def test_clear_progress(self):
config.CACHE_EXPIRY = datetime.timedelta(seconds=1)
runid = 'runtest_clear_progress'
save_current_progress(1, runid, config)
assert 1 == get_progress(runid)
clear_progress(runid)
assert get_progress(runid) is None
def test_progress_increments(self):
config.CACHE_EXPIRY = datetime.timedelta(seconds=1)
runid = 'test_progress_increments'
save_current_progress(1, runid, config)
cached_progress = get_progress(runid)
assert cached_progress == 1
for i in range(99):
save_current_progress(1, runid, config)
assert 100 == get_progress(runid)
def test_progress_expires(self):
# Uses the minimum expiry of 1 second
config.CACHE_EXPIRY = datetime.timedelta(seconds=1)
runid = 'test_progress_expires'
save_current_progress(42, runid, config)
cached_progress = get_progress(runid)
assert cached_progress == 42
time.sleep(1)
# After expiry the progress should be reset to None
assert get_progress(runid) is None
def test_storing_wrong_type(self):
config.CACHE_EXPIRY = datetime.timedelta(seconds=1)
runid = 'test_storing_wrong_type'
with pytest.raises(redis.exceptions.ResponseError):
save_current_progress(1.5, runid, config)
def compute_filter_similarity(chunk_info,
project_id,
run_id,
threshold,
encoding_size,
parent_span=None):
"""Compute filter similarity between a chunk of filters in dataprovider 1,
and a chunk of filters in dataprovider 2.
:param chunk_info:
Chunk info returned by ``anonlink.concurrency.split_to_chunks``.
Additionally, "storeFilename" is added to each dataset chunk.
:param project_id:
:param threshold:
:param encoding_size: The size in bytes of each encoded entry
:param parent_span: A serialized opentracing span context.
@returns A 2-tuple: (num_results, results_filename_in_object_store)
"""
log = logger.bind(pid=project_id, run_id=run_id)
log.debug("Computing similarity for a chunk of filters")
span = compute_filter_similarity.span
log.debug(
"Checking that the resource exists (in case of job being canceled)")
with DBConn() as db:
if not check_project_exists(db, project_id) or not check_run_exists(
db, project_id, run_id):
log.info("Failing task as project or run not found in database.")
raise DBResourceMissing("project or run not found in database")
chunk_info_dp1, chunk_info_dp2 = chunk_info
t0 = time.time()
log.debug("Fetching and deserializing chunk of filters for dataprovider 1")
chunk_dp1, chunk_dp1_size = get_chunk_from_object_store(
chunk_info_dp1, encoding_size)
t1 = time.time()
log.debug("Fetching and deserializing chunk of filters for dataprovider 2")
chunk_dp2, chunk_dp2_size = get_chunk_from_object_store(
chunk_info_dp2, encoding_size)
t2 = time.time()
span.log_kv({'event': 'chunks are fetched and deserialized'})
log.debug("Calculating filter similarity")
span.log_kv({'size1': chunk_dp1_size, 'size2': chunk_dp2_size})
chunk_results = anonlink.concurrency.process_chunk(
chunk_info, (chunk_dp1, chunk_dp2),
anonlink.similarities.dice_coefficient_accelerated,
threshold,
k=min(chunk_dp1_size, chunk_dp2_size))
t3 = time.time()
span.log_kv({'event': 'similarities calculated'})
# Update the number of comparisons completed
comparisons_computed = chunk_dp1_size * chunk_dp2_size
save_current_progress(comparisons_computed, run_id)
t4 = time.time()
sims, _, _ = chunk_results
num_results = len(sims)
if num_results:
result_filename = Config.SIMILARITY_SCORES_FILENAME_FMT.format(
generate_code(12))
log.info("Writing {} intermediate results to file: {}".format(
num_results, result_filename))
bytes_iter, file_size \
= anonlink.serialization.dump_candidate_pairs_iter(chunk_results)
iter_stream = iterable_to_stream(bytes_iter)
mc = connect_to_object_store()
try:
mc.put_object(Config.MINIO_BUCKET, result_filename, iter_stream,
file_size)
except minio.ResponseError as err:
log.warning("Failed to store result in minio")
raise
else:
result_filename = None
file_size = None
t5 = time.time()
log.info("run={} Comparisons: {}, Links above threshold: {}".format(
run_id, comparisons_computed, len(chunk_results)))
log.info(
"Prep: {:.3f} + {:.3f}, Solve: {:.3f}, Progress: {:.3f}, Save: {:.3f}, Total: {:.3f}"
.format(t1 - t0, t2 - t1, t3 - t2, t4 - t3, t5 - t4, t5 - t0))
return num_results, file_size, result_filename
def compute_filter_similarity(chunk_info_dp1, chunk_info_dp2, project_id, run_id, threshold, encoding_size, parent_span=None):
"""Compute filter similarity between a chunk of filters in dataprovider 1,
and a chunk of filters in dataprovider 2.
:param chunk_info_dp1:
A tuple containing:
- object store filename
- Chunk start index
- Chunk stop index
:param chunk_info_dp2:
:param project_id:
:param threshold:
:param encoding_size: The size in bytes of each encoded entry
:param parent_span: A serialized opentracing span context.
"""
log = logger.bind(pid=project_id, run_id=run_id)
log.debug("Computing similarity for a chunk of filters")
span = compute_filter_similarity.span
log.debug("Checking that the resource exists (in case of job being canceled)")
with DBConn() as db:
if not check_project_exists(db, project_id) or not check_run_exists(db, project_id, run_id):
log.info("Stopping as project or run not found in database.")
return None
t0 = time.time()
log.debug("Fetching and deserializing chunk of filters for dataprovider 1")
chunk_dp1, chunk_dp1_size = get_chunk_from_object_store(chunk_info_dp1, encoding_size)
t1 = time.time()
log.debug("Fetching and deserializing chunk of filters for dataprovider 2")
chunk_dp2, chunk_dp2_size = get_chunk_from_object_store(chunk_info_dp2, encoding_size)
t2 = time.time()
span.log_kv({'event': 'chunks are fetched and deserialized'})
log.debug("Calculating filter similarity")
span.log_kv({'size1': chunk_dp1_size, 'size2': chunk_dp2_size})
chunk_results = anonlink.entitymatch.calculate_filter_similarity(chunk_dp1, chunk_dp2,
threshold=threshold,
k=min(chunk_dp1_size, chunk_dp2_size),
use_python=False)
t3 = time.time()
span.log_kv({'event': 'similarities calculated'})
# Update the number of comparisons completed
comparisons_computed = chunk_dp1_size * chunk_dp2_size
save_current_progress(comparisons_computed, run_id)
t4 = time.time()
partial_sparse_result = []
# offset chunk's index
offset_dp1 = chunk_info_dp1[1]
offset_dp2 = chunk_info_dp2[1]
log.debug("Offset DP1 by: {}, DP2 by: {}".format(offset_dp1, offset_dp2))
for (ia, score, ib) in chunk_results:
partial_sparse_result.append((ia + offset_dp1, ib + offset_dp2, score))
t5 = time.time()
num_results = len(partial_sparse_result)
if num_results > 0:
result_filename = 'chunk-res-{}.csv'.format(generate_code(12))
log.info("Writing {} intermediate results to file: {}".format(num_results, result_filename))
with open(result_filename, 'wt') as f:
csvwriter = csv.writer(f)
csvwriter.writerows(partial_sparse_result)
# Now write these to the object store. and return the filename and summary
# Will write a csv file for now
mc = connect_to_object_store()
try:
mc.fput_object(Config.MINIO_BUCKET, result_filename, result_filename)
except minio.ResponseError as err:
log.warning("Failed to store result in minio")
raise
# If we don't delete the file we *do* run out of space
os.remove(result_filename)
else:
result_filename = None
t6 = time.time()
log.info("run={} Comparisons: {}, Links above threshold: {}".format(run_id, comparisons_computed, len(chunk_results)))
log.info("Prep: {:.3f} + {:.3f}, Solve: {:.3f}, Progress: {:.3f}, Offset: {:.3f}, Save: {:.3f}, Total: {:.3f}".format(
t1 - t0,
t2 - t1,
t3 - t2,
t4 - t3,
t4 - t4,
t6 - t5,
t6 - t0)
)
return num_results, result_filename