def perform_analysis(housekeeping_job):
""" The entrypoint for analysis
:return: List of analyzers that have been processed and analyzed
"""
analyzers = load_analyzers()
housekeeping_job.update_analyzer_list(analyzers)
# In case the created analyzer is activated in test or run mode, add it to the list of analyzers to evaluate
analyzers_to_evaluate = list()
for analyzer in analyzers:
# Analyzers that produced an error during configuration parsing should not be processed
if analyzer.configuration_parsing_error:
continue
if analyzer.model_settings["run_model"] or analyzer.model_settings[
"test_model"]:
analyzers_to_evaluate.append(analyzer)
# In case a single analyzer is causing issues (for example taking up too much time & resources), then a naive
# shuffle will prevent this analyzer from blocking all the analyzers from running that come after it.
random.shuffle(analyzers_to_evaluate)
# Now it's time actually evaluate all the models. We also make sure to add some information that will be useful
# in the summary presented to the user at the end of running all the models.
for index, analyzer in enumerate(analyzers_to_evaluate):
try:
analyzer.analysis_start_time = datetime.today().timestamp()
analyzer.evaluate_model()
analyzer.analysis_end_time = datetime.today().timestamp()
analyzer.completed_analysis = True
es.flush_bulk_actions()
logging.logger.info(
"finished processing use case - %d / %d [%s%% done]",
index + 1, len(analyzers_to_evaluate), '{:.2f}'.format(
round(
(index + 1) / float(len(analyzers_to_evaluate)) * 100,
2)))
except elasticsearch.exceptions.NotFoundError:
analyzer.index_not_found_analysis = True
logging.logger.warning(
"index %s does not exist, skipping use case",
analyzer.model_settings["es_index"])
except elasticsearch.helpers.BulkIndexError as e:
analyzer.unknown_error_analysis = True
logging.logger.error(
f"BulkIndexError while analyzing use case: {e.args[0]}",
exc_info=False)
logging.logger.debug(
"Full stack trace and error message of BulkIndexError",
exc_info=True)
except Exception: # pylint: disable=broad-except
analyzer.unknown_error_analysis = True
logging.logger.error("error while analyzing use case",
exc_info=True)
return analyzers_to_evaluate
def perform_analysis():
""" The entrypoint for analysis """
analyzers = list()
for config_section_name in settings.config.sections():
_analyzer = None
try:
if config_section_name.startswith("simplequery_"):
_analyzer = SimplequeryAnalyzer(
config_section_name=config_section_name)
analyzers.append(_analyzer)
elif config_section_name.startswith("metrics_"):
_analyzer = MetricsAnalyzer(
config_section_name=config_section_name)
analyzers.append(_analyzer)
elif config_section_name.startswith("terms_"):
_analyzer = TermsAnalyzer(
config_section_name=config_section_name)
analyzers.append(_analyzer)
elif config_section_name.startswith("beaconing_"):
logging.logger.error(
"use of the beaconing model is deprecated, please use the terms model using "
+
"coeff_of_variation trigger method to convert use case " +
config_section_name)
elif config_section_name.startswith("word2vec_"):
_analyzer = Word2VecAnalyzer(
config_section_name=config_section_name)
analyzers.append(_analyzer)
except Exception:
logging.logger.error("error while initializing analyzer " +
config_section_name,
exc_info=True)
analyzers_to_evaluate = list()
for analyzer in analyzers:
if analyzer.should_run_model or analyzer.should_test_model:
analyzers_to_evaluate.append(analyzer)
random.shuffle(analyzers_to_evaluate)
for index, analyzer in enumerate(analyzers_to_evaluate):
if analyzer.configuration_parsing_error:
continue
try:
analyzer.analysis_start_time = datetime.today().timestamp()
analyzer.evaluate_model()
analyzer.analysis_end_time = datetime.today().timestamp()
analyzer.completed_analysis = True
logging.logger.info("finished processing use case - " +
str(index + 1) + "/" +
str(len(analyzers_to_evaluate)) + " [" +
'{:.2f}'.format(
round((index + 1) /
float(len(analyzers_to_evaluate)) *
100, 2)) + "% done" + "]")
except elasticsearch.exceptions.NotFoundError:
analyzer.index_not_found_analysis = True
logging.logger.warning(
"index %s does not exist, skipping use case" %
analyzer.es_index)
except Exception:
analyzer.unknown_error_analysis = True
logging.logger.error("error while analyzing use case",
exc_info=True)
finally:
es.flush_bulk_actions(refresh=True)
return analyzers_to_evaluate
def perform_analysis():
""" The entrypoint for analysis """
analyzers = list()
for config_section_name in settings.config.sections():
try:
if config_section_name.startswith("simplequery_"):
simplequery_analyzer = SimplequeryAnalyzer(
config_section_name=config_section_name)
analyzers.append(simplequery_analyzer)
if config_section_name.startswith("metrics_"):
metrics_analyzer = MetricsAnalyzer(
config_section_name=config_section_name)
analyzers.append(metrics_analyzer)
if config_section_name.startswith("terms_"):
terms_analyzer = TermsAnalyzer(
config_section_name=config_section_name)
analyzers.append(terms_analyzer)
if config_section_name.startswith("beaconing_"):
beaconing_analyzer = BeaconingAnalyzer(
config_section_name=config_section_name)
analyzers.append(beaconing_analyzer)
if config_section_name.startswith("word2vec_"):
word2vec_analyzer = Word2VecAnalyzer(
config_section_name=config_section_name)
analyzers.append(word2vec_analyzer)
except Exception:
logging.logger.error(traceback.format_exc())
analyzers_to_evaluate = list()
for idx, analyzer in enumerate(analyzers):
if analyzer.should_run_model or analyzer.should_test_model:
analyzers_to_evaluate.append(analyzer)
random.shuffle(analyzers_to_evaluate)
analyzed_models = 0
for analyzer in analyzers_to_evaluate:
try:
analyzer.evaluate_model()
analyzed_models = analyzed_models + 1
logging.logger.info("finished processing use case - " +
str(analyzed_models) + "/" +
str(len(analyzers_to_evaluate)) + " [" +
'{:.2f}'.format(
round(
float(analyzed_models) /
float(len(analyzers_to_evaluate)) *
100, 2)) + "% done" + "]")
except Exception:
logging.logger.error(traceback.format_exc())
finally:
es.flush_bulk_actions(refresh=True)
if analyzed_models == 0:
logging.logger.warning(
"no use cases were analyzed. are you sure your configuration file contains use cases, which are enabled?"
)
return analyzed_models == len(analyzers_to_evaluate)