def matrix_stores():
df = pd.DataFrame.from_dict(DATA_DICT).set_index(MatrixStore.indices)
with tempfile.TemporaryDirectory() as tmpdir:
project_storage = ProjectStorage(tmpdir)
tmpcsv = os.path.join(tmpdir, "df.csv.gz")
tmpyaml = os.path.join(tmpdir, "df.yaml")
with open(tmpyaml, "w") as outfile:
yaml.dump(METADATA, outfile, default_flow_style=False)
df.to_csv(tmpcsv, compression="gzip")
csv = CSVMatrixStore(project_storage, [], "df")
# first test with caching
with csv.cache():
yield csv
# with the caching out of scope they will be nuked
# and this last version will not have any cache
yield csv
def matrix_stores():
df = pd.DataFrame.from_dict(DATA_DICT).set_index(["entity_id"])
with tempfile.TemporaryDirectory() as tmpdir:
project_storage = ProjectStorage(tmpdir)
tmpcsv = os.path.join(tmpdir, "df.csv")
tmpyaml = os.path.join(tmpdir, "df.yaml")
tmphdf = os.path.join(tmpdir, "df.h5")
with open(tmpyaml, "w") as outfile:
yaml.dump(METADATA, outfile, default_flow_style=False)
df.to_csv(tmpcsv)
df.to_hdf(tmphdf, "matrix")
csv = CSVMatrixStore(project_storage, [], "df")
hdf = HDFMatrixStore(project_storage, [], "df")
assert csv.design_matrix.equals(hdf.design_matrix)
# first test with caching
with csv.cache(), hdf.cache():
yield csv
yield hdf
# with the caching out of scope they will be nuked
# and these last two versions will not have any cache
yield csv
yield hdf