def run(self, **kwargs):
logger.progress((4, "Starting tasks"))
self.result = self.start_tasks(**kwargs)
if self.result is None:
raise BaseDataControllerError("Not all tasks started! Exiting.")
# Store results in hdf5 file for processing later
output_h5_file = None
if kwargs.get('output_path') is not None:
output_h5_file = os.path.join(kwargs.get('output_path'),
'results.h5')
if self.thread_result_listener is True:
rl = threading.Thread(name="ResultListener",
target=self.listen_for_results,
args=(output_h5_file,
self.total_particle_count()))
rl.daemon = True
rl.start()
rl.join() # This blocks until the tasks are all done.
else:
self.listen_for_results(output_h5_file, self.total_particle_count(
)) # This blocks until the tasks are all done.
logger.info('Tasks are all finished... Cleaning up!!')
self.cleanup()
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
logger.progress((96, "Exporting results"))
# Make sure output_path is also included
if kwargs.get("output_path", None) is not None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for fmt in formats:
logger.info("Exporting to: %s" % fmt)
try:
# Calls the export function
fmt.export(output_path, output_h5_file)
except:
logger.exception("Failed to export to: %s" % fmt)
else:
logger.warn(
'The output_formats parameter should be a list, not saving any output!'
)
else:
logger.warn('No output path defined, not saving any output!')
else:
logger.warn(
'No output_formats parameter was defined, not saving any output!'
)
logger.progress((97, "Model Run Complete"))
return
def start_tasks(self, **kwargs):
try:
logger.info('Adding %i particles as tasks' % self.total_particle_count())
tasks = []
for part in self.particles:
forcer = BaseForcer(self.hydrodataset,
particle=part,
common_variables=self.common_variables,
timevar=self.timevar,
times=self.times,
start_time=self.start,
models=self._models,
release_location_centroid=self.reference_location.point,
usebathy=self._use_bathymetry,
useshore=self._use_shoreline,
usesurface=self._use_seasurface,
reverse_distance=self.reverse_distance,
bathy_path=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
time_method=self.time_method,
shoreline_index_buffer=self.shoreline_index_buffer)
tasks.append(forcer)
logger.progress((5, 'Running model'))
return self.pool.map_async(Runner(), tasks)
except Exception:
logger.exception("Something didn't start correctly!")
raise
def fill_polygon_with_points(cls, goal=None, polygon=None):
"""
Fill a shapely polygon with X number of points
"""
if goal is None:
raise ValueError("Must specify the number of points (goal) to fill the polygon with")
if polygon is None or (not isinstance(polygon, Polygon) and not isinstance(polygon, MultiPolygon)):
raise ValueError("Must specify a polygon to fill points with")
minx = polygon.bounds[0]
maxx = polygon.bounds[2]
miny = polygon.bounds[1]
maxy = polygon.bounds[3]
points = []
now = time.time()
while len(points) < goal:
random_x = random.uniform(minx, maxx)
random_y = random.uniform(miny, maxy)
p = Point(random_x, random_y)
if p.within(polygon):
points.append(p)
logger.info("Filling polygon with points took %f seconds" % (time.time() - now))
return points
def listen_for_logs():
pubsub = r.pubsub()
pubsub.subscribe("%s:log" % run_id)
for msg in pubsub.listen():
if msg['type'] != "message":
continue
if msg["data"] == "FINISHED":
break
try:
prog = json.loads(msg["data"])
if prog is not None:
if prog.get("level", "").lower() == "progress":
job.meta["progress"] = float(prog.get("value", job.meta.get("progress", None)))
job.meta["message"] = prog.get("message", job.meta.get("message", ""))
job.meta["updated"] = prog.get("time", datetime.utcnow().replace(tzinfo=pytz.utc).astimezone(pytz.utc))
job.save()
logger.info("PROGRESS: %(value).2f - %(message)s" % prog)
else:
getattr(logger, prog["level"].lower())(prog.get("message"))
except Exception:
logger.info("Got strange result: %s" % msg["data"])
pass
pubsub.close()
sys.exit()
def listen_for_results(output_h5_file, total_particles):
# Create output file (hdf5)
particles_finished = 0
results = ResultsPyTable(output_h5_file)
pubsub = r.pubsub()
pubsub.subscribe("%s:results" % run_id)
for msg in pubsub.listen():
if msg['type'] != "message":
continue
if msg["data"] == "FINISHED":
break
try:
json_msg = json.loads(msg["data"])
if json_msg.get("status", None):
# "COMPLETED" or "FAILED" when a particle finishes
particles_finished += 1
percent_complete = 90. * (float(particles_finished) / float(total_particles)) + 5 # Add the 5 progress that was used prior to the particles starting (controller)
r.publish("%s:log" % run_id, json.dumps({"time" : datetime.utcnow().isoformat(), "level" : "progress", "value" : percent_complete, "message" : "Particle #%s %s!" % (particles_finished, json_msg.get("status"))}))
if particles_finished == total_particles:
break
else:
# Write to HDF file
results.write(json_msg)
except Exception:
logger.info("Got strange result: %s" % msg["data"])
pass
pubsub.close()
results.compute()
results.close()
sys.exit()
def run(self):
while True:
try:
next_task = self.task_queue.get(True, 10)
except queue.Empty:
logger.info("No tasks left to complete, closing %s" % self.name)
break
else:
answer = (None, None)
try:
answer = (1, next_task(self.active))
except Exception:
logger.exception("Disabling Error")
if isinstance(next_task, CachingDataController):
answer = (-2, "CachingDataController")
# Tell the particles that the CachingDataController is releasing file
self.get_data.value = False
# The data controller has died, so don't process any more tasks
self.active.value = False
elif isinstance(next_task, BaseForcer):
answer = (-1, next_task.particle)
else:
logger.warn("Strange task raised an exception: %s" % str(next_task.__class__))
answer = (None, None)
finally:
self.result_queue.put(answer)
self.nproc_lock.acquire()
self.n_run.value = self.n_run.value - 1
self.nproc_lock.release()
self.task_queue.task_done()
def listen_for_results(self, output_h5_file, total_particles):
logger.info("Waiting for %i particle results" % total_particles)
particles = []
retrieved = 0
timeout = 200
while retrieved < total_particles:
try:
# self.result is an iterator that can timeout on next()
particle = self.result.next(timeout)
retrieved += 1
particles.append(particle)
except StopIteration:
assert retrieved >= total_particles
break
except:
logger.exception("Particle has FAILED!!")
continue
# We multiply by 90 here to save 10% for the exporting
logger.progress((round((float(retrieved) / total_particles) * 90., 1), "%s Particle(s) complete" % retrieved))
logger.info(particles)
results = ex.ResultsPyTable(output_h5_file)
for p in particles:
for x in range(len(p.locations)):
results.write(p.timestep_index_dump(x))
results.compute()
results.close()
return
def listen_for_results(self, output_h5_file, total_particles):
logger.info("Waiting for %i particle results" % total_particles)
particles = []
retrieved = 0
timeout = 200
while retrieved < total_particles:
try:
# self.result is an iterator that can timeout on next()
particle = self.result.next(timeout)
retrieved += 1
particles.append(particle)
except StopIteration:
assert retrieved >= total_particles
break
except:
logger.exception("Particle has FAILED!!")
continue
# We multiply by 90 here to save 10% for the exporting
logger.progress((round((float(retrieved) / total_particles) * 90.,
1), "%s Particle(s) complete" % retrieved))
logger.info(particles)
results = ex.ResultsPyTable(output_h5_file)
for p in particles:
for x in range(len(p.locations)):
results.write(p.timestep_index_dump(x))
results.compute()
results.close()
return
def __call__(self, active):
if active.value is True:
while self.get_data.value is True:
logger.info("Waiting for DataController to start...")
timer.sleep(5)
pass
return super(CachingForcer, self).__call__(active)
def __call__(self, active):
if active.value is True:
while self.get_data.value is True:
logger.info("Waiting for DataController to start...")
timer.sleep(5)
pass
return super(CachingForcer, self).__call__(active)
def run(self, **kwargs):
logger.progress((4, "Starting tasks"))
self.result = self.start_tasks(**kwargs)
if self.result is None:
raise BaseDataControllerError("Not all tasks started! Exiting.")
# Store results in hdf5 file for processing later
output_h5_file = None
if kwargs.get('output_path') is not None:
output_h5_file = os.path.join(kwargs.get('output_path'), 'results.h5')
if self.thread_result_listener is True:
rl = threading.Thread(name="ResultListener", target=self.listen_for_results, args=(output_h5_file, self.total_particle_count()))
rl.daemon = True
rl.start()
rl.join() # This blocks until the tasks are all done.
else:
self.listen_for_results(output_h5_file, self.total_particle_count()) # This blocks until the tasks are all done.
logger.info('Tasks are all finished... Cleaning up!!')
self.cleanup()
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
logger.progress((96, "Exporting results"))
# Make sure output_path is also included
if kwargs.get("output_path", None) is not None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for fmt in formats:
logger.info("Exporting to: %s" % fmt)
try:
# Calls the export function
fmt.export(output_path, output_h5_file)
except:
logger.exception("Failed to export to: %s" % fmt)
else:
logger.warn('The output_formats parameter should be a list, not saving any output!')
else:
logger.warn('No output path defined, not saving any output!')
else:
logger.warn('No output_formats parameter was defined, not saving any output!')
logger.progress((97, "Model Run Complete"))
return
def attempt(self, particle, depth):
# We may want to have settlement affect the u/v/w in the future
u = 0
v = 0
w = 0
# If the particle is settled, don't move it anywhere
if particle.settled:
return (0, 0, 0)
# A particle is negative down from the sea surface, so "-3" is 3 meters below the surface.
# We are assuming here that the bathymetry is also negative down.
if self.type.lower() == "benthic":
# Is the sea floor within the upper and lower bounds?
if self.upper >= depth >= self.lower:
# Move the particle to the sea floor.
# TODO: Should the particle just swim downwards?
newloc = Location4D(location=particle.location)
newloc.depth = depth
particle.location = newloc
particle.settle()
logger.info("Particle %d settled in %s mode" %
(particle.uid, self.type))
elif self.type.lower() == "pelagic":
# Are we are in enough water to settle
# Ignore this bathymetry test since we would need a high resolution
# dataset for this to work.
#if self.upper >= depth:
# Is the particle within the range?
if self.upper >= particle.location.depth >= self.lower:
# Just settle the particle
particle.settle()
logger.info("Particle %d settled in %s mode" %
(particle.uid, self.type))
else:
logger.debug(
"Particle did NOT settle. Depth conditions not met. Upper limit: %d - Lower limit: %d - Particle: %d"
% (self.upper, self.lower, particle.location.depth))
#else:
# logger.info("Particle did NOT settle. Water not deep enough. Upper limit: %d - Bathymetry: %d" % (self.upper, depth))
else:
logger.warn(
"Settlement type %s not recognized, not trying to settle Particle %d."
% (self.type, particle.uid))
return (u, v, w)
def setup_run(self, **kwargs):
super(CachingModelController, self).setup_run(**kwargs)
# Should we remove the cache file at the end of the run?
self.remove_cache = kwargs.get("remove_cache", False)
self.cache_path = kwargs.get("cache_path", None)
# Create a temp file for the cache if nothing was passed in
if self.cache_path is None:
default_cache_dir = os.path.join(os.path.dirname(__file__), "_cache")
temp_name = AsaRandom.filename(prefix=str(datetime.now().microsecond), suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
# Be sure the cache directory exists
if not os.path.exists(os.path.dirname(self.cache_path)):
logger.info("Creating cache directory: %s" % self.cache_path)
os.makedirs(os.path.dirname(self.cache_path))
# Create the shared state objects
# Particles use this to tell the Data Controller to "get_data".
# The CachingDataController sets this to False when it is done writing to the cache file.
# Particles will wait for this to be False before reading from the cache file.
# If we are caching, this starts as True so the Particles don't take off. If we
# are not caching, this is False so the Particles can start immediatly.
self.get_data = self.mgr.Value('bool', True)
# Particles use this to tell the DataContoller which indices to 'get_data' for
self.point_get = self.mgr.Value('list', [0, 0, 0])
# This locks access to the 'has_data_request_lock' value
self.data_request_lock = self.mgr.Lock()
# This tracks which Particle PID is asking the CachingDataController for data
self.has_data_request_lock = self.mgr.Value('int', -1)
# The lock that controls access to modifying 'has_read_lock' and 'read_count'
self.read_lock = self.mgr.Lock()
# List of Particle PIDs that are reading from the cache
self.has_read_lock = self.mgr.list()
# The number of Particles that are reading from the cache
self.read_count = self.mgr.Value('int', 0)
# When something is writing to the cache file
self.write_lock = self.mgr.Lock()
# PID of process with lock
self.has_write_lock = self.mgr.Value('int', -1)
def start_tasks(self):
# @TODO: this is more initialization, but need to prevent derived classes from doing this
if self.pool is None:
self.pool = multiprocessing.Pool()
try:
logger.info('Adding %i particles as tasks' % len(self.particles))
tasks = []
for part in self.particles:
forcer = BaseForcer(self.hydrodataset,
particle=part,
common_variables=self.common_variables,
timevar=self.timevar,
times=self.times,
start_time=self.start,
models=self._models,
release_location_centroid=self.reference_location.point,
usebathy=self._use_bathymetry,
useshore=self._use_shoreline,
usesurface=self._use_seasurface,
reverse_distance=self.reverse_distance,
bathy_path=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
time_method=self.time_method,
redis_url=self.redis_url,
redis_results_channel=self.redis_results_channel,
shoreline_index_buffer=self.shoreline_index_buffer)
tasks.append(forcer)
# @TODO: better mechanism than switching on type
if isinstance(self.pool, multiprocessing.pool.Pool):
aiter = self.pool.imap(Runner(), tasks)
else:
# IPython parallel View
aiter = self.pool.map_async(Runner(), tasks)
return aiter
except Exception:
logger.exception("Something didn't start correctly!")
raise
def attempt(self, particle, depth):
# We may want to have settlement affect the u/v/w in the future
u = 0
v = 0
w = 0
# If the particle is settled, don't move it anywhere
if particle.settled:
return (0,0,0)
# A particle is negative down from the sea surface, so "-3" is 3 meters below the surface.
# We are assuming here that the bathymetry is also negative down.
if self.type.lower() == "benthic":
# Is the sea floor within the upper and lower bounds?
if self.upper >= depth >= self.lower:
# Move the particle to the sea floor.
# TODO: Should the particle just swim downwards?
newloc = Location4D(location=particle.location)
newloc.depth = depth
particle.location = newloc
particle.settle()
logger.info("Particle %d settled in %s mode" % (particle.uid, self.type))
elif self.type.lower() == "pelagic":
# Are we are in enough water to settle
# Ignore this bathymetry test since we would need a high resolution
# dataset for this to work.
#if self.upper >= depth:
# Is the particle within the range?
if self.upper >= particle.location.depth >= self.lower:
# Just settle the particle
particle.settle()
logger.info("Particle %d settled in %s mode" % (particle.uid, self.type))
else:
logger.debug("Particle did NOT settle. Depth conditions not met. Upper limit: %d - Lower limit: %d - Particle: %d" % (self.upper, self.lower, particle.location.depth))
#else:
# logger.info("Particle did NOT settle. Water not deep enough. Upper limit: %d - Bathymetry: %d" % (self.upper, depth))
else:
logger.warn("Settlement type %s not recognized, not trying to settle Particle %d." % (self.type, particle.uid))
return (u,v,w)
def listen_for_results(self):
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
particles = []
retrieved = 0
timeout = 200
while retrieved < len(self.particles):
try:
# @TODO: better mechanism than switching on type
if isinstance(self.pool, multiprocessing.pool.Pool):
# self.result is an iterator that can timeout on next()
particle = self.result.next(timeout)
retrieved += 1
particles.append(particle)
else:
# IPython parallel View
# self.result is an AsyncMapResult
from IPython.parallel import TimeoutError
try:
new_particles = self.result.get(timeout=1)
except TimeoutError:
pass # this is fine, get incremental progress below
else:
particles = new_particles
# progress is absolute, not incremental
retrieved = self.result.progress
except StopIteration:
assert retrieved >= len(self.particles)
break
except:
logger.exception("Particle has FAILED!!")
#logger.warn("Particle %s has FAILED!!" % particle.uid)
continue
# We multiply by 95 here to save 5% for the exporting
logger.progress((round((float(retrieved) / self.number_of_tasks) * 90., 1), "%s Particle(s) complete" % retrieved))
return particles
def listen_for_results(self, output_h5_file, total_particles):
logger.info("Waiting for %i particle results" % total_particles)
particles = []
retrieved = 0
while retrieved < total_particles:
try:
# IPython parallel View
# self.result is an AsyncMapResult
from IPython.parallel import TimeoutError
try:
new_particles = self.result.get(timeout=1)
except TimeoutError:
pass # this is fine, get incremental progress below
else:
particles = new_particles
# progress is absolute, not incremental
retrieved = self.result.progress
except StopIteration:
assert retrieved >= total_particles
break
except:
logger.exception("Particle has FAILED!!")
continue
# We multiply by 90 here to save 10% for the exporting
logger.progress((round((float(retrieved) / total_particles) * 90., 1), "%s Particle(s) complete" % retrieved))
results = ex.ResultsPyTable(output_h5_file)
for p in particles:
for x in range(len(p.locations)):
results.write(p.timestep_index_dump(x))
results.compute()
results.close()
return
def start_tasks(self):
try:
logger.info('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcer = BaseForcer(self.hydrodataset,
particle=part,
common_variables=self.common_variables,
timevar=self.timevar,
times=self.times,
start_time=self.start,
models=self._models,
release_location_centroid=self.reference_location.point,
usebathy=self._use_bathymetry,
useshore=self._use_shoreline,
usesurface=self._use_seasurface,
reverse_distance=self.reverse_distance,
bathy_path=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
time_method=self.time_method,
redis_url=self.redis_url,
redis_results_channel=self.redis_results_channel,
shoreline_index_buffer=self.shoreline_index_buffer
)
self.tasks.put(forcer)
# Create workers for the particles.
self.procs = [ Consumer(self.tasks, self.results, self.n_run, self.nproc_lock, self.active, None, name="BaseForcer-%d" % i)
for i in xrange(self.nproc - 1) ]
for w in self.procs:
w.start()
logger.info('Started %s' % w.name)
return True
except Exception:
logger.exception("Something didn't start correctly!")
return False
def run(self):
while True:
try:
next_task = self.task_queue.get(True, 10)
except Queue.Empty:
logger.info("No tasks left to complete, closing %s" % self.name)
break
else:
answer = (None, None)
try:
answer = (1, next_task(self.name, self.active))
except Exception as detail:
exc_type, exc_value, exc_traceback = sys.exc_info()
logger.error("Disabling Error: " +\
repr(traceback.format_exception(exc_type, exc_value,
exc_traceback)))
if isinstance(next_task, DataController):
answer = (-2, "DataController")
# Tell the particles that the DataController is releasing file
self.get_data.value = False
# The data controller has died, so don't process any more tasks
self.active.value = False
elif isinstance(next_task, ForceParticle):
answer = (-1, next_task.part)
else:
logger.warn("Strange task raised an exception: %s" % str(next_task.__class__))
answer = (None, None)
finally:
self.result_queue.put(answer)
self.nproc_lock.acquire()
self.n_run.value = self.n_run.value - 1
self.nproc_lock.release()
self.task_queue.task_done()
def start_tasks(self):
try:
logger.info('Starting CachingDataController')
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
data_controller = CachingDataController(self.hydrodataset, self.common_variables, self.n_run, self.get_data, self.write_lock, self.has_write_lock, self.read_lock, self.read_count,
self.time_chunk, self.horiz_chunk, self.times, self.start, self.point_get, self.reference_location, cache_path=self.cache_path)
self.tasks.put(data_controller)
# Create CachingDataController worker
self.data_controller_process = Consumer(self.tasks, self.results, self.n_run, self.nproc_lock, self.active, self.get_data, name="CachingDataController")
self.data_controller_process.start()
logger.info('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcer = CachingForcer(self.cache_path,
particle=part,
common_variables=self.common_variables,
timevar=self.timevar,
times=self.times,
start_time=self.start,
models=self._models,
release_location_centroid=self.reference_location.point,
usebathy=self._use_bathymetry,
useshore=self._use_shoreline,
usesurface=self._use_seasurface,
reverse_distance=self.reverse_distance,
bathy_path=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
time_method=self.time_method,
redis_url=self.redis_url,
redis_results_channel=self.redis_results_channel,
shoreline_index_buffer=self.shoreline_index_buffer,
get_data=self.get_data,
read_lock=self.read_lock,
has_read_lock=self.has_read_lock,
read_count=self.read_count,
point_get=self.point_get,
data_request_lock=self.data_request_lock,
has_data_request_lock=self.has_data_request_lock
)
self.tasks.put(forcer)
# Create workers for the particles.
self.procs = [Consumer(self.tasks, self.results, self.n_run, self.nproc_lock, self.active, self.get_data, name="CachingForcer-%d" % i)
for i in xrange(self.nproc - 1) ]
for w in self.procs:
w.start()
logger.info('Started %s' % w.name)
return True
except Exception:
logger.exception("Something didn't start correctly!")
return False
def run(self):
while True:
try:
next_task = self.task_queue.get(True, 10)
except queue.Empty:
logger.info("No tasks left to complete, closing %s" %
self.name)
break
else:
answer = (None, None)
try:
answer = (1, next_task(self.active))
except Exception:
logger.exception("Disabling Error")
if isinstance(next_task, CachingDataController):
answer = (-2, "CachingDataController")
# Tell the particles that the CachingDataController is releasing file
self.get_data.value = False
# The data controller has died, so don't process any more tasks
self.active.value = False
elif isinstance(next_task, BaseForcer):
answer = (-1, next_task.particle)
else:
logger.warn("Strange task raised an exception: %s" %
str(next_task.__class__))
answer = (None, None)
finally:
self.result_queue.put(answer)
self.nproc_lock.acquire()
self.n_run.value = self.n_run.value - 1
self.nproc_lock.release()
self.task_queue.task_done()
def run(self, hydrodataset, **kwargs):
self.hydrodataset = hydrodataset
self.setup_run(**kwargs)
logger.progress((4, "Starting tasks"))
self.result = self.start_tasks()
if self.result is None:
raise BaseDataControllerError("Not all tasks started! Exiting.")
# This blocks until the tasks are all done.
self.particles = self.listen_for_results()
logger.info('Consumers are all finished!')
logger.info('Cleaning up')
self.cleanup()
if len(self.particles) > 0:
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
logger.progress((96, "Exporting results"))
# Make sure output_path is also included
if kwargs.get("output_path", None) is not None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for format in formats:
logger.info("Exporting to: %s" % format)
try:
self.export(output_path, format=format)
except:
logger.exception("Failed to export to: %s" % format)
else:
logger.warn('The output_formats parameter should be a list, not saving any output!')
else:
logger.warn('No output path defined, not saving any output!')
else:
logger.warn('No output format defined, not saving any output!')
else:
logger.warn("Model didn't actually do anything, check the log.")
if self.error_code == -2:
raise BaseDataControllerError("Error in the BaseDataController")
else:
raise ModelError("Error in the model")
logger.progress((97, "Model Run Complete"))
return self.particles
def listen_for_results(self):
try:
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
self.error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < self.number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = self.results.get(timeout=240)
except Queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not self.data_controller_process.is_alive() and self.data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
self.get_data.value is False
self.results.put((-2, "CachingDataController"))
new_procs = []
old_procs = []
for p in self.procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
self.results.put((-3, "ZombieParticle"))
# Decrement nproc (CachingDataController exits when this is 0)
with self.nproc_lock:
self.n_run.value = self.n_run.value - 1
# Remove task from queue (so they can be joined later on)
self.tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = Consumer(self.tasks, self.results, self.n_run, self.nproc_lock, self.active, self.get_data, name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in self.has_read_lock:
with self.read_lock:
self.read_count.value -= 1
self.has_read_lock.remove(p.pid)
if self.has_data_request_lock.value == p.pid:
self.has_data_request_lock.value = -1
try:
self.data_request_lock.release()
except:
pass
if self.has_write_lock.value == p.pid:
self.has_write_lock.value = -1
try:
self.write_lock.release()
except:
pass
for p in old_procs:
try:
self.procs.remove(p)
except ValueError:
logger.warn("Did not find %s in the list of processes. Continuing on." % p.name)
for p in new_procs:
self.procs.append(p)
logger.warn("Started a new consumer (%s) to replace a zombie consumer" % p.name)
p.start()
else:
# We got one.
retrieved += 1
if code is None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
self.error_code = code
logger.warn("CachingDataController has FAILED!! Removing cache file so the particles fail.")
try:
os.remove(self.cache_path)
except OSError:
logger.debug("Could not remove cache file, it probably never existed")
pass
elif code == -3:
self.error_code = code
logger.info("A zombie process was caught and task was removed from queue")
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress((round((retrieved / self.number_of_tasks) * 90., 1), "Particle %d finished" % tempres.uid))
elif tempres == "CachingDataController":
logger.info("CachingDataController finished")
logger.progress((round((retrieved / self.number_of_tasks) * 90., 1), "CachingDataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" % (int(retrieved), self.number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn("Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert self.results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
self.tasks.join()
self.particles = return_particles
finally:
# Join all processes
logger.info("Joining the processes")
for w in self.procs + [self.data_controller_process]:
# Wait 20 seconds
w.join(20.)
if w.is_alive():
# Process is hanging, kill it.
logger.info("Terminating %s forcefully. This should have exited itself." % w.name)
w.terminate()
def run(self):
self.load_initial_dataset()
redis_connection = None
if self.redis_url is not None and self.redis_results_channel is not None:
import redis
redis_connection = redis.from_url(self.redis_url)
# Setup shoreline
self._shoreline = None
if self.useshore is True:
self._shoreline = Shoreline(
path=self.shoreline_path,
feature_name=self.shoreline_feature,
point=self.release_location_centroid,
spatialbuffer=self.shoreline_index_buffer)
# Make sure we are not starting on land. Raises exception if we are.
self._shoreline.intersect(
start_point=self.release_location_centroid,
end_point=self.release_location_centroid)
# Setup Bathymetry
if self.usebathy is True:
try:
self._bathymetry = Bathymetry(file=self.bathy_path)
except Exception:
logger.exception(
"Could not load Bathymetry file: %s, using no Bathymetry for this run!"
% self.bathy_path)
self.usebathy = False
# Calculate datetime at every timestep
modelTimestep, newtimes = AsaTransport.get_time_objects_from_model_timesteps(
self.times, start=self.start_time)
if self.time_method == 'interp':
time_indexs = self.timevar.nearest_index(newtimes, select='before')
elif self.time_method == 'nearest':
time_indexs = self.timevar.nearest_index(newtimes)
else:
logger.warn("Method for computing u,v,w,temp,salt not supported!")
try:
assert len(newtimes) == len(time_indexs)
except AssertionError:
logger.exception(
"Time indexes are messed up. Need to have equal datetime and time indexes"
)
raise
# Keep track of how much time we spend in each area.
tot_boundary_time = 0.
tot_model_time = {}
tot_read_data = 0.
for m in self.models:
tot_model_time[m.name] = 0.
# Set the base conditions
# If using Redis, send the results
if redis_connection is not None:
redis_connection.publish(self.redis_results_channel,
json.dumps(self.particle.timestep_dump()))
# loop over timesteps
# We don't loop over the last time_index because
# we need to query in the time_index and set the particle's
# location as the 'newtime' object.
for loop_i, i in enumerate(time_indexs[0:-1]):
if self.active and self.active.value is False:
raise ValueError("Particle exiting due to Failure.")
newloc = None
st = time.clock()
# Get the variable data required by the models
if self.time_method == 'nearest':
u, v, w, temp, salt = self.get_nearest_data(i)
elif self.time_method == 'interp':
u, v, w, temp, salt = self.get_linterp_data(
i, newtimes[loop_i])
else:
logger.warn(
"Method for computing u,v,w,temp,salt is unknown. Only 'nearest' and 'interp' are supported."
)
tot_read_data += (time.clock() - st)
# Get the bathy value at the particles location
if self.usebathy is True:
bathymetry_value = self._bathymetry.get_depth(
self.particle.location)
else:
bathymetry_value = -999999999999999
# Age the particle by the modelTimestep (seconds)
# 'Age' meaning the amount of time it has been forced.
self.particle.age(seconds=modelTimestep[loop_i])
# loop over models - sort these in the order you want them to run
for model in self.models:
st = time.clock()
movement = model.move(self.particle,
u,
v,
w,
modelTimestep[loop_i],
temperature=temp,
salinity=salt,
bathymetry_value=bathymetry_value)
newloc = Location4D(latitude=movement['latitude'],
longitude=movement['longitude'],
depth=movement['depth'],
time=newtimes[loop_i + 1])
tot_model_time[m.name] += (time.clock() - st)
if logger.isEnabledFor(logging.DEBUG):
logger.debug(
"%s - moved %.3f meters (horizontally) and %.3f meters (vertically) by %s with data from %s"
% (self.particle.logstring(), movement['distance'],
movement['vertical_distance'],
model.__class__.__name__,
newtimes[loop_i].isoformat()))
if newloc:
st = time.clock()
self.boundary_interaction(
particle=self.particle,
starting=self.particle.location,
ending=newloc,
distance=movement['distance'],
angle=movement['angle'],
azimuth=movement['azimuth'],
reverse_azimuth=movement['reverse_azimuth'],
vertical_distance=movement['vertical_distance'],
vertical_angle=movement['vertical_angle'])
tot_boundary_time += (time.clock() - st)
if logger.isEnabledFor(logging.DEBUG):
logger.debug(
"%s - was forced by %s and is now at %s" %
(self.particle.logstring(), model.__class__.__name__,
self.particle.location.logstring()))
self.particle.note = self.particle.outputstring()
# Each timestep, save the particles status and environmental variables.
# This keep fields such as temp, salt, halted, settled, and dead matched up with the number of timesteps
self.particle.save()
# If using Redis, send the results
if redis_connection is not None:
redis_connection.publish(
self.redis_results_channel,
json.dumps(self.particle.timestep_dump()))
self.dataset.closenc()
# We won't pull data for the last entry in locations, but we need to populate it with fill data.
self.particle.fill_gap()
if self.usebathy is True:
self._bathymetry.close()
if self.useshore is True:
self._shoreline.close()
logger.info(
textwrap.dedent('''Particle %i Stats:
Data read: %f seconds
Model forcing: %s seconds
Boundary intersection: %f seconds''' %
(self.particle.uid, tot_read_data, {
s: '{:g} seconds'.format(f)
for s, f in list(tot_model_time.items())
}, tot_boundary_time)))
return self.particle
def setup_run(self, **kwargs):
logger.setLevel(logging.PROGRESS)
self.redis_url = None
self.redis_log_channel = None
self.redis_results_channel = None
if "redis" in kwargs.get("output_formats", []):
from paegan.logger.redis_handler import RedisHandler
self.redis_url = kwargs.get("redis_url")
self.redis_log_channel = kwargs.get("redis_log_channel")
self.redis_results_channel = kwargs.get("redis_results_channel")
rhandler = RedisHandler(self.redis_log_channel, self.redis_url)
rhandler.setLevel(logging.PROGRESS)
logger.addHandler(rhandler)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(unicode(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(unicode(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = range(0, (self._step*self._nstep)+1, self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
if kwargs.get("manager", True):
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
self.mgr = multiprocessing.Manager()
# This tracks if the system is 'alive'. Most looping whiles will check this
# and break out if it is False. This is True until something goes very wrong.
self.active = self.mgr.Value('bool', True)
# Each particle is a task, plus the CachingDataController
self.number_of_tasks = self.get_number_of_tasks()
# Either spin up the number of cores, or the number of tasks
self.nproc = min(multiprocessing.cpu_count() - 1, self.number_of_tasks)
# Number of tasks that we need to run. This is decremented everytime something exits.
self.n_run = self.mgr.Value('int', self.number_of_tasks)
# The lock that controls access to the 'n_run' variable
self.nproc_lock = self.mgr.Lock()
# Create the task queue for all of the particles and the CachingDataController
self.tasks = multiprocessing.JoinableQueue(self.number_of_tasks)
# Create the result queue for all of the particles and the CachingDataController
self.results = self.mgr.Queue(self.number_of_tasks)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(self.hydrodataset)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" % self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
except AssertionError:
logger.exception("Could not locate variables needed to run model: %s" % unicode(self.common_variables))
raise BaseDataControllerError("A required data variable was not found in %s" % self.hydrodataset)
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError("Start time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError("End time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[-1], model_start, model_end))
ds.closenc()
def setup_run(self, hydrodataset, **kwargs):
self.hydrodataset = hydrodataset
logger.setLevel(logging.PROGRESS)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(str(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(str(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = list(range(0, (self._step*self._nstep)+1, self._step))
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in range(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
logger.progress((3, "Initializing and caching hydro model's grid %s" % self.hydrodataset))
try:
ds = CommonDataset.open(self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" % self.hydrodataset)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
except AssertionError:
logger.exception("Could not locate variables needed to run model: %s" % str(self.common_variables))
raise BaseDataControllerError("A required data variable was not found in %s" % self.hydrodataset)
finally:
ds.closenc()
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError("Start time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError("End time for model (%s) is not available in source dataset (%s/%s)" % (self.datetimes[-1], model_start, model_end))
def listen_for_results(self):
try:
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
self.error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < self.number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = self.results.get(timeout=240)
except Queue.Empty:
new_procs = []
old_procs = []
for p in self.procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
self.results.put((-3, "Zombie"))
# Decrement nproc (Consumer exits when this is 0)
with self.nproc_lock:
self.n_run.value = self.n_run.value - 1
# Remove task from queue (so they can be joined later on)
self.tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = Consumer(self.tasks, self.results, self.n_run, self.nproc_lock, self.active, None, name=p.name)
new_procs.append(np)
old_procs.append(p)
for p in old_procs:
try:
self.procs.remove(p)
except ValueError:
logger.warn("Did not find %s in the list of processes. Continuing on." % p.name)
for p in new_procs:
self.procs.append(p)
logger.warn("Started a new consumer (%s) to replace a zombie consumer" % p.name)
p.start()
else:
# We got one.
retrieved += 1
if code is None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -3:
self.error_code = code
logger.info("A zombie process was caught and task was removed from queue")
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress((round((retrieved / self.number_of_tasks) * 90., 1), "Particle %d finished" % tempres.uid))
else:
logger.info("Got a strange result on results queue: %s" % str(tempres))
logger.info("Retrieved %i/%i results" % (int(retrieved), self.number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn("Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert self.results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
self.tasks.join()
self.particles = return_particles
finally:
# Join all processes
logger.info("Joining the processes")
for w in self.procs:
# Wait 20 seconds
w.join(20.)
if w.is_alive():
# Process is hanging, kill it.
logger.info("Terminating %s forcefully. This should have exited itself." % w.name)
w.terminate()
def setup_run(self, hydrodataset, **kwargs):
self.hydrodataset = hydrodataset
logger.setLevel(logging.PROGRESS)
# Relax.
time.sleep(0.5)
# Add ModelController description to logfile
logger.info(str(self))
# Add the model descriptions to logfile
for m in self._models:
logger.info(str(m))
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
self.times = list(range(0, (self._step * self._nstep) + 1, self._step))
# Calculate a datetime object for each model timestep
# This method is duplicated in CachingDataController and CachingForcer
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
self.modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(
self.times, start=self.start)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(
self.geometry, MultiPolygon):
point_locations = [
Location4D(latitude=loc.y,
longitude=loc.x,
depth=self._depth,
time=self.start)
for loc in AsaTransport.fill_polygon_with_points(
goal=self._npart, polygon=self.geometry)
]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in range(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
logger.progress((3, "Initializing and caching hydro model's grid %s" %
self.hydrodataset))
try:
ds = CommonDataset.open(self.hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
self.common_variables = self.get_common_variables_from_dataset(ds)
except Exception:
logger.exception("Failed to access dataset %s" % self.hydrodataset)
raise BaseDataControllerError("Inaccessible Dataset: %s" %
self.hydrodataset)
self.timevar = None
try:
assert self.common_variables.get("u") in ds._current_variables
assert self.common_variables.get("v") in ds._current_variables
assert self.common_variables.get("x") in ds._current_variables
assert self.common_variables.get("y") in ds._current_variables
self.timevar = ds.gettimevar(self.common_variables.get("u"))
model_start = self.timevar.get_dates()[0]
model_end = self.timevar.get_dates()[-1]
except AssertionError:
logger.exception(
"Could not locate variables needed to run model: %s" %
str(self.common_variables))
raise BaseDataControllerError(
"A required data variable was not found in %s" %
self.hydrodataset)
finally:
ds.closenc()
try:
assert self.start > model_start
assert self.start < model_end
except AssertionError:
raise BaseDataControllerError(
"Start time for model (%s) is not available in source dataset (%s/%s)"
% (self.datetimes[0], model_start, model_end))
try:
assert self.datetimes[-1] > model_start
assert self.datetimes[-1] < model_end
except AssertionError:
raise BaseDataControllerError(
"End time for model (%s) is not available in source dataset (%s/%s)"
% (self.datetimes[-1], model_start, model_end))
def setup_run(self, **kwargs):
super(CachingModelController, self).setup_run(**kwargs)
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
self.mgr = multiprocessing.Manager()
# This tracks if the system is 'alive'. Most looping whiles will check this
# and break out if it is False. This is True until something goes very wrong.
self.active = self.mgr.Value('bool', True)
# Either spin up the number of cores, or the number of tasks
self.nproc = min(multiprocessing.cpu_count() - 1, self.number_of_tasks)
# Number of tasks that we need to run. This is decremented everytime something exits.
self.n_run = self.mgr.Value('int', self.number_of_tasks)
# The lock that controls access to the 'n_run' variable
self.nproc_lock = self.mgr.Lock()
# Create the task queue for all of the particles and the CachingDataController
self.tasks = multiprocessing.JoinableQueue(self.number_of_tasks)
# Create the result queue for all of the particles and the CachingDataController
self.results = self.mgr.Queue(self.number_of_tasks)
# Should we remove the cache file at the end of the run?
self.remove_cache = kwargs.get("remove_cache", False)
self.cache_path = kwargs.get("cache_path", None)
# Create a temp file for the cache if nothing was passed in
if self.cache_path is None:
default_cache_dir = os.path.join(os.path.dirname(__file__), "_cache")
temp_name = AsaRandom.filename(prefix=str(datetime.now().microsecond), suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
# Be sure the cache directory exists
if not os.path.exists(os.path.dirname(self.cache_path)):
logger.info("Creating cache directory: %s" % self.cache_path)
os.makedirs(os.path.dirname(self.cache_path))
# Create the shared state objects
# Particles use this to tell the Data Controller to "get_data".
# The CachingDataController sets this to False when it is done writing to the cache file.
# Particles will wait for this to be False before reading from the cache file.
# If we are caching, this starts as True so the Particles don't take off. If we
# are not caching, this is False so the Particles can start immediatly.
self.get_data = self.mgr.Value('bool', True)
# Particles use this to tell the DataContoller which indices to 'get_data' for
self.point_get = self.mgr.Value('list', [0, 0, 0])
# This locks access to the 'has_data_request_lock' value
self.data_request_lock = self.mgr.Lock()
# This tracks which Particle PID is asking the CachingDataController for data
self.has_data_request_lock = self.mgr.Value('int', -1)
# The lock that controls access to modifying 'has_read_lock' and 'read_count'
self.read_lock = self.mgr.Lock()
# List of Particle PIDs that are reading from the cache
self.has_read_lock = self.mgr.list()
# The number of Particles that are reading from the cache
self.read_count = self.mgr.Value('int', 0)
# When something is writing to the cache file
self.write_lock = self.mgr.Lock()
# PID of process with lock
self.has_write_lock = self.mgr.Value('int', -1)
def run(self, hydrodataset, **kwargs):
# Add ModelController description to logfile
logger.info(self)
# Add the model descriptions to logfile
for m in self._models:
logger.info(m)
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
times = range(0, (self._step * self._nstep) + 1, self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in DataController and ForceParticle
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(
times, start=self.start)
time_chunk = self._time_chunk
horiz_chunk = self._horiz_chunk
low_memory = kwargs.get("low_memory", False)
# Should we remove the cache file at the end of the run?
remove_cache = kwargs.get("remove_cache", True)
self.bathy_path = kwargs.get("bathy", None)
self.cache_path = kwargs.get("cache", None)
if self.cache_path is None:
# Generate temp filename for dataset cache
default_cache_dir = os.path.join(os.path.dirname(__file__),
"_cache")
temp_name = AsaRandom.filename(prefix=str(
datetime.now().microsecond),
suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(
self.geometry, MultiPolygon):
point_locations = [
Location4D(latitude=loc.y,
longitude=loc.x,
depth=self._depth,
time=self.start)
for loc in AsaTransport.fill_polygon_with_points(
goal=self._npart, polygon=self.geometry)
]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
# This is where it makes sense to implement the multiprocessing
# looping for particles and models. Can handle each particle in
# parallel probably.
#
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
mgr = multiprocessing.Manager()
nproc = multiprocessing.cpu_count() - 1
if nproc <= 0:
raise ValueError(
"Model does not run using less than two CPU cores")
# Each particle is a task, plus the DataController
number_of_tasks = len(self.particles) + 1
# We need a process for each particle and one for the data controller
nproc = min(number_of_tasks, nproc)
# When a particle requests data
data_request_lock = mgr.Lock()
# PID of process with lock
has_data_request_lock = mgr.Value('int', -1)
nproc_lock = mgr.Lock()
# Create the task queue for all of the particles and the DataController
tasks = multiprocessing.JoinableQueue(number_of_tasks)
# Create the result queue for all of the particles and the DataController
results = mgr.Queue(number_of_tasks)
# Create the shared state objects
get_data = mgr.Value('bool', True)
# Number of tasks
n_run = mgr.Value('int', number_of_tasks)
updating = mgr.Value('bool', False)
# When something is reading from cache file
read_lock = mgr.Lock()
# list of PIDs that are reading
has_read_lock = mgr.list()
read_count = mgr.Value('int', 0)
# When something is writing to the cache file
write_lock = mgr.Lock()
# PID of process with lock
has_write_lock = mgr.Value('int', -1)
point_get = mgr.Value('list', [0, 0, 0])
active = mgr.Value('bool', True)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
common_variables = self.get_common_variables_from_dataset(ds)
logger.debug("Pickling time variable to disk for particles")
timevar = ds.gettimevar(common_variables.get("u"))
f, timevar_pickle_path = tempfile.mkstemp()
os.close(f)
f = open(timevar_pickle_path, "wb")
pickle.dump(timevar, f)
f.close()
ds.closenc()
except:
logger.warn("Failed to access remote dataset %s" % hydrodataset)
raise DataControllerError("Inaccessible DAP endpoint: %s" %
hydrodataset)
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
logger.debug('Starting DataController')
logger.progress((4, "Starting processes"))
data_controller = parallel.DataController(hydrodataset,
common_variables,
n_run,
get_data,
write_lock,
has_write_lock,
read_lock,
read_count,
time_chunk,
horiz_chunk,
times,
self.start,
point_get,
self.reference_location,
low_memory=low_memory,
cache=self.cache_path)
tasks.put(data_controller)
# Create DataController worker
data_controller_process = parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name="DataController")
data_controller_process.start()
logger.debug('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcing = parallel.ForceParticle(
part,
hydrodataset,
common_variables,
timevar_pickle_path,
times,
self.start,
self._models,
self.reference_location.point,
self._use_bathymetry,
self._use_shoreline,
self._use_seasurface,
get_data,
n_run,
read_lock,
has_read_lock,
read_count,
point_get,
data_request_lock,
has_data_request_lock,
reverse_distance=self.reverse_distance,
bathy=self.bathy_path,
shoreline_path=self.shoreline_path,
cache=self.cache_path,
time_method=self.time_method)
tasks.put(forcing)
# Create workers for the particles.
procs = [
parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name="ForceParticle-%d" % i)
for i in xrange(nproc - 1)
]
for w in procs:
w.start()
logger.debug('Started %s' % w.name)
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = results.get(timeout=240)
except Queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not data_controller_process.is_alive(
) and data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
get_data.value == False
results.put((-2, "DataController"))
new_procs = []
old_procs = []
for p in procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
results.put((-3, "ZombieParticle"))
# Decrement nproc (DataController exits when this is 0)
with nproc_lock:
n_run.value = n_run.value - 1
# Remove task from queue (so they can be joined later on)
tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = parallel.Consumer(tasks,
results,
n_run,
nproc_lock,
active,
get_data,
name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in has_read_lock:
with read_lock:
read_count.value -= 1
has_read_lock.remove(p.pid)
if has_data_request_lock.value == p.pid:
has_data_request_lock.value = -1
try:
data_request_lock.release()
except:
pass
if has_write_lock.value == p.pid:
has_write_lock.value = -1
try:
write_lock.release()
except:
pass
for p in old_procs:
try:
procs.remove(p)
except ValueError:
logger.warn(
"Did not find %s in the list of processes. Continuing on."
% p.name)
for p in new_procs:
procs.append(p)
logger.warn(
"Started a new consumer (%s) to replace a zombie consumer"
% p.name)
p.start()
else:
# We got one.
retrieved += 1
if code == None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
error_code = code
logger.warn(
"DataController has FAILED!! Removing cache file so the particles fail."
)
try:
os.remove(self.cache_path)
except OSError:
logger.debug(
"Could not remove cache file, it probably never existed"
)
pass
elif code == -3:
error_code = code
logger.info(
"A zombie process was caught and task was removed from queue"
)
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress(
(round((retrieved / number_of_tasks) * 90.,
1), "Particle %d finished" % tempres.uid))
elif tempres == "DataController":
logger.info("DataController finished")
logger.progress((round((retrieved / number_of_tasks) * 90.,
1), "DataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" %
(int(retrieved), number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn(
"Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
tasks.join()
# Join all processes
logger.info("Joining the processes")
for w in procs + [data_controller_process]:
# Wait 10 seconds
w.join(10.)
if w.is_alive():
# Process is hanging, kill it.
logger.info(
"Terminating %s forcefully. This should have exited itself."
% w.name)
w.terminate()
logger.info('Workers complete')
self.particles = return_particles
# Remove Manager so it shuts down
del mgr
# Remove pickled timevar
os.remove(timevar_pickle_path)
# Remove the cache file
if remove_cache is True:
try:
os.remove(self.cache_path)
except OSError:
logger.debug(
"Could not remove cache file, it probably never existed")
logger.progress((96, "Exporting results"))
if len(self.particles) > 0:
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
# Make sure output_path is also included
if kwargs.get("output_path", None) != None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for format in formats:
logger.info("Exporting to: %s" % format)
try:
self.export(output_path, format=format)
except:
logger.error("Failed to export to: %s" %
format)
else:
logger.warn(
'The output_formats parameter should be a list, not saving any output!'
)
else:
logger.warn(
'No output path defined, not saving any output!')
else:
logger.warn('No output format defined, not saving any output!')
else:
logger.warn("Model didn't actually do anything, check the log.")
if error_code == -2:
raise DataControllerError("Error in the DataController")
else:
raise ModelError("Error in the model")
logger.progress((99, "Model Run Complete"))
return
def run(self, hydrodataset, **kwargs):
# Add ModelController description to logfile
logger.info(self)
# Add the model descriptions to logfile
for m in self._models:
logger.info(m)
# Calculate the model timesteps
# We need times = len(self._nstep) + 1 since data is stored one timestep
# after a particle is forced with the final timestep's data.
times = range(0,(self._step*self._nstep)+1,self._step)
# Calculate a datetime object for each model timestep
# This method is duplicated in DataController and ForceParticle
# using the 'times' variables above. Will be useful in those other
# locations for particles released at different times
# i.e. released over a few days
modelTimestep, self.datetimes = AsaTransport.get_time_objects_from_model_timesteps(times, start=self.start)
time_chunk = self._time_chunk
horiz_chunk = self._horiz_chunk
low_memory = kwargs.get("low_memory", False)
# Should we remove the cache file at the end of the run?
remove_cache = kwargs.get("remove_cache", True)
self.bathy_path = kwargs.get("bathy", None)
self.cache_path = kwargs.get("cache", None)
if self.cache_path is None:
# Generate temp filename for dataset cache
default_cache_dir = os.path.join(os.path.dirname(__file__), "_cache")
temp_name = AsaRandom.filename(prefix=str(datetime.now().microsecond), suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
logger.progress((1, "Setting up particle start locations"))
point_locations = []
if isinstance(self.geometry, Point):
point_locations = [self.reference_location] * self._npart
elif isinstance(self.geometry, Polygon) or isinstance(self.geometry, MultiPolygon):
point_locations = [Location4D(latitude=loc.y, longitude=loc.x, depth=self._depth, time=self.start) for loc in AsaTransport.fill_polygon_with_points(goal=self._npart, polygon=self.geometry)]
# Initialize the particles
logger.progress((2, "Initializing particles"))
for x in xrange(0, self._npart):
p = LarvaParticle(id=x)
p.location = point_locations[x]
# We don't need to fill the location gaps here for environment variables
# because the first data collected actually relates to this original
# position.
# We do need to fill in fields such as settled, halted, etc.
p.fill_status_gap()
# Set the inital note
p.note = p.outputstring()
p.notes.append(p.note)
self.particles.append(p)
# This is where it makes sense to implement the multiprocessing
# looping for particles and models. Can handle each particle in
# parallel probably.
#
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
mgr = multiprocessing.Manager()
nproc = multiprocessing.cpu_count() - 1
if nproc <= 0:
raise ValueError("Model does not run using less than two CPU cores")
# Each particle is a task, plus the DataController
number_of_tasks = len(self.particles) + 1
# We need a process for each particle and one for the data controller
nproc = min(number_of_tasks, nproc)
# When a particle requests data
data_request_lock = mgr.Lock()
# PID of process with lock
has_data_request_lock = mgr.Value('int',-1)
nproc_lock = mgr.Lock()
# Create the task queue for all of the particles and the DataController
tasks = multiprocessing.JoinableQueue(number_of_tasks)
# Create the result queue for all of the particles and the DataController
results = mgr.Queue(number_of_tasks)
# Create the shared state objects
get_data = mgr.Value('bool', True)
# Number of tasks
n_run = mgr.Value('int', number_of_tasks)
updating = mgr.Value('bool', False)
# When something is reading from cache file
read_lock = mgr.Lock()
# list of PIDs that are reading
has_read_lock = mgr.list()
read_count = mgr.Value('int', 0)
# When something is writing to the cache file
write_lock = mgr.Lock()
# PID of process with lock
has_write_lock = mgr.Value('int',-1)
point_get = mgr.Value('list', [0, 0, 0])
active = mgr.Value('bool', True)
logger.progress((3, "Initializing and caching hydro model's grid"))
try:
ds = CommonDataset.open(hydrodataset)
# Query the dataset for common variable names
# and the time variable.
logger.debug("Retrieving variable information from dataset")
common_variables = self.get_common_variables_from_dataset(ds)
logger.debug("Pickling time variable to disk for particles")
timevar = ds.gettimevar(common_variables.get("u"))
f, timevar_pickle_path = tempfile.mkstemp()
os.close(f)
f = open(timevar_pickle_path, "wb")
pickle.dump(timevar, f)
f.close()
ds.closenc()
except:
logger.warn("Failed to access remote dataset %s" % hydrodataset)
raise DataControllerError("Inaccessible DAP endpoint: %s" % hydrodataset)
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
logger.debug('Starting DataController')
logger.progress((4, "Starting processes"))
data_controller = parallel.DataController(hydrodataset, common_variables, n_run, get_data, write_lock, has_write_lock, read_lock, read_count,
time_chunk, horiz_chunk, times,
self.start, point_get, self.reference_location,
low_memory=low_memory,
cache=self.cache_path)
tasks.put(data_controller)
# Create DataController worker
data_controller_process = parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name="DataController")
data_controller_process.start()
logger.debug('Adding %i particles as tasks' % len(self.particles))
for part in self.particles:
forcing = parallel.ForceParticle(part,
hydrodataset,
common_variables,
timevar_pickle_path,
times,
self.start,
self._models,
self.reference_location.point,
self._use_bathymetry,
self._use_shoreline,
self._use_seasurface,
get_data,
n_run,
read_lock,
has_read_lock,
read_count,
point_get,
data_request_lock,
has_data_request_lock,
reverse_distance=self.reverse_distance,
bathy=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
cache=self.cache_path,
time_method=self.time_method)
tasks.put(forcing)
# Create workers for the particles.
procs = [ parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name="ForceParticle-%d"%i)
for i in xrange(nproc - 1) ]
for w in procs:
w.start()
logger.debug('Started %s' % w.name)
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
error_code = 0
logger.info("Waiting for %i particle results" % len(self.particles))
logger.progress((5, "Running model"))
while retrieved < number_of_tasks:
try:
# Returns a tuple of code, result
code, tempres = results.get(timeout=240)
except Queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not data_controller_process.is_alive() and data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
get_data.value == False
results.put((-2, "DataController"))
new_procs = []
old_procs = []
for p in procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
results.put((-3, "ZombieParticle"))
# Decrement nproc (DataController exits when this is 0)
with nproc_lock:
n_run.value = n_run.value - 1
# Remove task from queue (so they can be joined later on)
tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = parallel.Consumer(tasks, results, n_run, nproc_lock, active, get_data, name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in has_read_lock:
with read_lock:
read_count.value -= 1
has_read_lock.remove(p.pid)
if has_data_request_lock.value == p.pid:
has_data_request_lock.value = -1
try:
data_request_lock.release()
except:
pass
if has_write_lock.value == p.pid:
has_write_lock.value = -1
try:
write_lock.release()
except:
pass
for p in old_procs:
try:
procs.remove(p)
except ValueError:
logger.warn("Did not find %s in the list of processes. Continuing on." % p.name)
for p in new_procs:
procs.append(p)
logger.warn("Started a new consumer (%s) to replace a zombie consumer" % p.name)
p.start()
else:
# We got one.
retrieved += 1
if code == None:
logger.warn("Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
error_code = code
logger.warn("DataController has FAILED!! Removing cache file so the particles fail.")
try:
os.remove(self.cache_path)
except OSError:
logger.debug("Could not remove cache file, it probably never existed")
pass
elif code == -3:
error_code = code
logger.info("A zombie process was caught and task was removed from queue")
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress((round((retrieved / number_of_tasks) * 90.,1), "Particle %d finished" % tempres.uid))
elif tempres == "DataController":
logger.info("DataController finished")
logger.progress((round((retrieved / number_of_tasks) * 90.,1), "DataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" % (int(retrieved),number_of_tasks))
if len(return_particles) != len(self.particles):
logger.warn("Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
tasks.join()
# Join all processes
logger.info("Joining the processes")
for w in procs + [data_controller_process]:
# Wait 10 seconds
w.join(10.)
if w.is_alive():
# Process is hanging, kill it.
logger.info("Terminating %s forcefully. This should have exited itself." % w.name)
w.terminate()
logger.info('Workers complete')
self.particles = return_particles
# Remove Manager so it shuts down
del mgr
# Remove pickled timevar
os.remove(timevar_pickle_path)
# Remove the cache file
if remove_cache is True:
try:
os.remove(self.cache_path)
except OSError:
logger.debug("Could not remove cache file, it probably never existed")
logger.progress((96, "Exporting results"))
if len(self.particles) > 0:
# If output_formats and path specified,
# output particle run data to disk when completed
if "output_formats" in kwargs:
# Make sure output_path is also included
if kwargs.get("output_path", None) != None:
formats = kwargs.get("output_formats")
output_path = kwargs.get("output_path")
if isinstance(formats, list):
for format in formats:
logger.info("Exporting to: %s" % format)
try:
self.export(output_path, format=format)
except:
logger.error("Failed to export to: %s" % format)
else:
logger.warn('The output_formats parameter should be a list, not saving any output!')
else:
logger.warn('No output path defined, not saving any output!')
else:
logger.warn('No output format defined, not saving any output!')
else:
logger.warn("Model didn't actually do anything, check the log.")
if error_code == -2:
raise DataControllerError("Error in the DataController")
else:
raise ModelError("Error in the model")
logger.progress((99, "Model Run Complete"))
return
def export(cls, folder, particles, datetimes):
shape_schema = {'geometry': 'Point',
'properties': OrderedDict([('particle', 'int'),
('date', 'str'),
('latitude', 'float'),
('longitude', 'float'),
('depth', 'float'),
('u_vector', 'float'),
('v_vector', 'float'),
('w_vector', 'float'),
('temp', 'float'),
('salinity', 'float'),
('age', 'float'),
('settled', 'str'),
('dead', 'str'),
('halted', 'str'),
('notes', 'str')])}
shape_crs = {'no_defs': True, 'ellps': 'WGS84', 'datum': 'WGS84', 'proj': 'longlat'}
if not os.path.exists(folder):
os.makedirs(folder)
filepath = os.path.join(folder, "gdalshape.shp")
with collection(filepath, "w", driver='ESRI Shapefile', schema=shape_schema, crs=shape_crs) as shape:
for particle in particles:
normalized_locations = particle.normalized_locations(datetimes)
normalized_temps = particle.temps
normalized_salts = particle.salts
normalized_u = particle.u_vectors
normalized_v = particle.v_vectors
normalized_w = particle.w_vectors
normalized_settled = particle.settles
normalized_dead = particle.deads
normalized_halted = particle.halts
normalized_ages = particle.ages
normalized_notes = particle.notes
if len(normalized_locations) != len(normalized_temps):
logger.info("No temperature being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_temps = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_temps = (-9999.9 if not x else x for x in normalized_temps)
if len(normalized_locations) != len(normalized_salts):
logger.info("No salinity being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_salts = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_salts = (-9999.9 if not x else x for x in normalized_salts)
if len(normalized_locations) != len(normalized_u):
logger.info("No U being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_u = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_u = (-9999.9 if not x else x for x in normalized_u)
if len(normalized_locations) != len(normalized_v):
logger.info("No V being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_v = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_v = (-9999.9 if not x else x for x in normalized_v)
if len(normalized_locations) != len(normalized_w):
logger.info("No W being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_w = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_w = (-9999.9 if not x else x for x in normalized_w)
if len(normalized_locations) != len(normalized_settled):
logger.info("No Settled being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_settled = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_dead):
logger.info("No Dead being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_dead = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_halted):
logger.info("No Halted being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_halted = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_ages):
logger.info("No W being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_ages = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_ages = (-9999.9 if not x else round(x, 3) for x in normalized_ages)
if len(normalized_locations) != len(normalized_notes):
logger.info("No Notes being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_notes = [None] * len(normalized_locations)
for loc, temp, salt, u, v, w, settled, dead, halted, age, note in zip(normalized_locations, normalized_temps, normalized_salts, normalized_u, normalized_v, normalized_w, normalized_settled, normalized_dead, normalized_halted, normalized_ages, normalized_notes):
shape.write({ 'geometry': mapping(loc.point),
'properties': OrderedDict([('particle', particle.uid),
('date', unicode(loc.time.isoformat())),
('latitude', float(loc.latitude)),
('longitude', float(loc.longitude)),
('depth', float(loc.depth)),
('temp', float(temp)),
('salinity', float(salt)),
('u_vector', float(u)),
('v_vector', float(v)),
('w_vector', float(w)),
('settled', unicode(settled)),
('dead', unicode(dead)),
('halted', unicode(halted)),
('age', float(age)),
('notes' , unicode(note))])})
# Zip the output
shpzip = zipfile.ZipFile(os.path.join(folder, "shapefile.shp.zip"), mode='w')
for f in glob.glob(os.path.join(folder, "gdalshape*")):
shpzip.write(f, os.path.basename(f))
os.remove(f)
shpzip.close()
def __call__(self, proc, active):
self.active = active
if self.usebathy is True:
try:
self._bathymetry = Bathymetry(file=self.bathy)
except Exception:
logger.exception("Could not load Bathymetry file: %s, using no Bathymetry for this run!" % self.bathy)
self.usebathy = False
self._shoreline = None
if self.useshore is True:
self._shoreline = Shoreline(path=self.shoreline_path, feature_name=self.shoreline_feature, point=self.release_location_centroid, spatialbuffer=0.25)
# Make sure we are not starting on land. Raises exception if we are.
self._shoreline.intersect(start_point=self.release_location_centroid, end_point=self.release_location_centroid)
if self.active.value is True:
while self.get_data.value is True:
logger.info("Waiting for DataController to start...")
timer.sleep(5)
pass
# Initialize commondataset of local cache, then
# close the related netcdf file
try:
if self.caching is True:
with self.read_lock:
self.read_count.value += 1
self.has_read_lock.append(os.getpid())
self.dataset = CommonDataset.open(self.hydrodataset)
self.dataset.closenc()
except StandardError:
logger.warn("No source dataset: %s. Particle exiting" % self.hydrodataset)
raise
finally:
if self.caching is True:
with self.read_lock:
self.read_count.value -= 1
self.has_read_lock.remove(os.getpid())
# Calculate datetime at every timestep
modelTimestep, newtimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start_time)
if self.time_method == 'interp':
time_indexs = self.timevar.nearest_index(newtimes, select='before')
elif self.time_method == 'nearest':
time_indexs = self.timevar.nearest_index(newtimes)
else:
logger.warn("Method for computing u,v,w,temp,salt not supported!")
try:
assert len(newtimes) == len(time_indexs)
except AssertionError:
logger.error("Time indexes are messed up. Need to have equal datetime and time indexes")
raise
# loop over timesteps
# We don't loop over the last time_index because
# we need to query in the time_index and set the particle's
# location as the 'newtime' object.
for loop_i, i in enumerate(time_indexs[0:-1]):
if self.active.value is False:
raise ValueError("Particle exiting due to Failure.")
newloc = None
# Get the variable data required by the models
if self.time_method == 'nearest':
u, v, w, temp, salt = self.data_nearest(i, newtimes[loop_i])
elif self.time_method == 'interp':
u, v, w, temp, salt = self.data_interp(i, newtimes[loop_i])
else:
logger.warn("Method for computing u,v,w,temp,salt is unknown. Only 'nearest' and 'interp' are supported.")
# Get the bathy value at the particles location
if self.usebathy is True:
bathymetry_value = self._bathymetry.get_depth(self.part.location)
else:
bathymetry_value = -999999999999999
# Age the particle by the modelTimestep (seconds)
# 'Age' meaning the amount of time it has been forced.
self.part.age(seconds=modelTimestep[loop_i])
# loop over models - sort these in the order you want them to run
for model in self.models:
movement = model.move(self.part, u, v, w, modelTimestep[loop_i], temperature=temp, salinity=salt, bathymetry_value=bathymetry_value)
newloc = Location4D(latitude=movement['latitude'], longitude=movement['longitude'], depth=movement['depth'], time=newtimes[loop_i+1])
logger.debug("%s - moved %.3f meters (horizontally) and %.3f meters (vertically) by %s with data from %s" % (self.part.logstring(), movement['distance'], movement['vertical_distance'], model.__class__.__name__, newtimes[loop_i].isoformat()))
if newloc:
self.boundary_interaction(particle=self.part, starting=self.part.location, ending=newloc,
distance=movement['distance'], angle=movement['angle'],
azimuth=movement['azimuth'], reverse_azimuth=movement['reverse_azimuth'],
vertical_distance=movement['vertical_distance'], vertical_angle=movement['vertical_angle'])
logger.debug("%s - was forced by %s and is now at %s" % (self.part.logstring(), model.__class__.__name__, self.part.location.logstring()))
self.part.note = self.part.outputstring()
# Each timestep, save the particles status and environmental variables.
# This keep fields such as temp, salt, halted, settled, and dead matched up with the number of timesteps
self.part.save()
self.dataset.closenc()
# We won't pull data for the last entry in locations, but we need to populate it with fill data.
self.part.fill_environment_gap()
if self.usebathy is True:
self._bathymetry.close()
if self.useshore is True:
self._shoreline.close()
return self.part
def run(self):
self.load_initial_dataset()
redis_connection = None
if self.redis_url is not None and self.redis_results_channel is not None:
import redis
redis_connection = redis.from_url(self.redis_url)
# Setup shoreline
self._shoreline = None
if self.useshore is True:
self._shoreline = Shoreline(path=self.shoreline_path, feature_name=self.shoreline_feature, point=self.release_location_centroid, spatialbuffer=self.shoreline_index_buffer)
# Make sure we are not starting on land. Raises exception if we are.
self._shoreline.intersect(start_point=self.release_location_centroid, end_point=self.release_location_centroid)
# Setup Bathymetry
if self.usebathy is True:
try:
self._bathymetry = Bathymetry(file=self.bathy_path)
except Exception:
logger.exception("Could not load Bathymetry file: %s, using no Bathymetry for this run!" % self.bathy_path)
self.usebathy = False
# Calculate datetime at every timestep
modelTimestep, newtimes = AsaTransport.get_time_objects_from_model_timesteps(self.times, start=self.start_time)
if self.time_method == 'interp':
time_indexs = self.timevar.nearest_index(newtimes, select='before')
elif self.time_method == 'nearest':
time_indexs = self.timevar.nearest_index(newtimes)
else:
logger.warn("Method for computing u,v,w,temp,salt not supported!")
try:
assert len(newtimes) == len(time_indexs)
except AssertionError:
logger.exception("Time indexes are messed up. Need to have equal datetime and time indexes")
raise
# Keep track of how much time we spend in each area.
tot_boundary_time = 0.
tot_model_time = {}
tot_read_data = 0.
for m in self.models:
tot_model_time[m.name] = 0.
# Set the base conditions
# If using Redis, send the results
if redis_connection is not None:
redis_connection.publish(self.redis_results_channel, json.dumps(self.particle.timestep_dump()))
# loop over timesteps
# We don't loop over the last time_index because
# we need to query in the time_index and set the particle's
# location as the 'newtime' object.
for loop_i, i in enumerate(time_indexs[0:-1]):
if self.active and self.active.value is False:
raise ValueError("Particle exiting due to Failure.")
newloc = None
st = time.clock()
# Get the variable data required by the models
if self.time_method == 'nearest':
u, v, w, temp, salt = self.get_nearest_data(i)
elif self.time_method == 'interp':
u, v, w, temp, salt = self.get_linterp_data(i, newtimes[loop_i])
else:
logger.warn("Method for computing u,v,w,temp,salt is unknown. Only 'nearest' and 'interp' are supported.")
tot_read_data += (time.clock() - st)
# Get the bathy value at the particles location
if self.usebathy is True:
bathymetry_value = self._bathymetry.get_depth(self.particle.location)
else:
bathymetry_value = -999999999999999
# Age the particle by the modelTimestep (seconds)
# 'Age' meaning the amount of time it has been forced.
self.particle.age(seconds=modelTimestep[loop_i])
# loop over models - sort these in the order you want them to run
for model in self.models:
st = time.clock()
movement = model.move(self.particle, u, v, w, modelTimestep[loop_i], temperature=temp, salinity=salt, bathymetry_value=bathymetry_value)
newloc = Location4D(latitude=movement['latitude'], longitude=movement['longitude'], depth=movement['depth'], time=newtimes[loop_i+1])
tot_model_time[m.name] += (time.clock() - st)
if logger.isEnabledFor(logging.DEBUG):
logger.debug("%s - moved %.3f meters (horizontally) and %.3f meters (vertically) by %s with data from %s" % (self.particle.logstring(), movement['distance'], movement['vertical_distance'], model.__class__.__name__, newtimes[loop_i].isoformat()))
if newloc:
st = time.clock()
self.boundary_interaction(particle=self.particle, starting=self.particle.location, ending=newloc,
distance=movement['distance'], angle=movement['angle'],
azimuth=movement['azimuth'], reverse_azimuth=movement['reverse_azimuth'],
vertical_distance=movement['vertical_distance'], vertical_angle=movement['vertical_angle'])
tot_boundary_time += (time.clock() - st)
if logger.isEnabledFor(logging.DEBUG):
logger.debug("%s - was forced by %s and is now at %s" % (self.particle.logstring(), model.__class__.__name__, self.particle.location.logstring()))
self.particle.note = self.particle.outputstring()
# Each timestep, save the particles status and environmental variables.
# This keep fields such as temp, salt, halted, settled, and dead matched up with the number of timesteps
self.particle.save()
# If using Redis, send the results
if redis_connection is not None:
redis_connection.publish(self.redis_results_channel, json.dumps(self.particle.timestep_dump()))
self.dataset.closenc()
# We won't pull data for the last entry in locations, but we need to populate it with fill data.
self.particle.fill_gap()
if self.usebathy is True:
self._bathymetry.close()
if self.useshore is True:
self._shoreline.close()
logger.info(textwrap.dedent('''Particle %i Stats:
Data read: %f seconds
Model forcing: %s seconds
Boundary intersection: %f seconds''' % (self.particle.uid, tot_read_data, { s: '{:g} seconds'.format(f) for s, f in list(tot_model_time.items()) }, tot_boundary_time)))
return self.particle
def setup_run(self, hydrodataset, **kwargs):
super(CachingModelController, self).setup_run(hydrodataset, **kwargs)
# Get the number of cores (may take some tuning) and create that
# many workers then pass particles into the queue for the workers
self.mgr = multiprocessing.Manager()
# This tracks if the system is 'alive'. Most looping whiles will check this
# and break out if it is False. This is True until something goes very wrong.
self.active = self.mgr.Value('bool', True)
# Either spin up the number of cores, or the number of tasks
self.nproc = min(multiprocessing.cpu_count() - 1,
self.total_task_count())
# Number of tasks that we need to run. This is decremented everytime something exits.
self.n_run = self.mgr.Value('int', self.total_task_count())
# The lock that controls access to the 'n_run' variable
self.nproc_lock = self.mgr.Lock()
# Create the task queue for all of the particles and the CachingDataController
self.tasks = multiprocessing.JoinableQueue(self.total_task_count())
# Create the result queue for all of the particles and the CachingDataController
self.results = self.mgr.Queue(self.total_task_count())
# Should we remove the cache file at the end of the run?
self.remove_cache = kwargs.get("remove_cache", False)
self.cache_path = kwargs.get("cache_path", None)
# Create a temp file for the cache if nothing was passed in
if self.cache_path is None:
default_cache_dir = os.path.join(os.path.dirname(__file__),
"_cache")
temp_name = AsaRandom.filename(prefix=str(
datetime.now().microsecond),
suffix=".nc")
self.cache_path = os.path.join(default_cache_dir, temp_name)
# Be sure the cache directory exists
if not os.path.exists(os.path.dirname(self.cache_path)):
logger.info("Creating cache directory: %s" % self.cache_path)
os.makedirs(os.path.dirname(self.cache_path))
# Create the shared state objects
# Particles use this to tell the Data Controller to "get_data".
# The CachingDataController sets this to False when it is done writing to the cache file.
# Particles will wait for this to be False before reading from the cache file.
# If we are caching, this starts as True so the Particles don't take off. If we
# are not caching, this is False so the Particles can start immediatly.
self.get_data = self.mgr.Value('bool', True)
# Particles use this to tell the DataContoller which indices to 'get_data' for
self.point_get = self.mgr.Value('list', [0, 0, 0])
# This locks access to the 'has_data_request_lock' value
self.data_request_lock = self.mgr.Lock()
# This tracks which Particle PID is asking the CachingDataController for data
self.has_data_request_lock = self.mgr.Value('int', -1)
# The lock that controls access to modifying 'has_read_lock' and 'read_count'
self.read_lock = self.mgr.Lock()
# List of Particle PIDs that are reading from the cache
self.has_read_lock = self.mgr.list()
# The number of Particles that are reading from the cache
self.read_count = self.mgr.Value('int', 0)
# When something is writing to the cache file
self.write_lock = self.mgr.Lock()
# PID of process with lock
self.has_write_lock = self.mgr.Value('int', -1)
def listen_for_results(self, output_h5_file, total_particles):
try:
# Get results back from queue, test for failed particles
return_particles = []
retrieved = 0.
self.error_code = 0
logger.info("Waiting for %i particle results" % total_particles)
while retrieved < self.total_task_count(
): # One for the CachingDataController
logger.info("looping in listen_for_results")
try:
# Returns a tuple of code, result
code, tempres = self.results.get(timeout=240)
except queue.Empty:
# Poll the active processes to make sure they are all alive and then continue with loop
if not self.data_controller_process.is_alive(
) and self.data_controller_process.exitcode != 0:
# Data controller is zombied, kill off other processes.
self.get_data.value is False
self.results.put((-2, "CachingDataController"))
new_procs = []
old_procs = []
for p in self.procs:
if not p.is_alive() and p.exitcode != 0:
# Do what the Consumer would do if something finished.
# Add something to results queue
self.results.put((-3, "ZombieParticle"))
# Decrement nproc (CachingDataController exits when this is 0)
with self.nproc_lock:
self.n_run.value = self.n_run.value - 1
# Remove task from queue (so they can be joined later on)
self.tasks.task_done()
# Start a new Consumer. It will exit if there are no tasks available.
np = Consumer(self.tasks,
self.results,
self.n_run,
self.nproc_lock,
self.active,
self.get_data,
name=p.name)
new_procs.append(np)
old_procs.append(p)
# Release any locks the PID had
if p.pid in self.has_read_lock:
with self.read_lock:
self.read_count.value -= 1
self.has_read_lock.remove(p.pid)
if self.has_data_request_lock.value == p.pid:
self.has_data_request_lock.value = -1
try:
self.data_request_lock.release()
except:
pass
if self.has_write_lock.value == p.pid:
self.has_write_lock.value = -1
try:
self.write_lock.release()
except:
pass
for p in old_procs:
try:
self.procs.remove(p)
except ValueError:
logger.warn(
"Did not find %s in the list of processes. Continuing on."
% p.name)
for p in new_procs:
self.procs.append(p)
logger.warn(
"Started a new consumer (%s) to replace a zombie consumer"
% p.name)
p.start()
else:
# We got one.
retrieved += 1
if code is None:
logger.warn(
"Got an unrecognized response from a task.")
elif code == -1:
logger.warn("Particle %s has FAILED!!" % tempres.uid)
elif code == -2:
self.error_code = code
logger.warn(
"CachingDataController has FAILED!! Removing cache file so the particles fail."
)
try:
os.remove(self.cache_path)
except OSError:
logger.debug(
"Could not remove cache file, it probably never existed"
)
pass
elif code == -3:
self.error_code = code
logger.info(
"A zombie process was caught and task was removed from queue"
)
elif isinstance(tempres, Particle):
logger.info("Particle %d finished" % tempres.uid)
return_particles.append(tempres)
# We mulitply by 95 here to save 5% for the exporting
logger.progress(
(round((retrieved / self.total_task_count()) * 90.,
1), "Particle %d finished" % tempres.uid))
elif tempres == "CachingDataController":
logger.info("CachingDataController finished")
logger.progress(
(round((retrieved / self.total_task_count()) * 90.,
1), "CachingDataController finished"))
else:
logger.info("Got a strange result on results queue")
logger.info(str(tempres))
logger.info("Retrieved %i/%i results" %
(int(retrieved), self.total_task_count()))
# Relax
time.sleep(1)
if len(return_particles) != total_particles:
logger.warn(
"Some particles failed and are not included in the output")
# The results queue should be empty at this point
assert self.results.empty() is True
# Should be good to join on the tasks now that the queue is empty
logger.info("Joining the task queue")
self.tasks.join()
self.tasks.close()
self.tasks.join_thread()
finally:
# Join all processes
logger.info("Joining the processes")
for w in self.procs + [self.data_controller_process]:
# Wait 20 seconds
w.join(20.)
if w.is_alive():
# Process is hanging, kill it.
logger.info(
"Terminating %s forcefully. This should have exited itself."
% w.name)
w.terminate()
if self.error_code == -2:
raise ValueError(
"Error in the BaseDataController (error_code was -2)")
results = ex.ResultsPyTable(output_h5_file)
for p in return_particles:
for x in range(len(p.locations)):
results.write(p.timestep_index_dump(x))
results.compute()
results.close()
return
def start_tasks(self, **kwargs):
try:
logger.info('Starting CachingDataController')
# Add data controller to the queue first so that it
# can get the initial data and is not blocked
data_controller = CachingDataController(self.hydrodataset,
self.common_variables,
self.n_run,
self.get_data,
self.write_lock,
self.has_write_lock,
self.read_lock,
self.read_count,
self.time_chunk,
self.horiz_chunk,
self.times,
self.start,
self.point_get,
self.reference_location,
cache_path=self.cache_path)
self.tasks.put(data_controller)
# Create CachingDataController worker
self.data_controller_process = Consumer(
self.tasks,
self.results,
self.n_run,
self.nproc_lock,
self.active,
self.get_data,
name="CachingDataController")
self.data_controller_process.start()
logger.info('Adding %i particles as tasks' %
self.total_particle_count())
for part in self.particles:
forcer = CachingForcer(
self.cache_path,
particle=part,
common_variables=self.common_variables,
timevar=self.timevar,
times=self.times,
start_time=self.start,
models=self._models,
release_location_centroid=self.reference_location.point,
usebathy=self._use_bathymetry,
useshore=self._use_shoreline,
usesurface=self._use_seasurface,
reverse_distance=self.reverse_distance,
bathy_path=self.bathy_path,
shoreline_path=self.shoreline_path,
shoreline_feature=self.shoreline_feature,
time_method=self.time_method,
shoreline_index_buffer=self.shoreline_index_buffer,
get_data=self.get_data,
read_lock=self.read_lock,
has_read_lock=self.has_read_lock,
read_count=self.read_count,
point_get=self.point_get,
data_request_lock=self.data_request_lock,
has_data_request_lock=self.has_data_request_lock)
self.tasks.put(forcer)
# Create workers for the particles.
self.procs = [
Consumer(self.tasks,
self.results,
self.n_run,
self.nproc_lock,
self.active,
self.get_data,
name="CachingForcer-%d" % i)
for i in range(self.nproc - 1)
]
logger.progress((5, 'Running model'))
for w in self.procs:
w.start()
logger.info('Started %s' % w.name)
return True
except Exception:
logger.exception("Something didn't start correctly!")
return False
def export(cls, folder, particles, datetimes, summary, **kwargs):
"""
Export particle data to CF trajectory convention
netcdf file
"""
time_units = 'seconds since 1990-01-01 00:00:00'
# Create netcdf file, overwrite existing
if not os.path.exists(folder):
os.makedirs(folder)
filepath = os.path.join(folder, 'trajectories.nc')
nc = netCDF4.Dataset(filepath, 'w')
# Create netcdf dimensions
nc.createDimension('time', None)
nc.createDimension('particle', None)
fillvalue = -9999.9
# Create netcdf variables
time = nc.createVariable('time', 'i', ('time',))
part = nc.createVariable('particle', 'i', ('particle',))
depth = nc.createVariable('depth', 'f', ('time', 'particle'))
lat = nc.createVariable('lat', 'f', ('time', 'particle'), fill_value=fillvalue)
lon = nc.createVariable('lon', 'f', ('time', 'particle'), fill_value=fillvalue)
salt = nc.createVariable('salt', 'f', ('time', 'particle'), fill_value=fillvalue)
temp = nc.createVariable('temp', 'f', ('time', 'particle'), fill_value=fillvalue)
u = nc.createVariable('u', 'f', ('time', 'particle'), fill_value=fillvalue)
v = nc.createVariable('v', 'f', ('time', 'particle'), fill_value=fillvalue)
w = nc.createVariable('w', 'f', ('time', 'particle'), fill_value=fillvalue)
settled = nc.createVariable('settled', 'f', ('time', 'particle'), fill_value=fillvalue)
dead = nc.createVariable('dead', 'f', ('time', 'particle'), fill_value=fillvalue)
halted = nc.createVariable('halted', 'f', ('time', 'particle'), fill_value=fillvalue)
# Loop through locations in each particle,
# add to netcdf file
for j, particle in enumerate(particles):
part[j] = particle.uid
i = 0
normalized_locations = particle.normalized_locations(datetimes)
normalized_temps = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.temps]
normalized_salts = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.salts]
normalized_u = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.u_vectors]
normalized_v = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.v_vectors]
normalized_w = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.w_vectors]
normalized_settled = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.settles]
normalized_dead = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.deads]
normalized_halted = [x if x is not None and not math.isnan(x) else fillvalue for x in particle.halts]
if len(normalized_locations) != len(normalized_temps):
logger.info("No temperature being added to netcdf.")
# Create list of 'fillvalue' equal to the length of locations
normalized_temps = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_salts):
logger.info("No salinity being added to netcdf.")
# Create list of 'fillvalue' equal to the length of locations
normalized_salts = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_u):
logger.info("No U being added to netcdf.")
# Create list of 'fillvalue' equal to the length of locations
normalized_u = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_v):
logger.info("No V being added to netcdf.")
# Create list of 'fillvalue' equal to the length of locations
normalized_v = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_w):
logger.info("No W being added to netcdf.")
# Create list of 'fillvalue' equal to the length of locations
normalized_w = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_settled):
logger.info("No Settled being added to shapefile.")
# Create list of 'fillvalue' equal to the length of locations
normalized_settled = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_dead):
logger.info("No Dead being added to shapefile.")
# Create list of 'fillvalue' equal to the length of locations
normalized_dead = [fillvalue] * len(normalized_locations)
if len(normalized_locations) != len(normalized_halted):
logger.info("No Halted being added to shapefile.")
# Create list of 'fillvalue' equal to the length of locations
normalized_halted = [fillvalue] * len(normalized_locations)
for loc, _temp, _salt, _u, _v, _w, _settled, _dead, _halted in zip(normalized_locations, normalized_temps, normalized_salts, normalized_u, normalized_v, normalized_w, normalized_settled, normalized_dead, normalized_halted):
if j == 0:
time[i] = int(round(netCDF4.date2num(loc.time, time_units)))
depth[i, j] = loc.depth
lat[i, j] = loc.latitude
lon[i, j] = loc.longitude
salt[i, j] = _salt
temp[i, j] = _temp
u[i, j] = _u
v[i, j] = _v
w[i, j] = _w
settled[i, j] = _settled
dead[i, j] = _dead
halted[i, j] = _halted
i += 1
# Variable attributes
depth.coordinates = "time particle lat lon"
depth.standard_name = "depth_below_sea_surface"
depth.units = "m"
depth.POSITIVE = "up"
depth.positive = "up"
salt.coordinates = "time particle lat lon"
salt.standard_name = "sea_water_salinity"
salt.units = "psu"
temp.coordinates = "time particle lat lon"
temp.standard_name = "sea_water_temperature"
temp.units = "degrees_C"
u.coordinates = "time particle lat lon"
u.standard_name = "eastward_sea_water_velocity"
u.units = "m/s"
v.coordinates = "time particle lat lon"
v.standard_name = "northward_sea_water_velocity"
v.units = "m/s"
w.coordinates = "time particle lat lon"
w.standard_name = "upward_sea_water_velocity"
w.units = "m/s"
settled.coordinates = "time particle lat lon"
settled.description = "Is the particle settled"
settled.standard_name = "particle_settled"
dead.coordinates = "time particle lat lon"
dead.description = "Is the particle dead"
dead.standard_name = "particle_dead"
halted.coordinates = "time particle lat lon"
halted.description = "Is the particle prevented from being forced by currents"
halted.standard_name = "particle_halted"
time.units = time_units
time.standard_name = "time"
lat.units = "degrees_north"
lon.units = "degrees_east"
part.cf_role = "trajectory_id"
# Global attributes
nc.featureType = "trajectory"
nc.summary = str(summary)
for key in kwargs:
nc.__setattr__(key, kwargs.get(key))
nc.sync()
nc.close()
def export(cls, folder, particles, datetimes):
shape_schema = {
'geometry':
'Point',
'properties':
OrderedDict([('Particle', 'int'),
('Date', 'str'), ('Lat', 'float'), ('Lon', 'float'),
('Depth', 'float'), ('Temp', 'float'),
('Salt', 'float'), ('U', 'float'), ('V', 'float'),
('W', 'float'), ('Settled', 'str'), ('Dead', 'str'),
('Halted', 'str'), ('Age', 'float'),
('Notes', 'str')])
}
shape_crs = {
'no_defs': True,
'ellps': 'WGS84',
'datum': 'WGS84',
'proj': 'longlat'
}
filepath = os.path.join(folder, "gdalshape.shp")
with collection(filepath,
"w",
driver='ESRI Shapefile',
schema=shape_schema,
crs=shape_crs) as shape:
for particle in particles:
normalized_locations = particle.normalized_locations(datetimes)
normalized_temps = particle.temps
normalized_salts = particle.salts
normalized_u = particle.u_vectors
normalized_v = particle.v_vectors
normalized_w = particle.w_vectors
normalized_settled = particle.settles
normalized_dead = particle.deads
normalized_halted = particle.halts
normalized_ages = particle.ages
normalized_notes = particle.notes
if len(normalized_locations) != len(normalized_temps):
logger.info("No temperature being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_temps = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_temps = (-9999.9 if not x else x
for x in normalized_temps)
if len(normalized_locations) != len(normalized_salts):
logger.info("No salinity being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_salts = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_salts = (-9999.9 if not x else x
for x in normalized_salts)
if len(normalized_locations) != len(normalized_u):
logger.info("No U being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_u = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_u = (-9999.9 if not x else x
for x in normalized_u)
if len(normalized_locations) != len(normalized_v):
logger.info("No V being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_v = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_v = (-9999.9 if not x else x
for x in normalized_v)
if len(normalized_locations) != len(normalized_w):
logger.info("No W being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_w = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_w = (-9999.9 if not x else x
for x in normalized_w)
if len(normalized_locations) != len(normalized_settled):
logger.info("No Settled being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_settled = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_dead):
logger.info("No Dead being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_dead = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_halted):
logger.info("No Halted being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_halted = [None] * len(normalized_locations)
if len(normalized_locations) != len(normalized_ages):
logger.info("No W being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_ages = [-9999.9] * len(normalized_locations)
else:
# Replace any None with fill value
normalized_ages = (-9999.9 if not x else round(x, 3)
for x in normalized_ages)
if len(normalized_locations) != len(normalized_notes):
logger.info("No Notes being added to shapefile.")
# Create list of 'None' equal to the length of locations
normalized_notes = [None] * len(normalized_locations)
for loc, temp, salt, u, v, w, settled, dead, halted, age, note in zip(
normalized_locations, normalized_temps,
normalized_salts, normalized_u, normalized_v,
normalized_w, normalized_settled, normalized_dead,
normalized_halted, normalized_ages, normalized_notes):
shape.write({
'geometry':
mapping(loc.point),
'properties':
OrderedDict([('Particle', particle.uid),
('Date', unicode(loc.time.isoformat())),
('Lat', float(loc.latitude)),
('Lon', float(loc.longitude)),
('Depth', float(loc.depth)),
('Temp', float(temp)),
('Salt', float(salt)), ('U', float(u)),
('V', float(v)), ('W', float(w)),
('Settled', unicode(settled)),
('Dead', unicode(dead)),
('Halted', unicode(halted)),
('Age', float(age)),
('Notes', unicode(note))])
})
# Zip the output
shpzip = zipfile.ZipFile(os.path.join(folder, "shapefile.shp.zip"),
mode='w')
for f in glob.glob(os.path.join(folder, "gdalshape*")):
shpzip.write(f, os.path.basename(f))
os.remove(f)
shpzip.close()
