def _job_candidates_options(candidates):
for jobid, remset in iteritems(candidates):
setup = job_params(jobid)
optdiff = defaultdict(dict)
for thing in remset:
section, name = thing.split('-', 1)
optdiff[section][name] = setup[section][name]
yield jobid, optdiff
def csvexport(sliceno, filename, labelsonfirstline):
assert len(options.separator) == 1
assert options.quote_fields in ('', "'", '"',)
d = datasets.source[0]
if not options.labels:
options.labels = sorted(d.columns)
if options.chain_source:
if jobids.previous:
prev_source = job_params(jobids.previous).datasets.source
assert len(datasets.source) == len(prev_source)
else:
prev_source = [None] * len(datasets.source)
lst = []
for src, stop in zip(datasets.source, prev_source):
lst.extend(src.chain(stop_ds=stop))
datasets.source = lst
if filename.lower().endswith('.gz'):
mkwrite = mkwrite_gz
elif filename.lower().endswith('.csv'):
mkwrite = mkwrite_uncompressed
else:
raise Exception("Filename should end with .gz for compressed or .csv for uncompressed")
iters = []
first = True
for label in options.labels:
it = d.iterate_list(sliceno, label, datasets.source, status_reporting=first)
first = False
t = d.columns[label].type
if t == 'unicode' and PY2:
it = imap(enc, it)
elif t == 'bytes' and PY3:
it = imap(lambda s: s.decode('utf-8', errors='backslashreplace'), it)
elif t in ('float32', 'float64', 'number'):
it = imap(repr, it)
elif t == 'json':
it = imap(dumps, it)
elif t not in ('unicode', 'ascii', 'bytes'):
it = imap(str, it)
iters.append(it)
it = izip(*iters)
with mkwrite(filename) as write:
q = options.quote_fields
sep = options.separator
if q:
qq = q + q
if labelsonfirstline:
write(enc(sep.join(q + n.replace(q, qq) + q for n in options.labels)))
for data in it:
write(sep.join(q + n.replace(q, qq) + q for n in data))
else:
if labelsonfirstline:
write(enc(sep.join(options.labels)))
for data in it:
write(sep.join(data))
def params(self):
from accelerator.extras import job_params
return job_params(self)
def execute_process(workdir,
jobid,
slices,
concurrency,
result_directory,
common_directory,
input_directory,
index=None,
workdirs=None,
server_url=None,
subjob_cookie=None,
parent_pid=0):
WORKDIRS.update(workdirs)
g.job = jobid
setproctitle('launch')
path = os.path.join(workdir, jobid)
try:
os.chdir(path)
except Exception:
print("Cannot cd to workdir", path)
exit(1)
g.params = params = job_params()
method_ref = import_module(params.package + '.a_' + params.method)
g.sliceno = -1
g.job = CurrentJob(jobid, params, result_directory, input_directory)
g.slices = slices
g.options = params.options
g.datasets = params.datasets
g.jobs = params.jobs
method_ref.options = params.options
method_ref.datasets = params.datasets
method_ref.jobs = params.jobs
g.server_url = server_url
g.running = 'launch'
statmsg._start('%s %s' % (
jobid,
params.method,
), parent_pid)
def dummy():
pass
prepare_func = getattr(method_ref, 'prepare', dummy)
analysis_func = getattr(method_ref, 'analysis', dummy)
synthesis_func = getattr(method_ref, 'synthesis', dummy)
synthesis_needs_analysis = 'analysis_res' in getarglist(synthesis_func)
fd2pid, names, masters, slaves = iowrapper.setup(
slices, prepare_func is not dummy, analysis_func is not dummy)
def switch_output():
fd = slaves.pop()
os.dup2(fd, 1)
os.dup2(fd, 2)
os.close(fd)
if analysis_func is dummy:
q = None
else:
q = LockFreeQueue()
iowrapper.run_reader(fd2pid, names, masters, slaves, q=q)
for fd in masters:
os.close(fd)
# A chain must be finished from the back, so sort on that.
sortnum_cache = {}
def dw_sortnum(name):
if name not in sortnum_cache:
dw = dataset._datasetwriters.get(name)
if not dw: # manually .finish()ed
num = -1
elif dw.previous and dw.previous.startswith(jobid + '/'):
pname = dw.previous.split('/')[1]
num = dw_sortnum(pname) + 1
else:
num = 0
sortnum_cache[name] = num
return sortnum_cache[name]
prof = {}
if prepare_func is dummy:
prof['prepare'] = 0 # truthish!
else:
t = monotonic()
switch_output()
g.running = 'prepare'
g.subjob_cookie = subjob_cookie
setproctitle(g.running)
with statmsg.status(g.running):
g.prepare_res = method_ref.prepare(**args_for(method_ref.prepare))
to_finish = [
dw.name for dw in dataset._datasetwriters.values()
if dw._started
]
if to_finish:
with statmsg.status("Finishing datasets"):
for name in sorted(to_finish, key=dw_sortnum):
dataset._datasetwriters[name].finish()
c_fflush()
prof['prepare'] = monotonic() - t
switch_output()
setproctitle('launch')
from accelerator.extras import saved_files
if analysis_func is dummy:
prof['per_slice'] = []
prof['analysis'] = 0
else:
t = monotonic()
g.running = 'analysis'
g.subjob_cookie = None # subjobs are not allowed from analysis
with statmsg.status(
'Waiting for all slices to finish analysis') as update:
g.update_top_status = update
prof['per_slice'], files, g.analysis_res = fork_analysis(
slices, concurrency, analysis_func, args_for(analysis_func),
synthesis_needs_analysis, slaves, q)
del g.update_top_status
prof['analysis'] = monotonic() - t
saved_files.update(files)
t = monotonic()
g.running = 'synthesis'
g.subjob_cookie = subjob_cookie
setproctitle(g.running)
with statmsg.status(g.running):
synthesis_res = synthesis_func(**args_for(synthesis_func))
if synthesis_res is not None:
blob.save(synthesis_res, temp=False)
if dataset._datasetwriters:
with statmsg.status("Finishing datasets"):
for name in sorted(dataset._datasetwriters, key=dw_sortnum):
dataset._datasetwriters[name].finish()
if dataset._datasets_written:
blob.save(dataset._datasets_written,
'DS/LIST',
temp=False,
_hidden=True)
c_fflush()
t = monotonic() - t
prof['synthesis'] = t
from accelerator.subjobs import _record
return None, (prof, saved_files, _record)
