def test_invalid_target_data_check_valid_labels_for_nonnegative_objectives(objective):
X = pd.DataFrame({'column_one': [100, 100, 200, 300, 100, 200, 100] * 25})
y = pd.Series([2, 2, 3, 3, 1, 1, 1] * 25)
data_checks = DataChecks([InvalidTargetDataCheck], {"InvalidTargetDataCheck": {"problem_type": "multiclass",
"objective": objective}})
assert data_checks.validate(X, y) == {"warnings": [], "errors": [], "actions": []}
def test_invalid_target_data_check_invalid_labels_for_nonnegative_objective_names(objective):
X = pd.DataFrame({'column_one': [100, 200, 100, 200, 200, 100, 200, 100] * 25})
y = pd.Series([2, 2, 3, 3, -1, -1, 1, 1] * 25)
data_checks = DataChecks([InvalidTargetDataCheck], {"InvalidTargetDataCheck": {"problem_type": "multiclass",
"objective": objective}})
assert data_checks.validate(X, y) == {
"warnings": [],
"errors": [DataCheckError(
message=f"Target has non-positive values which is not supported for {objective}",
data_check_name=invalid_targets_data_check_name,
message_code=DataCheckMessageCode.TARGET_INCOMPATIBLE_OBJECTIVE,
details={"Count of offending values": sum(val <= 0 for val in y.values.flatten())}).to_dict()],
"actions": []
}
X = pd.DataFrame({'column_one': [100, 200, 100, 200, 100]})
y = pd.Series([2, 3, 0, 1, 1])
invalid_targets_check = InvalidTargetDataCheck(problem_type="regression", objective=objective)
assert invalid_targets_check.validate(X, y) == {
"warnings": [],
"errors": [DataCheckError(
message=f"Target has non-positive values which is not supported for {objective}",
data_check_name=invalid_targets_data_check_name,
message_code=DataCheckMessageCode.TARGET_INCOMPATIBLE_OBJECTIVE,
details={"Count of offending values": sum(val <= 0 for val in y.values.flatten())}).to_dict()],
"actions": []
}
def test_invalid_target_data_check_invalid_labels_for_objectives(
time_series_core_objectives):
X = pd.DataFrame(
{'column_one': [100, 200, 100, 200, 200, 100, 200, 100] * 25})
y = pd.Series([2, 2, 3, 3, -1, -1, 1, 1] * 25)
for objective in time_series_core_objectives:
if not objective.positive_only:
data_checks = DataChecks(
[InvalidTargetDataCheck], {
"InvalidTargetDataCheck": {
"problem_type": "multiclass",
"objective": objective
}
})
assert data_checks.validate(X, y) == {"warnings": [], "errors": []}
X = pd.DataFrame({'column_one': [100, 200, 100, 200, 100]})
y = pd.Series([2, 3, 0, 1, 1])
for objective in time_series_core_objectives:
if not objective.positive_only:
invalid_targets_check = InvalidTargetDataCheck(
problem_type="regression", objective=objective)
assert invalid_targets_check.validate(X, y) == {
"warnings": [],
"errors": []
}
def test_data_checks_do_not_duplicate_actions(X_y_binary):
X, y = X_y_binary
class MockDataCheck(DataCheck):
def validate(self, X, y):
return {
"warnings": [],
"errors": [],
"actions": [
DataCheckAction(DataCheckActionCode.DROP_COL,
metadata={
"column": 'col_to_drop'
}).to_dict()
]
}
class MockDataCheckWithSameAction(DataCheck):
def validate(self, X, y):
return {"warnings": [], "errors": [], "actions": []}
data_checks_list = [MockDataCheck, MockDataCheckWithSameAction]
data_checks = DataChecks(data_checks=data_checks_list)
# Check duplicate actions are returned once
assert data_checks.validate(X, y) == {
"warnings": [],
"errors": [],
"actions": [
DataCheckAction(DataCheckActionCode.DROP_COL,
metadata={
"column": 'col_to_drop'
}).to_dict()
]
}
def test_data_checks(X_y_binary):
X, y = X_y_binary
class MockDataCheck(DataCheck):
def validate(self, X, y):
return {"warnings": [], "errors": [], "actions": []}
class MockDataCheckWarning(DataCheck):
def validate(self, X, y):
return {"warnings": [DataCheckWarning(message="warning one", data_check_name=self.name, message_code=None).to_dict()],
"errors": [],
"actions": []}
class MockDataCheckError(DataCheck):
def validate(self, X, y):
return {"warnings": [],
"errors": [DataCheckError(message="error one", data_check_name=self.name, message_code=None).to_dict()],
"actions": []}
class MockDataCheckErrorAndWarning(DataCheck):
def validate(self, X, y):
return {"warnings": [DataCheckWarning(message="warning two", data_check_name=self.name, message_code=None).to_dict()],
"errors": [DataCheckError(message="error two", data_check_name=self.name, message_code=None).to_dict()],
"actions": []}
data_checks_list = [MockDataCheck, MockDataCheckWarning, MockDataCheckError, MockDataCheckErrorAndWarning]
data_checks = DataChecks(data_checks=data_checks_list)
assert data_checks.validate(X, y) == {
"warnings": [DataCheckWarning(message="warning one", data_check_name="MockDataCheckWarning").to_dict(),
DataCheckWarning(message="warning two", data_check_name="MockDataCheckErrorAndWarning").to_dict()],
"errors": [DataCheckError(message="error one", data_check_name="MockDataCheckError").to_dict(),
DataCheckError(message="error two", data_check_name="MockDataCheckErrorAndWarning").to_dict()],
"actions": []
}
def test_data_checks_drop_index(X_y_binary):
X, y = X_y_binary
X = pd.DataFrame(X)
X['index_col'] = pd.Series(range(len(X)))
X = ww.DataTable(X)
X = X.set_index('index_col')
class MockDataCheck(DataCheck):
def validate(self, X, y):
return {"warnings": [], "errors": [], "actions": []}
assert MockDataCheck().validate(X, y)
MockDataCheck.validate = MagicMock()
checks = DataChecks([MockDataCheck, MockDataCheck, MockDataCheck])
checks.validate(X, y)
validate_args = MockDataCheck.validate.call_args_list
for arg in validate_args:
assert 'index_col' not in arg[0][0].columns