Build: #99 failed
Job: Test ManyLinux 2.28 Python 3.12 failed
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 99 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
- 616 mins
- Status
- Failed (New Failure)
Error Log
@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:142:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/testing_utils.py:381: in run
self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <tests.testing_utils.PipelineTester object at 0x7f29a8af9010>
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 6 result values within tolerances :
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 249574780
E new: 249563260
E diff: 11520
E percent_diff: 0.004615851008663616%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1958304
E new: 1935264
E diff: 23040
E percent_diff: 1.176528261189274%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_13.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1736584
E new: 1716424
E diff: 20160
E percent_diff: 1.1608997894717445%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_15.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1755616
E new: 1775776
E diff: -20160
E percent_diff: -1.148314893461896%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_9.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1861520
E new: 1873040
E diff: -11520
E percent_diff: -0.6188491125531823%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.spw_31.qa.metric.phase_vs_freqslope
E values differ by > a relative difference of 1e-07
E expected: 46.569797759406356
E new: 46.56980701614873
E diff: -9.256742373509041e-06
E percent_diff: -1.9877136725678237e-05%
E Worst absolute diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after: 23040
E Worst percentage diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after: 1.176528261189274%
tests/testing_utils.py:440: Failed
@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:142:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/testing_utils.py:381: in run
self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <tests.testing_utils.PipelineTester object at 0x7f29a8af9010>
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 6 result values within tolerances :
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 249574780
E new: 249563260
E diff: 11520
E percent_diff: 0.004615851008663616%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1958304
E new: 1935264
E diff: 23040
E percent_diff: 1.176528261189274%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_13.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1736584
E new: 1716424
E diff: 20160
E percent_diff: 1.1608997894717445%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_15.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1755616
E new: 1775776
E diff: -20160
E percent_diff: -1.148314893461896%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_9.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 1861520
E new: 1873040
E diff: -11520
E percent_diff: -0.6188491125531823%
E s21.hif_applycal.uid___A002_X1199f9e_X7c24.spw_31.qa.metric.phase_vs_freqslope
E values differ by > a relative difference of 1e-07
E expected: 46.569797759406356
E new: 46.56980701614873
E diff: -9.256742373509041e-06
E percent_diff: -1.9877136725678237e-05%
E Worst absolute diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after: 23040
E Worst percentage diff, s21.hif_applycal.uid___A002_X1199f9e_X7c24.scan_11.num_rows_flagged.after: 1.176528261189274%
tests/testing_utils.py:440: Failed