def worker_func(func_file_id):
# Have the output File expire in 7 days.
expires_at = (datetime.now() + timedelta(days=7)).isoformat()
client = civis.APIClient()
job_id = os.environ.get('CIVIS_JOB_ID')
run_id = os.environ.get('CIVIS_RUN_ID')
if not job_id or not run_id:
raise RuntimeError("This function must be run inside a "
"Civis container job.")
# Run the function.
result = None
try:
func, remote_backend = _robust_pickle_download(
func_file_id, client=client, n_retries=5, delay=0.5)
_backend = _setup_remote_backend(remote_backend)
# graceful nested context managers are ~hard across python versions,
# this just works...
if NO_SKLEARN:
with _joblib_para_backend(_backend):
result = func()
else:
# we are using the nested context managers to set the joblib
# backend to the requested one in both copes of joblib, the
# package and the copy shipped by sklearn at
# `sklearn.externals.joblib`. joblib maintains the current
# backend as global state in the package and thus there are
# two backends to set when you have two copies of the package
# in play.
with _sklearn_para_backend(_backend):
with _joblib_para_backend(_backend):
result = func()
except Exception:
print("Error! Attempting to record exception.")
# Wrap the exception in joblib's TransportableException
# so that joblib can properly display the results.
e_type, e_value, e_tb = sys.exc_info()
text = format_exc(e_type, e_value, e_tb, context=10, tb_offset=1)
result = TransportableException(text, e_type)
raise
finally:
# Serialize the result and upload it to the Files API.
if result is not None:
# If the function exits without erroring, we may not have a result.
result_buffer = BytesIO()
cloudpickle.dump(result, result_buffer, pickle.HIGHEST_PROTOCOL)
result_buffer.seek(0)
output_name = "Results from Joblib job {} / run {}".format(job_id,
run_id)
output_file_id = _robust_file_to_civis(result_buffer, output_name,
n_retries=5, delay=0.5,
expires_at=expires_at,
client=client)
client.scripts.post_containers_runs_outputs(job_id, run_id,
'File', output_file_id)
print("Results output to file ID: {}".format(output_file_id))
def test_format_exc_with_compiled_code():
# Trying to tokenize compiled C code raise SyntaxError.
# See https://github.com/joblib/joblib/issues/101 for more details.
try:
np.random.uniform('invalid_value')
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
formatted_exc = format_exc(exc_type, exc_value,
exc_traceback, context=10)
# The name of the extension can be something like
# mtrand.cpython-33m.so
pattern = 'mtrand[a-z0-9.-]*\.(so|pyd)'
assert_true(re.search(pattern, formatted_exc))
def test_format_exc_with_compiled_code():
# Trying to tokenize compiled C code raise SyntaxError.
# See https://github.com/joblib/joblib/issues/101 for more details.
try:
np.random.uniform('invalid_value')
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
formatted_exc = format_exc(exc_type, exc_value,
exc_traceback, context=10)
# The name of the extension can be something like
# mtrand.cpython-33m.so
pattern = r'mtrand[a-z0-9._-]*\.(so|pyd)'
assert re.search(pattern, formatted_exc)
def worker_func(func_file_id):
# Have the output File expire in 7 days.
expires_at = (datetime.now() + timedelta(days=7)).isoformat()
client = civis.APIClient()
job_id = os.environ.get('CIVIS_JOB_ID')
run_id = os.environ.get('CIVIS_RUN_ID')
if not job_id or not run_id:
raise RuntimeError("This function must be run inside a "
"Civis container job.")
func_buffer = BytesIO()
civis.io.civis_to_file(func_file_id, func_buffer)
func_buffer.seek(0)
func = joblib.load(func_buffer)
# Run the function.
result = None
try:
result = func()
except Exception:
print("Error! Attempting to record exception.")
# Wrap the exception in joblib's TransportableException
# so that joblib can properly display the results.
e_type, e_value, e_tb = sys.exc_info()
text = format_exc(e_type, e_value, e_tb, context=10, tb_offset=1)
result = TransportableException(text, e_type)
raise
finally:
# Serialize the result and upload it to the Files API.
# Note that if compress is 0, joblib will output multiple files.
# compress=3 is a good compromise between space and read/write times
# (https://github.com/joblib/joblib/blob/18f9b4ce95e8788cc0e9b5106fc22573d768c44b/joblib/numpy_pickle.py#L358).
if result is not None:
# If the function exits without erroring, we may not have a result.
result_buffer = BytesIO()
joblib.dump(result, result_buffer, compress=3)
result_buffer.seek(0)
output_name = "Results from Joblib job {} / run {}".format(
job_id, run_id)
output_file_id = civis.io.file_to_civis(result_buffer,
output_name,
expires_at=expires_at)
client.scripts.post_containers_runs_outputs(
job_id, run_id, 'File', output_file_id)
print("Results output to file ID: {}".format(
output_name, output_file_id))
