Build: #5 failed
Job: Test ManyLinux 2.28 Python 3.12 failed
13a 537 calibration PPr regression: Test case result
The below summarizes the result of the test " 13a 537 calibration PPr regression" in build 5 of PIPESPECS - Test Pipeline 2026.2.0 with Casa 6.7.4 - Test ManyLinux 2.28 Python 3.12.
- Description
- 13a 537 calibration PPr regression
- Test class
- tests.regression.fast.vla_fast_test
- Method
- test_13A_537__calibration__PPR__regression
- Duration
- 58 mins
- Status
- Failed (Existing Failure)
Error Log
def test_13A_537__calibration__PPR__regression():
"""Run VLA calibration regression with a PPR file.
PPR name: PPR_13A-537.xml
Dataset: 13A-537/13A-537.sb24066356.eb24324502.56514.05971091435
"""
ref_directory = 'pl-regressiontest/13A-537'
pt = PipelineTester(
visname=['13A-537.sb24066356.eb24324502.56514.05971091435'],
ppr=f'{ref_directory}/PPR_13A-537.xml',
input_dir=ref_directory,
output_dir='13A_537__calibration__PPR__regression',
expectedoutput_dir=ref_directory,
)
> pt.run(telescope='vla', omp_num_threads=1)
tests/regression/fast/vla_fast_test.py:44:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/testing_utils.py:381: in run
self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <tests.testing_utils.PipelineTester object at 0x7f8c0c8cc950>
new_file = '13A-537.sb24066356.eb24324502.56514.05971091435.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 23 result values within tolerances :
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 15177530
E new: 15178722
E diff: -1192
E percent_diff: -0.007853715327856378%
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s12.hifv_fluxboot.13A-537.sb24066356.eb24324502.56514.05971091435.flux_densities.spw_0
E values differ by > a relative difference of 1e-07
E expected: 0.7150110854670872
E new: 0.7155464779221782
E diff: -0.0005353924550909328
E percent_diff: -0.07487890271535902%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 48816980
E new: 48818190
E diff: -1210
E percent_diff: -0.0024786457499009567%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 48585576
E new: 48586786
E diff: -1210
E percent_diff: -0.002490451075438521%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 29069288
E new: 29070644
E diff: -1356
E percent_diff: -0.004664716934243454%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_5.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 9126980
E new: 9128895
E diff: -1915
E percent_diff: -0.020981748617834157%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_6.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7154975
E new: 7155295
E diff: -320
E percent_diff: -0.004472412552105353%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_7.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7755397
E new: 7754518
E diff: 879
E percent_diff: 0.011334042602848055%
E s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.mean
E values differ by > a relative difference of 1e-07
E expected: 0.6294082667176586
E new: 0.6287803138560883
E diff: 0.0006279528615702468
E percent_diff: 0.09976876612139182%
E s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.variance
E values differ by > a relative difference of 1e-07
E expected: 0.06275781189517324
E new: 0.06260783041816648
E diff: 0.0001499814770067609
E percent_diff: 0.23898455423729667%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 14429430
E new: 14429448
E diff: -18
E percent_diff: -0.00012474505229936316%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E Worst absolute diff, s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_5.num_rows_flagged.after: -1915
E Worst percentage diff, s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.variance: 0.23898455423729667%
tests/testing_utils.py:440: Failed
def test_13A_537__calibration__PPR__regression():
"""Run VLA calibration regression with a PPR file.
PPR name: PPR_13A-537.xml
Dataset: 13A-537/13A-537.sb24066356.eb24324502.56514.05971091435
"""
ref_directory = 'pl-regressiontest/13A-537'
pt = PipelineTester(
visname=['13A-537.sb24066356.eb24324502.56514.05971091435'],
ppr=f'{ref_directory}/PPR_13A-537.xml',
input_dir=ref_directory,
output_dir='13A_537__calibration__PPR__regression',
expectedoutput_dir=ref_directory,
)
> pt.run(telescope='vla', omp_num_threads=1)
tests/regression/fast/vla_fast_test.py:44:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tests/testing_utils.py:381: in run
self.__compare_results(new_file, default_relative_tolerance)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <tests.testing_utils.PipelineTester object at 0x7f8c0c8cc950>
new_file = '13A-537.sb24066356.eb24324502.56514.05971091435.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 23 result values within tolerances :
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 15177530
E new: 15178722
E diff: -1192
E percent_diff: -0.007853715327856378%
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s10.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s12.hifv_fluxboot.13A-537.sb24066356.eb24324502.56514.05971091435.flux_densities.spw_0
E values differ by > a relative difference of 1e-07
E expected: 0.7150110854670872
E new: 0.7155464779221782
E diff: -0.0005353924550909328
E percent_diff: -0.07487890271535902%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 48816980
E new: 48818190
E diff: -1210
E percent_diff: -0.0024786457499009567%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 48585576
E new: 48586786
E diff: -1210
E percent_diff: -0.002490451075438521%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_4.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 11498686
E new: 11499264
E diff: -578
E percent_diff: -0.005026661307213711%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s14.hifv_applycals.13A-537.sb24066356.eb24324502.56514.05971091435.scan_8.num_rows_flagged.before
E values differ by > a relative difference of 1e-07
E expected: 3678844
E new: 3679458
E diff: -614
E percent_diff: -0.01669002545364794%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 29069288
E new: 29070644
E diff: -1356
E percent_diff: -0.004664716934243454%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_5.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 9126980
E new: 9128895
E diff: -1915
E percent_diff: -0.020981748617834157%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_6.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7154975
E new: 7155295
E diff: -320
E percent_diff: -0.004472412552105353%
E s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_7.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7755397
E new: 7754518
E diff: 879
E percent_diff: 0.011334042602848055%
E s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.mean
E values differ by > a relative difference of 1e-07
E expected: 0.6294082667176586
E new: 0.6287803138560883
E diff: 0.0006279528615702468
E percent_diff: 0.09976876612139182%
E s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.variance
E values differ by > a relative difference of 1e-07
E expected: 0.06275781189517324
E new: 0.06260783041816648
E diff: 0.0001499814770067609
E percent_diff: 0.23898455423729667%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 14429430
E new: 14429448
E diff: -18
E percent_diff: -0.00012474505229936316%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_2.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 7526960
E new: 7526980
E diff: -20
E percent_diff: -0.00026571152231445364%
E s8.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_3.num_rows_flagged.after
E values differ by > a relative difference of 1e-07
E expected: 6902470
E new: 6902468
E diff: 2
E percent_diff: 2.897513498791012e-05%
E Worst absolute diff, s15.hifv_checkflag.13A-537.sb24066356.eb24324502.56514.05971091435.scan_5.num_rows_flagged.after: -1915
E Worst percentage diff, s16.hifv_statwt.13A-537.sb24066356.eb24324502.56514.05971091435.variance: 0.23898455423729667%
tests/testing_utils.py:440: Failed