def test_mape_time_series_model():
obj = MAPE()
s1_actual = np.array([0, 0, 1, 1, 1, 1, 2, 0, 2])
s1_predicted = np.array([0, 1, 0, 1, 1, 2, 1, 2, 0])
s2_actual = np.array([-1, -2, 1, 3])
s2_predicted = np.array([1, 2, -1, -3])
s3_actual = np.array([1, 2, 4, 2, 1, 2])
s3_predicted = np.array([0, 2, 2, 1, 3, 2])
with pytest.raises(
ValueError,
match=
"Mean Absolute Percentage Error cannot be used when targets contain the value 0."
):
obj.score(s1_actual, s1_predicted)
assert obj.score(s2_actual, s2_predicted) == pytest.approx(8 / 4 * 100)
assert obj.score(s3_actual, s3_predicted) == pytest.approx(4 / 6 * 100)
assert obj.score(pd.Series(s3_actual, index=range(-12, -6)),
s3_predicted) == pytest.approx(4 / 6 * 100)
assert obj.score(pd.Series(s2_actual, index=range(10, 14)),
pd.Series(s2_predicted,
index=range(20,
24))) == pytest.approx(8 / 4 * 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": []
}
@pytest.mark.parametrize("objective", [RootMeanSquaredLogError(), MeanSquaredLogError(), MAPE()])
def test_invalid_target_data_check_invalid_labels_for_nonnegative_objective_instances(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.name}",
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": []
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()
]
}
@pytest.mark.parametrize(
"objective", [RootMeanSquaredLogError(),
MeanSquaredLogError(),
MAPE()])
def test_invalid_target_data_check_invalid_labels_for_nonnegative_objective_instances(
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) == {