def distribution_learning_suite_v1(chembl_file_path: str, number_samples: int = 10000) -> \
List[DistributionLearningBenchmark]:
"""
Suite of distribution learning benchmarks, v1.
Args:
chembl_file_path: path to the file with the reference ChEMBL molecules
Returns:
List of benchmarks, version 1
"""
return [
ValidityBenchmark(number_samples=number_samples),
UniquenessBenchmark(number_samples=number_samples),
novelty_benchmark(training_set_file=chembl_file_path,
number_samples=number_samples),
kldiv_benchmark(training_set_file=chembl_file_path,
number_samples=number_samples),
frechet_benchmark(training_set_file=chembl_file_path,
number_samples=number_samples)
]
def assess_distribution_learning(model: DistributionMatchingGenerator,
training_file_path: str,
json_output_file: str,
number_samples: int) -> None:
LOG.info('Benchmarking distribution learning')
benchmarks = [
ValidityBenchmark(number_samples=number_samples),
UniquenessBenchmark(number_samples=number_samples),
novelty_benchmark(training_set_file=training_file_path, number_samples=number_samples),
kldiv_benchmark(training_set_file=training_file_path, number_samples=number_samples),
]
results = _evaluate_distribution_learning_benchmarks(model=model, benchmarks=benchmarks)
benchmark_results = OrderedDict()
benchmark_results['guacamol_version'] = guacamol.__version__
benchmark_results['timestamp'] = get_time_string()
benchmark_results['results'] = [vars(result) for result in results]
LOG.info('Save results to file %s', json_output_file)
with open(json_output_file, 'wt') as f:
f.write(json.dumps(benchmark_results, indent=4))