def test_dict_to_object(self):
coords = [[0, 0, 0], [0.75, 0.5, 0.75]]
lattice = Lattice([[3.8401979337, 0.00, 0.00],
[1.9200989668, 3.3257101909, 0.00],
[0.00, -2.2171384943, 3.1355090603]])
struct = Structure(lattice, ["Si"] * 2, coords)
d = {'structure_dict': [struct.as_dict(), struct.as_dict()]}
df = DataFrame(data=d)
df["structure"] = dict_to_object(df["structure_dict"])
self.assertEqual(df["structure"].tolist()[0], struct)
self.assertEqual(df["structure"].tolist()[1], struct)
def from_entries(
cls,
grouped_entries: List[ComputedEntry],
working_ion_entry: ComputedEntry,
battery_id: str,
host_structure: Structure,
) -> Union["InsertionElectrodeDoc", None]:
try:
ie = InsertionElectrode.from_entries(
entries=grouped_entries,
working_ion_entry=working_ion_entry,
strip_structures=True,
)
except IndexError:
return None
d = ie.get_summary_dict()
d["material_ids"] = d["stable_material_ids"] + d[
"unstable_material_ids"]
d["num_steps"] = d.pop("nsteps", None)
d["last_updated"] = datetime.utcnow()
elements = sorted(host_structure.composition.elements)
chemsys = "-".join(sorted(map(str, elements)))
framework = Composition(d["framework_formula"])
return cls(battery_id=battery_id,
host_structure=host_structure.as_dict(),
framework=framework,
electrode_object=ie.as_dict(),
elements=elements,
nelements=len(elements),
chemsys=chemsys,
formula_anonymous=framework.anonymized_formula,
**d)
def test_conversion_multiindex_dynamic(self):
# test dynamic target_col_id setting with multiindex
coords = [[0, 0, 0], [0.75, 0.5, 0.75]]
lattice = Lattice([[3.8401979337, 0.00, 0.00],
[1.9200989668, 3.3257101909, 0.00],
[0.00, -2.2171384943, 3.1355090603]])
struct = Structure(lattice, ["Si"] * 2, coords)
d = {'structure_dict': [struct.as_dict(), struct.as_dict()]}
df_2lvl = DataFrame(data=d)
df_2lvl.columns = MultiIndex.from_product((["custom"],
df_2lvl.columns.values))
dto = DictToObject()
df_2lvl = dto.featurize_dataframe(df_2lvl, ('custom', 'structure_dict'),
multiindex=True)
new_col_id = ('DictToObject', 'structure_dict_object')
self.assertEqual(df_2lvl[new_col_id].tolist()[0], struct)
self.assertEqual(df_2lvl[new_col_id].tolist()[1], struct)
def test_dict_to_object(self):
coords = [[0, 0, 0], [0.75, 0.5, 0.75]]
lattice = Lattice([[3.8401979337, 0.00, 0.00],
[1.9200989668, 3.3257101909, 0.00],
[0.00, -2.2171384943, 3.1355090603]])
struct = Structure(lattice, ["Si"] * 2, coords)
d = {'structure_dict': [struct.as_dict(), struct.as_dict()]}
df = DataFrame(data=d)
dto = DictToObject(target_col_id='structure')
df = dto.featurize_dataframe(df, 'structure_dict')
self.assertEqual(df["structure"].tolist()[0], struct)
self.assertEqual(df["structure"].tolist()[1], struct)
# test dynamic target_col_id setting
df = DataFrame(data=d)
dto = DictToObject()
df = dto.featurize_dataframe(df, 'structure_dict')
self.assertEqual(df["structure_dict_object"].tolist()[0], struct)
self.assertEqual(df["structure_dict_object"].tolist()[1], struct)
def read_cfgs(self, filename="output.data"):
"""
Read the configuration file.
Args:
filename (str): The configuration file to be read.
"""
data_pool = []
with zopen(filename, "rt") as f:
lines = f.read()
block_pattern = re.compile("begin\n(.*?)end", re.S)
lattice_pattern = re.compile("lattice(.*?)\n")
position_pattern = re.compile("atom(.*?)\n")
energy_pattern = re.compile("energy(.*?)\n")
for block in block_pattern.findall(lines):
d = {"outputs": {}}
lattice_str = lattice_pattern.findall(block)
lattice = Lattice(
np.array([latt.split() for latt in lattice_str],
dtype=np.float64) * self.bohr_to_angstrom)
position_str = position_pattern.findall(block)
positions = pd.DataFrame([pos.split() for pos in position_str])
positions.columns = [
"x", "y", "z", "specie", "charge", "atomic_energy", "fx", "fy",
"fz"
]
coords = np.array(positions.loc[:, ["x", "y", "z"]],
dtype=np.float64)
coords = coords * self.bohr_to_angstrom
species = np.array(positions["specie"])
forces = np.array(positions.loc[:, ["fx", "fy", "fz"]],
dtype=np.float64)
forces = forces / self.eV_to_Ha / self.bohr_to_angstrom
energy_str = energy_pattern.findall(block)[0]
energy = float(energy_str.lstrip()) / self.eV_to_Ha
struct = Structure(lattice=lattice,
species=species,
coords=coords,
coords_are_cartesian=True)
d["structure"] = struct.as_dict()
d["outputs"]["energy"] = energy
d["outputs"]["forces"] = forces
d["num_atoms"] = len(struct)
data_pool.append(d)
_, df = convert_docs(docs=data_pool)
return data_pool, df
def read_cfgs(self, filename='output.data'):
"""
Read the configuration file.
Args:
filename (str): The configuration file to be read.
"""
data_pool = []
with zopen(filename, 'rt') as f:
lines = f.read()
block_pattern = re.compile('begin\n(.*?)end', re.S)
lattice_pattern = re.compile('lattice(.*?)\n')
position_pattern = re.compile('atom(.*?)\n')
energy_pattern = re.compile('energy(.*?)\n')
for block in block_pattern.findall(lines):
d = {'outputs': {}}
lattice_str = lattice_pattern.findall(block)
lattice = Lattice(
np.array([latt.split() for latt in lattice_str],
dtype=np.float) * self.bohr_to_angstrom)
position_str = position_pattern.findall(block)
positions = pd.DataFrame([pos.split() for pos in position_str])
positions.columns = \
['x', 'y', 'z', 'specie', 'charge', 'atomic_energy', 'fx', 'fy', 'fz']
coords = np.array(positions.loc[:, ['x', 'y', 'z']],
dtype=np.float)
coords = coords * self.bohr_to_angstrom
species = np.array(positions['specie'])
forces = np.array(positions.loc[:, ['fx', 'fy', 'fz']],
dtype=np.float)
forces = forces / self.eV_to_Ha / self.bohr_to_angstrom
energy_str = energy_pattern.findall(block)[0]
energy = float(energy_str.lstrip()) / self.eV_to_Ha
struct = Structure(lattice=lattice,
species=species,
coords=coords,
coords_are_cartesian=True)
d['structure'] = struct.as_dict()
d['outputs']['energy'] = energy
d['outputs']['forces'] = forces
d['num_atoms'] = len(struct)
data_pool.append(d)
_, df = convert_docs(docs=data_pool)
return data_pool, df
def find_inequivalent_coords(structure: Structure,
df: DataFrame) -> List[CoordInfo]:
result = []
initial_sg = StructureSymmetrizer(structure).sg_number
added_structure = Structure.from_dict(structure.as_dict())
start_index = len(structure)
for _, column in df.iterrows():
coords = [column.a, column.b, column.c]
assert Element.Og not in structure.composition.elements
added_structure.append(Element.Og, coords)
end_index = len(added_structure)
symmetrizer = StructureSymmetrizer(added_structure)
if initial_sg != symmetrizer.sg_number:
logger.warning("The symmetry has changed, meaning all the symmetry "
"equivalent sites do not exist.")
sym_data = symmetrizer.spglib_sym_data
_indices = [i for i in range(start_index, end_index)]
repr_atom_pairs = zip(sym_data["equivalent_atoms"][_indices], _indices)
key = lambda x: x[0]
for _, equiv_sites in groupby(sorted(repr_atom_pairs, key=key), key=key):
coords, quantity = [], []
for repr_idx, atom_idx in equiv_sites:
fcoord = added_structure[atom_idx].frac_coords
coords.append(tuple(fcoord))
key = "ave_value" if "ave_value" in df else "value"
quantity.append(df[key][atom_idx - start_index])
if repr_idx == atom_idx:
site_sym = sym_data["site_symmetry_symbols"][atom_idx]
distances = Distances(structure, fcoord)
coordination = distances.coordination()
coord_info = CoordInfo(site_symmetry=remove_dot(site_sym),
coordination=coordination,
frac_coords=coords,
quantities=quantity)
result.append(coord_info)
return result
def read_cfgs(filename, predict=False):
"""
Read the configuration file.
Args:
filename (str): The configuration file to be read.
"""
type_convert = {'R': np.float32, 'I': np.int, 'S': np.str}
data_pool = []
with zopen(filename, 'rt') as f:
lines = f.read()
repl = re.compile('AT ')
lines = repl.sub('', string=lines)
block_pattern = re.compile(
r'(\n[0-9]+\n|^[0-9]+\n)(.+?)(?=\n[0-9]+\n|$)', re.S)
lattice_pattern = re.compile(r'Lattice="(.+)"')
# energy_pattern = re.compile('dft_energy=(-?[0-9]+.[0-9]+)', re.I)
energy_pattern = re.compile(
r'(?<=\S{3}\s|dft_)energy=(-?[0-9]+.[0-9]+)')
# stress_pattern = re.compile('dft_virial={(.+)}')
stress_pattern = re.compile(r'dft_virial=({|)(.+?)(}|) \S.*')
properties_pattern = re.compile(r'properties=(\S+)', re.I)
# position_pattern = re.compile('\n(.+)', re.S)
position_pattern = re.compile('\n(.+?)(?=\nE.*|\n\n.*|$)', re.S)
# formatify = lambda string: [float(s) for s in string.split()]
for (size, block) in block_pattern.findall(lines):
d = {'outputs': {}}
size = int(size)
lattice_str = lattice_pattern.findall(block)[0]
lattice = Lattice(
list(map(lambda s: float(s), lattice_str.split())))
energy_str = energy_pattern.findall(block)[-1]
energy = float(energy_str)
stress_str = stress_pattern.findall(block)[0][1]
virial_stress = np.array(
list(map(lambda s: float(s), stress_str.split())))
virial_stress = [virial_stress[i] for i in [0, 4, 8, 1, 5, 6]]
properties = properties_pattern.findall(block)[0].split(":")
labels_columns = OrderedDict()
labels = defaultdict()
for i in range(0, len(properties), 3):
labels_columns[properties[i]] = [
int(properties[i + 2]), properties[i + 1]
]
position_str = position_pattern.findall(block)[0].split('\n')
position = np.array([p.split() for p in position_str])
column_index = 0
for key in labels_columns:
num_columns, dtype = labels_columns[key]
labels[key] = position[:, column_index:column_index +
num_columns].astype(type_convert[dtype])
column_index += num_columns
struct = Structure(lattice=lattice,
species=labels['species'].ravel(),
coords=labels['pos'],
coords_are_cartesian=True)
if predict:
forces = labels['force']
else:
forces = labels['dft_force']
d['structure'] = struct.as_dict()
d['outputs']['energy'] = energy
assert size == struct.num_sites
d['num_atoms'] = size
d['outputs']['forces'] = forces
d['outputs']['virial_stress'] = virial_stress
data_pool.append(d)
_, df = convert_docs(docs=data_pool)
return data_pool, df
def read_cfgs(self, filename):
"""
Args:
filename (str): The configuration file to be read.
"""
def formatify(string):
return [float(s) for s in string.split()]
if not self.elements:
raise ValueError("No species given.")
data_pool = []
with zopen(filename, 'rt') as f:
lines = f.read()
block_pattern = re.compile('BEGIN_CFG\n(.*?)\nEND_CFG', re.S)
size_pattern = re.compile('Size\n(.*?)\n SuperCell', re.S | re.I)
lattice_pattern = re.compile('SuperCell\n(.*?)\n AtomData',
re.S | re.I)
position_pattern = re.compile('fz\n(.*?)\n Energy', re.S)
energy_pattern = re.compile('Energy\n(.*?)\n (?=PlusStress|Stress)',
re.S)
stress_pattern = re.compile('xy\n(.*?)(?=\n|$)', re.S)
for block in block_pattern.findall(lines):
d = {'outputs': {}}
size_str = size_pattern.findall(block)[0]
size = int(size_str.lstrip())
lattice_str = lattice_pattern.findall(block)[0]
lattice = Lattice(
np.array(list(map(formatify, lattice_str.split('\n')))))
position_str = position_pattern.findall(block)[0]
position = np.array(list(map(formatify, position_str.split('\n'))))
species = np.array(self.elements)[position[:, 1].astype(np.int)]
forces = position[:, 5:8].tolist()
position = position[:, 2:5]
energy_str = energy_pattern.findall(block)[0]
energy = float(energy_str.lstrip())
stress_str = stress_pattern.findall(block)[0]
virial_stress = np.array(list(map(formatify,
stress_str.split()))).reshape(
6, ).tolist()
virial_stress = [
virial_stress[self.mtp_stress_order.index(n)]
for n in self.vasp_stress_order
]
struct = Structure(lattice=lattice,
species=species,
coords=position,
coords_are_cartesian=True)
d['structure'] = struct.as_dict()
d['outputs']['energy'] = energy
assert size == struct.num_sites
d['num_atoms'] = size
d['outputs']['forces'] = forces
d['outputs']['virial_stress'] = virial_stress
data_pool.append(d)
_, df = convert_docs(docs=data_pool)
return data_pool, df
def to_istructure(structure: Structure) -> IStructure:
return IStructure.from_dict(structure.as_dict())
