def test_field_metadata():
expected = {
'field_id': 3,
'title': 'Verbal interview duration',
'availability': 0,
'stability': 0,
'private': 0,
'value_type': 11,
'base_type': 0,
'item_type': 0,
'strata': 2,
'instanced': 1,
'arrayed': 0,
'sexed': 0,
'units': 'seconds',
'main_category': 152,
'encoding_id': 0,
'instance_id': 2,
'instance_min': 0,
'instance_max': 3,
'array_min': 0,
'array_max': 0,
'notes': 'Time taken for interview',
'debut': '2012-01-05',
'version': '2019-09-05',
'num_participants': 501673,
'item_count': 561869,
'showcase_order': 0.0
}
assert helpers.get_field_metadata(3) == expected
assert helpers.get_field_metadata(999999) is None
if __name__ == '__main__':
df_output = pd.DataFrame()
df_output['eid'] = helpers.gen_fake_ids(TOTAL_PATIENTS)
# User has supplied field list
if args.field is not None:
all_field_ids = helpers.get_field_ids()
fields_to_process = set(all_field_ids).intersection(set(args.field))
assert len(fields_to_process) > 0, "Fields not found in lookup file."
else:
fields_to_process = helpers.get_field_ids()
for field_id in tqdm(fields_to_process):
r = helpers.get_field_metadata(field_id)
if args.verbose is True:
print(r)
field_title = r['title']
field_data_type = r['value_type']
field_encoding_id = r['encoding_id']
# Check if a field is instanced
# i.e. it has been collected at different
# recruitment instances.
field_instance_max = r.get('instance_max')
if field_instance_max == 0:
field_instance_max = 1