class TestMEGNetData(TestCase):
def setUp(self):
self.data_source= MEGNetElementData()
def test_get_property(self):
embedding_cu = self.data_source.get_elemental_property(Element("Cu"), "embedding 1")
self.assertAlmostEqual(0.18259364366531372, embedding_cu)
# MEGNet embeddings have element data for elements 1-94, plus 0 for
# "dummy" atoms.
embedding_md = self.data_source.get_elemental_property(Element("Md"), "embedding 1")
self.assertAlmostEqual(-0.044910576194524765, embedding_md)
embedding_dummy = self.data_source.all_element_data["Dummy"]["embedding 1"]
self.assertAlmostEqual(-0.044910576194524765, embedding_dummy)
def from_preset(cls, preset_name):
"""
Return ElementProperty from a preset string
Args:
preset_name: (str) can be one of "magpie", "deml", "matminer",
"matscholar_el", or "megnet_el".
Returns:
ElementProperty based on the preset name.
"""
if preset_name == "magpie":
data_source = "magpie"
features = [
"Number", "MendeleevNumber", "AtomicWeight", "MeltingT",
"Column", "Row", "CovalentRadius", "Electronegativity",
"NsValence", "NpValence", "NdValence", "NfValence", "NValence",
"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", "electronegativity", "electric_pol",
"GGAU_Etot", "mus_fere", "FERE correction"
]
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"
]
elif preset_name == "matscholar_el":
data_source = "matscholar_el"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = MatscholarElementData().prop_names
elif preset_name == "megnet_el":
data_source = "megnet_el"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = MEGNetElementData().prop_names
else:
raise ValueError("Invalid preset_name specified!")
return cls(data_source, features, 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()
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()
def setUp(self):
self.data_source = MEGNetElementData()
class ElementProperty(BaseFeaturizer):
"""
Class to calculate elemental property attributes.
To initialize quickly, use the from_preset() method.
Features: Based on the statistics of the data_source chosen, computed
by element stoichiometry. The format generally is:
"{data source} {statistic} {property}"
For example:
"PymetgenData range X" # Range of electronegativity from Pymatgen data
For a list of all statistics, see the PropertyStats documentation; for a
list of all attributes available for a given data_source, see the
documentation for the data sources (e.g., PymatgenData, MagpieData,
MatscholarElementData, etc.).
Args:
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 (list of strings): 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()
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()
@classmethod
def from_preset(cls, preset_name):
"""
Return ElementProperty from a preset string
Args:
preset_name: (str) can be one of "magpie", "deml", "matminer",
"matscholar_el", or "megnet_el".
Returns:
ElementProperty based on the preset name.
"""
if preset_name == "magpie":
data_source = "magpie"
features = [
"Number", "MendeleevNumber", "AtomicWeight", "MeltingT",
"Column", "Row", "CovalentRadius", "Electronegativity",
"NsValence", "NpValence", "NdValence", "NfValence", "NValence",
"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", "electronegativity", "electric_pol",
"GGAU_Etot", "mus_fere", "FERE correction"
]
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"
]
elif preset_name == "matscholar_el":
data_source = "matscholar_el"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = MatscholarElementData().prop_names
elif preset_name == "megnet_el":
data_source = "megnet_el"
stats = ["minimum", "maximum", "range", "mean", "std_dev"]
features = MEGNetElementData().prop_names
else:
raise ValueError("Invalid preset_name specified!")
return cls(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 = []
# Get the element names and fractions
elements, fractions = zip(*comp.element_composition.items())
for attr in self.features:
elem_data = [
self.data_source.get_elemental_property(e, attr)
for e in elements
]
for stat in self.stats:
all_attributes.append(
self.pstats.calc_stat(elem_data, stat, fractions))
return all_attributes
def feature_labels(self):
labels = []
for attr in self.features:
src = self.data_source.__class__.__name__
for stat in self.stats:
labels.append(f"{src} {stat} {attr}")
return labels
def citations(self):
if self.data_source.__class__.__name__ == "MagpieData":
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.__class__.__name__ == "DemlData":
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.__class__.__name__ == "PymatgenData":
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} } "
]
elif self.data_source.__class__.__name__ == "MEGNetElementData":
# TODO: Cite MEGNet publication (not preprint) once released!
citation = [
"@ARTICLE{2018arXiv181205055C,"
"author = {{Chen}, Chi and {Ye}, Weike and {Zuo}, Yunxing and {Zheng}, Chen and {Ong}, Shyue Ping},"
"title = '{Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals}',"
"journal = {arXiv e-prints},"
"keywords = {Condensed Matter - Materials Science, Physics - Computational Physics},"
"year = '2018',"
"month = 'Dec',"
"eid = {arXiv:1812.05055},"
"pages = {arXiv:1812.05055},"
"archivePrefix = {arXiv},"
"eprint = {1812.05055},"
"primaryClass = {cond-mat.mtrl-sci},"
"adsurl = {https://ui.adsabs.harvard.edu/\#abs/2018arXiv181205055C},"
"adsnote = {Provided by the SAO/NASA Astrophysics Data System}}"
]
else:
citation = []
return citation
def implementors(self):
return ["Jiming Chen", "Logan Ward", "Anubhav Jain", "Alex Dunn"]
def setUp(self):
self.data_source= MEGNetElementData()