2023 1 00228 s uid a002 x1199f9e x7c24 procedure hifa calimage diffgain regression: Test case result

The below summarizes the result of the test " 2023 1 00228 s uid a002 x1199f9e x7c24 procedure hifa calimage diffgain regression" in build 74 of PIPESPECS - Test Pipeline main with Casa master - Test ManyLinux 2.28 Python 3.12.

• Description: 2023 1 00228 s uid a002 x1199f9e x7c24 procedure hifa calimage diffgain regression
• Test class: tests.regression.fast.alma_if_fast_test
• Method: test_2023_1_00228_S__uid___A002_X1199f9e_X7c24__procedure_hifa_calimage_diffgain__regression

• Duration: 599 mins
• Status: Failed (Existing Failure)

Error Log

Failed: Failed to match 1 result value within tolerance :
s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags
	values differ by > a relative difference of 1e-07
	expected: 0.7951601163768378
	new:      1.0
	diff: -0.2048398836231622
	percent_diff: -25.76083475571172%
Worst absolute diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags: -0.2048398836231622
Worst percentage diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags: -25.76083475571172%
@pytest.mark.seven
    @pytest.mark.mpi
    def test_2023_1_00228_S__uid___A002_X1199f9e_X7c24__procedure_hifa_calimage_diffgain__regression():
        """Run ALMA cal+image regression on a 7m B2B dataset with differential gain calibration.
    
        Recipe name:                procedure_hifa_calimage_diffgain
        Dataset:                    2023.1.00228.S: uid___A002_X1199f9e_X7c24
        """
        ref_directory = 'pl-regressiontest/2023.1.00228.S'
    
        pt = PipelineTester(
            visname=['uid___A002_X1199f9e_X7c24'],
            recipe='procedure_hifa_calimage_diffgain.xml',
            input_dir=ref_directory,
            expectedoutput_dir=ref_directory,
            )
    
>       pt.run()

tests/regression/fast/alma_if_fast_test.py:143: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
tests/testing_utils.py:376: in run
    self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <tests.testing_utils.PipelineTester object at 0x7effcf2e6d50>
new_file = 'uid___A002_X1199f9e_X7c24.NEW.results.txt'
relative_tolerance = 1e-07

    def __compare_results(self, new_file: str, relative_tolerance: float) -> None:
        """
        Compare results between new one loaded from file and old one.
    
        Args:
            new_file : file path of new results
            relative_tolerance : relative tolerance of output value
        """
        with open(self.expectedoutput_file) as expected_fd, open(new_file) as new_fd:
            expected_results = expected_fd.readlines()
            new_results = new_fd.readlines()
            errors = []
            worst_diff = (0, 0)
            worst_percent_diff = (0, 0)
            for old, new in zip(expected_results, new_results):
                try:
                    oldkey, oldval, tol = self.__sanitize_results_string(old)
                    newkey, newval, _ = self.__sanitize_results_string(new)
                except ValueError as e:
                    errorstr = "The results: {0} could not be parsed. Error: {1}".format(new, str(e))
                    errors.append(errorstr)
                    continue
    
                assert oldkey == newkey, f"Expected key {oldkey} does not match new key {newkey}."
                tolerance = tol if tol else relative_tolerance
                if newval is not None:
                    LOG.info('Comparing %s to %s with a rel. tolerance of %s', oldval, newval, tolerance)
                    if oldval != pytest.approx(newval, rel=tolerance):
                        diff = oldval-newval
                        percent_diff = (oldval-newval)/oldval * 100 if oldval != 0 else 100
                        if abs(diff) > abs(worst_diff[0]):
                            worst_diff = diff, oldkey
                        if abs(percent_diff) > abs(worst_percent_diff[0]):
                            worst_percent_diff = percent_diff, oldkey
                        errorstr = f"{oldkey}\n\tvalues differ by > a relative difference of {tolerance}\n\texpected: {oldval}\n\tnew:      {newval}\n\tdiff: {diff}\n\tpercent_diff: {percent_diff}%"
                        errors.append(errorstr)
                elif oldval is not None:
                    # If only the new value is None, fail
                    errorstr = f"{oldkey}\n\tvalue is None\n\texpected: {oldval}\n\tnew:      {newval}"
                    errors.append(errorstr)
                else:
                    # If old and new values are both None, this is expected, so pass
                    LOG.info('Comparing %s and %s... both values are None.', oldval, newval)
    
            [LOG.warning(x) for x in errors]
            n_errors = len(errors)
            if n_errors > 0:
                summary_str = f"Worst absolute diff, {worst_diff[1]}: {worst_diff[0]}\nWorst percentage diff, {worst_percent_diff[1]}: {worst_percent_diff[0]}%"
                errors.append(summary_str)
>               pytest.fail("Failed to match {0} result value{1} within tolerance{1} :\n{2}".format(
                    n_errors, '' if n_errors == 1 else 's', '\n'.join(errors)), pytrace=True)
E               Failed: Failed to match 1 result value within tolerance :
E               s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags
E               	values differ by > a relative difference of 1e-07
E               	expected: 0.7951601163768378
E               	new:      1.0
E               	diff: -0.2048398836231622
E               	percent_diff: -25.76083475571172%
E               Worst absolute diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags: -0.2048398836231622
E               Worst percentage diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.qa.score.ApplycalFlags: -25.76083475571172%

tests/testing_utils.py:435: Failed