def test_rdf_and_peaks(self):
## Test diamond
rdf, bin_radius = RadialDistributionFunction().featurize(self.diamond)
# Make sure it the last bin is cutoff-bin_max
self.assertAlmostEquals(bin_radius.max(), 19.9)
# Verify bin sizes
self.assertEquals(len(rdf), len(bin_radius))
self.assertEquals(len(rdf), 200)
# Make sure it gets all of the peaks
self.assertEquals(np.count_nonzero(rdf), 116)
# Check the values for a few individual peaks
self.assertAlmostEqual(rdf[int(round(1.5 / 0.1))], 15.12755155)
self.assertAlmostEqual(rdf[int(round(2.9 / 0.1))], 12.53193948)
self.assertAlmostEqual(rdf[int(round(19.9 / 0.1))], 0.822126129)
# Make sure it finds the locations of non-zero peaks correctly
peaks = RadialDistributionFunctionPeaks().featurize(rdf, bin_radius)
self.assertEquals(len(peaks), 2)
self.assertAlmostEquals(2.5, peaks[0])
self.assertAlmostEquals(1.5, peaks[1])
# Repeat test with NaCl (omitting comments). Altering cutoff distance
rdf, bin_radius = RadialDistributionFunction().featurize(self.nacl,
cutoff=10)
self.assertAlmostEquals(bin_radius.max(), 9.9)
self.assertEquals(len(rdf), len(bin_radius))
self.assertEquals(len(rdf), 100)
self.assertEquals(np.count_nonzero(rdf), 11)
self.assertAlmostEqual(rdf[int(round(2.8 / 0.1))], 27.09214168)
self.assertAlmostEqual(rdf[int(round(4.0 / 0.1))], 26.83338723)
self.assertAlmostEqual(rdf[int(round(9.8 / 0.1))], 3.024406467)
peaks = RadialDistributionFunctionPeaks().featurize(rdf, bin_radius)
self.assertEquals(len(peaks), 2)
self.assertAlmostEquals(2.8, peaks[0])
self.assertAlmostEquals(4.0, peaks[1])
# Repeat test with CsCl. Altering cutoff distance and bin_size
rdf, bin_radius = RadialDistributionFunction().featurize(self.cscl,
cutoff=8,
bin_size=0.5)
self.assertAlmostEquals(bin_radius.max(), 7.5)
self.assertEquals(len(rdf), len(bin_radius))
self.assertEquals(len(rdf), 16)
self.assertEquals(np.count_nonzero(rdf), 5)
self.assertAlmostEqual(rdf[int(round(3.5 / 0.5))], 6.741265585)
self.assertAlmostEqual(rdf[int(round(4.0 / 0.5))], 3.937582548)
self.assertAlmostEqual(rdf[int(round(7.0 / 0.5))], 1.805505363)
peaks = RadialDistributionFunctionPeaks().featurize(rdf,
bin_radius,
n_peaks=3)
self.assertEquals(len(peaks), 3)
self.assertAlmostEquals(3.5, peaks[0])
self.assertAlmostEquals(6.5, peaks[1])
self.assertAlmostEquals(5, 5, peaks[2])
def test_rdf_and_peaks(self):
## Test diamond
rdforig = RadialDistributionFunction().featurize(
self.diamond)
rdf = rdforig[0]
# Make sure it the last bin is cutoff-bin_max
self.assertAlmostEqual(max(rdf['distances']), 19.9)
# Verify bin sizes
self.assertEqual(len(rdf['distribution']), 200)
# Make sure it gets all of the peaks
self.assertEqual(np.count_nonzero(rdf['distribution']), 116)
# Check the values for a few individual peaks
self.assertAlmostEqual(
rdf['distribution'][int(round(1.5 / 0.1))], 15.12755155)
self.assertAlmostEqual(
rdf['distribution'][int(round(2.9 / 0.1))], 12.53193948)
self.assertAlmostEqual(
rdf['distribution'][int(round(19.9 / 0.1))], 0.822126129)
# Repeat test with NaCl (omitting comments). Altering cutoff distance
rdforig = RadialDistributionFunction(cutoff=10).featurize(self.nacl)
rdf = rdforig[0]
self.assertAlmostEqual(max(rdf['distances']), 9.9)
self.assertEqual(len(rdf['distribution']), 100)
self.assertEqual(np.count_nonzero(rdf['distribution']), 11)
self.assertAlmostEqual(
rdf['distribution'][int(round(2.8 / 0.1))], 27.09214168)
self.assertAlmostEqual(
rdf['distribution'][int(round(4.0 / 0.1))], 26.83338723)
self.assertAlmostEqual(
rdf['distribution'][int(round(9.8 / 0.1))], 3.024406467)
# Repeat test with CsCl. Altering cutoff distance and bin_size
rdforig = RadialDistributionFunction(
cutoff=8, bin_size=0.5).featurize(self.cscl)
rdf = rdforig[0]
self.assertAlmostEqual(max(rdf['distances']), 7.5)
self.assertEqual(len(rdf['distribution']), 16)
self.assertEqual(np.count_nonzero(rdf['distribution']), 5)
self.assertAlmostEqual(
rdf['distribution'][int(round(3.5 / 0.5))], 6.741265585)
self.assertAlmostEqual(
rdf['distribution'][int(round(4.0 / 0.5))], 3.937582548)
self.assertAlmostEqual(
rdf['distribution'][int(round(7.0 / 0.5))], 1.805505363)
def featurize_structure(df: pd.DataFrame) -> pd.DataFrame:
""" Decorate input `pandas.DataFrame` of structures with structural
features from matminer.
Currently applies the set of all matminer structure features.
Args:
df (pandas.DataFrame): the input dataframe with `"structure"`
column containing `pymatgen.Structure` objects.
Returns:
pandas.DataFrame: the decorated DataFrame.
"""
logging.info("Applying structure featurizers...")
df = df.copy()
structure_features = [
DensityFeatures(),
GlobalSymmetryFeatures(),
RadialDistributionFunction(),
CoulombMatrix(),
PartialRadialDistributionFunction(),
SineCoulombMatrix(),
EwaldEnergy(),
BondFractions(),
StructuralHeterogeneity(),
MaximumPackingEfficiency(),
ChemicalOrdering(),
XRDPowderPattern(),
BagofBonds()
]
featurizer = MultipleFeaturizer([feature.fit(df["structure"]) for feature in structure_features])
df = featurizer.featurize_dataframe(df, "structure", multiindex=True, ignore_errors=True)
df.columns = df.columns.map('|'.join).str.strip('|')
dist = df["RadialDistributionFunction|radial distribution function"][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
}
df["GlobalSymmetryFeatures|crystal_system"] = df["GlobalSymmetryFeatures|crystal_system"].map(_crystal_system)
df["GlobalSymmetryFeatures|is_centrosymmetric"] = df["GlobalSymmetryFeatures|is_centrosymmetric"].map(int)
return clean_df(df)
def add_cs_features(df,rdf_flag=False):
df["composition"] = str_to_composition(df["pretty_formula"])
df["composition_oxid"] = composition_to_oxidcomposition(df["composition"])
df["structure"] = dict_to_object(df["structure"])
vo = ValenceOrbital()
df = vo.featurize_dataframe(df,"composition")
ox = OxidationStates()
df = ox.featurize_dataframe(df, "composition_oxid")
# structure features
den = DensityFeatures()
df = den.featurize_dataframe(df, "structure")
if rdf_flag:
rdf = RadialDistributionFunction(cutoff=15.0,bin_size=0.2)
df = rdf.featurize_dataframe(df, "structure")
return 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)
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)
import numpy as np
from matminer.featurizers.structure import RadialDistributionFunction
cen_structures = np.load('centrosymmetric_insulators.npy', allow_pickle=True)
#create rdf representations
rdf = RadialDistributionFunction() #r_cut=2.0,periodic=True,normalize=True)
cen_rdf = []
for item in cen_structures:
cen_rdf.append(rdf.featurize(item))
np.save('centrosymmetric_rdf_representation.npy', cen_rdf)
non_cen_structures = np.load('non_centrosymmetric_insulators.npy',
allow_pickle=True)
non_cen_rdf = []
for item in non_cen_structures:
non_cen_rdf.append(rdf.featurize(item))
np.save('non_centrosymmetric_rdf_representation.npy', non_cen_rdf)
structlist.append([Structure.from_file(directoryname + i)
]) #Converts CIF to pymatgen structure object
namelist.append(os.path.splitext(i)[0]) #Collects all the structure names
structs.append(Structure.from_file(directoryname + i))
#Creates Pandas dataframe with data being a list of structures and the row name being the structure name
dftest = pd.DataFrame(data=structlist, index=namelist, columns=namecolumns)
p = PartialRadialDistributionFunction()
p.fit(np.asarray(structs))
c = CoulombMatrix()
c.fit(np.asarray(structs))
erdf = ElectronicRadialDistributionFunction()
erdf.cutoff = 10 #longest diagonal of lattice...I picked a number semi-arbitrarily
#Featurizes the structures
featurizer = MultipleFeaturizer([
ElementProperty.from_preset('magpie'),
OxidationStates(),
AtomicOrbitals(),
BandCenter(),
ElectronegativityDiff(),
DensityFeatures(),
RadialDistributionFunction(), p, c, erdf
])
r = (featurizer.featurize_many(dftest, ['structure'])
) #Featurizes entire Pandas Dataframe
#Yay it runs!
