def get_dos_from_material_id(self, material_id: str):
"""
Get the complete density of states pymatgen object associated with a Materials Project ID.
Arguments:
materials_id (str): Materials Project ID for a material
Returns:
dos (CompleteDos): CompleteDos object
"""
es_rester = ElectronicStructureRester(endpoint=self.base_endpoint,
api_key=self.api_key)
dos_data = es_rester.get_data_by_id(document_id=material_id,
fields=["dos"]).dict()
if dos_data["dos"]:
dos_task_id = dos_data["dos"]["total"]["1"]["task_id"]
else:
raise MPRestError(
"No density of states data found for {}".format(material_id))
dos_obj = self.get_dos_from_task_id(dos_task_id)
if dos_obj:
b64_bytes = base64.b64decode(dos_obj[0], validate=True)
packed_bytes = zlib.decompress(b64_bytes)
json_data = msgpack.unpackb(packed_bytes, raw=False)
data = MontyDecoder().process_decoded(json_data["data"])
return data
else:
raise MPRestError("No density of states object found.")
def get_dos_from_material_id(self, material_id: str):
"""
Get the complete density of states pymatgen object associated with a Materials Project ID.
Arguments:
materials_id (str): Materials Project ID for a material
Returns:
dos (CompleteDos): CompleteDos object
"""
es_rester = ElectronicStructureRester(endpoint=self.base_endpoint,
api_key=self.api_key)
dos_data = es_rester.get_document_by_id(document_id=material_id,
fields=["dos"]).dict()
if dos_data["dos"]:
dos_calc_id = dos_data["dos"]["total"]["1"]["task_id"]
else:
raise MPRestError(
"No density of states data found for {}".format(material_id))
dos_obj = self.get_dos_from_calculation_id(dos_calc_id)
if dos_obj:
return dos_obj[0]["data"]
else:
raise MPRestError("No density of states object found.")
def find_structure(self, filename_or_structure, ltol=0.2, stol=0.3, angle_tol=5):
"""
Finds matching structures on the Materials Project site.
Args:
filename_or_structure: filename or Structure object
Returns:
A list of matching materials project ids for structure, \
including normalized rms distances and max distances between paired sites.
Raises:
MPRestError
"""
params = {"ltol": ltol, "stol": stol, "angle_tol": angle_tol}
try:
if isinstance(filename_or_structure, str):
s = Structure.from_file(filename_or_structure)
elif isinstance(filename_or_structure, PMGStructure):
s = filename_or_structure
else:
raise MPRestError("Provide filename or Structure object.")
payload = json.dumps(s.as_dict(), cls=MontyEncoder)
response = self.session.post(
self.endpoint + "find_structure", data=payload, params=params
)
if response.status_code == 200:
data = json.loads(response.text, cls=MontyDecoder)
if len(data.get("data", [])) > 0:
return data
else:
raise MPRestError("No matching structures found.")
else:
try:
data = json.loads(response.text)["detail"]
except (json.JSONDecodeError, KeyError):
data = "Response {}".format(response.text)
if isinstance(data, str):
message = data
else:
try:
message = ", ".join(
"{} - {}".format(entry["loc"][1], entry["msg"])
for entry in data
)
except (KeyError, IndexError):
message = str(data)
raise MPRestError(
f"REST query returned with error status code {response.status_code} "
f"on URL {response.url} with message:\n{message}"
)
except Exception as ex:
raise MPRestError(str(ex))
def get_bandstructure_from_material_id(
self,
material_id: str,
path_type: BSPathType = BSPathType.setyawan_curtarolo,
line_mode=True,
):
"""
Get the band structure pymatgen object associated with a Materials Project ID.
Arguments:
materials_id (str): Materials Project ID for a material
path_type (BSPathType): k-point path selection convention
line_mode (bool): Whether to return data for a line-mode calculation
Returns:
bandstructure (Union[BandStructure, BandStructureSymmLine]): BandStructure or BandStructureSymmLine object
"""
es_rester = ElectronicStructureRester(endpoint=self.base_endpoint,
api_key=self.api_key)
if line_mode:
bs_data = es_rester.get_document_by_id(
document_id=material_id,
fields=["bandstructure"]).bandstructure.dict()
if bs_data.get(path_type.value, None):
bs_calc_id = bs_data[path_type.value]["task_id"]
else:
raise MPRestError(
"No {} band structure data found for {}".format(
path_type.value, material_id))
else:
bs_data = es_rester.get_document_by_id(document_id=material_id,
fields=["dos"]).dos.dict()
if bs_data.get("total", None):
bs_calc_id = bs_data["total"]["1"]["task_id"]
else:
raise MPRestError(
"No uniform band structure data found for {}".format(
material_id))
bs_obj = self.get_bandstructure_from_calculation_id(bs_calc_id)
if bs_obj:
return bs_obj[0]["data"]
else:
raise MPRestError("No band structure object found.")
def get_charge_density_from_material_id(self, material_id: str):
"""
Get charge density data for a given Materials Project ID.
Arguments:
material_id (str): Material Project ID
Returns:
chgcar (dict): Pymatgen CHGCAR object.
"""
task_id = sorted(
self.get_charge_density_calculation_ids_from_material_id(
material_id),
key=lambda d: d["last_updated"],
reverse=True,
)[0]["task_id"]
result = self.search(task_ids=task_id,
fields=["task_id", "data"],
chunk_size=1)
if len(result) > 0:
return result[0]["data"]
else:
raise MPRestError("No charge density found")
def search(
self,
keywords: List[str],
num_chunks: Optional[int] = None,
chunk_size: Optional[int] = 100,
):
"""
Search text generated from Robocrystallographer.
Arguments:
keywords (List[str]): List of search keywords
num_chunks (Optional[int]): Maximum number of chunks of data to yield. None will yield all possible.
chunk_size (Optional[int]): Number of data entries per chunk.
Returns:
robocrys_docs (List[RobocrystallogapherDoc]): List of robocrystallographer documents
"""
keyword_string = ",".join(keywords)
robocrys_docs = self._query_resource(
criteria={
"keywords": keyword_string,
"_limit": chunk_size
},
suburl="text_search",
use_document_model=True,
chunk_size=100,
).get("data", None)
if robocrys_docs is None:
raise MPRestError("Cannot find any matches.")
return robocrys_docs
def search_robocrys_text(self, keywords: List[str]):
"""
Search text generated from Robocrystallographer.
Arguments:
keywords (List[str]): List of search keywords
Returns:
robocrys_docs (List[RobocrysDoc]): List of robocrystallographer documents
"""
keyword_string = ",".join(keywords)
robocrys_docs = self._query_resource(
criteria={
"keywords": keyword_string
},
suburl="text_search",
use_document_model=True,
).get("data", None)
if robocrys_docs is None:
raise MPRestError("Cannot find any matches.")
return robocrys_docs
def get_dos_from_task_id(self, task_id: str):
"""
Get the density of states pymatgen object associated with a given calculation ID.
Arguments:
task_id (str): Task ID for the density of states calculation
Returns:
bandstructure (CompleteDos): CompleteDos object
"""
result = self._query_resource(
criteria={
"task_id": task_id,
"_all_fields": True
},
suburl="object",
use_document_model=False,
num_chunks=1,
chunk_size=1,
)
if result.get("data", None) is not None:
return result["data"]
else:
raise MPRestError("No object found")
def get_structure_by_material_id(
self, material_id: str, version: Optional[str] = None
) -> Structure:
"""
Get a structure for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
version (str): Version of data to query on in the format 'YYYY.MM.DD'.
Defaults to None which will return data from the most recent database release.
Returns:
structure (Structure): Pymatgen structure object
"""
if version is None:
result = self._make_request("{}/?fields=structure".format(material_id))
else:
result = self._make_request(
"{}/?version={}&fields=structure".format(material_id, version)
)
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError(f"No document found for {material_id}")
def get_xas_doc(self, xas_id: str):
# TODO do some checking here for sub-components
query_params = {"all_fields": True}
result = self._query_resource(query_params, suburl=xas_id)
if len(result.get("data", [])) > 0:
return result["data"][0]
else:
raise MPRestError("No document found")
def get_database_versions(self):
"""
Get version tags available for the Materials Project core materials data.
These can be used to request data from previous releases.
Returns:
versions (List[str]): List of database versions as strings.
"""
result = self._make_request("versions")
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError("No data found")
def get_similar_structures(self, material_id: str):
"""
Get similar structures for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
results (Dict): Dictionary containing structure similarity data.
"""
result = self._make_request("{}/?all_fields=true".format(material_id))
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError("No document found")
def get_bandstructure_summary_from_material_id(self, material_id: str):
"""
Get a band structure summary doc for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
doc (dict): Band structure summary doc.
"""
result = self._make_request("{}/?all_fields=true".format(material_id))
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError("No document found")
def get_wulff_image_data_from_material_id(self, material_id: str):
"""
Get wulff image data for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
results (Dict): Dictionary containing wulff image data.
"""
result = self._make_request("{}/?all_fields=true".format(material_id))
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError("No document found")
def get_trajectory(self, task_id):
"""
Returns a Trajectory object containing the geometry of the
material throughout a calculation. This is most useful for
observing how a material relaxes during a geometry optimization.
:param task_id: A specified task_id
:return: List of trajectory objects
"""
traj_data = self._query_resource_data(suburl=f"trajectory/{task_id}/",
use_document_model=False)[0].get(
"trajectories", None)
if traj_data is None:
raise MPRestError(f"No trajectory data for {task_id} found")
return traj_data
def get_charge_density_from_material_id(self, material_id: str):
"""
Get charge density data for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
chgcar (dict): Pymatgen CHGCAR object.
"""
result = self._make_request(
"{}/?fields=data&all_fields=false".format(material_id))
if result.get("data", None) is not None:
return result["data"]
else:
raise MPRestError("No document found")
def get_dos_from_material_id(self, material_id: str):
"""
Get a density of states for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
dos (CompleteDos): Pymatgen density of states object
"""
result = self._make_request(
"object/?task_id={}&all_fields=true".format(material_id))
if result.get("object", None) is not None:
return result["object"]
else:
raise MPRestError("No document found")
def get_charge_density_from_calculation_id(self, task_id: str):
"""
Get charge density data for a given calculation ID.
Arguments:
task_id (str): Calculation ID
Returns:
chgcar (dict): Pymatgen CHGCAR object.
"""
result = self.search(task_ids=task_id,
fields=["task_id", "data"],
chunk_size=1)
if len(result) > 0:
return result[0]["data"]
else:
raise MPRestError("No charge density found")
def get_charge_density_from_material_id(
self,
material_id: str,
inc_task_doc: bool = False) -> Optional[Chgcar]:
"""
Get charge density data for a given Materials Project ID.
Arguments:
material_id (str): Material Project ID
inc_task_doc (bool): Whether to include the task document in the returned data.
Returns:
chgcar: Pymatgen Chgcar object.
"""
# TODO: really we want a recommended task_id for charge densities here
# this could potentially introduce an ambiguity
task_ids = self.get_task_ids_associated_with_material_id(
material_id,
calc_types=[CalcType.GGA_Static, CalcType.GGA_U_Static])
results: List[ChgcarDataDoc] = self.charge_density.search(
task_ids=task_ids) # type: ignore
if len(results) == 0:
return None
latest_doc = max(results, key=lambda x: x.last_updated)
chgcar = self.charge_density.get_charge_density_from_file_id(
latest_doc.fs_id)
if chgcar is None:
raise MPRestError(f"No charge density fetched for {material_id}.")
if inc_task_doc:
task_doc = self.tasks.get_data_by_id(latest_doc.task_id)
return chgcar, task_doc
return chgcar
def get_bandstructure_from_material_id(self, material_id: str,
path_type: BSPathType):
"""
Get a band structure for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
path_type (BSPathType): Band structure type determined by the k-path convention used.
Returns:
bandstructure (BandStructureSymmLine): Pymatgen band structure object
"""
result = self._make_request(
"object/?task_id={}&path_type={}&all_fields=true".format(
material_id, path_type.value))
if result.get("object", None) is not None:
return result["object"]
else:
raise MPRestError("No document found")
def get_task_from_material_id(
self,
material_id: str,
fields: Iterable[str] = ("task_id", "formula_pretty", "last_updated"),
):
"""
Get task document data for a given Materials Project ID.
Arguments:
material_id (str): Materials project ID
Returns:
data (dict): Task doc data for keys in fields. Defaults to
task_id, formula_pretty, and last_updated.
"""
field_vals = ",".join(fields)
result = self._make_request("{}/?fields={}".format(
material_id, field_vals))
if len(result.get("data", [])) > 0:
return result
else:
raise MPRestError("No document found")
def find_structure(self,
filename_or_structure,
ltol=0.2,
stol=0.3,
angle_tol=5,
limit=1):
"""
Finds matching structures on the Materials Project site.
Args:
filename_or_structure: filename or Structure object
Returns:
A list of matching materials project ids for structure, \
including normalized rms distances and max distances between paired sites.
Raises:
MPRestError
"""
params = {
"ltol": ltol,
"stol": stol,
"angle_tol": angle_tol,
"limit": limit
}
if isinstance(filename_or_structure, str):
s = Structure.from_file(filename_or_structure)
elif isinstance(filename_or_structure, Structure):
s = filename_or_structure
else:
raise MPRestError("Provide filename or Structure object.")
return self._post_resource(
body=s.as_dict(),
params=params,
suburl="find_structure",
use_document_model=False,
).get("data")
def get_bandstructure_from_calculation_id(self, task_id: str):
"""
Get the band structure pymatgen object associated with a given calculation ID.
Arguments:
task_id (str): Calculation ID for the band structure calculation
Returns:
bandstructure (BandStructure): BandStructure or BandStructureSymmLine object
"""
result = self._query_resource(
criteria={
"task_id": task_id,
"all_fields": True
},
suburl="object",
use_document_model=False,
)
if result.get("data", None) is not None:
return result["data"]
else:
raise MPRestError("No object found")
def search(
self,
keywords: Optional[List[str]] = None,
synthesis_type: Optional[List[SynthesisTypeEnum]] = None,
target_formula: Optional[str] = None,
precursor_formula: Optional[str] = None,
operations: Optional[List[OperationTypeEnum]] = None,
condition_heating_temperature_min: Optional[float] = None,
condition_heating_temperature_max: Optional[float] = None,
condition_heating_time_min: Optional[float] = None,
condition_heating_time_max: Optional[float] = None,
condition_heating_atmosphere: Optional[List[str]] = None,
condition_mixing_device: Optional[List[str]] = None,
condition_mixing_media: Optional[List[str]] = None,
num_chunks: Optional[int] = None,
chunk_size: Optional[int] = 10,
):
"""
Search synthesis recipe text.
Arguments:
keywords (Optional[List[str]]): List of string keywords to search synthesis paragraph text with
synthesis_type (Optional[List[SynthesisTypeEnum]]): Type of synthesis to include
target_formula (Optional[str]): Chemical formula of the target material
precursor_formula (Optional[str]): Chemical formula of the precursor material
operations (Optional[List[OperationTypeEnum]]): List of operations that syntheses must have
condition_heating_temperature_min (Optional[float]): Minimal heating temperature
condition_heating_temperature_max (Optional[float]): Maximal heating temperature
condition_heating_time_min (Optional[float]): Minimal heating time
condition_heating_time_max (Optional[float]): Maximal heating time
condition_heating_atmosphere (Optional[List[str]]): Required heating atmosphere, such as "air", "argon"
condition_mixing_device (Optional[List[str]]): Required mixing device, such as "zirconia", "Al2O3".
condition_mixing_media (Optional[List[str]]): Required mixing media, such as "alcohol", "water"
num_chunks (Optional[int]): Maximum number of chunks of data to yield. None will yield all possible.
chunk_size (Optional[int]): Number of data entries per chunk.
Returns:
synthesis_docs ([SynthesisDoc]): List of synthesis documents
"""
# Turn None and empty list into None
keywords = keywords or None
synthesis_type = synthesis_type or None
operations = operations or None
condition_heating_atmosphere = condition_heating_atmosphere or None
condition_mixing_device = condition_mixing_device or None
condition_mixing_media = condition_mixing_media or None
if keywords:
keywords = ",".join([word.strip()
for word in keywords]) # type: ignore
synthesis_docs = self._query_resource(
criteria={
"keywords": keywords,
"synthesis_type": synthesis_type,
"target_formula": target_formula,
"precursor_formula": precursor_formula,
"operations": operations,
"condition_heating_temperature_min":
condition_heating_temperature_min,
"condition_heating_temperature_max":
condition_heating_temperature_max,
"condition_heating_time_min": condition_heating_time_min,
"condition_heating_time_max": condition_heating_time_max,
"condition_heating_atmosphere": condition_heating_atmosphere,
"condition_mixing_device": condition_mixing_device,
"condition_mixing_media": condition_mixing_media,
"_limit": chunk_size,
},
chunk_size=chunk_size,
num_chunks=num_chunks,
).get("data", None)
if synthesis_docs is None:
raise MPRestError("Cannot find any matches.")
return synthesis_docs
def get_bandstructure_from_material_id(
self,
material_id: str,
path_type: BSPathType = BSPathType.setyawan_curtarolo,
line_mode=True,
):
"""
Get the band structure pymatgen object associated with a Materials Project ID.
Arguments:
materials_id (str): Materials Project ID for a material
path_type (BSPathType): k-point path selection convention
line_mode (bool): Whether to return data for a line-mode calculation
Returns:
bandstructure (Union[BandStructure, BandStructureSymmLine]): BandStructure or BandStructureSymmLine object
"""
es_rester = ElectronicStructureRester(endpoint=self.base_endpoint,
api_key=self.api_key)
if line_mode:
bs_data = es_rester.get_data_by_id(document_id=material_id,
fields=["bandstructure"
]).bandstructure
if bs_data is None:
raise MPRestError(
"No {} band structure data found for {}".format(
path_type.value, material_id))
else:
bs_data = bs_data.dict()
if bs_data.get(path_type.value, None):
bs_task_id = bs_data[path_type.value]["task_id"]
else:
raise MPRestError(
"No {} band structure data found for {}".format(
path_type.value, material_id))
else:
bs_data = es_rester.get_data_by_id(document_id=material_id,
fields=["dos"]).dos
if bs_data is None:
raise MPRestError(
"No uniform band structure data found for {}".format(
material_id))
else:
bs_data = bs_data.dict()
if bs_data.get("total", None):
bs_task_id = bs_data["total"]["1"]["task_id"]
else:
raise MPRestError(
"No uniform band structure data found for {}".format(
material_id))
bs_obj = self.get_bandstructure_from_task_id(bs_task_id)
if bs_obj:
b64_bytes = base64.b64decode(bs_obj[0], validate=True)
packed_bytes = zlib.decompress(b64_bytes)
json_data = msgpack.unpackb(packed_bytes, raw=False)
data = MontyDecoder().process_decoded(json_data["data"])
return data
else:
raise MPRestError("No band structure object found.")
def search_synthesis_text(
self,
keywords: Optional[List[str]] = None,
synthesis_type: Optional[List[SynthesisTypeEnum]] = None,
target_formula: Optional[str] = None,
precursor_formula: Optional[str] = None,
operations: Optional[List[OperationTypeEnum]] = None,
condition_heating_temperature_min: Optional[float] = None,
condition_heating_temperature_max: Optional[float] = None,
condition_heating_time_min: Optional[float] = None,
condition_heating_time_max: Optional[float] = None,
condition_heating_atmosphere: Optional[List[str]] = None,
condition_mixing_device: Optional[List[str]] = None,
condition_mixing_media: Optional[List[str]] = None,
):
"""
Search synthesis recipe text.
Arguments:
keywords (Optional[List[str]]): List of string keywords to search synthesis paragraph text with
synthesis_type (Optional[List[SynthesisTypeEnum]]): Type of synthesis to include
target_formula (Optional[str]): Chemical formula of the target material
precursor_formula (Optional[str]): Chemical formula of the precursor material
operations (Optional[List[OperationTypeEnum]]): List of operations that syntheses must have
condition_heating_temperature_min (Optional[float]): Minimal heating temperature
condition_heating_temperature_max (Optional[float]): Maximal heating temperature
condition_heating_time_min (Optional[float]): Minimal heating time
condition_heating_time_max (Optional[float]): Maximal heating time
condition_heating_atmosphere (Optional[List[str]]): Required heating atmosphere, such as "air", "argon"
condition_mixing_device (Optional[List[str]]): Required mixing device, such as "zirconia", "Al2O3".
condition_mixing_media (Optional[List[str]]): Required mixing media, such as "alcohol", "water"
Returns:
synthesis_docs ([SynthesisDoc]): List of synthesis documents
"""
# Turn None and empty list into None
keywords = keywords or None
synthesis_type = synthesis_type or None
operations = operations or None
condition_heating_atmosphere = condition_heating_atmosphere or None
condition_mixing_device = condition_mixing_device or None
condition_mixing_media = condition_mixing_media or None
synthesis_docs = self._query_resource(
criteria={
"keywords": keywords,
"synthesis_type": synthesis_type,
"target_formula": target_formula,
"precursor_formula": precursor_formula,
"operations": operations,
"condition_heating_temperature_min":
condition_heating_temperature_min,
"condition_heating_temperature_max":
condition_heating_temperature_max,
"condition_heating_time_min": condition_heating_time_min,
"condition_heating_time_max": condition_heating_time_max,
"condition_heating_atmosphere": condition_heating_atmosphere,
"condition_mixing_device": condition_mixing_device,
"condition_mixing_media": condition_mixing_media,
},
use_document_model=True,
).get("data", None)
if synthesis_docs is None:
raise MPRestError("Cannot find any matches.")
return synthesis_docs
def find_structure(
self,
filename_or_structure,
ltol=_EMMET_SETTINGS.LTOL,
stol=_EMMET_SETTINGS.STOL,
angle_tol=_EMMET_SETTINGS.ANGLE_TOL,
allow_multiple_results=False,
) -> Union[List[str], str]:
"""
Finds matching structures from the Materials Project database.
Multiple results may be returned of "similar" structures based on
distance using the pymatgen StructureMatcher algorithm, however only
a single result should match with the same spacegroup, calculated to the
default tolerances.
Args:
filename_or_structure: filename or Structure object
ltol: fractional length tolerance
stol: site tolerance
angle_tol: angle tolerance in degrees
allow_multiple_results: changes return type for either
a single material_id or list of material_ids
Returns:
A matching material_id if one is found or list of results if allow_multiple_results
is True
Raises:
MPRestError
"""
params = {
"ltol": ltol,
"stol": stol,
"angle_tol": angle_tol,
"_limit": 1
}
if isinstance(filename_or_structure, str):
s = Structure.from_file(filename_or_structure)
elif isinstance(filename_or_structure, Structure):
s = filename_or_structure
else:
raise MPRestError("Provide filename or Structure object.")
results = self._post_resource(
body=s.as_dict(),
params=params,
suburl="find_structure",
use_document_model=False,
).get("data")
if len(results) > 1: # type: ignore
if not allow_multiple_results:
raise ValueError(
"Multiple matches found for this combination of tolerances, but "
"`allow_multiple_results` set to False.")
return results # type: ignore
if results:
return results[0]["material_id"]
else:
return []