def test_composition_to_oxidcomposition(self):
df = DataFrame(data={"composition": [Composition("Fe2O3")]})
cto = CompositionToOxidComposition()
df = cto.featurize_dataframe(df, 'composition')
self.assertEqual(df["composition_oxid"].tolist()[0],
Composition({
"Fe3+": 2,
"O2-": 3
}))
# test error handling
df = DataFrame(data={"composition": [Composition("Fe2O3")]})
cto = CompositionToOxidComposition(return_original_on_error=False,
max_sites=2)
self.assertRaises(ValueError, cto.featurize_dataframe, df,
'composition')
# check non oxi state structure returned correctly
cto = CompositionToOxidComposition(return_original_on_error=True,
max_sites=2)
df = cto.featurize_dataframe(df, 'composition')
self.assertEqual(df["composition_oxid"].tolist()[0],
Composition({
"Fe": 2,
"O": 3
}))
def test_composition_to_oxidcomposition(self):
df = DataFrame(data={"composition": [Composition("Fe2O3")]})
cto = CompositionToOxidComposition()
df = cto.featurize_dataframe(df, 'composition')
self.assertEqual(df["composition_oxid"].tolist()[0],
Composition({
"Fe3+": 2,
"O2-": 3
}))
def test_composition_to_oxidcomposition(self):
df = DataFrame(data={"composition": [Composition("Fe2O3")]})
cto = CompositionToOxidComposition()
df = cto.featurize_dataframe(df, 'composition')
self.assertEqual(df["composition_oxid"].tolist()[0],
Composition({"Fe3+": 2, "O2-": 3}))
# test error handling
df = DataFrame(data={"composition": [Composition("Fe2O3")]})
cto = CompositionToOxidComposition(
return_original_on_error=False, max_sites=2)
self.assertRaises(ValueError, cto.featurize_dataframe, df,
'composition')
# check non oxi state structure returned correctly
cto = CompositionToOxidComposition(
return_original_on_error=True, max_sites=2)
df = cto.featurize_dataframe(df, 'composition')
self.assertEqual(df["composition_oxid"].tolist()[0],
Composition({"Fe": 2, "O": 3}))
def _tidy_column(self, df, featurizer_type):
"""
Various conversions to homogenize columns for featurization input.
For example, take a column of compositions and ensure they are decorated
with oxidation states, are not strings, etc.
Args:
df (pandas.DataFrame)
featurizer_type: The key defining the featurizer input. For example,
composition featurizers should have featurizer_type of
"composition".
Returns:
df (pandas.DataFrame): DataFrame with featurizer_type column
ready for featurization.
"""
# todo: Make the following conversions more robust (no [0] type checking)
type_tester = df[featurizer_type].iloc[0]
if featurizer_type == self.composition_col:
# Convert formulas to composition objects
if isinstance(type_tester, str):
self.logger.info(
self._log_prefix +
"Compositions detected as strings. Attempting "
"conversion to Composition objects...")
stc = StrToComposition(overwrite_data=True,
target_col_id=featurizer_type)
df = stc.featurize_dataframe(df,
featurizer_type,
multiindex=self.multiindex,
ignore_errors=True,
inplace=False)
elif isinstance(type_tester, dict):
self.logger.info(self._log_prefix +
"Compositions detected as dicts. Attempting "
"conversion to Composition objects...")
df[featurizer_type] = [
Composition.from_dict(d) for d in df[featurizer_type]
]
# Convert non-oxidstate containing comps to oxidstate comps
if self.guess_oxistates:
self.logger.info(
self._log_prefix +
"Guessing oxidation states of compositions, as"
" they were not present in input.")
cto = CompositionToOxidComposition(
target_col_id=featurizer_type,
overwrite_data=True,
return_original_on_error=True,
max_sites=-50)
try:
df = cto.featurize_dataframe(df,
featurizer_type,
multiindex=self.multiindex,
inplace=False)
except Exception as e:
self.logger.info(self._log_prefix +
"Could not decorate oxidation states due "
"to {}. Excluding featurizers based on "
"composition oxistates".format(e))
classes_require_oxi = [
c.__class__.__name__
for c in CompositionFeaturizers().need_oxi
]
self.exclude.extend(classes_require_oxi)
else:
# Convert structure/bs/dos dicts to objects (robust already)
if isinstance(type_tester, (dict, str)):
self.logger.info(self._log_prefix.capitalize() +
"{} detected as string or dict. Attempting "
"conversion to {} objects..."
"".format(featurizer_type, featurizer_type))
if isinstance(type_tester, str):
raise ValueError("{} column is type {}. Cannot convert."
"".format(featurizer_type,
type(type_tester)))
dto = DictToObject(overwrite_data=True,
target_col_id=featurizer_type)
df = dto.featurize_dataframe(df,
featurizer_type,
inplace=False)
# Decorate with oxidstates
if featurizer_type == self.structure_col and \
self.guess_oxistates:
self.logger.info(
self._log_prefix +
"Guessing oxidation states of structures if they were "
"not present in input.")
sto = StructureToOxidStructure(
target_col_id=featurizer_type,
overwrite_data=True,
return_original_on_error=True,
max_sites=-50)
try:
df = sto.featurize_dataframe(
df,
featurizer_type,
multiindex=self.multiindex,
inplace=False)
except Exception as e:
self.logger.info(
self._log_prefix +
"Could not decorate oxidation states on structures "
"due to {}.".format(e))
return df
#from matminer.featurizers.structure import StructuralHeterogeneity
#structural_heterogeneity = StructuralHeterogeneity()
#structural_heterogeneity.set_n_jobs(28)
#labels.append(structural_heterogeneity.feature_labels())
#df = structural_heterogeneity.featurize_dataframe(df, 'structures',ignore_errors=False)
#convert structure to composition
from matminer.featurizers.conversions import StructureToComposition
structures_to_compositions = StructureToComposition()
df = structures_to_compositions.featurize_dataframe(df, 'structures')
#convert composition to oxidcomposition
from matminer.featurizers.conversions import CompositionToOxidComposition
OxidCompositions = CompositionToOxidComposition()
print(OxidCompositions.feature_labels())
df = OxidCompositions.featurize_dataframe(df, 'composition')
#CohesiveEnergy
from matminer.featurizers.composition import CohesiveEnergy
cohesive_energy = CohesiveEnergy()
cohesive_energy.set_n_jobs(28)
labels.append(cohesive_energy.feature_labels())
df = cohesive_energy.featurize_dataframe(df,
'composition',
ignore_errors=True)
#ValenceOrbital
from matminer.featurizers.composition import ValenceOrbital
valence_orbital = ValenceOrbital()
valence_orbital.set_n_jobs(28)
labels.append(valence_orbital.feature_labels())
df = df.drop(unwanted_columns, axis=1) from matminer.featurizers.conversions import StrToComposition sc_feat = StrToComposition() df = sc_feat.featurize_dataframe(df, col_id='formula') from matminer.featurizers.composition import ElementProperty ep_feat = ElementProperty.from_preset(preset_name='magpie') df = ep_feat.featurize_dataframe(df, col_id='composition') from matminer.featurizers.conversions import CompositionToOxidComposition co_feat = CompositionToOxidComposition() df = co_feat.featurize_dataframe(df, col_id='composition') from matminer.featurizers.composition import OxidationStates os_feat = OxidationStates() df = os_feat.featurize_dataframe(df, col_id='composition_oxid') from matminer.featurizers.structure import DensityFeatures df_feat = DensityFeatures() df = df_feat.featurize_dataframe(df, col_id='structure') """ formula, structure, elastic_anisotropy, G_Reuss, G_VRH, G_Voigt, K_Reuss, K_VRH, K_Voigt, poisson_ratio, compliance_tensor, elastic_tensor, elastic_tensor_original, composition """