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_dois():
f = Forge(index="mdf")
# One doi
f.match_dois("https://dx.doi.org/10.13011/M3B36G")
res1 = f.search()
assert res1 != []
assert check_field(res1, "dc.identifier.identifier",
"https://dx.doi.org/10.13011/M3B36G") == 0
# Multiple dois
f.match_dois(["https://dx.doi.org/10.13011/M3B36G", "10.18126/M23P9G"])
res2 = f.search()
# # res1 is ça subset of res2
assert len(res2) > len(res1)
assert all([r1 in res2 for r1 in res1])
assert check_field(res2, "dc.identifier.identifier",
"10.18126/M23P9G") == 2
# No doi
assert f.match_dois("") == f
