def test_gaussiansymmfunc(self): data = pd.DataFrame({'struct': [self.cscl], 'site': [0]}) gsf = GaussianSymmFunc() gsfs = gsf.featurize_dataframe(data, ['struct', 'site']) self.assertAlmostEqual(gsfs['G2_0.05'][0], 5.0086817867593822) self.assertAlmostEqual(gsfs['G2_4.0'][0], 1.2415138042932981) self.assertAlmostEqual(gsfs['G2_20.0'][0], 0.00696) self.assertAlmostEqual(gsfs['G2_80.0'][0], 0.0) self.assertAlmostEqual(gsfs['G4_0.005_1.0_1.0'][0], 2.6399416897128658) self.assertAlmostEqual(gsfs['G4_0.005_1.0_-1.0'][0], 0.90049182882301426) self.assertAlmostEqual(gsfs['G4_0.005_4.0_1.0'][0], 1.1810690738596332) self.assertAlmostEqual(gsfs['G4_0.005_4.0_-1.0'][0], 0.033850556557100071)
def test_gaussiansymmfunc(self): data = pd.DataFrame({'struct': [self.cscl], 'site': [0]}) gsf = GaussianSymmFunc() gsfs = gsf.featurize_dataframe(data, ['struct', 'site']) self.assertAlmostEqual(gsfs['G2_0.05'][0], 5.0086817867593822) self.assertAlmostEqual(gsfs['G2_4.0'][0], 1.2415138042932981) self.assertAlmostEqual(gsfs['G2_20.0'][0], 0.00696) self.assertAlmostEqual(gsfs['G2_80.0'][0], 0.0) self.assertAlmostEqual(gsfs['G4_0.005_1.0_1.0'][0], 2.6399416897128658) self.assertAlmostEqual(gsfs['G4_0.005_1.0_-1.0'][0], 0.90049182882301426) self.assertAlmostEqual(gsfs['G4_0.005_4.0_1.0'][0], 1.1810690738596332) self.assertAlmostEqual(gsfs['G4_0.005_4.0_-1.0'][0], 0.033850556557100071)
def featurizer(self): """Return the featurizer (with the suitable cutoff)""" cutoff = self.cutoff return MultipleFeaturizer( [ CrystalNNFingerprint.from_preset("ops", search_cutoff=cutoff), LocalPropertyStatsNew.from_preset("interpretable", cutoff=cutoff), GaussianSymmFunc(), ] )
def __init__(self, structure: Structure, outpath: Union[str, Path]): """Generates features for a structures Args: structure (Structure): Pymatgen Structure object outpath (Union[str, Path]): path to which the features will be dumped Returns: """ featurizelogger = logging.getLogger("Featurize") featurizelogger.setLevel(logging.INFO) logging.basicConfig( format="%(filename)s: %(message)s", level=logging.INFO, ) self.outpath = outpath if ((outpath != "") and (outpath is not None) and (not os.path.exists(self.outpath))): os.mkdir(self.outpath) self.logger = featurizelogger self.path = None self.structure = structure self.metal_sites = [] self.metal_indices = [] self.features = [] if self.path is not None: self.outname = os.path.join( self.outpath, "".join([Path(self.path).stem, ".pkl"])) else: self.outname = os.path.join( self.outpath, "".join([self.structure.formula.replace(" ", "_"), ".pkl"]), ) self.featurizer = MultipleFeaturizer([ CrystalNNFingerprint.from_preset("ops"), LocalPropertyStatsNew.from_preset("interpretable"), GaussianSymmFunc(), ])
def __init__(self, structure, outpath): """Generates features for a list of structures Args: structure outpath (str): path to which the features will be dumped Returns: """ featurizelogger = logging.getLogger('Featurize') featurizelogger.setLevel(logging.INFO) logging.basicConfig( format='%(filename)s: %(message)s', level=logging.INFO, ) self.outpath = outpath if outpath != '' and not os.path.exists(self.outpath): os.mkdir(self.outpath) self.logger = featurizelogger self.path = None self.structure = structure self.metal_sites = [] self.metal_indices = [] self.features = [] if self.path is not None: self.outname = os.path.join( self.outpath, ''.join([Path(self.path).stem, '.pkl'])) else: self.outname = os.path.join( self.outpath, ''.join([self.structure.formula.replace(' ', '_'), '.pkl']), ) self.featurizer = MultipleFeaturizer([ CrystalNNFingerprint.from_preset('ops'), LocalPropertyStatsNew.from_preset('interpretable'), GaussianSymmFunc(), ])
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 predict_log10_eps( target: Union[Structure, Composition], dielectric_type: str, model_type: str, ) -> float: """ :param target: structure or composition to predict dielectric constants :param dielectric_type: "el" or "ion" :param model_type: "comp" or "comp_st" :return: Descriptor vector """ if dielectric_type not in ["el", "ion"]: raise ValueError( f'Specify dielectric type "el" or "ion"\nInput: {dielectric_type}') if model_type not in ["comp", "comp_st"]: raise ValueError( f'Specify regression_type "comp" or "comp_st"\nInput: {model_type}' ) if model_type == "comp": if isinstance(target, Structure): comp = target.composition else: comp = target comp_oxi = comp.add_charges_from_oxi_state_guesses() if dielectric_type == "el": ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"), comp) valence = ScalarFeaturizer(ValenceOrbital(), comp) ion_prop = ScalarFeaturizer(IonProperty(), comp) en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi) oxi_state = ScalarFeaturizer(OxidationStates.from_preset("deml"), comp_oxi) atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp) descriptor = [ ep.get_from_label("PymatgenData minimum X"), ep.get_from_label("PymatgenData range X"), ep.get_from_label("PymatgenData std_dev X"), ep.get_from_label("PymatgenData mean row"), ep.get_from_label("PymatgenData std_dev row"), ep.get_from_label("PymatgenData mean group"), ep.get_from_label("PymatgenData mean block"), ep.get_from_label("PymatgenData std_dev block"), ep.get_from_label("PymatgenData mean atomic_mass"), ep.get_from_label("PymatgenData std_dev atomic_mass"), ep.get_from_label("PymatgenData std_dev atomic_radius"), ep.get_from_label("PymatgenData minimum mendeleev_no"), ep.get_from_label("PymatgenData range mendeleev_no"), ep.get_from_label("PymatgenData std_dev mendeleev_no"), ep.get_from_label("PymatgenData mean thermal_conductivity"), ep.get_from_label("PymatgenData std_dev thermal_conductivity"), ep.get_from_label("PymatgenData mean melting_point"), ep.get_from_label("PymatgenData std_dev melting_point"), valence.get_from_label("avg s valence electrons"), valence.get_from_label("avg d valence electrons"), valence.get_from_label("frac s valence electrons"), valence.get_from_label("frac p valence electrons"), valence.get_from_label("frac d valence electrons"), ion_prop.get_from_label("avg ionic char"), TMetalFraction().featurize(comp)[0], en_diff.get_from_label("maximum EN difference"), en_diff.get_from_label("range EN difference"), en_diff.get_from_label("mean EN difference"), en_diff.get_from_label("std_dev EN difference"), BandCenter().featurize(comp)[0], oxi_state.get_from_label("std_dev oxidation state"), atomic_orbital.get_from_label("HOMO_energy"), atomic_orbital.get_from_label("LUMO_energy"), atomic_orbital.get_from_label("gap_AO"), ] elif dielectric_type == "ion": stoich = ScalarFeaturizer(Stoichiometry(), comp) ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"), comp) valence = ScalarFeaturizer(ValenceOrbital(), comp) ion_prop = ScalarFeaturizer(IonProperty(), comp) en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi) oxi_state = ScalarFeaturizer(OxidationStates.from_preset("deml"), comp_oxi) atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp) at_pack_eff = ScalarFeaturizer(AtomicPackingEfficiency(), comp) descriptor = [ stoich.get_from_label("3-norm"), stoich.get_from_label("5-norm"), ep.get_from_label("PymatgenData mean X"), ep.get_from_label("PymatgenData mean row"), ep.get_from_label("PymatgenData std_dev row"), ep.get_from_label("PymatgenData std_dev group"), ep.get_from_label("PymatgenData mean block"), ep.get_from_label("PymatgenData std_dev block"), ep.get_from_label("PymatgenData maximum atomic_mass"), ep.get_from_label("PymatgenData range atomic_mass"), ep.get_from_label("PymatgenData mean atomic_mass"), ep.get_from_label("PymatgenData std_dev atomic_mass"), ep.get_from_label("PymatgenData maximum atomic_radius"), ep.get_from_label("PymatgenData range atomic_radius"), ep.get_from_label("PymatgenData mean atomic_radius"), ep.get_from_label("PymatgenData std_dev atomic_radius"), ep.get_from_label("PymatgenData minimum mendeleev_no"), ep.get_from_label("PymatgenData mean mendeleev_no"), ep.get_from_label("PymatgenData std_dev mendeleev_no"), ep.get_from_label("PymatgenData mean thermal_conductivity"), ep.get_from_label("PymatgenData std_dev thermal_conductivity"), ep.get_from_label("PymatgenData mean melting_point"), ep.get_from_label("PymatgenData std_dev melting_point"), valence.get_from_label("avg s valence electrons"), valence.get_from_label("frac s valence electrons"), valence.get_from_label("frac p valence electrons"), valence.get_from_label("frac d valence electrons"), ion_prop.get_from_label("avg ionic char"), TMetalFraction().featurize(comp)[0], en_diff.get_from_label("minimum EN difference"), en_diff.get_from_label("range EN difference"), en_diff.get_from_label("mean EN difference"), en_diff.get_from_label("std_dev EN difference"), oxi_state.get_from_label("range oxidation state"), oxi_state.get_from_label("std_dev oxidation state"), atomic_orbital.get_from_label("LUMO_energy"), atomic_orbital.get_from_label("gap_AO"), at_pack_eff.get_from_label("mean simul. packing efficiency"), at_pack_eff.get_from_label( "mean abs simul. packing efficiency"), at_pack_eff.get_from_label( "dist from 1 clusters |APE| < 0.010"), at_pack_eff.get_from_label( "dist from 3 clusters |APE| < 0.010"), at_pack_eff.get_from_label( "dist from 5 clusters |APE| < 0.010"), ] elif model_type == "comp_st": if isinstance(target, Composition): raise ValueError( 'comp_st (Using compositional and structural descriptor) is specified, ' 'but target is composition') comp: Composition = target.composition comp_oxi = comp.add_charges_from_oxi_state_guesses() target_orig = deepcopy(target) target.add_oxidation_state_by_guess() if dielectric_type == "el": ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"), comp) valence = ScalarFeaturizer(ValenceOrbital(), comp) en_diff = ScalarFeaturizer(ElectronegativityDiff(), comp_oxi) atomic_orbital = ScalarFeaturizer(AtomicOrbitals(), comp) density = ScalarFeaturizer(DensityFeatures(), target) dist_btw_nn = MinimumRelativeDistances().featurize(target_orig) opsf = SiteFeaturizer(OPSiteFingerprint(), target) voro_fp = SiteFeaturizer(VoronoiFingerprint(use_symm_weights=True), target) gsf = SiteFeaturizer(GaussianSymmFunc(), target) lpd = SiteFeaturizer( LocalPropertyDifference.from_preset("ward-prb-2017"), target) descriptor = [ ep.get_from_label("PymatgenData std_dev X"), ep.get_from_label("PymatgenData mean block"), ep.get_from_label("PymatgenData std_dev atomic_mass"), valence.get_from_label("frac d valence electrons"), TMetalFraction().featurize(comp)[0], en_diff.get_from_label("maximum EN difference"), en_diff.get_from_label("mean EN difference"), atomic_orbital.get_from_label("HOMO_energy"), atomic_orbital.get_from_label("LUMO_energy"), density.get_from_label("density"), np.mean(dist_btw_nn), np.std(dist_btw_nn), opsf.get_from_label_func("tetrahedral CN_4", np.max), opsf.get_from_label_func("rectangular see-saw-like CN_4", np.max), np.max([ EwaldSiteEnergy(accuracy=4).featurize(target, i) for i in range(target.num_sites) ]), voro_fp.get_from_label_func("Voro_area_std_dev", np.max), voro_fp.get_from_label_func("Voro_area_std_dev", np.mean), voro_fp.get_from_label_func("Voro_dist_minimum", np.min), voro_fp.get_from_label_func("Voro_dist_minimum", np.std), gsf.get_from_label_func("G2_20.0", np.std), gsf.get_from_label_func("G2_80.0", np.max), gsf.get_from_label_func("G4_0.005_4.0_-1.0", np.mean), lpd.get_from_label_func("local difference in NdValence", np.mean), lpd.get_from_label_func("local difference in NValence", np.min), lpd.get_from_label_func("local difference in NValence", np.std), lpd.get_from_label_func("local difference in NdUnfilled", np.mean), lpd.get_from_label_func("local difference in NUnfilled", np.min), lpd.get_from_label_func("local difference in NUnfilled", np.mean), lpd.get_from_label_func("local difference in GSmagmom", np.mean) ] elif dielectric_type == "ion": ep = ScalarFeaturizer(ElementProperty.from_preset("matminer"), comp) atomic_orbitals = ScalarFeaturizer(AtomicOrbitals(), comp) density = ScalarFeaturizer(DensityFeatures(), target) str_het = ScalarFeaturizer(StructuralHeterogeneity(), target) opsf = SiteFeaturizer(OPSiteFingerprint(), target) voro_fp = SiteFeaturizer(VoronoiFingerprint(use_symm_weights=True), target) gsf = SiteFeaturizer(GaussianSymmFunc(), target) lpd = SiteFeaturizer( LocalPropertyDifference.from_preset("ward-prb-2017"), target) descriptor = [ ep.get_from_label("PymatgenData std_dev row"), ep.get_from_label("PymatgenData mean thermal_conductivity"), ep.get_from_label("PymatgenData std_dev melting_point"), TMetalFraction().featurize(comp)[0], atomic_orbitals.get_from_label("gap_AO"), density.get_from_label("density"), density.get_from_label("packing fraction"), str_het.get_from_label("mean neighbor distance variation"), str_het.get_from_label("avg_dev neighbor distance variation"), opsf.get_from_label_func("sgl_bd CN_1", np.mean), opsf.get_from_label_func("bent 150 degrees CN_2", np.mean), opsf.get_from_label_func("linear CN_2", np.mean), opsf.get_from_label_func("trigonal planar CN_3", np.mean), opsf.get_from_label_func("pentagonal planar CN_5", np.std), opsf.get_from_label_func("octahedral CN_6", np.max), opsf.get_from_label_func("octahedral CN_6", np.std), opsf.get_from_label_func("q6 CN_12", np.mean), np.max([ EwaldSiteEnergy(accuracy=4).featurize(target, i) for i in range(target.num_sites) ]), voro_fp.get_from_label_func("Symmetry_weighted_index_4", np.std), voro_fp.get_from_label_func("Voro_vol_maximum", np.mean), voro_fp.get_from_label_func("Voro_area_std_dev", np.mean), voro_fp.get_from_label_func("Voro_area_minimum", np.std), voro_fp.get_from_label_func("Voro_area_maximum", np.min), voro_fp.get_from_label_func("Voro_dist_std_dev", np.mean), gsf.get_from_label_func("G2_80.0", np.min), gsf.get_from_label_func("G4_0.005_4.0_1.0", np.std), lpd.get_from_label_func("local difference in Number", np.max), lpd.get_from_label_func("local difference in MendeleevNumber", np.max), lpd.get_from_label_func("local difference in MendeleevNumber", np.min), lpd.get_from_label_func("local difference in AtomicWeight", np.max), lpd.get_from_label_func("local difference in AtomicWeight", np.mean), lpd.get_from_label_func("local difference in MeltingT", np.mean), lpd.get_from_label_func("local difference in Row", np.max), lpd.get_from_label_func( "local difference in Electronegativity", np.min), lpd.get_from_label_func("local difference in NValence", np.std), lpd.get_from_label_func("local difference in NsUnfilled", np.mean), lpd.get_from_label_func("local difference in NdUnfilled", np.max), lpd.get_from_label_func("local difference in NdUnfilled", np.std), lpd.get_from_label_func("local difference in NUnfilled", np.max), lpd.get_from_label_func("local difference in NUnfilled", np.min), lpd.get_from_label_func("local difference in NUnfilled", np.mean), lpd.get_from_label_func("local difference in NUnfilled", np.std), lpd.get_from_label_func("local difference in GSvolume_pa", np.max), lpd.get_from_label_func("local difference in GSvolume_pa", np.min), lpd.get_from_label_func("local difference in SpaceGroupNumber", np.max), ] with open( f"{os.path.dirname(__file__)}/{dielectric_type}_{model_type}.joblib", "rb") as fr: model: RandomForestRegressor = joblib.load(fr) with open( f"{os.path.dirname(__file__)}/{dielectric_type}_{model_type}_scaler.joblib", "rb") as fr: scaler: StandardScaler = joblib.load(fr) descriptor = scaler.transform([descriptor]) return model.predict(descriptor)[0]
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)