uid a002 x85c183 x36f procedure hsd calimage regression: Test case result

The below summarizes the result of the test " uid a002 x85c183 x36f procedure hsd calimage regression" in build 72 of PIPESPECS - Test Pipeline main with Casa master - Test ManyLinux 2.28 Python 3.12.

• Description: uid a002 x85c183 x36f procedure hsd calimage regression
• Test class: tests.regression.fast.alma_sd_fast_test
• Method: test_uid___A002_X85c183_X36f__procedure_hsd_calimage__regression

• Duration: 85 mins
• Status: Failed (New Failure)

Error Log

Failed: Failed to match 1 result value within tolerance :
s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags
	values differ by > a relative difference of 1e-07
	expected: 0.9579857010836426
	new:      1.0
	diff: -0.04201429891635744
	percent_diff: -4.38569165164284%
Worst absolute diff, s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags: -0.04201429891635744
Worst percentage diff, s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags: -4.38569165164284%
def test_uid___A002_X85c183_X36f__procedure_hsd_calimage__regression():
        """Run ALMA single-dish cal+image regression on the observation data of M100.
    
        Recipe name:                procedure_hsd_calimage
        Dataset:                    uid___A002_X85c183_X36f
        """
        ref_directory = 'pl-regressiontest/uid___A002_X85c183_X36f'
    
        pt = PipelineTester(
            visname=['uid___A002_X85c183_X36f'],
            recipe='procedure_hsd_calimage.xml',
            input_dir=ref_directory,
            expectedoutput_dir=ref_directory,
            )
    
>       pt.run()

tests/regression/fast/alma_sd_fast_test.py:22: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
tests/testing_utils.py:376: in run
    self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <tests.testing_utils.PipelineTester object at 0x7fe12ea1e990>
new_file = 'uid___A002_X85c183_X36f.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               s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags
E               	values differ by > a relative difference of 1e-07
E               	expected: 0.9579857010836426
E               	new:      1.0
E               	diff: -0.04201429891635744
E               	percent_diff: -4.38569165164284%
E               Worst absolute diff, s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags: -0.04201429891635744
E               Worst percentage diff, s7.hsd_applycal.uid___A002_X85c183_X36f.qa.score.ApplycalFlags: -4.38569165164284%

tests/testing_utils.py:435: Failed