def test_forge_aggregate_sources():
# Test limit
f = Forge(index="mdf")
res1 = f.aggregate_sources("nist_xps_db")
assert isinstance(res1, list)
assert len(res1) > 10000
assert isinstance(res1[0], dict)
def test_forge_globus_download():
f = Forge(index="mdf")
# Simple case
f.globus_download(example_result1)
assert os.path.exists("./test_fetch.txt")
os.remove("./test_fetch.txt")
# With dest and preserve_dir
dest_path = os.path.expanduser("~/mdf")
f.globus_download(example_result1, dest=dest_path, preserve_dir=True)
assert os.path.exists(os.path.join(dest_path, "test", "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test", "test_fetch.txt"))
os.rmdir(os.path.join(dest_path, "test"))
# With multiple files
f.globus_download(example_result2, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
f.globus_download(example_result3, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
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 test_forge_search_by_titles():
f = Forge(index="mdf")
titles1 = ['"High-throughput Ab-initio Dilute Solute Diffusion Database"']
res1 = f.search_by_titles(titles1)
assert check_field(
res1, "dc.titles.[].title",
"High-throughput Ab-initio Dilute Solute Diffusion Database") == 0
titles2 = ["Database"]
res2 = f.search_by_titles(titles2)
assert check_field(res2, "dc.titles.[].title",
"NIST X-ray Photoelectron Spectroscopy Database") == 2
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 __init__(self,
no_browser=False,
no_local_server=False,
search_index="mdf-test",
**data):
super().__init__(**data)
auths = mdf_toolbox.login(
services=[
"data_mdf",
"search",
"petrel",
"transfer",
"dlhub",
"https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all",
],
app_name="Foundry",
make_clients=True,
no_browser=no_browser,
no_local_server=no_local_server,
)
self.forge_client = Forge(
index=search_index,
services=None,
search_client=auths["search"],
transfer_client=auths["transfer"],
data_mdf_authorizer=auths["data_mdf"],
petrel_authorizer=auths["petrel"],
)
self.dlhub_client = DLHubClient(
dlh_authorizer=auths["dlhub"],
search_client=auths["search"],
fx_authorizer=auths[
"https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all"],
force_login=False,
)
self.xtract_tokens = {
'auth_token':
auths['petrel'].access_token,
'transfer_token':
auths['transfer'].authorizer.access_token,
'funx_token':
auths[
'https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all']
.access_token
}
def test_forge_chaining():
f = Forge(index="mdf")
f.match_field("source_name", "cip")
f.match_field("material.elements", "Al")
res1 = f.search()
res2 = f.match_field("source_name",
"cip").match_field("material.elements",
"Al").search()
assert all([r in res2 for r in res1]) and all([r in res1 for r in res2])
def test_forge_match_resource_types():
f = Forge(index="mdf")
# Test one type
f.match_resource_types("record")
res1 = f.search(limit=10)
assert check_field(res1, "mdf.resource_type", "record") == 0
# Test two types
f.match_resource_types(["collection", "dataset"])
res2 = f.search()
assert check_field(res2, "mdf.resource_type", "record") == -1
# Test zero types
assert f.match_resource_types("") == f
def test_forge_anonymous(capsys):
f = Forge(anonymous=True)
# Test search
assert len(
f.search("mdf.source_name:ab_initio_solute_database",
advanced=True,
limit=300)) == 300
# Test aggregation
assert len(f.aggregate("mdf.source_name:nist_xps_db")) > 10000
# Error on auth-only functions
# http_download
assert f.http_download({})["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous HTTP download not yet supported." in out
# globus_download
assert f.globus_download({})["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous Globus Transfer not supported." in out
# http_stream
res = f.http_stream({})
assert next(res)["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous HTTP download not yet supported." in out
with pytest.raises(StopIteration):
next(res)
def test_forge_http_stream(capsys):
f = Forge(index="mdf")
# Simple case
res1 = f.http_stream(example_result1)
assert isinstance(res1, types.GeneratorType)
assert next(
res1
) == "This is a test document for Forge testing. Please do not remove.\n"
# With multiple files
res2 = f.http_stream((example_result2, {"info": {}}))
assert isinstance(res2, types.GeneratorType)
assert next(
res2
) == "This is a test document for Forge testing. Please do not remove.\n"
assert next(
res2
) == "This is a second test document for Forge testing. Please do not remove.\n"
assert next(
res2
) == "This is a test document for Forge testing. Please do not remove.\n"
assert next(
res2
) == "This is a second test document for Forge testing. Please do not remove.\n"
res3 = f.http_stream((example_result3, {"info": {}}))
assert isinstance(res3, types.GeneratorType)
assert next(
res3
) == "This is a test document for Forge testing. Please do not remove.\n"
assert next(
res3
) == "This is a second test document for Forge testing. Please do not remove.\n"
assert next(
res3
) == "This is a test document for Forge testing. Please do not remove.\n"
assert next(
res3
) == "This is a second test document for Forge testing. Please do not remove.\n"
# Too many results
res4 = f.http_stream(list(range(10001)))
assert next(res4)["success"] is False
out, err = capsys.readouterr()
assert "Too many results supplied. Use globus_download()" in out
with pytest.raises(StopIteration):
next(res4)
# "Missing" files
assert next(f.http_stream(example_result_missing)) is None
out, err = capsys.readouterr()
assert not os.path.exists("./should_not_exist.txt")
assert (
"Error 404 when attempting to access "
"'https://data.materialsdatafacility.org/test/should_not_exist.txt'"
) in out
def test_forge_match_organizations():
f = Forge(index="mdf")
# One repo
f.match_organizations("NIST")
res1 = f.search()
assert res1 != []
check_val1 = check_field(res1, "mdf.organizations", "NIST")
assert check_val1 == 1
# Multi-repo
f.match_organizations(["NIST", "PRISMS"], match_all=False)
res2 = f.search()
assert check_field(res2, "mdf.organizations", "PRISMS") == 2
assert check_field(res2, "mdf.organizations", "NIST") == 2
# No repos
assert f.match_organizations("") == f
def test_forge_match_elements():
f = Forge(index="mdf")
# One element
f.match_elements("Al")
res1 = f.search()
assert res1 != []
check_val1 = check_field(res1, "material.elements", "Al")
assert check_val1 == 0 or check_val1 == 1
# Multi-element
f.match_elements(["Al", "Cu"])
res2 = f.search()
assert check_field(res2, "material.elements", "Al") == 1
assert check_field(res2, "material.elements", "Cu") == 1
# No elements
assert f.match_elements("") == f
def test_forge_match_titles():
# One title
f = Forge(index="mdf")
titles1 = '"High-throughput Ab-initio Dilute Solute Diffusion Database"'
res1 = f.match_titles(titles1).search()
assert res1 != []
assert check_field(
res1, "dc.titles.[].title",
"High-throughput Ab-initio Dilute Solute Diffusion Database") == 0
# Multiple titles
titles2 = [
'"High-throughput Ab-initio Dilute Solute Diffusion Database"',
'"Khazana (VASP)"'
]
res2 = f.match_titles(titles2).search()
assert res2 != []
assert check_field(res2, "dc.titles.[].title", "Khazana (VASP)") == 2
# No titles
assert f.match_titles("") == f
def test_forge_test_match_records():
f = Forge(index="mdf")
# One record
f.match_records("cip", 1006)
res = f.search()
assert len(res) == 1
assert check_field(res, "mdf.source_name", "cip") == 0
assert check_field(res, "mdf.scroll_id", 1006) == 0
# Multi-record, strip version info
f.match_records("cip_v3.4", [1006, 1002])
res = f.search()
assert len(res) == 2
assert check_field(res, "mdf.source_name", "cip") == 0
assert check_field(res, "mdf.scroll_id", 1006) == 2
# No args
assert f.match_records("", "") == f
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_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
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
def test_get_dataset_version():
# Get the version number of the OQMD
f = Forge()
hits = f.search('mdf.source_name:oqmd AND mdf.resource_type:dataset',
advanced=True,
limit=1)
assert hits[0]['mdf']['version'] == f.get_dataset_version('oqmd')
# Test invalid source_name
with pytest.raises(ValueError):
f.get_dataset_version('notreal')
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_search_by_dois():
f = Forge(index="mdf")
res1 = f.search_by_dois("https://dx.doi.org/10.13011/M3B36G")
assert check_field(res1, "dc.identifier.identifier",
"https://dx.doi.org/10.13011/M3B36G") == 0
def test_forge_match_years(capsys):
# One year of data/results
f = Forge(index="mdf")
res1 = f.match_years("2015").search()
assert res1 != []
assert check_field(res1, "dc.publicationYear", 2015) == 0
# Multiple years
res2 = f.match_years(years=["2015", 2016]).search()
assert check_field(res2, "dc.publicationYear", 2016) == 2
# Wrong input
with pytest.raises(AttributeError) as excinfo:
f.match_years(["20x5"]).search()
assert "Invalid year: '20x5'" in str(excinfo.value)
with pytest.raises(AttributeError) as excinfo:
f.match_years(start="20x5").search()
assert "Invalid start year: '20x5'" in str(excinfo.value)
with pytest.raises(AttributeError) as excinfo:
f.match_years(stop="20x5").search()
assert "Invalid stop year: '20x5'" in str(excinfo.value)
# No filters with no input
f.match_years()
assert f.current_query() == ""
# Test range
res4 = f.match_years(start=2015, stop=2015, inclusive=True).search()
assert check_field(res4, "dc.publicationYear", 2015) == 0
res5 = f.match_years(start=2014, stop=2017, inclusive=False).search()
assert check_field(res5, "dc.publicationYear", 2013) == -1
assert check_field(res5, "dc.publicationYear", 2014) == -1
assert check_field(res5, "dc.publicationYear", 2015) == 2
assert check_field(res5, "dc.publicationYear", 2016) == 2
assert check_field(res5, "dc.publicationYear", 2017) == -1
assert f.match_years(start=2015, stop=2015, inclusive=False).search() == []
def test_describe_field(capsys):
f = Forge()
# Basic usage (raw=True for ease of testing)
res = f.describe_field("dataset", raw=True)
assert res["success"]
assert "dc" in res["schema"]["properties"].keys()
assert res["schema"]["properties"]["mdf"]["properties"]["source_id"]
# Specific field
res = f.describe_field("dataset", field="dc", raw=True)
assert "mdf" not in res["schema"]["properties"].keys()
assert "titles" in res["schema"]["properties"].keys()
# Special case
res = f.describe_field("list", raw=True)
assert isinstance(res["schema"], list)
assert "mdf" in res["schema"]
# Printing to stdout
f.describe_field("record")
out, err = capsys.readouterr()
assert "- custom" in out
# Specific field
f.describe_field("record", field="mdf")
out, err = capsys.readouterr()
assert "- custom" not in out
assert "- source_id" in out
# Errors
# Invalid resource_type
res = f.describe_field("notexists", raw=True)
assert res["success"] is False
assert res["schema"] is None
assert res["error"].startswith("Error 404")
# stdout
f.describe_field("notexists")
out, err = capsys.readouterr()
assert "Error 404" in out
# Invalid field
res = f.describe_field("dataset", field="foo.bar", raw=True)
assert res["success"] is False
assert res["schema"] is None
assert res["error"].startswith("Error: Field 'foo' (from 'foo.bar')")
# stdout
f.describe_field("dataset", field="foo.bar")
out, err = capsys.readouterr()
assert "Error: Field 'foo' (from 'foo.bar')" in out
def generate_stats(raw=False, return_all=False, many_cutoff=100):
"""Generates statistics on datasets in MDF Search.
Arguments:
raw (bool): When False, will print stats to stdout and display a progress bar.
When True, will return a dict of stats and will not display a progress bar.
Default False.
return_all (bool): When False or when raw is False, generate summary statistics.
When True and raw is True, return the dataset source_ids for each category.
Extremely verbose.
Default False.
many_cutoff (int): The number of records required to be considered "many" records.
Thie value is inclusive.
Default 100.
Returns:
dict: Stats, when raw is True (else these are printed)
"""
mdf = Forge()
dataset_list = mdf.match_resource_types("dataset").search()
all_datasets = []
num_records = 0
zero_records = []
one_record = []
multiple_records = []
many_records = []
for ds in tqdm(dataset_list, disable=raw):
source_id = ds["mdf"]["source_id"]
record_count = mdf.match_resource_types("record") \
.match_source_names(source_id) \
.search(limit=0, info=True)[1]["total_query_matches"]
all_datasets.append((source_id, record_count))
num_records += record_count
if record_count == 0:
zero_records.append(source_id)
elif record_count == 1:
one_record.append(source_id)
elif record_count > 1:
multiple_records.append(source_id)
if record_count >= int(many_cutoff):
many_records.append(source_id)
if raw:
returnable = {}
returnable["all_datasets_count"] = len(all_datasets)
returnable["all_records_count"] = num_records
returnable["zero_records_count"] = len(zero_records)
returnable["one_record_count"] = len(one_record)
returnable["multiple_records_count"] = len(multiple_records)
returnable["many_records_count"] = len(many_records)
returnable["one_or_more_count"] = len(one_record) + len(
multiple_records)
if return_all:
returnable["all_datasets"] = all_datasets
returnable["zero_records"] = zero_records
returnable["one_record"] = one_record
returnable["multiple_records"] = multiple_records
returnable["many_records"] = many_records
returnable["one_or_more"] = one_record + multiple_records
return returnable
else:
print("MDF Search Statistics")
print("---------------------")
print("Total datasets:", len(all_datasets))
print("Total records:", num_records)
print("Datasets with zero records:", len(zero_records))
print("Datasets with any records: ",
len(one_record) + len(multiple_records))
print("{}% of datasets have records".format(
int((len(one_record) + len(multiple_records)) / len(all_datasets) *
100)))
print()
print("Datasets with exactly one record: ", len(one_record))
print("Datasets with more than one record: ", len(multiple_records))
print("Datasets with more than", many_cutoff, "records:",
len(many_records))
print()
return
def test_forge_http_download(capsys):
f = Forge(index="mdf")
# Simple case
f.http_download(example_result1)
assert os.path.exists("./test_fetch.txt")
# Test conflicting filenames
f.http_download(example_result1)
assert os.path.exists("./test_fetch(1).txt")
f.http_download(example_result1)
assert os.path.exists("./test_fetch(2).txt")
os.remove("./test_fetch.txt")
os.remove("./test_fetch(1).txt")
os.remove("./test_fetch(2).txt")
# With dest and preserve_dir, and tuple of results
dest_path = os.path.expanduser("~/mdf")
f.http_download(([example_result1], {
"info": None
}),
dest=dest_path,
preserve_dir=True)
assert os.path.exists(os.path.join(dest_path, "test", "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test", "test_fetch.txt"))
os.rmdir(os.path.join(dest_path, "test"))
# With multiple files
f.http_download(example_result2, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "petrel_fetch.txt"))
os.remove(os.path.join(dest_path, "petrel_multifetch.txt"))
f.http_download(example_result3, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "petrel_fetch.txt"))
os.remove(os.path.join(dest_path, "petrel_multifetch.txt"))
# Too many files
assert f.http_download(list(range(10001)))["success"] is False
out, err = capsys.readouterr()
assert "Too many results supplied. Use globus_download()" in out
# "Missing" files
f.http_download(example_result_missing)
out, err = capsys.readouterr()
assert not os.path.exists("./should_not_exist.txt")
assert (
"Error 404 when attempting to access "
"'https://data.materialsdatafacility.org/test/should_not_exist.txt'"
) in out
# No datasets
f.http_download(example_dataset)
out, err = capsys.readouterr()
assert not os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert (
"Skipping datset entry for 'foobar_v1': Cannot download dataset over HTTPS. "
"Use globus_download() for datasets.") in out
# Bad resource_type
f.http_download(example_bad_resource)
out, err = capsys.readouterr()
assert "Error: Found unknown resource_type 'foobar'. Skipping entry." in out
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) == []
def test_describe_organization(capsys):
f = Forge()
# Basic usage (with raw=True)
res = f.describe_organization("Argonne National Laboratory", raw=True)
assert res["success"]
assert isinstance(res["organization"], dict)
assert res["organization"][
"canonical_name"] == "Argonne National Laboratory"
assert "ANL" in res["organization"]["aliases"]
# List
res = f.describe_organization("list", raw=True)
assert isinstance(res["organization"], list)
assert "Center for Hierarchical Materials Design" in res["organization"]
# All
res = f.describe_organization("all", raw=True)
assert isinstance(res["organization"], list)
assert isinstance(res["organization"][0], dict)
# Print to stdout
f.describe_organization("CHiMaD")
out, err = capsys.readouterr()
assert "canonical_name: Center for Hierarchical Materials Design" in out
assert "CHiMaD" in out
assert "public" in out
# List
f.describe_organization("list")
out, err = capsys.readouterr()
assert "Center for Hierarchical Materials Design" in out
assert "CHiMaD" not in out
assert "Argonne National Laboratory" in out
assert "ANL" not in out
# Summary flag
f.describe_organization("chimad", summary=True)
out, err = capsys.readouterr()
assert "canonical_name: Center for Hierarchical Materials Design" not in out
assert "Center for Hierarchical Materials Design" in out
assert "CHiMaD" in out
assert "public" not in out
# Errors
# Invalid org
res = f.describe_organization("foobar", raw=True)
assert res["success"] is False
assert "Error 404" in res["error"]
assert res["status_code"] == 404
# stdout
res = f.describe_organization("foobar")
out, err = capsys.readouterr()
assert "Error 404" in out
class Foundry(FoundryMetadata):
"""Foundry Client Base Class
TODO:
-------
Add Docstring
"""
# transfer_client: Any
dlhub_client: Any
forge_client: Any
# connect_client: #Add this back in later, not necessary for current functionality
xtract_tokens: Any
def __init__(self,
no_browser=False,
no_local_server=False,
search_index="mdf-test",
**data):
super().__init__(**data)
auths = mdf_toolbox.login(
services=[
"data_mdf",
"search",
"petrel",
"transfer",
"dlhub",
"https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all",
],
app_name="Foundry",
make_clients=True,
no_browser=no_browser,
no_local_server=no_local_server,
)
self.forge_client = Forge(
index=search_index,
services=None,
search_client=auths["search"],
transfer_client=auths["transfer"],
data_mdf_authorizer=auths["data_mdf"],
petrel_authorizer=auths["petrel"],
)
self.dlhub_client = DLHubClient(
dlh_authorizer=auths["dlhub"],
search_client=auths["search"],
fx_authorizer=auths[
"https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all"],
force_login=False,
)
self.xtract_tokens = {
'auth_token':
auths['petrel'].access_token,
'transfer_token':
auths['transfer'].authorizer.access_token,
'funx_token':
auths[
'https://auth.globus.org/scopes/facd7ccc-c5f4-42aa-916b-a0e270e2c2a9/all']
.access_token
}
def load(self, name, download=True, globus=True, verbose=False, **kwargs):
"""Load the metadata for a Foundry dataset into the client
Args:
name (str): Name of the foundry dataset
download (bool): If True, download the data associated with the package (default is True)
Keyword Args:
interval (int): How often to poll Globus to check if transfers are complete
Returns
-------
self
"""
# MDF specific logic
res = self.forge_client.match_field(
"mdf.organizations", "foundry").match_resource_types("dataset")
res = res.match_field("mdf.source_id", name).search()
res = res[0]
res["dataset"] = res["projects"]["foundry"]
res["dataset"]["type"] = res["dataset"]["package_type"]
del res["projects"]["foundry"]
self = Foundry(**res)
if download is True: # Add check for package existence
self.download(interval=kwargs.get("interval", 10),
globus=globus,
verbose=verbose)
return self
def list(self):
"""List available Foundry data packages
Returns
-------
(pandas.DataFrame): DataFrame with summary list of Foundry data packages including name, title, and publication year
"""
res = (self.forge_client.match_field(
"mdf.organizations",
"foundry").match_resource_types("dataset").search())
return pd.DataFrame([{
"source_id": r["mdf"]["source_id"],
"name": r["dc"]["titles"][0]["title"],
"year": r["dc"].get("publicationYear", None),
} for r in res])
def get_packages(self, paths=False):
"""Get available local data packages
Args:
paths (bool): If True return paths in addition to package, if False return package name only
Returns
-------
(list): List describing local Foundry packages
"""
pkg_paths = glob.glob(self.config.local_cache_dir + "/*/")
if paths:
return [{
"path": path,
"package": path.split("/")[-2]
} for path in pkg_paths]
else:
return [path.split("/")[-2] for path in pkg_paths]
def collect_dataframes(self, inputs=[], outputs=[], packages=None):
"""Collect dataframes of local data packages
Args:
inputs (list): List of strings for input columns
outputs (list): List of strings for output columns
Returns
-------
(pandas.DataFrame): Collected dataframe with specified inputs and outputs
"""
frame_files = glob.glob(self.config.local_cache_dir + "/*/*dataframe*",
recursive=True)
frames = []
for frame in frame_files:
df_tmp = pd.read_json(frame)
df_tmp["source"] = frame
frames.append(df_tmp)
df = pd.concat(frames)
if inputs and outputs:
return df[inputs], df[outputs]
else:
return df
def run(self, name, inputs, **kwargs):
"""Run a model on data
Args:
name (str): DLHub model name
inputs: Data to send to DLHub as inputs (should be JSON serializable)
Returns
-------
Returns results after invocation via the DLHub service
TODO:
-------
- Pass **kwargs through to DLHub client and document kwargs
"""
return self.dlhub_client.run(name, inputs=inputs)
def load_data(self, source_id=None, globus=True):
"""Load in the data associated with the prescribed dataset
Tabular Data Type: Data are arranged in a standard data frame
stored in self.dataframe_file. The contents are read, and
File Data Type: <<Add desc>>
For more complicated data structures, users should
subclass Foundry and override the load_data function
Args:
inputs (list): List of strings for input columns
outputs (list): List of strings for output columns
Returns
-------
(tuple): Tuple of X, y values
"""
if source_id:
path = os.path.join(self.config.local_cache_dir, source_id)
else:
path = os.path.join(self.config.local_cache_dir,
self.mdf["source_id"])
# Handle Foundry-defined types.
if self.dataset.type.value == "tabular":
# If the file is not local, fetch the contents with Globus
# Check if the contents are local
# TODO: Add hashes and versioning to metadata and checking to the file
try:
self.dataset.dataframe = pd.read_json(
os.path.join(path, self.config.dataframe_file))
except:
# Try to read individual lines instead
self.dataset.dataframe = pd.read_json(os.path.join(
path, self.config.dataframe_file),
lines=True)
return (
self.dataset.dataframe[self.dataset.inputs],
self.dataset.dataframe[self.dataset.outputs],
)
elif self.dataset.type.value == "hdf5":
f = h5py.File(os.path.join(path, self.config.data_file), "r")
inputs = [f[i[0:]] for i in self.dataset.inputs]
outputs = [f[i[0:]] for i in self.dataset.outputs]
return (inputs, outputs)
else:
raise NotImplementedError
def describe(self):
print("DC:{}".format(self.dc))
print("Dataset:{}".format(self.dataset.json(exclude={"dataframe"})))
def publish(self, foundry_metadata, update=False, **kwargs):
"""Submit a data package for publication
Args:
foundry_metadata (dict): Path to the file containing
update (bool): True if this is an update to a prior data package
(default: self.config.metadata_file)
Keyword Args:
title (str): Title of the data package
authors (list): List of data package author names e.g., Jack Black or Nunez, Victoria
affiliations (list): List of author affiliations
tags (list): List of tags to apply to the data package
Returns
-------
(dict) MDF Connect Response: Response from MDF Connect to allow tracking of dataset
"""
self.connect_client.create_dc_block(
title=kwargs["title"],
authors=kwargs["authors"],
affiliations=kwargs.get("affiliations", []),
subjects=kwargs.get("tags", ["machine learning", "foundry"]),
)
self.connect_client.add_organization("Foundry")
self.connect_client.set_project_block("foundry", foundry_metadata)
self.connect_client.add_data_source(kwargs.get("data_sources", []))
res = self.connect_client.submit_dataset(update=update)
return res
def from_file(self, file=None):
"""Create a Foundry client from a file
Args:
file (str): Path to the file containing
(default: self.config.metadata_file)
Returns
-------
(Foundry): an newly instantiated Foundry client
"""
if file is None:
file = self.config.metadata_file
with open("./{}".format(file)) as fp:
obj = json.load(fp)
return Foundry(**obj)
def to_file(self, file=None):
"""Create a Foundry client from a file
Args:
file (str): Path to the file to save metadata to
(default: self.config.metadata_file)
Returns
-------
(Foundry) self: for chaining
"""
if file is None:
file = self.config.metadata_file
with open("./{}".format(file)) as fp:
obj = json.dump(
self.json(exclude={"dlhub_client", "forge_client"}), fp)
return self
def configure(self, **kwargs):
self.config = FoundryConfig(**kwargs)
return self
def download(self, globus=True, verbose=False, **kwargs):
# Check if the dir already exists
path = os.path.join(self.config.local_cache_dir, self.mdf["source_id"])
if os.path.isdir(path):
return self
res = self.forge_client.search(
"mdf.source_id:{name}".format(name=self.mdf["source_id"]),
advanced=True)
if globus:
self.forge_client.globus_download(
res,
dest=self.config.local_cache_dir,
dest_ep=self.config.destination_endpoint,
interval=kwargs.get("interval", 20),
download_datasets=True,
)
else:
source_id = self.mdf['source_id']
xtract_base_url = "http://xtract-crawler-4.eba-ghixpmdf.us-east-1.elasticbeanstalk.com"
# MDF Materials Data at NCSA
source_ep_id = "82f1b5c6-6e9b-11e5-ba47-22000b92c6ec"
base_url = "https://data.materialsdatafacility.org"
folder_to_crawl = f"/foundry/{source_id}/"
# This only matters if you want files grouped together.
grouper = "matio"
auth_token = self.xtract_tokens['auth_token']
transfer_token = self.xtract_tokens['transfer_token']
funcx_token = self.xtract_tokens['transfer_token']
headers = {
'Authorization': f"Bearer {auth_token}",
'Transfer': transfer_token,
'FuncX': funcx_token,
'Petrel': auth_token
}
if verbose: print(f"Headers: {headers}")
# Initialize the crawl. This kicks off the Globus EP crawling service on the backend.
crawl_url = f'{xtract_base_url}/crawl'
if verbose: print(f"Crawl URL is : {crawl_url}")
crawl_req = requests.post(crawl_url,
json={
'repo_type': "GLOBUS",
'eid': source_ep_id,
'dir_path': folder_to_crawl,
'Transfer': transfer_token,
'Authorization': funcx_token,
'grouper': grouper,
'https_info': {
'base_url': base_url
}
})
if verbose: print('Crawl response:', crawl_req)
crawl_id = json.loads(crawl_req.content)['crawl_id']
if verbose: print(f"Crawl ID: {crawl_id}")
# Wait for the crawl to finish before we can start fetching our metadata.
while True:
crawl_status = requests.get(
f'{xtract_base_url}/get_crawl_status',
json={'crawl_id': crawl_id})
if verbose: print(crawl_status)
crawl_content = json.loads(crawl_status.content)
if verbose: print(f"Crawl Status: {crawl_content}")
if crawl_content['crawl_status'] == 'SUCCEEDED':
files_crawled = crawl_content['files_crawled']
if verbose: print("Our crawl has succeeded!")
break
else:
if verbose: print("Sleeping before re-polling...")
time.sleep(2)
# Now we fetch our metadata. Here you can configure n to be maximum number of
# messages you want at once.
file_ls = []
fetched_files = 0
while fetched_files < files_crawled:
fetch_mdata = requests.get(
f'{xtract_base_url}/fetch_crawl_mdata',
json={
'crawl_id': crawl_id,
'n': 2
})
fetch_content = json.loads(fetch_mdata.content)
for file_path in fetch_content['file_ls']:
file_ls.append(file_path)
fetched_files += 1
if fetch_content['queue_empty']:
if verbose: print("Queue is empty! Continuing...")
time.sleep(2)
source_path = os.path.join(self.config.local_cache_dir,
self.mdf['source_id'])
if not os.path.exists(self.config.local_cache_dir):
os.mkdir(self.config.local_cache_dir)
os.mkdir(source_path)
elif not os.path.exists(source_path):
os.mkdir(source_path)
num_cores = multiprocessing.cpu_count()
def download_file(file):
requests.packages.urllib3.disable_warnings(
InsecureRequestWarning)
url = 'https://data.materialsdatafacility.org' + file['path']
destination = 'data/' + source_id + '/' + file['path'][
file['path'].rindex("/") + 1:]
response = requests.get(url, verify=False)
with open(destination, 'wb') as f:
f.write(response.content)
return {file['path'] + ' status': True}
results = Parallel(n_jobs=num_cores)(delayed(download_file)(file)
for file in file_ls)
print('Done curling.')
print(results)
return self
# -*- coding: utf-8 -*-
"""
@Project : formationEPres
@Author : Xu-Shan Zhao
@Filename: mdfOqmdRetrieval202005280940.py
@IDE : PyCharm
@Time1 : 2020-05-28 09:40:27
@Time2 : 2020/5/28 9:40
@Month1 : 5月
@Month2 : 五月
"""
from mdf_forge import Forge
mdf = Forge()
dataset_name = 'oqmd'
# ro = mdf.match_source_names(dataset_name)
# ro = ro.search(limit=-1)
ro = mdf.aggregate_sources(dataset_name)
import pymongo
client = pymongo.MongoClient(host='localhost', port=27017)
collection = client['MDF_datasets']['oqmd']
# collection.insert_many(ro)
for i in range(len(ro)):
try:
collection.insert_one(ro[i])
except:
print(i)
client.add_service("mrr")
# Make the source name "nist_MDR_[item_number]" to make retrieval easy
client.set_source_name("mdr_item_{}".format(item_id))
return client
def _make_failure(req):
return RuntimeError('Problem connecting with {}. HTTP Status Code: {}'.format(req.url,
req.status_code))
if __name__ == "__main__":
# Make the client
client = MDFConnectClient()
forge = Forge()
# Create an array to store the source_id
source_ids = []
# Loop through all items
for item in tqdm(get_all_publications()):
# Check if we have done it already
if has_been_submitted(item, forge):
continue
# If not, ready the client to submit
prepare_client_submission(item, client)
# Skip if no data
if len(client.data) == 0:
