.55 ** 2 + 2 * 0.5 ** 2)
left_xdist = 4.209 * 0.55
self.assertAlmostEqual(4 * (
right_xdist / right_dist * np.exp(-(right_dist / 0.8) ** 2) * 0.5 * (np.cos(np.pi * right_dist / 4) + 1) -
left_xdist / left_dist * np.exp(-(left_dist / 0.8) ** 2) * 0.5 * (np.cos(np.pi * left_dist / 4) + 1)),
site1[8])
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 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)
