def test_elem(self):
df_elem = ElementProperty().featurize_dataframe(self.df,
col_id="composition")
self.assertAlmostEqual(df_elem["minimum Number"][0], 8)
self.assertAlmostEqual(df_elem["maximum Number"][0], 26)
self.assertAlmostEqual(df_elem["range Number"][0], 18)
self.assertAlmostEqual(df_elem["mean Number"][0], 15.2)
self.assertAlmostEqual(df_elem["avg_dev Number"][0], 8.64)
self.assertAlmostEqual(df_elem["mode Number"][0], 8)
def test_fere_corr(self):
df_fere_corr = ElementProperty(features=["FERE correction"],
stats=["minimum", "maximum", "range", "mean", "std_dev"],
data_source="deml")\
.featurize_dataframe(self.df, col_id="composition")
self.assertAlmostEqual(df_fere_corr["minimum FERE correction"][0], -0.15213431610903)
self.assertAlmostEqual(df_fere_corr["maximum FERE correction"][0], 0.23)
self.assertAlmostEqual(df_fere_corr["range FERE correction"][0], 0.382134316)
self.assertAlmostEqual(df_fere_corr["mean FERE correction"][0], 0.077146274)
self.assertAlmostEqual(df_fere_corr["std_dev FERE correction"][0], 0.270209766)
def test_elem_deml(self):
df_elem_deml = ElementProperty("deml").featurize_dataframe(
self.df, col_id="composition")
self.assertAlmostEqual(df_elem_deml["minimum atom_num"][0], 8)
self.assertAlmostEqual(df_elem_deml["maximum atom_num"][0], 26)
self.assertAlmostEqual(df_elem_deml["range atom_num"][0], 18)
self.assertAlmostEqual(df_elem_deml["mean atom_num"][0], 15.2)
self.assertAlmostEqual(df_elem_deml["std_dev atom_num"][0], 8.81816307)
#Charge dependent property
self.assertAlmostEqual(df_elem_deml["minimum magn_moment"][0], 0)
self.assertAlmostEqual(df_elem_deml["maximum magn_moment"][0], 5.2)
self.assertAlmostEqual(df_elem_deml["range magn_moment"][0], 5.2)
self.assertAlmostEqual(df_elem_deml["mean magn_moment"][0], 2.08)
self.assertAlmostEqual(df_elem_deml["std_dev magn_moment"][0],
2.547469332)
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()
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
from sklearn.metrics import mean_squared_error
import numpy as np
lr = LinearRegression()
lr.fit(X, y)
}
# define valid magpie featueres
# https://github.com/hackingmaterials/
# matminer/blob/master/matminer/featurizers/
# composition.py
features = [
"Number", "MendeleevNumber", "AtomicWeight", "MeltingT", "Column", "Row",
"CovalentRadius", "Electronegativity", "NsValence", "NpValence",
"NdValence", "NfValence", "NValence", "NsUnfilled", "NpUnfilled",
"NdUnfilled", "NfUnfilled", "NUnfilled", "GSvolume_pa", "GSbandgap",
"GSmagmom", "SpaceGroupNumber"
]
# initialize matminer featurizer
elemprop = ElementProperty('magpie', features, ['mean'])
# featurize each element, getting the element propertie in a list
X = {}
valid_symbols = list(elem_dict.values())[1:98]
for symbol in valid_symbols:
comp = pymatgen.Composition(symbol)
x_i = elemprop.featurize(comp)
X[symbol] = x_i
# rename element properties to match magpie features
X = pd.DataFrame(X).T
X.columns = features
# fill missing features with the median from each column
for column in X: