def test_miedema_all(self):
df = pd.DataFrame({
"composition": [
Composition("TiZr"),
Composition("Mg10Cu50Ca40"),
Composition("Fe2O3")
]
})
miedema = Miedema(struct_types='all')
self.assertTrue(miedema.precheck(df["composition"].iloc[0]))
self.assertFalse(miedema.precheck(df["composition"].iloc[-1]))
self.assertAlmostEqual(miedema.precheck_dataframe(df, "composition"),
2 / 3)
# test precheck for oxidation-state decorated compositions
df = CompositionToOxidComposition(return_original_on_error=True).\
featurize_dataframe(df, 'composition')
self.assertTrue(miedema.precheck(df["composition_oxid"].iloc[0]))
self.assertFalse(miedema.precheck(df["composition_oxid"].iloc[-1]))
self.assertAlmostEqual(
miedema.precheck_dataframe(df, "composition_oxid"), 2 / 3)
mfps = miedema.featurize_dataframe(df, col_id="composition")
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][0],
-0.003445022152)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][0], 0.0707658836300)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][1],
-0.235125978427)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][1], -0.164541848271)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][1],
-0.05280843311)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_inter'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_amor'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_min'][2]),
True)
# make sure featurization works equally for compositions with or without
# oxidation states
mfps = miedema.featurize_dataframe(df, col_id="composition_oxid")
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][0],
-0.003445022152)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][0], 0.0707658836300)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
def test_miedema_all(self):
df = pd.DataFrame({
"composition": [
Composition("TiZr"),
Composition("Mg10Cu50Ca40"),
Composition("Fe2O3")
]
})
miedema = Miedema(struct_types='all')
self.assertFalse(miedema.precheck(df["composition"].iloc[-1]))
self.assertAlmostEqual(miedema.precheck_dataframe(df, "composition"),
2 / 3)
mfps = miedema.featurize_dataframe(df, col_id="composition")
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][0],
-0.003445022152)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][0], 0.0707658836300)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][1],
-0.235125978427)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][1], -0.164541848271)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][1],
-0.05280843311)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_inter'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_amor'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_min'][2]),
True)
def test_miedema_all(self):
df = pd.DataFrame({"composition": [Composition("TiZr"),
Composition("Mg10Cu50Ca40"),
Composition("Fe2O3")]})
miedema = Miedema(struct_types='all')
mfps = miedema.featurize_dataframe(df, col_id="composition")
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][0], -0.003445022152)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][0], 0.0707658836300)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_inter'][1], -0.235125978427)
self.assertAlmostEqual(mfps['Miedema_deltaH_amor'][1], -0.164541848271)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][1], -0.05280843311)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_inter'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_amor'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_min'][2]), True)
def _generate_pairwise_features(self):
"""Generates features for each bonding pair.
Column labels contain a prefix "pairwise_feature {}", where the
string in parethesis is either "bcc_tet1", "bcc_tet2", or "tet1_tet2".
"""
# initializes requested matminer featurizers
feat_element_property = PairwiseElementProperty(
data_source='deml',
features=[
'atom_radius', 'electronegativity', 'first_ioniz', 'col_num',
'row_num', 'molar_vol', 'heat_fusion', 'melting_point',
'GGAU_Etot', 'mus_fere', 'FERE correction'
],
stats=['difference', 'mean'])
feat_miedema = Miedema(struct_types=['inter', 'amor'])
# generates freatures for each bonding pair
for bonding_pair in ['bcc_tet1', 'bcc_tet2', 'tet1_tet2']:
# gets the string composition of the bonding pairs
composition_index = 'pairwise_composition {}'.format(bonding_pair)
composition = self.memory[[composition_index]]
# adds ElementProperty features
features = feat_element_property.featurize_dataframe(
df=composition, col_id=composition_index, inplace=False).drop(
labels=composition_index, axis=1).add_prefix(
prefix='pairwise_feature {} '.format(bonding_pair))
self.memory = concat([self.memory, features], axis=1)
# gets the pymatgen.Composition of the bonding pairs
composition[composition_index] = [
Composition(i) for i in composition[composition_index]
]
# adds Miedema features
features = feat_miedema.featurize_dataframe(
df=composition, col_id=composition_index, inplace=False).drop(
labels=composition_index, axis=1).add_prefix(
prefix='pairwise_feature {} '.format(bonding_pair))
self.memory = concat([self.memory, features], axis=1)
def test_miedema_ss(self):
df = pd.DataFrame({
"composition": [
Composition("TiZr"),
Composition("Mg10Cu50Ca40"),
Composition("Fe2O3")
]
})
miedema = Miedema(struct_types='ss',
ss_types=['min', 'fcc', 'bcc', 'hcp', 'no_latt'])
mfps = miedema.featurize_dataframe(df, col_id="composition")
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_fcc'][0], 0.04700027066)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_bcc'][0], 0.08327522653)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_hcp'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_no_latt'][0],
0.036635998)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][1],
-0.05280843311)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_fcc'][1], 0.03010575174)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_bcc'][1],
-0.05280843311)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_hcp'][1], 0.03010575174)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_no_latt'][1],
-0.0035781359)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_min'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_fcc'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_bcc'][2]),
True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_hcp'][2]),
True)
self.assertAlmostEqual(
math.isnan(mfps['Miedema_deltaH_ss_no_latt'][2]), True)
def test_miedema_ss(self):
df = pd.DataFrame({"composition": [Composition("TiZr"),
Composition("Mg10Cu50Ca40"),
Composition("Fe2O3")]})
miedema = Miedema(struct_types='ss', ss_types=['min', 'fcc', 'bcc',
'hcp', 'no_latt'])
mfps = miedema.featurize_dataframe(df, col_id="composition")
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_fcc'][0], 0.04700027066)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_bcc'][0], 0.08327522653)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_hcp'][0], 0.03663599755)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_no_latt'][0], 0.036635998)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_min'][1], -0.05280843311)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_fcc'][1], 0.03010575174)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_bcc'][1], -0.05280843311)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_hcp'][1], 0.03010575174)
self.assertAlmostEqual(mfps['Miedema_deltaH_ss_no_latt'][1], -0.0035781359)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_min'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_fcc'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_bcc'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_hcp'][2]), True)
self.assertAlmostEqual(math.isnan(mfps['Miedema_deltaH_ss_no_latt'][2]), True)
def AddFeatures(df): # Add features by Matminer
from matminer.featurizers.conversions import StrToComposition
df = StrToComposition().featurize_dataframe(df, "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")
from matminer.featurizers.composition import ElectronAffinity
ea_feat = ElectronAffinity()
df = ea_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import BandCenter
bc_feat = BandCenter()
df = bc_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import CohesiveEnergy
ce_feat = CohesiveEnergy()
df = ce_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import Miedema
m_feat = Miedema()
df = m_feat.featurize_dataframe(df, "composition_oxid", ignore_errors=True)
from matminer.featurizers.composition import TMetalFraction
tmf_feat = TMetalFraction()
df = tmf_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import ValenceOrbital
vo_feat = ValenceOrbital()
df = vo_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.composition import YangSolidSolution
yss_feat = YangSolidSolution()
df = yss_feat.featurize_dataframe(df,
"composition_oxid",
ignore_errors=True)
from matminer.featurizers.structure import GlobalSymmetryFeatures
# This is the border between compositional features and structural features. Comment out the following featurizers to use only compostional features.
gsf_feat = GlobalSymmetryFeatures()
df = gsf_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralComplexity
sc_feat = StructuralComplexity()
df = sc_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import ChemicalOrdering
co_feat = ChemicalOrdering()
df = co_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MaximumPackingEfficiency
mpe_feat = MaximumPackingEfficiency()
df = mpe_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import MinimumRelativeDistances
mrd_feat = MinimumRelativeDistances()
df = mrd_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import StructuralHeterogeneity
sh_feat = StructuralHeterogeneity()
df = sh_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import SiteStatsFingerprint
from matminer.featurizers.site import AverageBondLength
from pymatgen.analysis.local_env import CrystalNN
bl_feat = SiteStatsFingerprint(
AverageBondLength(CrystalNN(search_cutoff=20)))
df = bl_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import AverageBondAngle
ba_feat = SiteStatsFingerprint(
AverageBondAngle(CrystalNN(search_cutoff=20)))
df = ba_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import BondOrientationalParameter
bop_feat = SiteStatsFingerprint(BondOrientationalParameter())
df = bop_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.site import CoordinationNumber
cn_feat = SiteStatsFingerprint(CoordinationNumber())
df = cn_feat.featurize_dataframe(df, "structure", ignore_errors=True)
from matminer.featurizers.structure import DensityFeatures
df_feat = DensityFeatures()
df = df_feat.featurize_dataframe(df, "structure", ignore_errors=True)
return (df)