def __init__(self, data_source, features, stats):
if data_source == "pymatgen":
self.data_source = PymatgenData()
elif data_source == "magpie":
self.data_source = MagpieData()
elif data_source == "deml":
self.data_source = DemlData()
else:
self.data_source = data_source
self.features = features
self.stats = stats
class ElectronAffinity(BaseFeaturizer):
"""
Calculate average electron affinity times formal charge of anion elements.
Note: The formal charges must already be computed before calling `featurize`.
Generates average (electron affinity*formal charge) of anions.
"""
def __init__(self):
self.data_source = DemlData()
def featurize(self, comp):
"""
Args:
comp: (Composition) Composition to be featurized
Returns:
avg_anion_affin (single-element list): average electron affinity*formal charge of anions
"""
# Check if oxidation states have been computed
if not has_oxidation_states(comp):
raise ValueError('Composition lacks oxidation states')
# Get the species and fractions
species, fractions = zip(*comp.items())
# Determine which species are anions
anions, fractions = zip(*[(s, f) for s, f in zip(species, fractions) if s.oxi_state < 0])
# Compute the electron_affinity*formal_charge for each anion
electron_affin = [
self.data_source.get_elemental_property(s.element, "electron_affin") * s.oxi_state
for s in anions
]
# Compute the average affinity
avg_anion_affin = PropertyStats.mean(electron_affin, fractions)
return [avg_anion_affin]
def feature_labels(self):
return ["avg anion electron affinity"]
def citations(self):
citation = [
"@article{deml_ohayre_wolverton_stevanovic_2016, title={Predicting density "
"functional theory total energies and enthalpies of formation of metal-nonmetal "
"compounds by linear regression}, volume={47}, DOI={10.1002/chin.201644254}, "
"number={44}, journal={ChemInform}, author={Deml, Ann M. and Ohayre, Ryan and "
"Wolverton, Chris and Stevanovic, Vladan}, year={2016}}"]
return citation
def implementors(self):
return ["Jiming Chen", "Logan Ward"]
class TestDemlData(TestCase):
"""Tests for the DemlData Class"""
def setUp(self):
self.data_source = DemlData()
def test_get_property(self):
self.assertAlmostEqual(
-4.3853,
self.data_source.get_elemental_property(Element("Bi"), "mus_fere"),
4)
self.assertEqual(
59600,
self.data_source.get_elemental_property(Element("Li"),
"electron_affin"))
self.assertAlmostEqual(
2372300,
self.data_source.get_elemental_property(Element("He"),
"first_ioniz"))
self.assertAlmostEqual(
sum([2372300, 5250500]),
self.data_source.get_charge_dependent_property_from_specie(
Specie("He", 2), "total_ioniz"))
self.assertAlmostEqual(
18.6,
self.data_source.get_charge_dependent_property_from_specie(
Specie("V", 3), "xtal_field_split"))
def test_get_oxidation(self):
self.assertEqual([1],
self.data_source.get_oxidation_states(Element("Li")))
def __init__(self, data_source, features, stats):
if data_source == "pymatgen":
self.data_source = PymatgenData()
elif data_source == "magpie":
self.data_source = MagpieData()
elif data_source == "deml":
self.data_source = DemlData()
elif data_source == "matscholar_el":
self.data_source = MatscholarElementData()
elif data_source == "megnet_el":
self.data_source = MEGNetElementData()
else:
self.data_source = data_source
self.features = features
self.stats = stats
# Initialize stats computer
self.pstats = PropertyStats()
class TestDemlData(TestCase):
"""Tests for the DemlData Class"""
def setUp(self):
self.data_source = DemlData()
def test_get_property(self):
self.assertAlmostEqual(-4.3853, self.data_source.get_elemental_property(Element("Bi"), "mus_fere"), 4)
self.assertEqual(59600, self.data_source.get_elemental_property(Element("Li"), "electron_affin"))
self.assertAlmostEqual(2372300, self.data_source.get_elemental_property(Element("He"), "first_ioniz"))
self.assertAlmostEqual(sum([2372300,5250500]),
self.data_source.get_charge_dependent_property_from_specie(Specie("He", 2),
"total_ioniz"))
self.assertAlmostEqual(18.6, self.data_source.get_charge_dependent_property_from_specie(Specie("V", 3),
"xtal_field_split"))
def test_get_oxidation(self):
self.assertEqual([1], self.data_source.get_oxidation_states(Element("Li")))
def __init__(self):
self.data_source = DemlData()
def setUp(self):
self.data_source = DemlData()
def __init__(self, data_source=DemlData(), stats=None):
self.data_source = data_source
if stats == None:
self.stats = ["minimum", "maximum", "range", "mean", "std_dev"]
else:
self.stats = stats
class ElementProperty(BaseFeaturizer):
"""
Class to calculate elemental property attributes. To initialize quickly,
use the from_preset() method.
Parameters:
data_source (AbstractData or str): source from which to retrieve
element property data (or use str for preset: "pymatgen",
"magpie", or "deml")
features (list of strings): List of elemental properties to use
(these must be supported by data_source)
stats (string): a list of weighted statistics to compute to for each
property (see PropertyStats for available stats)
"""
def __init__(self, data_source, features, stats):
if data_source == "pymatgen":
self.data_source = PymatgenData()
elif data_source == "magpie":
self.data_source = MagpieData()
elif data_source == "deml":
self.data_source = DemlData()
else:
self.data_source = data_source
self.features = features
self.stats = stats
@staticmethod
def from_preset(preset_name):
"""
Return ElementProperty from a preset string
Args:
preset_name: (str) can be one of "magpie", "deml", or "matminer"
Returns:
"""
if preset_name == "magpie":
data_source = "magpie"
features = [
"Number", "MendeleevNumber", "AtomicWeight", "MeltingT",
"Column", "Row", "CovalentRadius", "Electronegativity",
"NsValence", "NpValence", "NdValence", "NfValence", "NValance",
"NsUnfilled", "NpUnfilled", "NdUnfilled", "NfUnfilled",
"NUnfilled", "GSvolume_pa", "GSbandgap", "GSmagmom",
"SpaceGroupNumber"
]
stats = ["minimum", "maximum", "range", "mean", "avg_dev", "mode"]
elif preset_name == "deml":
data_source = "deml"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = [
"atom_num", "atom_mass", "row_num", "col_num", "atom_radius",
"molar_vol", "heat_fusion", "melting_point", "boiling_point",
"heat_cap", "first_ioniz", "total_ioniz", "electronegativity",
"formal_charge", "xtal_field_split", "magn_moment",
"so_coupling", "sat_magn", "electric_pol", "GGAU_Etot",
"mus_fere"
]
elif preset_name == "matminer":
data_source = "pymatgen"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = [
"X", "row", "group", "block", "atomic_mass", "atomic_radius",
"mendeleev_no", "electrical_resistivity", "velocity_of_sound",
"thermal_conductivity", "melting_point", "bulk_modulus",
"coefficient_of_linear_thermal_expansion"
]
else:
raise ValueError("Invalid preset_name specified!")
return ElementProperty(data_source, features, stats)
def featurize(self, comp):
"""
Get elemental property attributes
Args:
comp: Pymatgen composition object
Returns:
all_attributes: Specified property statistics of features
"""
all_attributes = []
for attr in self.features:
elem_data = self.data_source.get_property(comp, attr)
for stat in self.stats:
all_attributes.append(PropertyStats().calc_stat(
elem_data, stat))
return all_attributes
def feature_labels(self):
labels = []
for attr in self.features:
for stat in self.stats:
labels.append("%s %s" % (stat, attr))
return labels
def citations(self):
if self.data_source == "magpie":
citation = (
"@article{ward_agrawal_choudary_wolverton_2016, title={A general-purpose "
"machine learning framework for predicting properties of inorganic materials}, "
"volume={2}, DOI={10.1038/npjcompumats.2017.28}, number={1}, journal={npj "
"Computational Materials}, author={Ward, Logan and Agrawal, Ankit and Choudhary, "
"Alok and Wolverton, Christopher}, year={2016}}")
elif self.data_source == "deml":
citation = (
"@article{deml_ohayre_wolverton_stevanovic_2016, title={Predicting density "
"functional theory total energies and enthalpies of formation of metal-nonmetal "
"compounds by linear regression}, volume={47}, DOI={10.1002/chin.201644254}, "
"number={44}, journal={ChemInform}, author={Deml, Ann M. and Ohayre, Ryan and "
"Wolverton, Chris and Stevanovic, Vladan}, year={2016}}")
elif self.data_source == "pymatgen":
citation = (
"@article{Ong2013, author = {Ong, Shyue Ping and Richards, William Davidson and Jain, Anubhav and Hautier, "
"Geoffroy and Kocher, Michael and Cholia, Shreyas and Gunter, Dan and Chevrier, Vincent L. and Persson, "
"Kristin A. and Ceder, Gerbrand}, doi = {10.1016/j.commatsci.2012.10.028}, issn = {09270256}, "
"journal = {Computational Materials Science}, month = {feb}, pages = {314--319}, "
"publisher = {Elsevier B.V.}, title = {{Python Materials Genomics (pymatgen): A robust, open-source python "
"library for materials analysis}}, url = {http://linkinghub.elsevier.com/retrieve/pii/S0927025612006295}, "
"volume = {68}, year = {2013} } ")
return citation
def implementors(self):
return ["Jiming Chen", "Logan Ward", "Anubhav Jain"]
def setUp(self):
self.data_source = DemlData()
