def _get_test_evaluator(out_dir, overwrite=False):
return evaluator.Evaluator(
evaluation_config=self.evaluation_config,
sketch_estimator_config_list=self.sketch_estimator_config_list,
run_name=self.run_name,
out_dir=out_dir,
overwrite=overwrite)
def _run_evaluation_and_simulation(out_dir):
self.evaluator = evaluator.Evaluator(
evaluation_config=self.evaluation_config,
sketch_estimator_config_list=self.sketch_estimator_config_list,
run_name=self.evaluation_run_name,
out_dir=out_dir)
self.evaluator()
self.analyzer = analyzer.CardinalityEstimatorEvaluationAnalyzer(
out_dir=out_dir,
evaluation_directory=out_dir,
evaluation_run_name=self.evaluation_run_name,
evaluation_name=self.evaluation_config.name,
estimable_criteria_list=[(0.05, 0.95), (1.01, 0.9)])
self.analyzer()
def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
noiser_flip_probability = 1 / (1 + np.exp(FLAGS.noiser_epsilon))
universe_size = int(100 * FLAGS.sketch_size)
## config all decay rates
estimator_config_list = []
for a in FLAGS.exponential_bloom_filter_decay_rate:
estimator_config_exponential_bloom_filter = SketchEstimatorConfig(
name='exp_BF_' + str(int(a)),
sketch_factory=ExponentialBloomFilter.get_sketch_factory(
FLAGS.sketch_size, a),
estimator=FirstMomentEstimator(
method='exp',
denoiser=SurrealDenoiser(probability=noiser_flip_probability)),
sketch_noiser=BlipNoiser(FLAGS.noiser_epsilon))
estimator_config_list += [estimator_config_exponential_bloom_filter]
# config evaluation
scenario_config_list = []
for set_size_ratio in FLAGS.set_size_ratio:
set_size = int(set_size_ratio * FLAGS.sketch_size)
## list scenarios
scenario_config_list += [
configs.ScenarioConfig(
name=str(int(set_size_ratio)),
set_generator_factory=(set_generator.IndependentSetGenerator.
get_generator_factory_with_num_and_size(
universe_size=universe_size,
num_sets=FLAGS.number_of_sets,
set_size=set_size)))
]
evaluation_config = configs.EvaluationConfig(
name='3_vary_decay_rate_' + str(int(FLAGS.sketch_size / 1000)) + "k",
num_runs=FLAGS.number_of_trials,
scenario_config_list=scenario_config_list)
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=estimator_config_list,
run_name="eval_adbf_result",
out_dir=".",
workers=10)
generate_results()
def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
## config all decay rates
estimator_config_list = []
for sketch_size in FLAGS.sketch_size:
for epsilon in FLAGS.noiser_epsilon:
estimator_config_exponential_bloom_filter = SketchEstimatorConfig(
## flipping prob
name=str(int(sketch_size / 1000)) + "k_" + \
"{:.2f}".format(1 / (1 + np.exp(epsilon))),
sketch_factory=ExponentialBloomFilter.get_sketch_factory(
sketch_size, FLAGS.exponential_bloom_filter_decay_rate),
estimator=FirstMomentEstimator(
method='exp',
denoiser=SurrealDenoiser(epsilon)),
sketch_noiser=BlipNoiser(epsilon))
estimator_config_list += [
estimator_config_exponential_bloom_filter
]
# config evaluation
scenario_config_list = []
for universe_size in FLAGS.universe_size:
scenario_config_list += [
configs.ScenarioConfig(
name="{:.1f}".format(universe_size / 1000000),
set_generator_factory=(set_generator.IndependentSetGenerator.
get_generator_factory_with_num_and_size(
universe_size=universe_size,
num_sets=FLAGS.number_of_sets,
set_size=FLAGS.set_size)))
]
evaluation_config = configs.EvaluationConfig(
name='5_prediction',
num_runs=FLAGS.number_of_trials,
scenario_config_list=scenario_config_list)
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=estimator_config_list,
run_name="eval_adbf_result",
out_dir=".",
workers=10)
generate_results()
def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
required_flags = ('evaluation_out_dir', 'analysis_out_dir',
'evaluation_config', 'sketch_estimator_configs',
'evaluation_run_name', 'num_runs')
for f in required_flags:
flags.mark_flag_as_required(f)
logging.set_verbosity(logging.INFO)
logging.info('====Running %s using evaluation %s for:\n%s',
FLAGS.evaluation_config, FLAGS.evaluation_run_name,
', '.join(FLAGS.sketch_estimator_configs))
evaluation_config = evaluation_configs.NAME_TO_EVALUATION_CONFIGS[
FLAGS.evaluation_config](FLAGS.num_runs)
sketch_estimator_config_list = [
evaluation_configs.NAME_TO_ESTIMATOR_CONFIGS[conf]
for conf in FLAGS.sketch_estimator_configs
]
# Run simulations.
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=sketch_estimator_config_list,
run_name=FLAGS.evaluation_run_name,
out_dir=FLAGS.evaluation_out_dir)
generate_results()
# Analyze results.
logging.info('====Analyzing the results.')
generate_summary = analyzer.CardinalityEstimatorEvaluationAnalyzer(
out_dir=FLAGS.analysis_out_dir,
evaluation_directory=FLAGS.evaluation_out_dir,
evaluation_run_name=FLAGS.evaluation_run_name,
evaluation_name=evaluation_config.name,
error_margin=FLAGS.error_margin,
proportion_of_runs=FLAGS.proportion_of_runs,
plot_params={
analyzer.BOXPLOT_SIZE_WIDTH_INCH: FLAGS.boxplot_size_width_inch,
analyzer.BOXPLOT_SIZE_HEIGHT_INCH: FLAGS.boxplot_size_height_inch,
})
generate_summary()
logging.info('====Evaluation and analysis done!')
def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
noiser_flip_probability = 1 / (1 + np.exp(FLAGS.noiser_epsilon))
## list three adbf estimators
estimator_config_geometric_bloom_filter = SketchEstimatorConfig(
name='geo_BF',
sketch_factory=GeometricBloomFilter.get_sketch_factory(
FLAGS.sketch_size, FLAGS.geometric_bloom_filter_probability),
estimator=FirstMomentEstimator(
method='geo',
denoiser=SurrealDenoiser(
probability=noiser_flip_probability)),
sketch_noiser=BlipNoiser(FLAGS.noiser_epsilon))
estimator_config_logarithmic_bloom_filter = SketchEstimatorConfig(
name='log_BF',
sketch_factory=LogarithmicBloomFilter.get_sketch_factory(
FLAGS.sketch_size),
estimator=FirstMomentEstimator(
method='log',
denoiser=SurrealDenoiser(
probability=noiser_flip_probability)),
sketch_noiser=BlipNoiser(FLAGS.noiser_epsilon))
estimator_config_exponential_bloom_filter = SketchEstimatorConfig(
name='exp_BF',
sketch_factory=ExponentialBloomFilter.get_sketch_factory(
FLAGS.sketch_size, FLAGS.exponential_bloom_filter_decay_rate),
estimator=FirstMomentEstimator(
method='exp',
denoiser=SurrealDenoiser(
probability=noiser_flip_probability)),
sketch_noiser=BlipNoiser(FLAGS.noiser_epsilon))
estimator_config_list = [
estimator_config_geometric_bloom_filter,
estimator_config_logarithmic_bloom_filter,
estimator_config_exponential_bloom_filter,
]
# list scenarios of different set sizes
scenario_config_list = []
for set_size_ratio in FLAGS.set_size_ratio:
set_size = int(set_size_ratio * FLAGS.sketch_size)
scenario_config_list += [
configs.ScenarioConfig(
name="{:.1f}".format(set_size_ratio),
set_generator_factory=(
set_generator.IndependentSetGenerator
.get_generator_factory_with_num_and_size(
universe_size=FLAGS.universe_size,
num_sets=FLAGS.number_of_sets,
set_size=set_size)))
]
evaluation_config = configs.EvaluationConfig(
name='2_vary_set_size',
num_runs=FLAGS.number_of_trials,
scenario_config_list=scenario_config_list)
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=estimator_config_list,
run_name="eval_adbf_result",
out_dir=".",
workers=10)
generate_results()
def _run(run_evaluation,
run_analysis,
generate_html_report,
evaluation_out_dir,
analysis_out_dir,
report_out_dir,
evaluation_config,
sketch_estimator_configs,
evaluation_run_name,
num_runs,
num_workers,
error_margin,
proportion_of_runs,
boxplot_xlabel_rotate,
boxplot_size_width_inch,
boxplot_size_height_inch,
analysis_type,
max_frequency,
barplot_size_width_inch=None,
barplot_size_height_inch=None,
universe_size=None):
"""Run evaluation."""
evaluation_config_args = {'num_runs': num_runs}
if universe_size is not None:
evaluation_config_args.update({'universe_size': int(universe_size)})
evaluation_config = evaluation_configs.get_evaluation_config(
evaluation_config)(**evaluation_config_args)
sketch_estimator_config_list = evaluation_configs.get_estimator_configs(
sketch_estimator_configs, max_frequency)
if run_evaluation:
logging.info('====Running %s using evaluation %s for:\n%s',
evaluation_config, evaluation_run_name,
', '.join(sketch_estimator_configs))
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=sketch_estimator_config_list,
run_name=evaluation_run_name,
out_dir=evaluation_out_dir,
workers=num_workers)
generate_results()
error_margin = [float(x) for x in error_margin]
proportion_of_runs = [float(x) for x in proportion_of_runs]
estimable_criteria_list = list(
map(tuple, zip(error_margin, proportion_of_runs)))
if analysis_type == 'frequency':
estimator_analyzer_func = analyzer.FrequencyEstimatorEvaluationAnalyzer
report_generator_func = report_generator.FrequencyReportGenerator
else:
estimator_analyzer_func = analyzer.CardinalityEstimatorEvaluationAnalyzer
report_generator_func = report_generator.CardinalityReportGenerator
if run_analysis:
logging.info('====Analyzing the results.')
generate_summary = estimator_analyzer_func(
out_dir=analysis_out_dir,
evaluation_directory=evaluation_out_dir,
evaluation_run_name=evaluation_run_name,
evaluation_name=evaluation_config.name,
estimable_criteria_list=estimable_criteria_list,
plot_params={
analyzer.XLABEL_ROTATE: boxplot_xlabel_rotate,
analyzer.BOXPLOT_SIZE_WIDTH_INCH: boxplot_size_width_inch,
analyzer.BOXPLOT_SIZE_HEIGHT_INCH: boxplot_size_height_inch,
analyzer.BARPLOT_SIZE_WIDTH_INCH: barplot_size_width_inch,
analyzer.BARPLOT_SIZE_HEIGHT_INCH: barplot_size_height_inch,
})
generate_summary()
logging.info('====Evaluation and analysis done!')
if generate_html_report:
generate_report = report_generator_func(
out_dir=report_out_dir,
analysis_out_dir=analysis_out_dir,
evaluation_run_name=evaluation_run_name,
evaluation_name=evaluation_config.name)
report_url = generate_report()
logging.info('====Report generated: %s.', report_url)
def get_test_evaluator(self, out_dir):
return evaluator.Evaluator(
evaluation_config=self.evaluation_config,
sketch_estimator_config_list=self.sketch_estimator_config_list,
run_name=self.run_name,
out_dir=out_dir)
def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
## list all estimators
estimator_config_list = []
for epsilon in FLAGS.noiser_epsilon:
## flipping prob
noiser_flip_probability = 1 / (1 + np.exp(epsilon))
# estimator_config_bloom_filter = SketchEstimatorConfig(
# name='unif_BF_' + "{:.2f}".format(noiser_flip_probability),
# sketch_factory=BloomFilter.get_sketch_factory(
# FLAGS.sketch_size, FLAGS.num_bloom_filter_hashes),
# estimator=UnionEstimator(),
# sketch_noiser=BlipNoiser(epsilon))
estimator_config_geometric_bloom_filter = SketchEstimatorConfig(
name='geo_BF_' + "{:.2f}".format(noiser_flip_probability),
sketch_factory=GeometricBloomFilter.get_sketch_factory(
FLAGS.sketch_size, FLAGS.geometric_bloom_filter_probability),
estimator=FirstMomentEstimator(method='geo',
denoiser=SurrealDenoiser(epsilon)),
sketch_noiser=BlipNoiser(epsilon))
estimator_config_logarithmic_bloom_filter = SketchEstimatorConfig(
name='log_BF_' + "{:.2f}".format(noiser_flip_probability),
sketch_factory=LogarithmicBloomFilter.get_sketch_factory(
FLAGS.sketch_size),
estimator=FirstMomentEstimator(method='log',
denoiser=SurrealDenoiser(epsilon)),
sketch_noiser=BlipNoiser(epsilon))
estimator_config_exponential_bloom_filter = SketchEstimatorConfig(
name='exp_BF_' + "{:.2f}".format(noiser_flip_probability),
sketch_factory=ExponentialBloomFilter.get_sketch_factory(
FLAGS.sketch_size, FLAGS.exponential_bloom_filter_decay_rate),
estimator=FirstMomentEstimator(method='exp',
denoiser=SurrealDenoiser(epsilon)),
sketch_noiser=BlipNoiser(epsilon))
estimator_config_list += [
# estimator_config_bloom_filter,
estimator_config_geometric_bloom_filter,
estimator_config_logarithmic_bloom_filter,
estimator_config_exponential_bloom_filter,
]
# config evaluation
evaluation_config = configs.EvaluationConfig(
name='1_vary_flip_prob',
num_runs=FLAGS.number_of_trials,
scenario_config_list=[
configs.ScenarioConfig(
name='independent',
set_generator_factory=(set_generator.IndependentSetGenerator.
get_generator_factory_with_num_and_size(
universe_size=FLAGS.universe_size,
num_sets=FLAGS.number_of_sets,
set_size=FLAGS.set_size)))
])
generate_results = evaluator.Evaluator(
evaluation_config=evaluation_config,
sketch_estimator_config_list=estimator_config_list,
run_name="eval_adbf_result",
out_dir=".",
workers=10)
generate_results()
