def test_cohesive_energy(self):
mpr = MPRester()
if not mpr.api_key:
raise SkipTest(
"Materials Project API key not set; Skipping cohesive energy test"
)
df_cohesive_energy = CohesiveEnergy().featurize_dataframe(
self.df, col_id="composition")
self.assertAlmostEqual(df_cohesive_energy["cohesive energy"][0], 5.179,
2)
def __init__(self,
cation_site=None,
site_ox_lim={
'A': [0, 10],
'B': [0, 10],
'X': [-10, 0]
},
site_base_ox={
'A': 2,
'B': 4,
'X': -2
},
ordered_formulas=False,
A_site_occupancy=1,
anions=None):
if cation_site is None and ordered_formulas is False:
raise ValueError(
'Either cation sites must be assigned, or formulas must be ordered. Otherwise site assignments can not be determined'
)
self.cation_site = cation_site
self.site_ox_lim = site_ox_lim
self.site_base_ox = site_base_ox
self.ordered_formulas = ordered_formulas
self.A_site_occupancy = A_site_occupancy
self.anions = anions
#matminer featurizers
self.ValenceOrbital = ValenceOrbital()
self.AtomicOrbitals = AtomicOrbitalsMod()
self.CohesiveEnergy = CohesiveEnergy()
#custom ElementProperty featurizer
elemental_properties = [
'BoilingT', 'MeltingT', 'BulkModulus', 'ShearModulus', 'Row',
'Column', 'Number', 'MendeleevNumber', 'SpaceGroupNumber',
'Density', 'MolarVolume', 'FusionEnthalpy', 'HeatVaporization',
'NsUnfilled', 'NpUnfilled', 'NdUnfilled', 'NfUnfilled',
'Polarizability', 'ThermalConductivity'
]
self.ElementProperty = ElementProperty(
data_source='magpie',
features=elemental_properties,
stats=["mean", "std_dev", "range"])
self.check_matminer_featurizers()
self.featurize_options = {}
def __init__(self,radius_type='ionic_radius',normalize_formula=False): self.radius_type = radius_type self.normalize_formula = normalize_formula self.ValenceOrbital = ValenceOrbital() self.AtomicOrbitals = AtomicOrbitalsMod() self.CohesiveEnergy = CohesiveEnergy() self.BandCenter = BandCenter() self.ValenceOrbitalEnergy = ValenceOrbitalEnergy() #custom ElementProperty featurizer elemental_properties = ['BoilingT', 'MeltingT', 'BulkModulus', 'ShearModulus', 'Row', 'Column', 'Number', 'MendeleevNumber', 'SpaceGroupNumber', 'Density','MolarVolume', 'FusionEnthalpy','HeatVaporization', 'Polarizability', 'ThermalConductivity'] self.ElementProperty = ElementProperty(data_source='magpie',features=elemental_properties, stats=["mean", "std_dev"]) #check matminer featurizers self.check_matminer_featurizers()
def __init__(self,normalize_formula=False):
self.normalize_formula = normalize_formula
# don't need ValenceOrbital - valence counts etc. covered in ElementProperty.from_preset('magpie')
# self.ValenceOrbital = ValenceOrbital()
self.AtomicOrbitals = AtomicOrbitalsMod()
self.CohesiveEnergy = CohesiveEnergy()
self.BandCenter = BandCenter()
self.ValenceOrbitalEnergy = ValenceOrbitalEnergy()
# ElementProperty featurizer with magpie properties plus additional properties
self.ElementProperty = ElementProperty.from_preset('magpie')
self.ElementProperty.features += ['BoilingT',
'BulkModulus', 'ShearModulus',
'Density','MolarVolume',
'FusionEnthalpy','HeatVaporization',
'Polarizability',
'ThermalConductivity']
# range, min, max are irrelevant inside the ternary
# self.ElementProperty.stats = ['mean', 'avg_dev','mode']
# check matminer featurizers
self.check_matminer_featurizers()
def _extract_features(self, df_input):
"""
Extract features using Matminer from the 'structure' column in
df_input
Args:
df_input (DataFrame): Pandas DataFrame whcih conatains features
from Materials Project Database of the input samples
Returns:
df_extracted (DataFrame): Pandas DataFrame which contains
features of input samples extracted using Matminer
"""
# Dropping the 'theoretical' column
df_input.drop(columns=["theoretical"], inplace=True)
# Extracting the features
dfeat = DensityFeatures()
symmfeat = GlobalSymmetryFeatures()
mfeat = Meredig()
cefeat = CohesiveEnergy()
df_input["density"] = df_input.structure.apply(
lambda x: dfeat.featurize(x)[0])
df_input["vpa"] = df_input.structure.apply(
lambda x: dfeat.featurize(x)[1])
df_input["packing fraction"] = df_input.structure.apply(
lambda x: dfeat.featurize(x)[2])
df_input["spacegroup_num"] = df_input.structure.apply(
lambda x: symmfeat.featurize(x)[0])
df_input["cohesive_energy"] = df_input.apply(
lambda x: cefeat.featurize(
x.structure.composition,
formation_energy_per_atom=x.formation_energy_per_atom,
)[0],
axis=1,
)
df_input["mean AtomicWeight"] = df_input.structure.apply(
lambda x: mfeat.featurize(x.composition)[-17])
df_input["range AtomicRadius"] = df_input.structure.apply(
lambda x: mfeat.featurize(x.composition)[-12])
df_input["mean AtomicRadius"] = df_input.structure.apply(
lambda x: mfeat.featurize(x.composition)[-11])
df_input["range Electronegativity"] = df_input.structure.apply(
lambda x: mfeat.featurize(x.composition)[-10])
df_input["mean Electronegativity"] = df_input.structure.apply(
lambda x: mfeat.featurize(x.composition)[-9])
# Drop 'structure' column
df_input.drop(columns=["structure"], inplace=True)
# ignore compounds that failed to featurize
df_extracted = df_input.fillna(
df_input.mean()).query("cohesive_energy > 0.0")
# Re-arranging the 'PU Label' column
pu_label = df_extracted["PU_label"]
df_extracted = df_extracted.drop(["PU_label"], axis=1)
df_extracted["PU_label"] = pu_label
# Drop the icsd_ids column
df_extracted.drop(columns=["icsd_ids"], inplace=True)
return df_extracted
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)
#df = structural_heterogeneity.featurize_dataframe(df, 'structures',ignore_errors=False)
#convert structure to composition
from matminer.featurizers.conversions import StructureToComposition
structures_to_compositions = StructureToComposition()
df = structures_to_compositions.featurize_dataframe(df, 'structures')
#convert composition to oxidcomposition
from matminer.featurizers.conversions import CompositionToOxidComposition
OxidCompositions = CompositionToOxidComposition()
print(OxidCompositions.feature_labels())
df = OxidCompositions.featurize_dataframe(df, 'composition')
#CohesiveEnergy
from matminer.featurizers.composition import CohesiveEnergy
cohesive_energy = CohesiveEnergy()
cohesive_energy.set_n_jobs(28)
labels.append(cohesive_energy.feature_labels())
df = cohesive_energy.featurize_dataframe(df,
'composition',
ignore_errors=True)
#ValenceOrbital
from matminer.featurizers.composition import ValenceOrbital
valence_orbital = ValenceOrbital()
valence_orbital.set_n_jobs(28)
labels.append(valence_orbital.feature_labels())
df = valence_orbital.featurize_dataframe(df,
'composition',
ignore_errors=True)
def test_cohesive_energy(self):
df_cohesive_energy = CohesiveEnergy().featurize_dataframe(
self.df, col_id="composition")
self.assertAlmostEqual(df_cohesive_energy["Cohesive Energy"][0],
-18.24568582)