def setUpTestData(cls):
cls.project = Project.objects.create()
make_cdc_units_and_targets(cls.project)
cls.forecast_model = ForecastModel.objects.create(
project=cls.project, name='name', abbreviation='abbrev')
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2017, 1)))
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
cls.forecast1 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2017, 2)))
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW2-KoTstable-2017-01-23.csv'
) # EW02 2017
cls.forecast2 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2016, 51)))
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW51-KoTstable-2017-01-03.csv'
) # EW51 2016
cls.forecast3 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2016, 52)))
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW52-KoTstable-2017-01-09.csv'
) # EW52 2016
cls.forecast4 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
# 'mini' season for testing. from:
# model_error_calculations.txt -> model_error_calculations.py -> model_error_calculations.xlsx:
cls.exp_target_to_mae = {
'1 wk ahead': 0.215904853,
'2 wk ahead': 0.458186984,
'3 wk ahead': 0.950515864,
'4 wk ahead': 1.482010693
}
load_truth_data(
cls.project,
Path('forecast_app/tests/truth_data/mean-abs-error-truths.csv'))
# score needed for MAE calculation
Score.ensure_all_scores_exist()
cls.score = Score.objects.filter(
abbreviation='abs_error').first() # hard-coded official abbrev
cls.score.update_score_for_model(cls.forecast_model)
def test_model_score_change_forecasts(self):
# creating a new model should set its score_change.changed_at
project2 = Project.objects.create()
make_cdc_units_and_targets(project2)
time_zero = TimeZero.objects.create(
project=project2, timezero_date=datetime.date.today())
forecast_model2 = ForecastModel.objects.create(project=project2,
name='name',
abbreviation='abbrev')
self.assertIsInstance(forecast_model2.score_change.changed_at,
datetime.datetime)
# adding a forecast should update its model's score_change.changed_at
before_changed_at = forecast_model2.score_change.changed_at
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
forecast2 = load_cdc_csv_forecast_file(2016, forecast_model2,
csv_file_path, time_zero)
self.assertNotEqual(before_changed_at,
forecast_model2.score_change.changed_at)
self.assertLess(
before_changed_at,
forecast_model2.score_change.changed_at) # was updated later
# deleting a forecast should update its model's score_change.changed_at
before_changed_at = forecast_model2.score_change.changed_at
forecast2.delete()
self.assertNotEqual(before_changed_at,
forecast_model2.score_change.changed_at)
self.assertLess(
before_changed_at,
forecast_model2.score_change.changed_at) # was updated later
# bulk-deleting a model's forecasts will update its score_change.changed_at. (this basically tests that a signal
# is used instead of a customized delete() - see set_model_changed_at() comment
for idx in range(2):
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
forecast = load_cdc_csv_forecast_file(2016, forecast_model2,
csv_file_path, time_zero)
forecast.issue_date += datetime.timedelta(
days=idx + 1) # newer version avoids unique constraint errors
forecast.save()
before_changed_at = forecast_model2.score_change.changed_at
forecast_model2.forecasts.all().delete()
self.assertNotEqual(before_changed_at,
forecast_model2.score_change.changed_at)
self.assertLess(
before_changed_at,
forecast_model2.score_change.changed_at) # was updated later
def load_cdc_csv_forecasts_from_dir(forecast_model, data_dir, season_start_year):
"""
Adds Forecast objects to forecast_model using the cdc csv files under data_dir. Assumes TimeZeros match those in my
Project. Skips files that have already been loaded. Skips files that cause load_forecast() to raise a RuntimeError.
:param forecast_model: a ForecastModel to load the data into
:param data_dir: Path of the directory that contains cdc csv files
:param season_start_year: optional (used only if the files in data_dir have the date-related targets
'Season onset' or 'Season peak week')
:return list of loaded Forecasts
"""
forecasts = []
for cdc_csv_file, timezero_date, _, _ in cdc_csv_components_from_data_dir(data_dir):
timezero = forecast_model.project.time_zero_for_timezero_date(timezero_date)
if not timezero:
click.echo("x (no TimeZero found)\t{}\t".format(cdc_csv_file.name))
continue
found_forecast_for_time_zero = forecast_model.forecast_for_time_zero(timezero)
if found_forecast_for_time_zero:
click.echo("s (found forecast)\t{}\t".format(cdc_csv_file.name))
continue
try:
forecast = load_cdc_csv_forecast_file(season_start_year, forecast_model, cdc_csv_file, timezero)
forecasts.append(forecast)
click.echo("o\t{}\t".format(cdc_csv_file.name))
except RuntimeError as rte:
click.echo("f\t{}\t{}".format(cdc_csv_file.name, rte))
if not forecasts:
click.echo("Warning: no valid forecast files found in directory: {}".format(data_dir))
return forecasts
def fill_cdc_project(project, mo_user, is_public):
project.description = "description"
project.home_url = "http://example.com/"
project.core_data = "http://example.com/"
# make the Units and Targets via cdc-project.json (recall it has no timezeros)
make_cdc_units_and_targets(project)
# make two TimeZeros - one for ground truth, and one for the forecast's data:
# EW1-KoTsarima-2017-01-17-small.csv -> pymmwr.date_to_mmwr_week(datetime.date(2017, 1, 17)) # EW01 2017
# -> {'year': 2017, 'week': 3, 'day': 3}
time_zero1 = TimeZero.objects.create(project=project,
timezero_date=datetime.date(
2017, 1, 17),
data_version_date=None)
TimeZero.objects.create(project=project,
timezero_date=datetime.date(2017, 1, 24),
data_version_date=None)
# load ground truth
load_truth_data(
project,
Path('forecast_app/tests/truth_data/2017-01-17-truths.csv'),
is_convert_na_none=True)
# create the two models
click.echo("creating ForecastModel")
forecast_model1 = ForecastModel.objects.create(
project=project,
name=f'Test ForecastModel1 ({"public" if is_public else "private"})',
abbreviation='model1_abbrev',
team_name='ForecastModel1 team',
description="a ForecastModel for testing",
home_url='http://example.com',
owner=mo_user)
# load the forecasts using a small data file
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv') # EW01 2017
click.echo(
"* loading forecast into forecast_model={}, csv_file_path={}".format(
forecast_model1, csv_file_path))
start_time = timeit.default_timer()
forecast1 = load_cdc_csv_forecast_file(2016, forecast_model1,
csv_file_path, time_zero1)
click.echo(" loaded forecast={}. {}".format(
forecast1,
timeit.default_timer() - start_time))
ForecastModel.objects.create(
project=project,
name=f'Test ForecastModel2 ({"public" if is_public else "private"})',
abbreviation='model2_abbrev',
# team_name='ForecastModel2 team', # leave default ('')
description="a second ForecastModel for testing",
home_url='http://example.com',
owner=mo_user)
def test_num_pred_ele_rows_all_models(self):
# 154 initial (11 * 7 * 2 = locations * targets * points/bins)
self.assertEqual(
11 * 7 * 2,
self.project.num_pred_ele_rows_all_models(is_oracle=False))
time_zero2 = TimeZero.objects.create(project=self.project,
timezero_date=datetime.date(
2017, 1, 2))
# EW01 2017. 165 rows, 6 zero bins. same number of unique prediction elements, though
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv')
load_cdc_csv_forecast_file(2016, self.forecast_model, csv_file_path,
time_zero2)
self.assertEqual(
(11 * 7 * 2) * 2,
self.project.num_pred_ele_rows_all_models(is_oracle=False))
def setUpTestData(cls):
cls.project = Project.objects.create()
make_cdc_units_and_targets(cls.project)
cls.forecast_model = ForecastModel.objects.create(
project=cls.project, name='name', abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2017, 1)))
cls.forecast1 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW2-KoTstable-2017-01-23.csv'
) # EW02 2017
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2017, 2)))
cls.forecast2 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW51-KoTstable-2017-01-03.csv'
) # EW51 2016
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2016, 51)))
cls.forecast3 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW52-KoTstable-2017-01-09.csv'
) # EW52 2016
time_zero = TimeZero.objects.create(
project=cls.project,
timezero_date=(pymmwr.mmwr_week_to_date(2016, 52)))
cls.forecast4 = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, time_zero)
def test_cdc_forecast_data_validation(self):
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bad-point-na-2017-01-17.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn(
"None point values are only valid for 'Season onset' targets",
str(context.exception))
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bin-doesnt-sum-to-one-2017-01-17.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn(
"Entries in the database rows in the `prob` column must be numbers in [0, 1]",
str(context.exception))
try:
# date-based Point row w/NA value is OK:
csv_file_path = Path(
'forecast_app/tests/EW1-ok-point-na-2017-01-17.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
except Exception as ex:
self.fail(f"unexpected exception: {ex}")
def test_d3_foresight_out_of_season(self):
project = Project.objects.create()
make_cdc_units_and_targets(project)
# pymmwr.mmwr_week_to_date(2016, 29) -> datetime.date(2016, 7, 17):
time_zero = TimeZero.objects.create(
project=project,
timezero_date=datetime.date(2016, 7,
17), # 29 < SEASON_START_EW_NUMBER
data_version_date=None,
is_season_start=True,
season_name='2016')
# 20161030-KoTstable-20161114.cdc.csv {'year': 2016, 'week': 44, 'day': 1} -> datetime.date(2016, 10, 30):
TimeZero.objects.create(
project=project,
timezero_date=datetime.date(2016, 10, 30),
data_version_date=None,
is_season_start=True,
season_name='2017') # season has no forecast data
forecast_model = ForecastModel.objects.create(
project=project,
name='forecast_model1 name',
abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, forecast_model, csv_file_path,
time_zero)
with open(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small-exp-flusight-no-points.json',
'r') as fp:
exp_json_template_str = fp.read()
exp_json_template = Template(exp_json_template_str)
exp_json_str = exp_json_template.render(
Context({'forecast_model_id': forecast_model.id}))
exp_flusight_data_dict = json.loads(exp_json_str)
act_flusight_data_dict = flusight_unit_to_data_dict(
project, '2017')
self.assertEqual(exp_flusight_data_dict, act_flusight_data_dict)
def setUpTestData(cls):
cls.project = Project.objects.create()
cls.time_zero = TimeZero.objects.create(project=cls.project,
timezero_date=datetime.date(
2017, 1, 1))
make_cdc_units_and_targets(cls.project)
cls.forecast_model = ForecastModel.objects.create(
project=cls.project, name='fm1', abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
cls.forecast = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, cls.time_zero)
def test_load_forecast_created_at_field(self):
project2 = Project.objects.create()
make_cdc_units_and_targets(project2)
time_zero2 = TimeZero.objects.create(
project=project2, timezero_date=datetime.date.today())
forecast_model2 = ForecastModel.objects.create(project=project2,
name='name',
abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
forecast2 = load_cdc_csv_forecast_file(2016, forecast_model2,
csv_file_path, time_zero2)
self.assertIsNotNone(forecast2.created_at)
def test_d3_foresight(self):
project = Project.objects.create()
make_cdc_units_and_targets(project)
time_zero = TimeZero.objects.create(
project=project,
timezero_date=datetime.date(2016, 10, 23),
# 20161023-KoTstable-20161109.cdc.csv {'year': 2016, 'week': 43, 'day': 1}
data_version_date=datetime.date(2016, 10,
22)) # -> outputs dataVersionTime
TimeZero.objects.create(
project=project,
timezero_date=datetime.date(2016, 10, 30),
# 20161030-KoTstable-20161114.cdc.csv {'year': 2016, 'week': 44, 'day': 1}
data_version_date=datetime.date(2016, 10, 29))
forecast_model1 = ForecastModel.objects.create(
project=project,
name='forecast_model1 name',
abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, forecast_model1, csv_file_path,
time_zero)
# we treat the json file as a Django's template b/c mode lIDs are hard-coded, but can vary depending on the
# RDBMS
with open(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small-exp-flusight.json',
'r') as fp:
exp_json_template_str = fp.read()
exp_json_template = Template(exp_json_template_str)
exp_json_str = exp_json_template.render(
Context({'forecast_model_id': forecast_model1.id}))
exp_flusight_data_dict = json.loads(exp_json_str)
act_flusight_data_dict = flusight_unit_to_data_dict(project, None)
self.assertEqual(exp_flusight_data_dict, act_flusight_data_dict)
def test_forecast_for_time_zero(self):
time_zero = TimeZero.objects.create(
project=self.project,
timezero_date=datetime.date.today(),
data_version_date=None)
self.assertEqual(None,
self.forecast_model.forecast_for_time_zero(time_zero))
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17.csv') # EW01 2017
forecast2 = load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, time_zero)
self.assertEqual(forecast2,
self.forecast_model.forecast_for_time_zero(time_zero))
forecast2.delete()
def setUpTestData(cls):
cls.project = Project.objects.create()
make_cdc_units_and_targets(cls.project)
cls.forecast_model = ForecastModel.objects.create(
project=cls.project, name='name', abbreviation='abbrev')
cls.time_zero = TimeZero.objects.create(project=cls.project,
timezero_date=datetime.date(
2017, 1, 1))
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
cls.forecast = load_cdc_csv_forecast_file(2016, cls.forecast_model,
csv_file_path, cls.time_zero)
cls.forecast.issued_at -= datetime.timedelta(
days=1) # older version avoids unique constraint errors
cls.forecast.save()
def test_delete_forecast(self):
# add a second forecast version, check its rows were added, delete it, and test that the data was deleted (via
# CASCADE)
self.assertEqual(
1, self.forecast_model.forecasts.count()) # from setUpTestData()
self.assertEqual(11 * 7 * 2, self.forecast.pred_eles.count()
) # locations * targets * points/bins
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17.csv') # EW01 2017
forecast2 = load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertEqual(2, self.forecast_model.forecasts.count()) # now two
self.assertEqual(11 * 7 * 2, self.forecast.pred_eles.count())
# turns out there are the 17 duplicates that are not loaded. MUS: from an sqlite3 run:
# f cls u t is_r hash
# [(2, 2, 1, 1, 0, 'af49e5f6850e59638eb322a2293bd6c4'), # {'value': '2016-12-26'} 'HHS Region 1', 'Season onset'
# (2, 2, 1, 2, 0, 'edb5fbaf20fbba5d1d1455d864f2bc95'), # {'value': '2017-02-06'} 'HHS Region 1', 'Season peak week'
# (2, 2, 10, 1, 0, '73c3608a9829c5fe4103d1fd2b26c369'), # {'value': '2016-12-12'} 'HHS Region 10', 'Season onset'
# (2, 2, 10, 2, 0, '5959bec40e3eb79763a6cd78e150e145'), # {'value': '2017-01-09'} 'HHS Region 10', 'Season peak week'
# (2, 2, 2, 1, 0, 'f0cc965a8f901a09412f4a8e87c5aa3e'), # {'value': '2016-11-21'}
# (2, 2, 3, 1, 0, '0f6791070c029b74186f03f98e487b59'), # {'value': '2016-12-19'}
# (2, 2, 4, 1, 0, '3b2bdabc810ce299f0e35a55b107c374'), # {'value': '2016-11-14'}
# (2, 2, 4, 2, 0, '177183a5a9c19cedca454389aa796aee'), # {'value': '2017-02-13'}
# (2, 2, 5, 1, 0, 'af49e5f6850e59638eb322a2293bd6c4'), # {'value': '2016-12-26'}
# (2, 2, 6, 1, 0, 'af49e5f6850e59638eb322a2293bd6c4'), # {'value': '2016-12-26'} ...
# (2, 2, 6, 2, 0, '177183a5a9c19cedca454389aa796aee'), # {'value': '2017-02-13'}
# (2, 2, 7, 1, 0, 'af49e5f6850e59638eb322a2293bd6c4'), # {'value': '2016-12-26'}
# (2, 2, 8, 1, 0, '0f6791070c029b74186f03f98e487b59'), # {'value': '2016-12-19'}
# (2, 2, 9, 1, 0, '0f6791070c029b74186f03f98e487b59'), # {'value': '2016-12-19'}
# (2, 2, 9, 2, 0, 'edb5fbaf20fbba5d1d1455d864f2bc95'), # {'value': '2017-02-06'}
# (2, 2, 11, 1, 0, '73c3608a9829c5fe4103d1fd2b26c369'), # {'value': '2016-12-12'} 'US National', 'Season onset'
# (2, 2, 11, 2, 0, '86bf4bd34d86b349754bcc7412857faa') # {'value': '2017-01-30'} 'US National', 'Season peak week'
# ]
self.assertEqual(
(11 * 7 * 2 - 17),
forecast2.pred_eles.count()) # 154 - 17 duplicates = 137
forecast2.delete()
self.assertEqual(1,
self.forecast_model.forecasts.count()) # back to one
self.assertEqual(0, forecast2.pred_eles.count())
def test_delete_forecast(self):
# add a second forecast, check its rows were added, delete it, and test that the data was deleted (via CASCADE)
self.assertEqual(
1, self.forecast_model.forecasts.count()) # from setUpTestData()
self.assertEqual(8019, self.forecast.get_num_rows()) # ""
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17.csv') # EW01 2017
forecast2 = load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertEqual(2,
self.forecast_model.forecasts.count()) # includes new
self.assertEqual(5237, forecast2.get_num_rows(
)) # 8019 total rows - 2782 zero-valued bin rows = 5237 non-zero
self.assertEqual(8019, self.forecast.get_num_rows()) # didn't change
forecast2.delete()
self.assertEqual(1,
self.forecast_model.forecasts.count()) # back to one
self.assertEqual(0, forecast2.get_num_rows()) # cascaded DELETE
def test_load_forecast(self):
self.assertEqual(1, len(self.forecast_model.forecasts.all()))
self.assertIsInstance(self.forecast, Forecast)
self.assertEqual('EW1-KoTstable-2017-01-17.csv', self.forecast.source)
self.assertEqual(11 * 7 * 2, self.forecast.pred_eles.count()
) # locations * targets * points/bins
# check 'US National' targets: spot-check a few point rows
act_points_qs = self.forecast.pred_eles.filter(
unit__name='US National', pred_class=PredictionElement.POINT_CLASS)
self.assertEqual(7, act_points_qs.count())
# test empty file
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bad_file_no_header-2017-01-17.csv'
) # EW01 2017?
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn('empty file', str(context.exception))
# test a bad data file header
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bad_file_header-2017-01-17.csv'
) # EW01 2017?
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn('invalid header', str(context.exception))
# test load_forecast() with timezero not in the project
project2 = Project.objects.create() # no TimeZeros
make_cdc_units_and_targets(project2)
forecast_model2 = ForecastModel.objects.create(project=project2,
name='name',
abbreviation='abbrev')
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, forecast_model2, csv_file_path,
self.time_zero)
self.assertIn("time_zero was not in project", str(context.exception))
def test__tz_unit_targ_pks_to_truth_values(self):
# setup
project = Project.objects.create()
make_cdc_units_and_targets(project)
# load truth only for the TimeZero in truths-2016-2017-reichlab.csv we're testing against
time_zero = TimeZero.objects.create(project=project,
timezero_date=datetime.date(
2017, 1, 1),
is_season_start=True,
season_name='season1')
load_truth_data(
project,
Path(
'utils/ensemble-truth-table-script/truths-2016-2017-reichlab.csv'
))
forecast_model = ForecastModel.objects.create(project=project,
name='test model',
abbreviation='abbrev')
csv_file_path = Path(
'forecast_app/tests/EW1-KoTsarima-2017-01-17-small.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, forecast_model, csv_file_path,
time_zero)
# test
tz_pk = time_zero.pk
loc1_pk = Unit.objects.filter(project=project,
name='HHS Region 1').first().pk
loc2_pk = Unit.objects.filter(project=project,
name='HHS Region 2').first().pk
loc3_pk = Unit.objects.filter(project=project,
name='HHS Region 3').first().pk
loc4_pk = Unit.objects.filter(project=project,
name='HHS Region 4').first().pk
loc5_pk = Unit.objects.filter(project=project,
name='HHS Region 5').first().pk
loc6_pk = Unit.objects.filter(project=project,
name='HHS Region 6').first().pk
loc7_pk = Unit.objects.filter(project=project,
name='HHS Region 7').first().pk
loc8_pk = Unit.objects.filter(project=project,
name='HHS Region 8').first().pk
loc9_pk = Unit.objects.filter(project=project,
name='HHS Region 9').first().pk
loc10_pk = Unit.objects.filter(project=project,
name='HHS Region 10').first().pk
loc11_pk = Unit.objects.filter(project=project,
name='US National').first().pk
target1_pk = Target.objects.filter(project=project,
name='Season onset').first().pk
target2_pk = Target.objects.filter(project=project,
name='Season peak week').first().pk
target3_pk = Target.objects.filter(
project=project, name='Season peak percentage').first().pk
target4_pk = Target.objects.filter(project=project,
name='1 wk ahead').first().pk
target5_pk = Target.objects.filter(project=project,
name='2 wk ahead').first().pk
target6_pk = Target.objects.filter(project=project,
name='3 wk ahead').first().pk
target7_pk = Target.objects.filter(project=project,
name='4 wk ahead').first().pk
exp_dict = { # {timezero_pk: {unit_pk: {target_id: truth_value}}}
tz_pk: {
loc1_pk: {
target1_pk: ['2016-12-25'],
target2_pk: [datetime.date(2017, 2, 5)],
target3_pk: [3.19221],
target4_pk: [1.52411],
target5_pk: [1.73987],
target6_pk: [2.06524],
target7_pk: [2.51375]
},
loc2_pk: {
target1_pk: ['2016-11-20'],
target2_pk: [datetime.date(2017, 2, 5)],
target3_pk: [6.93759],
target4_pk: [5.07086],
target5_pk: [5.68166],
target6_pk: [6.01053],
target7_pk: [6.49829]
},
loc3_pk: {
target1_pk: ['2016-12-18'],
target2_pk: [datetime.date(2017, 2, 12)],
target3_pk: [5.20003],
target4_pk: [2.81366],
target5_pk: [3.09968],
target6_pk: [3.45232],
target7_pk: [3.73339]
},
loc4_pk: {
target1_pk: ['2016-11-13'],
target2_pk: [datetime.date(2017, 2, 12)],
target3_pk: [5.5107],
target4_pk: [2.89395],
target5_pk: [3.68564],
target6_pk: [3.69188],
target7_pk: [4.53169]
},
loc5_pk: {
target1_pk: ['2016-12-25'],
target2_pk: [datetime.date(2017, 2, 12)],
target3_pk: [4.31787],
target4_pk: [2.11757],
target5_pk: [2.4432],
target6_pk: [2.76295],
target7_pk: [3.182]
},
loc6_pk: {
target1_pk: ['2017-01-08'],
target2_pk: [datetime.date(2017, 2, 5)],
target3_pk: [9.87589],
target4_pk: [4.80185],
target5_pk: [5.26955],
target6_pk: [6.10427],
target7_pk: [8.13221]
},
loc7_pk: {
target1_pk: ['2016-12-25'],
target2_pk: [datetime.date(2017, 2, 5)],
target3_pk: [6.35948],
target4_pk: [2.75581],
target5_pk: [3.46528],
target6_pk: [4.56991],
target7_pk: [5.52653]
},
loc8_pk: {
target1_pk: ['2016-12-18'],
target2_pk: [datetime.date(2017, 2, 12)],
target3_pk: [2.72703],
target4_pk: [1.90851],
target5_pk: [2.2668],
target6_pk: [2.07104],
target7_pk: [2.27632]
},
loc9_pk: {
target1_pk: ['2016-12-18'],
target2_pk: [datetime.date(2016, 12, 25)],
target3_pk: [3.30484],
target4_pk: [2.83778],
target5_pk: [2.68071],
target6_pk: [2.9577],
target7_pk: [3.03987]
},
loc10_pk: {
target1_pk: ['2016-12-11'],
target2_pk: [datetime.date(2016, 12, 25)],
target3_pk: [3.67061],
target4_pk: [2.15197],
target5_pk: [3.25108],
target6_pk: [2.51434],
target7_pk: [2.28634]
},
loc11_pk: {
target1_pk: ['2016-12-11'],
target2_pk: [datetime.date(2017, 2, 5)],
target3_pk: [5.06094],
target4_pk: [3.07623],
target5_pk: [3.50708],
target6_pk: [3.79872],
target7_pk: [4.43601]
}
}
}
act_dict = _tz_unit_targ_pks_to_truth_values(forecast_model.project)
self.assertEqual(exp_dict, act_dict)
def test_load_forecast(self):
self.assertEqual(1, len(self.forecast_model.forecasts.all()))
self.assertIsInstance(self.forecast, Forecast)
self.assertEqual('EW1-KoTstable-2017-01-17.csv', self.forecast.source)
self.assertEqual(8019,
self.forecast.get_num_rows()) # excluding header
# check 'US National' targets: spot-check a few point rows
exp_points = [
('US National', '1 wk ahead', None, 3.00101461253164, None, None,
None), # _i, _f, _t, _d, _b
('US National', '2 wk ahead', None, 2.72809349594878, None, None,
None),
('US National', '3 wk ahead', None, 2.5332588357381, None, None,
None),
('US National', '4 wk ahead', None, 2.42985946508278, None, None,
None),
('US National', 'Season onset', None, None, '2016-12-12', None,
None),
('US National', 'Season peak percentage', None, 3.30854920241938,
None, None, None),
('US National', 'Season peak week', None, None, None,
datetime.date(2017, 1, 30), None)
]
act_points_qs = self.forecast.point_prediction_qs() \
.filter(unit__name='US National') \
.order_by('unit__name', 'target__name') \
.values_list('unit__name', 'target__name', 'value_i', 'value_f', 'value_t', 'value_d', 'value_b')
self.assertEqual(exp_points, list(act_points_qs))
# test empty file
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bad_file_no_header-2017-01-17.csv'
) # EW01 2017?
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn('empty file', str(context.exception))
# test a bad data file header
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/EW1-bad_file_header-2017-01-17.csv'
) # EW01 2017?
load_cdc_csv_forecast_file(2016, self.forecast_model,
csv_file_path, self.time_zero)
self.assertIn('invalid header', str(context.exception))
# test load_forecast() with timezero not in the project
project2 = Project.objects.create() # no TimeZeros
make_cdc_units_and_targets(project2)
forecast_model2 = ForecastModel.objects.create(project=project2,
name='name',
abbreviation='abbrev')
with self.assertRaises(RuntimeError) as context:
csv_file_path = Path(
'forecast_app/tests/model_error/ensemble/EW1-KoTstable-2017-01-17.csv'
) # EW01 2017
load_cdc_csv_forecast_file(2016, forecast_model2, csv_file_path,
self.time_zero)
self.assertIn("time_zero was not in project", str(context.exception))
