def test_BandFeaturizer(self):
df_bf = BandFeaturizer().featurize_dataframe(self.df, col_id='bs')
self.assertAlmostEqual(df_bf['band_gap'][0], 0.612, 3)
self.assertAlmostEqual(df_bf['direct_gap'][0], 2.557, 3)
self.assertAlmostEqual(df_bf['n_ex1_norm'][0], 0.58413, 5)
self.assertAlmostEqual(df_bf['p_ex1_norm'][0], 0.0, 5)
self.assertEquals(df_bf['is_gap_direct'][0], False)
def test_BandFeaturizer(self):
bs_featurizer = BandFeaturizer(self.si_kpts)
df_bf = bs_featurizer.featurize_dataframe(self.df, col_id='bs_line')
self.assertAlmostEqual(df_bf['band_gap'][0], 0.612, 3)
self.assertAlmostEqual(df_bf['direct_gap'][0], 2.557, 3)
self.assertAlmostEqual(df_bf['n_ex1_norm'][0], 0.58413, 5)
self.assertAlmostEqual(df_bf['p_ex1_norm'][0], 0.0, 5)
self.assertEqual(df_bf['is_gap_direct'][0], False)
self.assertEqual(df_bf['n_ex1_degen'][0], 6)
self.assertEqual(df_bf['p_ex1_degen'][0], 1)
self.assertEqual(df_bf['p_0.0;0.0;0.0_en'][0], 0.0)
self.assertEqual(df_bf['p_0.0;0.0;0.0_en'][0], 0.0)
self.assertAlmostEqual(df_bf['p_0.375;0.375;0.75_en'][0], -2.3745, 4)
self.assertAlmostEqual(df_bf['p_0.5;0.0;0.5_en'][0], -2.7928, 4)
self.assertAlmostEqual(df_bf['p_0.625;0.25;0.625_en'][0], -2.3745, 4)
self.assertAlmostEqual(df_bf['p_0.5;0.5;0.5_en'][0], -1.1779, 4)
self.assertAlmostEqual(df_bf['n_0.0;0.0;0.0_en'][0], 1.945, 4)
self.assertAlmostEqual(df_bf['n_0.5;0.25;0.75_en'][0], 3.6587, 4)
self.assertAlmostEqual(df_bf['n_0.5;0.5;0.5_en'][0], 0.8534, 4)
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_BandFeaturizer(self):
# silicon:
bs_featurizer = BandFeaturizer(kpoints=self.si_kpts, nbands=5)
self.assertTrue(len(bs_featurizer.feature_labels()) > 0)
df_bf = bs_featurizer.featurize_dataframe(self.df, col_id='bs_line')
self.assertAlmostEqual(df_bf['band_gap'][0], 0.612, 3)
self.assertAlmostEqual(df_bf['direct_gap'][0], 2.557, 3)
self.assertAlmostEqual(df_bf['n_ex1_norm'][0], 0.58413, 5)
self.assertAlmostEqual(df_bf['p_ex1_norm'][0], 0.0, 5)
self.assertEqual(df_bf['is_gap_direct'][0], False)
self.assertEqual(df_bf['n_ex1_degen'][0], 6)
self.assertEqual(df_bf['p_ex1_degen'][0], 1)
# \\Gamma:
self.assertAlmostEqual(df_bf['n_0.0;0.0;0.0_en4'][0], 2.5169, 4)
self.assertAlmostEqual(df_bf['n_0.0;0.0;0.0_en1'][0], 1.945, 4)
self.assertEqual(df_bf['p_0.0;0.0;0.0_en1'][0], 0.0)
self.assertEqual(df_bf['p_0.0;0.0;0.0_en2'][0], 0.0)
self.assertEqual(df_bf['p_0.0;0.0;0.0_en4'][0], -11.8118)
# K:
self.assertAlmostEqual(df_bf['p_0.375;0.375;0.75_en1'][0], -2.3745, 4)
# X:
self.assertAlmostEqual(df_bf['n_0.5;0.0;0.5_en2'][0], 0.1409, 4)
self.assertAlmostEqual(df_bf['n_0.5;0.0;0.5_en1'][0], 0.1409, 4)
self.assertAlmostEqual(df_bf['p_0.5;0.0;0.5_en1'][0], -2.7928, 4)
# U:
self.assertAlmostEqual(df_bf['p_0.625;0.25;0.625_en1'][0], -2.3745, 4)
self.assertAlmostEqual(df_bf['p_0.625;0.25;0.625_en4'][0], -8.1598, 4)
self.assertTrue(math.isnan(df_bf['p_0.625;0.25;0.625_en5'][0]))
# L:
self.assertAlmostEqual(df_bf['n_0.5;0.5;0.5_en2'][0], 2.7381, 4)
self.assertAlmostEqual(df_bf['n_0.5;0.5;0.5_en1'][0], 0.8534, 4)
self.assertAlmostEqual(df_bf['p_0.5;0.5;0.5_en1'][0], -1.1779, 4)
# W:
self.assertAlmostEqual(df_bf['n_0.5;0.25;0.75_en1'][0], 3.6587, 4)
# VBr2 with unoccupied Spin.down electrons for ib<ib_VBM but E>E_CBM:
bs_featurizer = BandFeaturizer(kpoints=self.vbr2kpts, nbands=3)
df_bf2 = bs_featurizer.featurize_dataframe(self.df2, col_id='bs_line')
self.assertTrue(math.isnan(df_bf2['p_ex1_degen'][0]))
# \\Gamma:
self.assertAlmostEqual(df_bf2['n_0.0;0.0;0.0_en3'][0], 0.8020, 4)
self.assertAlmostEqual(df_bf2['n_0.0;0.0;0.0_en2'][0], 0.4243, 4)
self.assertAlmostEqual(df_bf2['n_0.0;0.0;0.0_en1'][0], 0.4243, 4)
self.assertAlmostEqual(df_bf2['p_0.0;0.0;0.0_en1'][0], -0.3312, 4)
self.assertAlmostEqual(df_bf2['p_0.0;0.0;0.0_en2'][0], -0.6076, 4)
self.assertAlmostEqual(df_bf2['p_0.0;0.0;0.0_en3'][0], -0.6076, 4)
# M:
self.assertAlmostEqual(df_bf2['n_0.5;0.0;0.0_en3'][0], 0.5524, 4)
self.assertAlmostEqual(df_bf2['n_0.5;0.0;0.0_en2'][0], 0.5074, 4)
self.assertAlmostEqual(df_bf2['n_0.5;0.0;0.0_en1'][0], 0.2985, 4)
self.assertAlmostEqual(df_bf2['p_0.5;0.0;0.0_en1'][0], -0.0636, 4)
self.assertAlmostEqual(df_bf2['p_0.5;0.0;0.0_en2'][0], -0.1134, 4)
self.assertAlmostEqual(df_bf2['p_0.5;0.0;0.0_en3'][0], -0.8091, 4)
# between \\Gamma and M:
self.assertAlmostEqual(df_bf2['n_0.2;0.0;0.0_en3'][0], 0.6250, 4)
self.assertAlmostEqual(df_bf2['n_0.2;0.0;0.0_en2'][0], 0.3779, 4)
self.assertAlmostEqual(df_bf2['n_0.2;0.0;0.0_en1'][0], 0.1349, 4)
self.assertAlmostEqual(df_bf2['p_0.2;0.0;0.0_en1'][0], -0.1049, 4)
self.assertAlmostEqual(df_bf2['p_0.2;0.0;0.0_en2'][0], -0.3044, 4)
self.assertAlmostEqual(df_bf2['p_0.2;0.0;0.0_en3'][0], -0.6399, 4)
# L:
self.assertAlmostEqual(df_bf2['n_0.5;0.0;0.5_en2'][0], 0.4448, 4)
self.assertAlmostEqual(df_bf2['n_0.5;0.0;0.5_en1'][0], 0.3076, 4)
self.assertAlmostEqual(df_bf2['p_0.5;0.0;0.5_en1'][0], -0.0639, 4)
self.assertAlmostEqual(df_bf2['p_0.5;0.0;0.5_en2'][0], -0.1133, 4)