def test_any_multiple_columns(main_csv, gp_csv):
cohort_criteria = {'any_of': [('6148', "4")], 'all_of': [], 'none_of': []}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(
["1037918", "1033149", "1016017", "1033388", "1030520", "1003670"])
assert exp_ids == set(ids)
def test_any_singleton_query(main_csv, gp_csv):
cohort_criteria = {'any_of': [('6070', "1")], 'all_of': [], 'none_of': []}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set([
"1041796", "1037058", "1024938", "1016017", "1038882", "1030520",
"1003670", "1027017"
])
assert exp_ids == set(ids)
def test_none_basic(main_csv, gp_csv):
cohort_criteria = {'none_of': [('6070', "1")], 'all_of': [], 'any_of': []}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
print(gen_query)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
print(ids)
exp_ids = set(
["1037918", "1033149", "1033388", "1031625", "1031595", "1008947"])
assert exp_ids == set(ids)
def test_any_pair_same_field_query(main_csv, gp_csv):
cohort_criteria = {
'any_of': [('41270', "Block H40-H42"), ('6119', "3"), ('6148', '4')],
'all_of': [(('6070', "1"))],
'none_of': [('read_2', "XE0of")]
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(["1041796", "1037058", "1030520", "1003670"])
assert exp_ids == set(ids)
def test_all_gp_clinical_read2and3(main_csv, gp_csv):
cohort_criteria = {
'all_of': [],
'any_of': [('read_2', "XE0of"), ('read_3', 'XE0Gu')],
'none_of': []
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(["1016017", "1037918"])
assert exp_ids == set(ids)
def test_missing_fields(main_csv, gp_csv):
cohort_criteria = {
'all_of': [('6070', "nan")],
'any_of': [],
'none_of': []
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set([])
assert exp_ids == set(ids)
def test_fields_with_spaces(main_csv, gp_csv):
cohort_criteria = {
'all_of': [('41270', "Block H40-H42")],
'any_of': [],
'none_of': []
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(["1033149", "1041796"])
assert exp_ids == set(ids)
def test_none_returns_empty(main_csv, gp_csv):
cohort_criteria = {
'all_of': [('6148', "4")],
'any_of': [],
'none_of': [("6070", "2"), ("6070", "1")]
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(["1033149", "1033388"])
assert exp_ids == set(ids)
def test_all_gp_clinical_read2(main_csv, gp_csv):
cohort_criteria = {
'all_of': [('read_2', "4662.")],
'any_of': [],
'none_of': []
}
gen_query = query.create_queries(cohort_criteria,
main_filename=main_csv,
gpc_path=gp_csv)
ids = query.query_databases(cohort_criteria=cohort_criteria,
queries=gen_query,
main_filename=main_csv,
write_dir=None,
gpc_path=gp_csv,
out_filename=None,
write=False)
exp_ids = set(["1041796"])
assert exp_ids == set(ids)