def featurize_structures(self, featurizer=None, **kwargs):
"""
Featurizes the hypothetical structures available from
hypo_structures method. Hypothetical structures for which
featurization fails are removed and valid structures are
made available as valid_structures
Args:
featurizer (Featurizer): A MatMiner Featurizer.
Defaults to MultipleFeaturizer with PRB Ward
Voronoi descriptors.
**kwargs (dict): kwargs passed to featurize_many
method of featurizer.
Returns:
(pandas.DataFrame): features
"""
# Note the redundancy here is for pandas to work
if self.hypo_structures is None:
warnings.warn("No structures available. Generating structures.")
self.get_structures()
print("Generating features")
featurizer = featurizer if featurizer else MultipleFeaturizer([
SiteStatsFingerprint.from_preset("CoordinationNumber_ward-prb-2017"),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset("LocalPropertyDifference_ward-prb-2017"),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=['frac'])),
StructureComposition(IonProperty(fast=True))
])
features = featurizer.featurize_many(
self.hypo_structures['structure'],
ignore_errors=True, **kwargs)
n_species, formula = [], []
for s in self.hypo_structures['structure']:
n_species.append(len(s.composition.elements))
formula.append(s.composition.formula)
self._features_df = pd.DataFrame.from_records(
features, columns=featurizer.feature_labels())
self._features_df.index = self.hypo_structures.index
self._features_df['N_species'] = n_species
self._features_df['Composition'] = formula
self._features_df['structure'] = self.hypo_structures['structure']
self.features = self._features_df.dropna(axis=0, how='any')
self.features = self.features.reindex(sorted(self.features.columns), axis=1)
self._valid_structure_labels = list(self.features.index)
self.valid_structures = self.hypo_structures.loc[self._valid_structure_labels]
print("{} out of {} structures were successfully featurized.".format(
self.features.shape[0], self._features_df.shape[0]))
return self.features
def similarity(_parents, target):
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset("CoordinationNumber_ward-prb-2017"),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
"LocalPropertyDifference_ward-prb-2017"),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=["frac"])),
StructureComposition(IonProperty(fast=True)),
])
# HACK celery doesn't work with multiprocessing (used by matminer)
try:
from celery import current_task
if current_task:
featurizer.set_n_jobs(1)
except ImportError:
pass
x_target = pd.DataFrame.from_records([featurizer.featurize(target)],
columns=featurizer.feature_labels())
x_parent = pd.DataFrame.from_records(
featurizer.featurize_many(_parents, ignore_errors=True, pbar=False),
columns=featurizer.feature_labels(),
)
nulls = x_parent[x_parent.isnull().any(axis=1)].index.values
x_parent.fillna(100000, inplace=True)
x_target = x_target.reindex(sorted(x_target.columns), axis=1)
x_parent = x_parent.reindex(sorted(x_parent.columns), axis=1)
with open(os.path.join(settings.rxn_files, "scaler2.pickle"), "rb") as f:
scaler = pickle.load(f)
with open(os.path.join(settings.rxn_files, "quantiles.pickle"), "rb") as f:
quantiles = pickle.load(f)
X = scaler.transform(x_parent.append(x_target))
D = [pairwise_distances(np.array([row, X[-1]]))[0, 1] for row in X[:-1]]
_res = []
for d in D:
_res.append(np.linspace(0, 1, 101)[np.abs(quantiles - d).argmin()])
_res = np.array(_res)
_res[nulls] = -1
return _res
def get_structure_properties(structure: Structure, mode: str = 'all') -> dict:
if mode == 'all':
featurizer = MultipleFeaturizer([
SiteStatsFingerprint.from_preset(
'CoordinationNumber_ward-prb-2017'),
StructuralHeterogeneity(),
ChemicalOrdering(),
DensityFeatures(),
MaximumPackingEfficiency(),
SiteStatsFingerprint.from_preset(
'LocalPropertyDifference_ward-prb-2017'),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
else:
# Calculate only those which do not need a Voronoi tesselation
featurizer = MultipleFeaturizer([
DensityFeatures(),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset('magpie')),
StructureComposition(ValenceOrbital(props=['frac'])),
])
X = featurizer.featurize(structure)
matminer_dict = dict(list(zip(featurizer.feature_labels(), X)))
matminer_dict['volume'] = structure.volume
return matminer_dict
def test_composition_features(self):
comp = ElementProperty.from_preset("magpie")
f = StructureComposition(featurizer=comp)
# Test the fitting (should not crash)
f.fit([self.nacl, self.diamond])
# Test the features
features = f.featurize(self.nacl)
self.assertArrayAlmostEqual(comp.featurize(self.nacl.composition),
features)
# Test the citations/implementors
self.assertEqual(comp.citations(), f.citations())
self.assertEqual(comp.implementors(), f.implementors())
'MeltingT', 'NsValence', 'NpValence', 'NdValence',
'NfValence', 'NValence', 'NsUnfilled', 'NpUnfilled',
'NdUnfilled', 'NfUnfilled', 'NUnfilled', 'GSvolume_pa',
'SpaceGroupNumber', 'GSbandgap', 'GSmagmom')
#The following features will be created by using matminer package.
featurizer = MultipleFeaturizer([
SiteStatsFingerprint(CoordinationNumber().from_preset('VoronoiNN'),
stats=('mean', 'std_dev', 'minimum', 'maximum')),
StructuralHeterogeneity(),
ChemicalOrdering(),
MaximumPackingEfficiency(),
SiteStatsFingerprint(
LocalPropertyDifference(properties=element_properties),
stats=('mean', 'std_dev', 'minimum', 'maximum', 'range')),
StructureComposition(Stoichiometry()),
StructureComposition(ElementProperty.from_preset("magpie")),
StructureComposition(ValenceOrbital(props=['frac'])),
StructureComposition(IonProperty(fast=True))
])
#Generate VT based features from the material's crystal lat_params.
feature_data = featurizer.featurize_dataframe(df,
col_id=['structure'],
ignore_errors=True)
#"lat_params","compound possible" and "material_id" are not resonable physical features, so we drop these three columns
feature_data = feature_data.drop(
["structure", "compound possible", "material_id"], axis=1)
#write the data into a csv file for later use
feature_data.to_csv("data_delta_e_data.csv", index=False)
from sklearn.model_selection import KFold, cross_val_score
#Grabs all CIF files in a directory
CIFfiles = []
directoryname = '../examples/' #The directory it looks in
allfiles = os.listdir(directoryname)
for i in allfiles:
if os.path.splitext(i)[-1] == '.cif':
CIFfiles.append(i) #List of CIF files
#Creates a list of pymatgen.structure objects and a name of each structure
structlist = []
namelist = []
namecolumns = ['structure']
for i in CIFfiles:
structlist.append([Structure.from_file(directoryname + i)
]) #Converts CIF to pymatgen structure object
namelist.append(os.path.splitext(i)[0]) #Collects all the structure names
#Creates Pandas dataframe with data being a list of structures and the row name being the structure name
dftest = pd.DataFrame(data=structlist, index=namelist, columns=namecolumns)
#Featurizes the structures
featurizer = MultipleFeaturizer([
StructuralHeterogeneity(), #sets the featurizers that are going to be used
StructureComposition(ElementProperty.from_preset('magpie'))
]) # This one also collects the composition from the structures
#more featurizers can be added
r = (featurizer.featurize_dataframe(dftest, ['structure'])
) #Featurizes entire Pands Dataframe