def _get_pifquery(self, composition):
pif_query = PifQuery(system=SystemQuery(
chemical_formula=ChemicalFieldQuery(filter=ChemicalFilter(
equal=composition))))
# Check if any results found
if 'hits' not in self.client.search(pif_query).as_dictionary():
raise KeyError('No results found!')
pifquery = self.client.search(pif_query).as_dictionary()['hits']
return pifquery
def _get_pifquery(self, composition):
# TODO: does this stop csv generation on first invalid composition?
# TODO: Is there a way to send many compositions in one call to citrine?
pif_query = PifQuery(system=SystemQuery(
chemical_formula=ChemicalFieldQuery(filter=ChemicalFilter(
equal=composition))))
# Check if any results found
if 'hits' not in self.client.search(pif_query).as_dictionary():
raise KeyError('No results found!')
pifquery = self.client.search(pif_query).as_dictionary()['hits']
return pifquery
def get_data(self,
formula=None,
prop=None,
data_type=None,
reference=None,
min_measurement=None,
max_measurement=None,
from_record=None,
data_set_id=None,
max_results=None):
"""
Gets raw api data from Citrine in json format. See api_link for more
information on input parameters
Args:
formula: (str) filter for the chemical formula field; only those
results that have chemical formulas that contain this string
will be returned
prop: (str) name of the property to search for
data_type: (str) 'EXPERIMENTAL'/'COMPUTATIONAL'/'MACHINE_LEARNING';
filter for properties obtained from experimental work,
computational methods, or machine learning.
reference: (str) filter for the reference field; only those
results that have contributors that contain this string
will be returned
min_measurement: (str/num) minimum of the property value range
max_measurement: (str/num) maximum of the property value range
from_record: (int) index of first record to return (indexed from 0)
data_set_id: (int) id of the particular data set to search on
max_results: (int) number of records to limit the results to
Returns: (list) of jsons/pifs returned by Citrine's API
"""
json_data = []
start = from_record if from_record else 0
per_page = 100
refresh_time = 3 # seconds to wait between search calls
# Construct all of the relevant queries from input args
formula_query = ChemicalFieldQuery(filter=ChemicalFilter(
equal=formula))
prop_query = PropertyQuery(
name=FieldQuery(filter=Filter(equal=prop)),
value=FieldQuery(
filter=Filter(min=min_measurement, max=max_measurement)),
data_type=FieldQuery(filter=Filter(equal=data_type)))
ref_query = ReferenceQuery(doi=FieldQuery(filter=Filter(
equal=reference)))
system_query = PifSystemQuery(chemical_formula=formula_query,
properties=prop_query,
references=ref_query)
dataset_query = DatasetQuery(id=Filter(equal=data_set_id))
data_query = DataQuery(system=system_query, dataset=dataset_query)
while True:
# use per_page=max_results, eg: in case of max_results=68 < 100
if max_results and max_results < per_page:
pif_query = PifSystemReturningQuery(query=data_query,
from_index=start,
size=max_results)
else:
pif_query = PifSystemReturningQuery(query=data_query,
from_index=start,
size=per_page)
# Check if any results found
if "hits" not in self.client.search.pif_search(
pif_query).as_dictionary():
raise KeyError("No results found!")
data = self.client.search.pif_search(
pif_query).as_dictionary()["hits"]
size = len(data)
start += size
json_data.extend(data)
# check if limit is reached
if max_results and len(json_data) > max_results:
# get first multiple of 100 records
json_data = json_data[:max_results]
break
if size < per_page: # break out of last loop of results
break
time.sleep(refresh_time)
return json_data