class TestPymatgenData(TestCase):
def setUp(self):
self.data_source = PymatgenData()
def test_get_property(self):
self.assertAlmostEqual(9.012182, self.data_source.get_elemental_property(Element("Be"), "atomic_mass"))
self.assertAlmostEqual(1.26, self.data_source.get_charge_dependent_property(Element("Ac"), 3, "ionic_radii"))
def test_get_oxidation(self):
self.assertEqual((3,), self.data_source.get_oxidation_states(Element("Nd")))
self.data_source.use_common_oxi_states = False
self.assertEqual((2, 3), self.data_source.get_oxidation_states(Element("Nd")))
class TestPymatgenData(TestCase):
def setUp(self):
self.data_source = PymatgenData()
def test_get_property(self):
self.assertAlmostEqual(9.012182, self.data_source.get_elemental_property(Element("Be"), "atomic_mass"))
self.assertAlmostEqual(1.26, self.data_source.get_charge_dependent_property(Element("Ac"), 3, "ionic_radii"))
def test_get_oxidation(self):
self.assertEqual((3,), self.data_source.get_oxidation_states(Element("Nd")))
self.data_source.use_common_oxi_states = False
self.assertEqual((2, 3), self.data_source.get_oxidation_states(Element("Nd")))
def get_fps(structure, cutoff=10.0, processes=8):
all_descrs = []
try:
coordination_number_ = CoordinationNumber.from_preset('VoronoiNN')
voronoi_fps_ = VoronoiFingerprintModified(
cutoff=cutoff).featurize_structure(structure)
crystal_nn_fingerprint_ = CrystalNNFingerprint.from_preset('cn')
op_site_fingerprint_ = OPSiteFingerprint()
agni_fingerprints_ = AGNIFingerprints()
gaussian_symm_func_fps_ = GaussianSymmFuncModified(
).featurize_structure(structure)
pymatgen_data_ = PymatgenData()
magpie_data_ = MagpieData()
data_list = [[
structure, i, site, coordination_number_, voronoi_fps_,
crystal_nn_fingerprint_, op_site_fingerprint_, agni_fingerprints_,
gaussian_symm_func_fps_, pymatgen_data_, magpie_data_
] for i, site in enumerate(structure)]
pool = multiprocessing.Pool(processes=processes)
all_descrs = np.array(pool.map(get_all_site_descrs, data_list))
except (AttributeError, IndexError) as error:
pass
return all_descrs
def __init__(self, data_source=PymatgenData(), fast=False):
"""
Args:
data_source - (OxidationStateMixin) - A AbstractData class that supports
the `get_oxidation_state` method.
fast - (boolean) whether to assume elements exist in a single oxidation state,
which can dramatically accelerate the calculation of whether an ionic compound
is possible, but will miss heterovalent compounds like Fe3O4.
"""
self.data_source = data_source
self.fast = fast
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
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 = PymatgenData()
df=df.set_index("material_id")
df = df[df['elasticity.K_VRH'] > 0]
df = df[df['e_above_hull'] < 0.1]
df['vpa'] = df['volume']/df['nsites']
df['poisson_ratio']=df[["elasticity.K_VRH","elasticity.G_VRH"]].apply(lambda x:(3*x["elasticity.K_VRH"]-2*x["elasticity.G_VRH"])/(6*x["elasticity.K_VRH"]+2*x["elasticity.G_VRH"]),axis=1)
from matminer.featurizers.conversions import StrToComposition
df = StrToComposition().featurize_dataframe(df, "pretty_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")
dataset = PymatgenData()
descriptors = ['row', 'group', 'atomic_mass',
'atomic_radius', 'boiling_point', 'melting_point', 'X']
stats = ["mean", "std_dev"]
ep = ElementProperty(data_source=dataset, features=descriptors, stats=stats)
df = ep.featurize_dataframe(df, "composition")
#Remove NaN values
df = df.dropna()
#y = df['elasticity.K_VRH'].values
y=df['Tensile Strength, Yield'].values
excluded = ["elasticity.G_VRH", "elasticity.K_VRH", "pretty_formula", 'volume','nsites','spacegroup.symbol','e_above_hull','Tensile Strength, Yield','Elongation at Break ','Tensile Strength,Ultimate',
"poisson_ratio", "composition", "composition_oxid"]#"elastic_anisotropy"
X = df.drop(excluded, axis=1)
print("There are {} possible descriptors:\n\n{}".format(X.shape[1], X.columns.values))
from sklearn.linear_model import LinearRegression
def setUp(self):
self.data_source = PymatgenData()