def test_regression_model_with_constant_variation(self):
"""Estimate the model and run it on the same data as the estimation. The result should be equal to the original data.
If there is a change in the explanatory variables, the result should not be equal.
"""
storage = StorageFactory().get_storage('dict_storage')
table_name = 'dataset_table'
data = {
"attr1": array([30, 0, 90, 100, 65, 50]),
"attr2": array([2002, 1968, 1880, 1921, 1956, 1989]),
"attr3": array([0.5, 0.1, 0.3, 0.9, 0.2, 0.8]),
"outcome": array([20, 40, 15, 5, 40, 30], dtype="int32"),
"id": array([1, 2, 3, 4, 5, 6])
}
storage.write_table(table_name=table_name, table_data=data)
dataset = Dataset(in_storage=storage,
in_table_name=table_name,
id_name="id")
specification = EquationSpecification(variables=("attr1", "attr2",
"attr3", "constant"),
coefficients=("b1", "b2", "b3",
"constant"))
model = RegressionModelWithAdditionInitialResiduals(
outcome_attribute="outcome")
coef, dummy = model.estimate(
specification,
dataset,
outcome_attribute="outcome",
procedure="opus_core.estimate_linear_regression")
result = model.run(specification, coef, dataset)
# if estimated and run on the same data, it should give the original outcome
self.assertEqual(ma.allequal(result, data["outcome"]), True)
# if some values changed it shoudn't be the same for those elements
dataset.set_values_of_one_attribute("attr1", array([32, 10]),
arange(2))
result2 = model.run(specification, coef, dataset)
self.assertEqual(ma.allequal(result2[0:2], data["outcome"][0:2]),
False)
self.assertEqual(ma.allequal(result2[2:], data["outcome"][2:]), True)
# check if exclusion of missing values is working
dataset.set_values_of_one_attribute("outcome", array([0, 0]),
array([2, 4]))
dataset.delete_one_attribute("_init_error_outcome")
model.run(specification,
coef,
dataset,
run_config=Configuration(
{'exclude_missing_values_from_initial_error': True}))
initial_error = dataset.get_attribute("_init_error_outcome")
self.assertEqual(ma.allequal(initial_error[array([2, 4])], 0), True)
self.assertEqual(ma.allequal(initial_error[array([0, 1, 3, 4, 5])], 0),
False)
def test_regression_model_with_constant_variation(self):
"""Estimate the model and run it on the same data as the estimation. The result should be equal to the original data.
If there is a change in the explanatory variables, the result should not be equal.
"""
storage = StorageFactory().get_storage('dict_storage')
table_name = 'dataset_table'
data = {
"attr1":array([30, 0, 90, 100, 65, 50]),
"attr2":array([2002, 1968, 1880, 1921, 1956, 1989]),
"attr3":array([0.5, 0.1, 0.3, 0.9, 0.2, 0.8]),
"outcome": array([20, 40, 15, 5, 40, 30], dtype="int32"),
"id": array([1,2,3,4, 5, 6])
}
storage.write_table(
table_name=table_name,
table_data=data
)
dataset = Dataset(in_storage=storage, in_table_name=table_name, id_name= "id")
specification = EquationSpecification(variables=(
"attr1", "attr2", "attr3", "constant"),
coefficients=("b1", "b2", "b3", "constant"))
model = RegressionModelWithAdditionInitialResiduals(outcome_attribute = "outcome")
coef, dummy = model.estimate(specification, dataset, outcome_attribute = "outcome",
procedure = "opus_core.estimate_linear_regression")
result = model.run(specification, coef, dataset)
# if estimated and run on the same data, it should give the original outcome
self.assertEqual(ma.allequal(result, data["outcome"]), True)
# if some values changed it shoudn't be the same for those elements
dataset.set_values_of_one_attribute("attr1", array([32, 10]), arange(2))
result2 = model.run(specification, coef, dataset)
self.assertEqual(ma.allequal(result2[0:2], data["outcome"][0:2]), False)
self.assertEqual(ma.allequal(result2[2:], data["outcome"][2:]), True)
# check if exclusion of missing values is working
dataset.set_values_of_one_attribute("outcome", array([0,0]), array([2,4]))
dataset.delete_one_attribute("_init_error_outcome")
model.run(specification, coef, dataset, run_config=Configuration({
'exclude_missing_values_from_initial_error': True}))
initial_error = dataset.get_attribute("_init_error_outcome")
self.assertEqual(ma.allequal(initial_error[array([2,4])], 0), True)
self.assertEqual(ma.allequal(initial_error[array([0,1,3,4,5])], 0), False)
