def test_data_is_aggregated(self):
# there are 11 rows in the input file; 2 are for the same
# practice/presentation and should be collapsed, and 1 is for
# an UNKNONWN SURGERY (see issue #349)
raw_data_path = ("frontend/tests/fixtures/commands/" +
"convert_hscic_prescribing/2016_01/" +
"EPD_201601.csv")
gcs_path = "hscic/prescribing_v2/2016_01/EPD_201601.csv"
client = StorageClient()
bucket = client.get_bucket()
blob = bucket.blob(gcs_path)
with open(raw_data_path, "rb") as f:
blob.upload_from_file(f)
call_command("convert_hscic_prescribing", filename=raw_data_path)
# Test that data added to prescribing table
client = BQClient()
sql = """SELECT *
FROM {hscic}.prescribing_v2
WHERE month = TIMESTAMP('2016-01-01')"""
rows = list(results_to_dicts(client.query(sql)))
self.assertEqual(len(rows), 9)
for row in rows:
if row["practice"] == "P92042" and row[
"bnf_code"] == "0202010B0AAABAB":
self.assertEqual(row["quantity"], 1288)
def test_data_is_aggregated(self):
# there are 11 rows in the input file; 2 are for the same
# practice/presentation and should be collapsed, and 1 is for
# an UNKNONWN SURGERY (see issue #349)
raw_data_path = 'frontend/tests/fixtures/commands/' +\
'convert_hscic_prescribing/2016_01/' +\
'Detailed_Prescribing_Information.csv'
converted_data_path = 'frontend/tests/fixtures/commands/' +\
'convert_hscic_prescribing/2016_01/' +\
'Detailed_Prescribing_Information_formatted.CSV'
gcs_path = 'hscic/prescribing/2016_01/' +\
'Detailed_Prescribing_Information.csv'
client = StorageClient()
bucket = client.get_bucket()
blob = bucket.blob(gcs_path)
with open(raw_data_path) as f:
blob.upload_from_file(f)
call_command('convert_hscic_prescribing', filename=raw_data_path)
# Test that data added to prescribing table
client = BQClient()
sql = '''SELECT *
FROM {hscic}.prescribing
WHERE month = TIMESTAMP('2016-01-01')'''
rows = list(results_to_dicts(client.query(sql)))
self.assertEqual(len(rows), 9)
for row in rows:
if row['practice'] == 'P92042' and \
row['bnf_code'] == '0202010B0AAABAB':
self.assertEqual(row['quantity'], 1288)
# Test that downloaded data is correct
with open(converted_data_path) as f:
rows = list(csv.reader(f))
self.assertEqual(len(rows), 9)
for row in rows:
if row[1] == 'P92042' and row[2] == '0202010B0AAABAB':
self.assertEqual(row[6], '1288')