def test_index_date ():
expected_indx_dates = {19: datetime.datetime(2014, 2, 2, 0, 0), 99: datetime.datetime(2013, 10, 13, 0, 0), 24581: datetime.datetime(2013, 11, 0o7, 0, 0), 3014: datetime.datetime(2015, 11, 17, 0, 0)}
calculate_index_date(events_df, mortality_df, deliverables_path)
indx_date_df = pd.read_csv(deliverables_path + 'etl_index_dates.csv', parse_dates=['indx_date'])
indx_date = dict(list(zip(indx_date_df.patient_id, indx_date_df.indx_date)))
if isinstance(indx_date, pd.DataFrame):
indx_date = dict(list(zip(indx_date.patient_id, indx_date.indx_date)))
res= True
if len(indx_date) != len(expected_indx_dates):
res = False
else:
for key, value in list(expected_indx_dates.items()):
if key not in indx_date:
res = False;
break;
if not abs(indx_date[key].date() == value.date()):
res = False;
break;
eq_(res, True, "Index dates do not match")
def test_filtered_events ():
expected_data = []
with open('tests/expected_etl_filtered_events.csv') as expected_file:
expected_data = expected_file.readlines()
expected_data = expected_data[1:]
expected_data.sort()
indx_dates_df = calculate_index_date(events_df, mortality_df, deliverables_path)
filter_events(events_df, indx_dates_df, deliverables_path)
actual_data = []
with open(deliverables_path + 'etl_filtered_events.csv') as actual_file:
actual_data = actual_file.readlines()
actual_data = actual_data[1:]
actual_data.sort()
res = True
msg = ""
for idx,line in enumerate(expected_data):
first = line.split(',')
second = actual_data[idx].split(',')
if not (float(first[0])==float(second[0]) and first[1] == second[1] and float(first[2])==float(second[2])):
res = False
msg = "Mistmatch on line %d. \n\nExpected: %s \nActual: %s " %(idx+1, line, actual_data[idx])
break
eq_(res, True, "Filtered events do not match. " + msg)