def test_config_valid(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("some_new_key.csv", "some_bucket")
errors = config.validate()
assert not errors
def test_config_dependent_dataset_dependencies(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("DatasetsFromRetailDemandTRMProphet",
"some_bucket")
datasets = config.datasets(dataset_file)
def test_config_validation_bad_dataset_reference(configuration_data):
config = Config()
config.config = configuration_data
configuration_data["InvalidReference"] = {
"DatasetGroup": {
"Domain": "Retail"
},
"Datasets": {
"From": "DoesNotExist"
},
"Predictor": {
"PerformAutoML": True,
"ForecastHorizon": 30,
"FeaturizationConfig": {
"ForecastFrequency": "D"
},
},
"Forecast": {
"ForecastTypes": ["0.50"]
},
}
errors = config.validate()
assert len(errors) == 1
assert "no config found for datasets in that group" in errors[0]
def test_config_required_datasets(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("some_new_key.csv", "some_bucket")
assert config.required_datasets(dataset_file) == ["TARGET_TIME_SERIES"]
def test_forecast_arn(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
forecast = config.forecast(dataset_file, "RetailDemandTNPTS")
forecast.cli = forecast_stub.client
forecast_stub.add_response(
"list_forecasts",
{
"Forecasts": [
{
"LastModificationTime": datetime(2015, 1, 1),
"ForecastArn": "arn:2015-1-1",
},
{
"LastModificationTime": datetime(2017, 1, 1),
"ForecastArn": "arn:2017-1-1",
},
]
},
)
assert forecast.arn == "arn:2017-1-1"
def test_forecast_history(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
forecast = config.forecast(dataset_file, "RetailDemandTNPTS")
forecast.cli = forecast_stub.client
forecast_stub.add_response(
"list_forecasts",
{
"Forecasts": [
{
"LastModificationTime": datetime(2015, 1, 1),
"ForecastArn": "arn:2015-1-1",
"Status": "ACTIVE",
},
{
"LastModificationTime": datetime(2017, 1, 1),
"ForecastArn": "arn:2017-1-1",
"Status": "CREATE_IN_PROGRESS",
},
]
},
)
history = forecast.history()
assert history[0].get("LastModificationTime") == datetime(2017, 1, 1)
assert history[1].get("LastModificationTime") == datetime(2015, 1, 1)
def test_dataset_default(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("some_new_key.csv", "some_bucket")
ds = config.dataset(dataset_file)
assert ds.data_frequency == "D"
assert ds.dataset_type == DatasetType.TARGET_TIME_SERIES
assert ds.dataset_domain == DatasetDomain.RETAIL
assert ds.dataset_name == "some_new_key"
assert ds.dataset_schema == {
"Attributes": [
{
"AttributeName": "item_id",
"AttributeType": "string"
},
{
"AttributeName": "timestamp",
"AttributeType": "timestamp",
},
{
"AttributeName": "demand",
"AttributeType": "float"
},
]
}
def test_status_still_good(forecast_stub, configuration_data, expected_dataset_arns):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
predictor = config.predictor(dataset_file)
predictor.cli = forecast_stub.client
forecast_stub.add_response(
"list_predictors",
{
"Predictors": [
{"PredictorArn": "arn:", "CreationTime": datetime.now(timezone.utc)}
]
},
)
forecast_stub.add_response(
"describe_dataset_group", {"DatasetArns": expected_dataset_arns}
)
for arn in expected_dataset_arns:
forecast_stub.add_response(
"describe_dataset", {"Status": "ACTIVE", "DatasetArn": arn}
)
forecast_stub.add_response(
"describe_predictor",
{"CreationTime": datetime.now(timezone.utc), "Status": "ACTIVE"},
)
assert predictor.status == Status.ACTIVE
def test_dataset_import_job_arn(configuration_data, forecast_stub, mocker):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRM.csv", "some_bucket")
dataset_import_job = config.dataset_import_job(dataset_file)
# create some job history
forecast_stub.add_response(
"list_dataset_import_jobs",
{
"DatasetImportJobs": [
{
"LastModificationTime": datetime(2015, 1, 1),
"DatasetImportJobArn": "arn:2015-1-1",
},
{
"LastModificationTime":
datetime(2017, 1, 1),
"DatasetImportJobArn":
"arn:aws:forecast:abcdefghijkl:us-east-1:dataset-import-job/RetailDemandTRM/RetailDemandTRM_2017_01_01_00_00_00",
},
{
"LastModificationTime": datetime(2016, 1, 1),
"DatasetImportJobArn": "arn:2016-1-1",
},
]
},
)
dataset_import_job.cli = forecast_stub.client
assert (
dataset_import_job.arn ==
f"arn:aws:forecast:abcdefghijkl:us-east-1:dataset-import-job/RetailDemandTRM/RetailDemandTRM_2017_01_01_00_00_00"
)
def test_predictor_arn(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
predictor = config.predictor(dataset_file, "RetailDemandTNPTS")
predictor.cli = forecast_stub.client
forecast_stub.add_response(
"list_predictors",
{
"Predictors": [
{
"CreationTime": datetime(2015, 1, 1),
"PredictorArn": "arn:2015-1-1"
},
{
"CreationTime": datetime(2017, 1, 1),
"PredictorArn": "arn:2017-1-1"
},
]
},
)
assert predictor.arn == "arn:2017-1-1"
def mocked_dsg(dataset_file, configuration_data, mocker):
with mock_sts():
config = Config()
config.config = configuration_data
dataset_group = config.dataset_group(dataset_file)
dsg = DatasetGroup(
dataset_group_name=dataset_group.dataset_group_name,
dataset_domain=dataset_group.dataset_group_domain,
)
dsg.cli = mocker.MagicMock()
dsg.cli.describe_dataset_group.return_value = {
"DatasetArns": ["arn::1", "arn::2", "arn::3"]
}
dsg.cli.describe_dataset.return_value = {"DatasetArn": 'arn::1', "Status": "ACTIVE", 'LastModificationTime': datetime.now()}
dsg.cli.get_paginator().paginate.return_value = [{
'DatasetImportJobs': [
{
"DatasetImportJobArn": f"arn::{i}",
"Status": "ACTIVE",
"LastModificationTime": datetime.now()
}
for i in range(3)
]
}]
yield dsg
def test_predictor_history(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
predictor = config.predictor(dataset_file, "RetailDemandTNPTS")
predictor.cli = forecast_stub.client
forecast_stub.add_response(
"list_predictors",
{
"Predictors": [
{
"CreationTime": datetime(2015, 1, 1),
"PredictorArn": "arn:2015-1-1",
"Status": "ACTIVE",
},
{
"CreationTime": datetime(2017, 1, 1),
"PredictorArn": "arn:2017-1-1",
"Status": "CREATE_IN_PROGRESS",
},
]
},
)
history = predictor.history()
assert history[0].get("CreationTime") == datetime(2017, 1, 1)
assert history[1].get("CreationTime") == datetime(2015, 1, 1)
def test_config_dataset_groups(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRMProphet", "some_bucket")
dsgs = config.dataset_groups(dataset_file)
assert len(dsgs) == 2
def test_config_validation_doesnt_mutate_config(configuration_data):
config = Config()
config.config = configuration_data
config_copy = copy.deepcopy(configuration_data)
config.validate()
assert config.config == config_copy
def test_config_required_datasets_override(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("Override.csv", "some_bucket")
required_datasets = config.required_datasets(dataset_file)
assert "TARGET_TIME_SERIES" in required_datasets
assert "RELATED_TIME_SERIES" in required_datasets
assert "ITEM_METADATA" in required_datasets
def test_config_dependent_dataset_groups(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRMProphet", "some_bucket")
dependents = config.dependent_dataset_groups(dataset_file)
assert len(dependents) == 2
assert "DatasetsFromRetailDemandTRMProphet" in dependents
def test_dataset_group_mismatch(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("Mismatch.csv", "some_bucket")
with pytest.raises(ValueError) as excinfo:
config.dataset_group(dataset_file)
assert "must match" in str(excinfo.value)
def test_duplicate_timeseries(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandDuplicateDatasets.csv",
"some_bucket")
with pytest.raises(ValueError) as excinfo:
config.required_datasets(dataset_file)
assert "duplicate dataset types" in str(excinfo.value)
def test_config_predictor_from_dependent(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRMProphet", "some_bucket")
predictor = config.predictor(dataset_file,
"DatasetsFromRetailDemandTRMProphet")
assert (predictor.validator.expected_params["AlgorithmArn"] ==
"arn:aws:forecast:::algorithm/CNN-QR")
def test_missing_timeseries(configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandForgottenDatasets.csv",
"some_bucket")
with pytest.raises(ValueError) as excinfo:
config.required_datasets(dataset_file)
assert "you must configure a TARGET_TIME_SERIES dataset" in str(
excinfo.value)
def test_create(dataset_file, configuration_data):
config = Config()
config.config = configuration_data
dataset_group = config.dataset_group(dataset_file)
dsg = DatasetGroup(
dataset_group_name=dataset_group.dataset_group_name,
dataset_domain=dataset_group.dataset_group_domain,
)
assert dsg.arn == "arn:aws:forecast:us-east-1:abcdefghijkl:dataset-group/data"
def test_status_not_yet_created(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
forecast = config.forecast(dataset_file, "RetailDemandTNPTS")
forecast.cli = forecast_stub.client
forecast_stub.add_response("list_forecasts", {"Forecasts": []})
assert forecast.status == Status.DOES_NOT_EXIST
forecast_stub.assert_no_pending_responses()
def test_init_forecast(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
forecast = config.forecast(dataset_file, "RetailDemandTNPTS")
dataset_group = config.dataset_group(dataset_file)
assert (
forecast._dataset_group.dataset_group_name == dataset_group.dataset_group_name
)
assert forecast._forecast_config == config.config_item(dataset_file, "Forecast")
def test_status(dataset_file, configuration_data, mock_forecast_dsg_exists):
config = Config()
config.config = configuration_data
dataset_group = config.dataset_group(dataset_file)
dsg = DatasetGroup(
dataset_group_name=dataset_group.dataset_group_name,
dataset_domain=dataset_group.dataset_group_domain,
)
dsg.cli = mock_forecast_dsg_exists
assert dsg.status == Status.ACTIVE
def test_init_predictor(forecast_stub, configuration_data):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
predictor = config.predictor(dataset_file, "RetailDemandTNPTS")
predictor.cli = forecast_stub.client
assert predictor._dataset_file == dataset_file
for k, v in config.config_item(dataset_file, "Predictor").items():
if k != "MaxAge":
assert predictor._predictor_params.get(k) == v
def test_dataset_import_timestamp_format_none(configuration_data,
forecast_stub):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRM.csv", "some_bucket")
dataset = config.dataset(dataset_file)
forecast_stub.add_response("list_dataset_import_jobs",
{"DatasetImportJobs": []})
dataset.cli = forecast_stub.client
assert dataset.timestamp_format == None
def test_dataset_status_lifecycle(configuration_data, forecast_stub):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRM.csv", "some_bucket")
dataset = config.dataset(dataset_file)
forecast_stub.add_client_error("describe_dataset", "ResourceNotFoundException")
forecast_stub.add_response("describe_dataset", {"Status": "ACTIVE"})
dataset.cli = forecast_stub.client
assert dataset.status == Status.DOES_NOT_EXIST
assert dataset.status == "ACTIVE"
def test_can_update(forecast_stub, configuration_data, expected_dataset_arns):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTNPTS.csv", "some_bucket")
predictor = config.predictor(dataset_file)
predictor.cli = forecast_stub.client
forecast_stub.add_response(
"describe_dataset_group", {"DatasetArns": expected_dataset_arns}
)
for arn in expected_dataset_arns:
forecast_stub.add_response("describe_dataset", {"Status": "ACTIVE"})
assert predictor.can_update
def test_dataset_create_noop_errors(configuration_data, forecast_stub):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("RetailDemandTRM.csv", "some_bucket")
dataset = config.dataset(dataset_file)
configured_dataset = configuration_data.get("RetailDemandTRM").get(
"Datasets")[2]
params = {
"DatasetType": configured_dataset.get("DatasetType"),
"DatasetName": "RetailDemandTRM",
"Domain": configured_dataset.get("Domain"),
"Schema": configured_dataset.get("Schema"),
"DataFrequency": configured_dataset.get("DataFrequency"),
}
create_params = deepcopy(params)
create_params["Tags"] = [{"Key": "SolutionId", "Value": "SOL0123"}]
forecast_stub.add_response(
"describe_dataset",
params,
)
forecast_stub.add_response("create_dataset", {"DatasetArn": dataset.arn},
create_params)
forecast_stub.add_response(
"describe_dataset",
params,
)
dataset.cli = forecast_stub.client
dataset.create()
# clobber the values to trigger some exceptions
# this is likey caused by a user changing configuration unexpectedly
dataset._dataset_type = DatasetType.RELATED_TIME_SERIES
dataset._dataset_domain = DatasetDomain.WORK_FORCE
dataset._data_frequency = DataFrequency("1min")
dataset._dataset_schema = {}
with pytest.raises(ValueError) as excinfo:
dataset.create()
assert "dataset type" in str(excinfo.value)
assert "dataset domain" in str(excinfo.value)
assert "data frequency" in str(excinfo.value)
assert "dataset schema" in str(excinfo.value)
def test_dataset_import_job_default(configuration_data, forecast_stub):
config = Config()
config.config = configuration_data
dataset_file = DatasetFile("some_new_key.csv", "some_bucket")
dsij = config.dataset_import_job(dataset_file)
assert (dsij.dataset_arn ==
"arn:aws:forecast:us-east-1:abcdefghijkl:dataset/some_new_key")
# the stubber needs to be initialized because the ARN needs dataset import job history
dsij.cli = forecast_stub.client
forecast_stub.add_response(method="list_dataset_import_jobs",
service_response={"DatasetImportJobs": []})
assert not dsij.arn