def test_calculate_average():
# Independently test getting the average
# of a data array based on method
date_base = datetime.datetime(2019, 1, 1)
date_array = np.array(
[date_base + datetime.timedelta(days=i) for i in range(5)])
expected_stat_file_dates = []
for date in date_array:
dt = date.time()
expected_stat_file_dates.append(date.strftime('%Y%m%d_%H%M%S'))
model_data_index = pd.MultiIndex.from_product(
[['MODEL_TEST'], expected_stat_file_dates],
names=['model_plot_name', 'dates'])
model_data_array = np.array([[
3600, 5525.75062, 5525.66493, 30615218.26089, 30615764.49722,
30614724.90979, 5.06746
],
[
3600, 5519.11108, 5519.1014,
30549413.45946, 30549220.68868,
30549654.24048, 5.12344
],
[
3600, 5516.80228, 5516.79513,
30522742.16484, 30522884.89927,
30522660.30975, 5.61752
],
[
3600, 5516.93924, 5517.80544,
30525709.03932, 30520984.50965,
30530479.99675, 4.94325
],
[
3600, 5514.52274, 5514.68224,
30495695.82208, 30494633.24046,
30496805.48259, 5.20369
]])
model_data = pd.DataFrame(
model_data_array,
index=model_data_index,
columns=['TOTAL', 'FBAR', 'OBAR', 'FOBAR', 'FFBAR', 'OOBAR', 'MAE'])
stat_values_array = np.array([[[(5525.75062 - 5525.66493),
(5519.11108 - 5519.1014),
(5516.80228 - 5516.79513),
(5516.93924 - 5517.80544),
(5514.52274 - 5514.68224)]]])
# Test 1
average_method = 'MEAN'
stat = 'bias'
model_dataframe = model_data
model_stat_values = stat_values_array[:, 0, :]
expected_average_array = np.array([-0.184636])
test_average_array = plot_util.calculate_average(logger, average_method,
stat, model_dataframe,
model_stat_values)
assert (len(test_average_array) == len(expected_average_array))
for l in range(len(test_average_array)):
assert (round(test_average_array[l], 6) == expected_average_array[l])
# Test 2
average_method = 'MEDIAN'
stat = 'bias'
model_dataframe = model_data
model_stat_values = stat_values_array[:, 0, :]
expected_average_array = np.array([0.00715])
test_average_array = plot_util.calculate_average(logger, average_method,
stat, model_dataframe,
model_stat_values)
assert (len(test_average_array) == len(expected_average_array))
for l in range(len(test_average_array)):
assert (round(test_average_array[l], 6) == expected_average_array[l])
# Test 3
average_method = 'AGGREGATION'
stat = 'bias'
model_dataframe = model_data
model_stat_values = stat_values_array[:, 0, :]
expected_average_array = np.array([-0.184636])
test_average_array = plot_util.calculate_average(logger, average_method,
stat, model_dataframe,
model_stat_values)
assert (len(test_average_array) == len(expected_average_array))
for l in range(len(test_average_array)):
assert (round(test_average_array[l], 6) == expected_average_array[l])
# Test 4
stat_values_array = np.array(
[[[5525.75062, 5519.11108, 5516.80228, 5516.93924, 5514.52274]],
[[5525.66493, 5519.1014, 5516.79513, 5517.80544, 5514.68224]]])
average_method = 'MEAN'
stat = 'fbar_obar'
model_dataframe = model_data
model_stat_values = stat_values_array[:, 0, :]
expected_average_array = np.array([5518.625192, 5518.809828])
test_average_array = plot_util.calculate_average(logger, average_method,
stat, model_dataframe,
model_stat_values)
assert (len(test_average_array) == len(expected_average_array))
for l in range(len(test_average_array)):
assert (round(test_average_array[l], 6) == expected_average_array[l])
# Test 5
average_method = 'MEDIAN'
stat = 'fbar_obar'
model_dataframe = model_data
model_stat_values = stat_values_array[:, 0, :]
expected_average_array = np.array([5516.93924, 5517.80544])
test_average_array = plot_util.calculate_average(logger, average_method,
stat, model_dataframe,
model_stat_values)
assert (len(test_average_array) == len(expected_average_array))
for l in range(len(test_average_array)):
assert (round(test_average_array[l], 6) == expected_average_array[l])
'fcst_level': fcst_var_level,
'obs_level': obs_var_level,
'fcst_thresh': fcst_var_thresh,
'obs_thresh': obs_var_thresh,
}
model_stat_file = do_string_sub(model_stat_template,
**string_sub_dict)
lead_avg_file = get_lead_avg_file(stat, model_stat_file, fcst_lead,
output_base_dir)
logger.debug("Writing model " + str(model_num) + " " + model_name +
" " + "with name on plot " + model_plot_name +
" lead " + fcst_lead + " average to file: " +
lead_avg_file)
model_stat_average_array = plot_util.calculate_average(
logger, average_method, stat,
model_data.loc[[model_plot_name]], model_stat_values_array)
with open(lead_avg_file, 'a') as file2write:
file2write.write(fcst_lead)
if fcst_var_units_plot_title != '':
file2write.write(' ' + fcst_var_units_plot_title)
else:
file2write.write(' [NA]')
if obs_var_units_plot_title != '':
file2write.write(' ' + obs_var_units_plot_title)
else:
file2write.write(' [NA]')
for l in range(len(model_stat_average_array)):
file2write.write(' ' + str(model_stat_average_array[l]))
file2write.write('\n')
# Write confidence intervals to file, if requested,