def test_non_numeric_or_negative_values_raise_exception(self):
"""checks that an error is raised when a negative or non-numeric
value is used for:
- area
- age (when using_age_class is false)
- delay
- spatial reference (negatives allowed here)
"""
classifiers, classifier_values = self.get_mock_classifiers()
disturbance_types = self.get_mock_disturbance_types()
for data in [
("b", "a", "F", "x", 1, 0, 0),
("b", "a", "F", -1, 1, 0, 0),
("b", "a", "F", 0, "x", 0, 0),
("b", "a", "F", 0, -1, 0, 0),
("b", "a", "F", 0, 0, "x", 0),
("b", "a", "F", 0, 0, -1, 0),
("b", "a", "F", 0, 0, -1, 0, "dist1", "dist1", "x")]:
inventory_table = pd.DataFrame([data])
with self.assertRaises(ValueError):
sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values,
disturbance_types, None)
def test_spatial_reference_mixed_with_using_age_class(self):
"""checks that an error is raised when a row has both non-negative
spatial reference value and a True "using_age_class" value
"""
classifiers, classifier_values = self.get_mock_classifiers()
disturbance_types = self.get_mock_disturbance_types()
age_classes = self.get_mock_age_classes()
for data in [("b", "a", True, 1, 0, 0, 0, "dist1", "dist1", 1)]:
inventory_table = pd.DataFrame([data])
with self.assertRaises(ValueError):
sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values,
disturbance_types, age_classes)
def test_missing_classifier_values_raise_exception(self):
"""checks that an error is raised when a classifier value is not
defined in sit classifiers metadata.
"""
classifiers, classifier_values = self.get_mock_classifiers()
disturbance_types = self.get_mock_disturbance_types()
for data in [("MISSING", "a", "F", 0, 0, 0, 0),
("b", "MISSING", "F", 0, 0, 0, 0)]:
inventory_table = pd.DataFrame([data])
with self.assertRaises(ValueError):
sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values,
disturbance_types, None)
def test_exception_on_missing_age_class_id(self):
"""Checks the age class expansion feature "using_age_class"
"""
inventory_table = pd.DataFrame(
data=[
("b", "a", "TRUE", "MISSING", 1, 0, 0),
("a", "a", False, 100, 1, 0, 0),
("a", "a", "-1", 4, 1, 0, 0)])
classifiers, classifier_values = self.get_mock_classifiers()
age_classes = self.get_mock_age_classes()
with self.assertRaises(ValueError):
sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values, None,
age_classes)
def test_expected_result_with_numeric_classifiers(self):
"""Checks that numeric classifiers that appear in inventory data
are parsed as strings
"""
inventory_table = pd.DataFrame(
data=[
("1", 1, "F", "1", 1, 0, 0),
(2.0, 1, False, 100, 1, 0, 0),
(1, 1, "-1", 4, 1, 0, 0)])
classifiers = pd.DataFrame(
data=[
(1, "classifier1"),
(2, "classifier2")
],
columns=["id", "name"]
)
classifier_values = pd.DataFrame(
data=[
(1, "1", "1"),
(1, "2.0", "2"),
(2, "1", "1"),
],
columns=["classifier_id", "name", "description"]
)
age_classes = self.get_mock_age_classes()
result = sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values, None, age_classes)
self.assertTrue((result.classifier1 == ["1", "2.0", "1"]).all())
def test_duplicate_spatial_reference_raises_error(self):
"""Checks that any duplicate spatial reference values in the inventory
table triggers an error
"""
classifiers, classifier_values = self.get_mock_classifiers()
disturbance_types = self.get_mock_disturbance_types()
age_classes = self.get_mock_age_classes()
inventory_table = pd.DataFrame([
("a", "a", False, 100, 1, 0, 0, "dist2", "dist1", 10000),
("a", "a", "-1", 4, 1, 0, 0, "dist1", "dist1", 10000)])
# note the same identifier 10000 appears 2 times
with self.assertRaises(ValueError):
sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values,
disturbance_types, age_classes)
def test_expected_result_with_using_non_zero_age_class(self):
"""Checks the age class expansion feature "using_age_class"
"""
inventory_table = pd.DataFrame(
data=[
("b", "a", "TRUE", "1", 1, 0, 0),
("a", "a", False, 100, 1, 0, 0),
("a", "a", "-1", 4, 1, 0, 0)])
classifiers, classifier_values = self.get_mock_classifiers()
age_classes = self.get_mock_age_classes()
result = sit_inventory_parser.parse(
inventory_table, classifiers, classifier_values, None, age_classes)
self.assertTrue(result.shape[0] == len(inventory_table) + 1)
self.assertTrue(result.area.sum() == 3)
self.assertTrue(set(result.age) == {100, 4, 1, 2})
def parse(sit_classifiers,
sit_disturbance_types,
sit_age_classes,
sit_inventory,
sit_yield,
sit_events=None,
sit_transitions=None,
sit_eligibilities=None):
"""Parses and validates CBM Standard import tool formatted data including
the complicated interdependencies in the SIT format. Returns an object
containing the validated result.
The returned object has the following properties:
- classifiers: a pandas.DataFrame of classifiers in the sit_classifiers
input
- classifier_values: a pandas.DataFrame of the classifier values in the
sit_classifiers input
- classifier_aggregates: a dictionary of the classifier aggregates
in the sit_classifiers input
- disturbance_types: a pandas.DataFrame based on the disturbance types in
the sit_disturbance_types input
- age_classes: a pandas.DataFrame of the age classes based on
sit_age_classes
- inventory: a pandas.DataFrame of the inventory based on sit_inventory
- yield_table: a pandas.DataFrame of the merchantable volume yield curves
in the sit_yield input
- disturbance_events: a pandas.DataFrame of the disturbance events based
on sit_events. If the sit_events parameter is None this field is None.
- transition_rules: a pandas.DataFrame of the transition rules based on
sit_transitions. If the sit_transitions parameter is None this field
is None.
- disturbance_eligibilities: a pandas.DataFrame of the disturbance event
eligibilities based on sit_eligibilities. If the sit_events parameter
is None this field is None.
Args:
sit_classifiers (pandas.DataFrame): SIT formatted classifiers
sit_disturbance_types (pandas.DataFrame): SIT formatted disturbance
types
sit_age_classes (pandas.DataFrame): SIT formatted age classes
sit_inventory (pandas.DataFrame): SIT formatted inventory
sit_yield (pandas.DataFrame): SIT formatted yield curves
sit_events (pandas.DataFrame, optional): SIT formatted disturbance
events
sit_transitions (pandas.DataFrame, optional): SIT formatted transition
rules. Defaults to None.
sit_eligibilities (pandas.DataFrame, optional): SIT formatted
disturbance eligibilities. Defaults to None.
Returns:
object: an object containing parsed and validated SIT dataset
"""
s = SimpleNamespace()
classifiers, classifier_values, classifier_aggregates = \
sit_classifier_parser.parse(sit_classifiers)
s.classifiers = classifiers
s.classifier_values = classifier_values
s.classifier_aggregates = classifier_aggregates
s.disturbance_types = sit_disturbance_type_parser.parse(
sit_disturbance_types)
s.age_classes = sit_age_class_parser.parse(sit_age_classes)
s.inventory = sit_inventory_parser.parse(sit_inventory, classifiers,
classifier_values,
s.disturbance_types,
s.age_classes)
s.yield_table = sit_yield_parser.parse(sit_yield, s.classifiers,
s.classifier_values, s.age_classes)
if sit_events is not None:
separate_eligibilities = False
if sit_eligibilities is not None:
separate_eligibilities = True
s.disturbance_events = sit_disturbance_event_parser.parse(
sit_events, s.classifiers, s.classifier_values,
s.classifier_aggregates, s.disturbance_types, s.age_classes,
separate_eligibilities)
if sit_eligibilities is not None:
s.disturbance_eligibilities = \
sit_disturbance_event_parser.parse_eligibilities(
s.disturbance_events, sit_eligibilities)
else:
s.disturbance_eligibilities = None
else:
s.disturbance_events = None
s.disturbance_eligibilities = None
if sit_transitions is not None:
s.transition_rules = sit_transition_rule_parser.parse(
sit_transitions, s.classifiers, s.classifier_values,
s.classifier_aggregates, s.disturbance_types, s.age_classes)
else:
s.transition_rules = None
return s