def test_forge_fetch_datasets_from_results():
# Get some results
f = Forge(index="mdf")
# Record from OQMD
res01 = f.search("mdf.source_name:oqmd AND mdf.resource_type:record",
advanced=True,
limit=1)
# Record from OQMD with info
res02 = f.search("mdf.source_name:oqmd AND mdf.resource_type:record",
advanced=True,
limit=1,
info=True)
# Records from JANAF
res03 = f.search(
"mdf.source_name:khazana_vasp AND mdf.resource_type:record",
advanced=True,
limit=2)
# Dataset for NIST XPS DB
res04 = f.search(
"mdf.source_name:nist_xps_db AND mdf.resource_type:dataset",
advanced=True)
# Get the correct dataset entries
oqmd = f.search("mdf.source_name:oqmd AND mdf.resource_type:dataset",
advanced=True)[0]
khazana_vasp = f.search(
"mdf.source_name:khazana_vasp AND mdf.resource_type:dataset",
advanced=True)[0]
# Fetch single dataset
res1 = f.fetch_datasets_from_results(res01[0])
assert mdf_toolbox.insensitive_comparison(res1[0], oqmd)
# Fetch dataset with results + info
res2 = f.fetch_datasets_from_results(res02)
assert mdf_toolbox.insensitive_comparison(res2[0], oqmd)
# Fetch multiple datasets
rtemp = res01 + res03
res3 = f.fetch_datasets_from_results(rtemp)
assert len(res3) == 2
assert oqmd in res3
assert khazana_vasp in res3
# Fetch dataset from dataset
res4 = f.fetch_datasets_from_results(res04)
assert mdf_toolbox.insensitive_comparison(res4, res04)
# Fetch entries from current query
f.match_source_names("nist_xps_db")
assert f.fetch_datasets_from_results() == res04
# Fetch nothing
unknown_entry = {"mdf": {"resource_type": "unknown"}}
assert f.fetch_datasets_from_results(unknown_entry) == []
class FoundryDatasets():
"""
Class to download datasets hosted on Materials Data Facility
Args:
no_local_server: (bool), whether or not the server is local. Set to True if running on e.g. Google Colab
anonymous: (bool), whether to use your MDF user or be anonymous. Some functionality may be disabled if True
test: (bool), whether to be in test mode. Some functionality may be disabled if True
Methods:
download_data: downloads specified data from MDF and saves to current directory
Args:
name: (str), name of the dataset to download
doi: (str), digital object identifier of the dataset to download
download: (bool), whether or not to download the full dataset
Returns:
None
"""
def __init__(self, no_local_server, anonymous, test):
self.no_local_server = no_local_server
self.anonymous = anonymous
self.test = test
self.mdf = Forge(no_local_server=self.no_local_server,
anonymous=self.anonymous,
test=self.test)
def download_data(self, name=None, doi=None, download=False):
if name is not None:
self.mdf.match_source_names(name)
elif doi is not None:
self.mdf.match_dois(doi)
else:
print('ERROR: please specify either the dataset name or DOI for lookup MDF')
result = self.mdf.search()
if len(result) == 1:
print('Successfully found the desired dataset on MDF')
print('MDF entry:')
pprint(result)
if download == True:
print('Downloading dataset from MDF')
self.mdf.globus_download(results=result)
return
def test_forge_match_source_names():
f = Forge(index="mdf")
# One source
f.match_source_names("khazana_vasp")
res1 = f.search()
assert res1 != []
assert check_field(res1, "mdf.source_name", "khazana_vasp") == 0
# Multi-source, strip version info
f.match_source_names(["khazana_vasp", "ta_melting_v3.4"])
res2 = f.search()
# res1 is a subset of res2
assert len(res2) > len(res1)
assert all([r1 in res2 for r1 in res1])
assert check_field(res2, "mdf.source_name", "ta_melting") == 2
# No source
assert f.match_source_names("") == f
def test_forge_search_by_elements():
f = Forge(index="mdf")
elements = ["Cu", "Al"]
sources = ["oqmd", "nist_xps_db"]
res1, info1 = f.match_source_names(sources).match_elements(
elements).search(limit=10000, info=True)
res2, info2 = f.search_by_elements(elements,
sources,
limit=10000,
info=True)
assert all([r in res2 for r in res1]) and all([r in res1 for r in res2])
assert check_field(res1, "material.elements", "Al") == 1
assert check_field(res1, "mdf.source_name", "oqmd") == 2
def test_forge_match_source_names():
os.system('echo hello')
f = Forge(index="mdf", no_local_server=True, no_browser=True)
os.system('echo there')
assert True
# One source
f.match_source_names("khazana_vasp")
res1 = f.search()
assert res1 != []
assert check_field(res1, "mdf.source_name", "khazana_vasp") == 0
# Multi-source, strip version info
f.match_source_names(["khazana_vasp", "ta_melting_v3.4"])
res2 = f.search()
# res1 is a subset of res2
assert len(res2) > len(res1)
assert all([r1 in res2 for r1 in res1])
assert check_field(res2, "mdf.source_name", "ta_melting") == 2
# No source
assert f.match_source_names("") == f
