def get_phase_space(dataframe):
"""
Gets PhaseSpace object associated with dataframe
Args:
dataframe (DataFrame): dataframe with columns "Composition"
containing formula and "delta_e" containing
formation energy per atom
"""
phases = []
for data in dataframe.iterrows():
phases.append(
Phase(
data[1]["Composition"],
energy=data[1]["delta_e"],
per_atom=True,
description=data[0],
))
for el in ELEMENTS:
phases.append(Phase(el, 0.0, per_atom=True))
pd = PhaseData()
pd.add_phases(phases)
space = PhaseSpaceAL(bounds=ELEMENTS, data=pd)
return space
def get_pd(self, chemsys=None):
"""
Refresh the phase diagram associated with the seed_data
Args:
chemsys (str): chemical system for which to filter
seed data to provide partial phase diagram
Returns:
None
"""
self.pd = PhaseData()
# Filter seed data by relevant chemsys
if chemsys:
total_comp = Composition(chemsys.replace('-', ''))
filtered = filter_dataframe_by_composition(self.seed_data,
total_comp)
else:
filtered = self.seed_data
phases = [
Phase(
row["Composition"],
energy=row["delta_e"],
per_atom=True,
description=row_index,
) for row_index, row in filtered.iterrows()
]
phases.extend([Phase(el, 0.0, per_atom=True) for el in ELEMENTS])
self.pd.add_phases(phases)
return self.pd
def get_pd(self):
"""
Refresh the phase diagram associated with the seed_data
Returns:
None
"""
self.pd = PhaseData()
phases = [
Phase(row['Composition'],
energy=row['delta_e'],
per_atom=True,
description=row_index)
for row_index, row in self.seed_data.iterrows()
]
phases.extend([Phase(el, 0.0, per_atom=True) for el in ELEMENTS])
self.pd.add_phases(phases)
return self.pd
def get_phase_space(self, df=None):
"""
Gets PhaseSpace object associated with dataframe
"""
_df = df if df is not None else self.df
phases = []
for data in _df.iterrows():
phases.append(
Phase(data[1]['Composition'],
energy=data[1]['delta_e'],
per_atom=True,
description=data[0]))
for el in ELEMENTS:
phases.append(Phase(el, 0.0, per_atom=True))
pd = PhaseData()
pd.add_phases(phases)
space = PhaseSpaceAL(bounds=ELEMENTS, data=pd)
return space
def update_candidate_stabilities(self,
formation_energies,
sort=True,
floor=-6.0):
"""
Updates the candidate dataframe with the stabilities
of the candidate compositions according to the requisite
phase diagram analysis.
Args:
formation_energies ([float]): list of predictions for formation
energies corresponding to candidate_data ordering
sort (bool): whether or not to sort final list
floor (float): a float intended to add a floor to the predicted
formation energies
Returns:
(DataFrame): dataframe corresponding to self.candidate_data
"""
# Preprocess formation energies with floor
if floor is not None:
formation_energies = np.array(formation_energies)
formation_energies[formation_energies < floor] = floor
# Update formation energy predictions
self.candidate_data['pred_delta_e'] = formation_energies
# Construct candidate phases
candidate_phases = [
Phase(data['Composition'],
energy=data['pred_delta_e'],
per_atom=True,
description=m_id)
for m_id, data in self.candidate_data.iterrows()
]
# Refresh and copy seed PD
pd_ml = deepcopy(self.get_pd())
pd_ml.add_phases(candidate_phases)
space_ml = PhaseSpaceAL(bounds=ELEMENTS, data=pd_ml)
# Compute and return stabilities
if self.multiprocessing:
space_ml.compute_stabilities_multi(candidate_phases)
else:
space_ml.compute_stabilities_mod(candidate_phases)
self.candidate_data['pred_stability'] = \
[phase.stability for phase in candidate_phases]
if sort:
self.candidate_data = self.candidate_data.sort_values(
'pred_stability')
return self.candidate_data