def __init__(self, filename="*&$#$%#", file_mode="r", cachesize=1048576):
# If the filename isn't specified, use the default one (None has a
# special meaning, so we can't use it - it means create a temp file)
if filename == "*&$#$%#":
filename = _DEFAULT_TREE_DATA
logging.info("Initializing tree with data from %r", filename)
self._tree = StringDBDict(persistent_file=filename,
file_mode=file_mode,
cachesize=cachesize)
self._invlookup = None # Init the inverse name lookup database lazily
self._origname = filename
self.terms = self._tree.keys()
self.terms.sort()
# This one is for speedy retrieval and indexing
self._term_list_as_dict = None
self._search_dict = None
self.num_terms = len(self.terms)
return
def __init__(self, reader, graph_builder, ranker, eval_parameters,
ranking_cutoff, mesh_tree_filename, distance_matrix_filename,
distance_function, umls_converter_data_filename,
umls_concept_data_filename, output_file):
logging.debug("Setting up a Workflow instance.")
logging.debug("My reader is: %r", reader)
self._reader = reader
logging.debug("My graph builder is: %r", graph_builder)
self._graph_builder = graph_builder
self._ranker = MappedRanker(ranker)
logging.debug("My ranker is: %r", self._ranker)
self._ranking_cutoff = ranking_cutoff
logging.debug("My ranking cutoff is: %r", self._ranking_cutoff)
logging.debug("Creating a Tree instance from %s", mesh_tree_filename)
self._mesh_tree = Tree(mesh_tree_filename)
logging.debug(
"Creating SAVCC distance matrix with %r and distance "
"function %r", distance_matrix_filename, distance_function)
self._matrix = SavccNormalizedMatrix(
open(distance_matrix_filename, "rb"), distance_function)
logging.debug("Filling in the rest of the evaluation parameters.")
self._eval_parameters = eval_parameters
self._eval_parameters.mesh_tree = self._mesh_tree
self._eval_parameters.savcc_matrix = self._matrix
logging.debug("My evaluation parameters are: %r",
self._eval_parameters)
if umls_converter_data_filename is None:
converter_data = None
else:
converter_data = pickle.load(
open(umls_converter_data_filename, "rb"))
self._umls_converter = RankedConverter(
Converter(self._mesh_tree, converter_data))
logging.debug("My converter is: %r", self._umls_converter)
logging.debug("Initializing Concept storage from %s",
umls_concept_data_filename)
if umls_concept_data_filename is None:
Concept.init_storage()
else:
Concept.init_storage(StringDBDict(umls_concept_data_filename))
self._output_file = output_file
logging.debug("My output file is: %r", self._output_file)
return
def main():
mrsty_file=sys.argv[3]
original_filename=sys.argv[2]
data_store_name=sys.argv[1]
original_file=Text(bz2.BZ2File(original_filename, 'r'))
print "Loading semantic types from %s" % mrsty_file
stypes=SemanticTypes()
stypes.build_from_mrsty_file(MRSTYTable(bz2.BZ2File(mrsty_file)))
print "Semantic types loaded."
print "Turning the data from %s into %s. Please wait." % (
original_filename, data_store_name)
data_store=StringDBDict(data_store_name,
sync_every_transactions=0,
write_out_every_transactions=200000,
file_mode='c')
data_store.sync_every=0
build_concept_dictionary(original_file, data_store, stypes)
data_store.sync_every=100
print "Conversion done."
def __init__(self):
try:
self._cache_location = sys.argv[2]
except IndexError:
self._cache_location = DEFAULT_CACHE_NAME
self._cache = StringDBDict(self._cache_location, file_mode="c")
def __init__(self):
try:
self._cache_location = sys.argv[2]
except IndexError:
self._cache_location = _DEFAULT_CONCEPT_STORAGE
self._cache = StringDBDict(self._cache_location, file_mode="r")
chunk=chunk.strip()
for k, v in tok_bact.iteritems():
chunk=chunk.replace(k, v)
if reduce(operator.or_,
[x in chunk.lower() for x in useless_lines]): continue
if len(chunk) < 2: continue
outfile.write('%010d|%s\n' % (chunkid, chunk))
chunkmap[fakename].append(chunkid)
chunkid += 1
outfile.close()
print "Saving chunkmap"
pickle.dump(chunkmap, open(outmapname, "wb"), pickle.HIGHEST_PROTOCOL)
print "These files couldn't be processed:"
print '\n'.join(skipped)
print "Opening (or creating) cache in", sys.argv[2]
the_cache=StringDBDict(os.path.join(sys.argv[2], DEFAULT_CACHE_NAME),
file_mode='c')
PubMed.download_many([str(x) for x in known_articles if str(x) not in
the_cache.keys()], download_callback,
parser=Medline.RecordParser())
mti_filename=sys.argv[1]+'.mti'
print "Finished processing the cache. Using the cache to build", \
mti_filename
mti_file=open(mti_filename, "w")
chunkmap={}
hexfinder=re.compile(r'\\x[a-f0-9][a-f0-9]', re.IGNORECASE)
for article in known_articles:
try:
article_record=the_cache[str(article)]
except KeyError:
print "Article doesn't exist in cache. Skipping."
continue
trees[term] = TreeNode(term, role, synonyms, set(position))
return trees
if __name__ == "__main__":
# The pickling and unpickling make this horribly slow, so we'll trade some
# memory for speed in the build process and later turn the dictionary into
# a DB-backed one.
tree_storage = {}
for treefile in sys.argv[2:]:
treesfile = bz2.BZ2File(treefile, 'rU')
print "Reading %s..." % treefile
tree_storage = build_tree_from_descriptor_file(treesfile, tree_storage)
print "Tree built. It has %d unique terms." % len(tree_storage)
print "For example... arm=", tree_storage['arm'], " and eye=", \
tree_storage['eye']
print "Done generating tree."
print "Storing tree in", sys.argv[1]
tree_on_disk = StringDBDict(persistent_file=sys.argv[1],
sync_every_transactions=0,
write_out_every_transactions=0,
file_mode='c')
write_counter = 0
for k, v in tree_storage.iteritems():
tree_on_disk[k] = v
write_counter += 1
if write_counter % 1000 == 0:
print "Stored", write_counter, "terms."
tree_on_disk.sync_every = 1
print "Done storing."
def multi_processor(reader,
workflow_class,
graph_builder_constructor, graph_builder_params,
ranker_constructor, ranker_params,
eval_parameters,
ranking_cutoff,
mesh_tree_filename, distance_matrix_filename,
distance_function,
umls_converter_data_filename,
umls_concept_data_filename,
extra_data_name,
extra_data_contents,
output_file,
num_threads=None,
queue_size=None,
output_callback=output,
output_headers_callback=output_headers,
output_item_callback=output_one_item,
performance_tuning=True):
"""
Perform the evaluation.
Multithreading notes: It's the responsibility of the caller to make sure
that extra_data_contents, if any, are thread-safe.
"""
if num_threads is None:
num_threads=1
logging.debug("Initializing Concept storage from %s",
umls_concept_data_filename)
# Since there's no direct way of setting the concept cache's title,
# we set it here, wait for it to be inherited, and then get the 'real'
# process title for this one.
if umls_concept_data_filename is None:
Concept.init_storage()
else:
Concept.init_storage(StringDBDict(umls_concept_data_filename))
Pmid.init_storage()
threads=[]
logging.info("Creating %d worker threads.", num_threads)
#task_queue=[JoinableQueue(queue_size) for x in xrange(num_processes)]
task_queues=[Queue(queue_size) for x in xrange(num_threads)]
this_output_queue=Queue(2*queue_size)
# Create an output processor
output_processor=Thread(target=output_callback,
args=(output_file,
this_output_queue,
output_headers_callback,
output_item_callback))
output_processor.start()
for i in xrange(num_threads):
this_thread=Thread(target=processor, args=(workflow_class,
graph_builder_constructor,
graph_builder_params,
ranker_constructor,
ranker_params,
eval_parameters,
ranking_cutoff,
mesh_tree_filename,
distance_matrix_filename,
distance_function,
umls_converter_data_filename,
extra_data_name,
extra_data_contents,
task_queues[i],
this_output_queue),
name="MEDRank-Worker-%d" % i)
logging.log(ULTRADEBUG, "Created thread: %r", this_thread)
this_thread.start()
threads.append((this_thread, this_output_queue, task_queues[i]))
all_results={}
count=0
# Use a single dispatch queue for automagical load balancing
# CHANGED - Now uses multiple queues to avoid starving due to waiting on semlocks
for each_article in reader:
count+=1
# logging.info("Dispatching article %d: %r", count, each_article)
target_thread=(count-1) % num_threads
logging.info("Dispatching article %d: %s to %s",
count,
each_article.set_id,
threads[target_thread][0].name)
task_queues[target_thread].put(each_article)
#task_queue[target_process].put(each_article)
#task_queue.put(each_article)
#logging.info("The task queue is approximately %d items long.",
# task_queue.qsize())
logging.log(ULTRADEBUG, "Waiting for processing to end.")
all_results={}
alive_threads=[x for x in threads if x[0].is_alive()]
remaining_threads=len(alive_threads)
logging.info("There are %d threads (out of %d) still alive.",
remaining_threads,
num_threads)
for i in xrange(remaining_threads):
alive_threads[i][2].put('STOP')
#alive_threads[i][2].close()
logging.debug("Sent STOP requests. Notifying queue that no further "
"requests will come.")
logging.info("All information sent to the threads.")
# Note end of output
while len(threads)>0:
a_thread=threads.pop()
# We join the process to wait for the end of the reading
a_thread[0].join()
# logging.log(ULTRADEBUG, "Fetching results from finished process.")
# all_results.update(a_process[1].get()) # Add results to result pool
# logging.log(ULTRADEBUG, "Received results.")
logging.info("Finishing writing out results.")
this_output_queue.put("STOP")
output_processor.join()
logging.info("Results written. Finishing multithreading.")
Pmid.close_storage()
return
def multi_processor(reader,
workflow_class,
graph_builder_constructor,
graph_builder_params,
ranker_constructor,
ranker_params,
eval_parameters,
ranking_cutoff,
mesh_tree_filename,
distance_matrix_filename,
distance_function,
umls_converter_data_filename,
umls_concept_data_filename,
extra_data_name,
extra_data_contents,
output_file,
num_processes=None,
queue_size=None,
output_callback=output,
output_headers_callback=output_headers,
output_item_callback=output_one_item,
performance_tuning=True):
"""
Perform the evaluation.
Multiprocessing notes: It's the responsibility of the caller to make sure that
extra_data_contents, if any, are multiprocessing-safe. For example, by using
a SyncManager and Namespace and passing the proxy. See umls/concept for an example.
"""
if num_processes is None:
num_processes = cpu_count()
if performance_tuning:
# Since reading the file involves an awful lot of object creation
# and destruction we'll tweak the gc adjustments to sweep less frequently
# IOW - we have a LOT of short-lived objects. No sense garbage-collecting
# the latter generations very often.
# (this is about 10x, 5x, and 5x the usual)
original_threshold = gc.get_threshold()
gc.set_threshold(10 * original_threshold[0], 5 * original_threshold[1],
5 * original_threshold[1])
original_check_interval = sys.getcheckinterval()
# Similarly, we'll try to minimize overhead from thread switches
# 5x usual value
sys.setcheckinterval(5 * original_check_interval)
logging.debug("Initializing Concept storage from %s",
umls_concept_data_filename)
if umls_concept_data_filename is None:
Concept.init_storage()
else:
Concept.init_storage(StringDBDict(umls_concept_data_filename))
Pmid.init_storage()
proctitle.setproctitle("MEDRank-main")
processes = []
logging.info("Creating %d worker processes.", num_processes)
#task_queue=[JoinableQueue(queue_size) for x in xrange(num_processes)]
task_queues = [Queue(queue_size) for x in xrange(num_processes)]
this_output_queue = Queue(2 * queue_size)
# Create an output processor
output_processor = Process(target=output_callback,
args=(output_file, this_output_queue,
output_headers_callback,
output_item_callback))
output_processor.start()
for i in xrange(num_processes):
this_process = Process(
target=processor,
args=(workflow_class, graph_builder_constructor,
graph_builder_params, ranker_constructor, ranker_params,
eval_parameters, ranking_cutoff, mesh_tree_filename,
distance_matrix_filename, distance_function,
umls_converter_data_filename, extra_data_name,
extra_data_contents, task_queues[i], this_output_queue,
"MEDRank-Worker-%d" % i),
name="MEDRank-Worker-%d" % i)
logging.log(ULTRADEBUG, "Created process: %r", this_process)
this_process.start()
processes.append((this_process, this_output_queue, task_queues[i]))
all_results = {}
count = 0
# Use a single dispatch queue for automagical load balancing
# CHANGED - Now uses multiple queues to avoid starving due to waiting on semlocks
for each_article in reader:
count += 1
#queues_and_sizes=[(task_queues[x].qsize(), x)
# for x in xrange(num_processes)]
#queues_and_sizes.sort()
#target_process=queues_and_sizes[0][1]
# logging.info("Dispatching article %d: %r", count, each_article)
target_process = (count - 1) % num_processes
#Lowest-loaded process first.
logging.info("Dispatching article %d: %s to %s", count,
each_article.set_id, processes[target_process][0].name)
task_queues[target_process].put(each_article)
#task_queue[target_process].put(each_article)
#task_queue.put(each_article)
#logging.info("The task queue is approximately %d items long.",
# task_queue.qsize())
logging.log(ULTRADEBUG, "Waiting for processing to end.")
all_results = {}
alive_processes = [x for x in processes if x[0].is_alive()]
remaining_processes = len(alive_processes)
logging.info("There are %d processes (out of %d) still alive.",
remaining_processes, num_processes)
for i in xrange(remaining_processes):
alive_processes[i][2].put('STOP')
alive_processes[i][2].close()
logging.debug("Sent STOP requests. Notifying queue that no further "
"requests will come.")
logging.info("All information sent to the processors.")
# Back to normal
if performance_tuning:
gc.set_threshold(original_threshold[0], original_threshold[1],
original_threshold[2])
sys.setcheckinterval(original_check_interval)
# Note end of output
while len(processes) > 0:
a_process = processes.pop()
# We join the process to wait for the end of the reading
a_process[0].join()
# logging.log(ULTRADEBUG, "Fetching results from finished process.")
# all_results.update(a_process[1].get()) # Add results to result pool
# logging.log(ULTRADEBUG, "Received results.")
logging.info("Finishing writing out results.")
this_output_queue.put("STOP")
output_processor.join()
logging.info("Results written. Finishing multiprocessing.")
return