def run_predictions(input_path, output_path, thresholds_file, num_skip,
check_existing):
"""Creates thread pool which will concurrently run the prediction for every
protein map in the 'input_path'
Parameters
----------
input_path: str
Path of the input directory where the different protein directories are
located
output_path: str
Path of the folder where all generated files will be stored
thresholds_file: str
Path of the JSON file which contains the threshold values for the input
files
num_skip: int
The number of prediction steps that should be skipped
check_existing: bool
If set prediction steps are only executed if their results are not
existing in the output path yet
"""
# Create list of parameters for every prediction
params_list = [
(emdb_id, input_path, output_path, thresholds_file, num_skip,
check_existing) for emdb_id in filter(
lambda d: os.path.isdir(input_path + d), os.listdir(input_path))
]
start_time = time()
pool = Pool(min(cpu_count(), len(params_list)))
results = pool.map(run_prediction, params_list)
# Filter 'None' results
results = filter(lambda r: r is not None, results)
evaluator = Evaluator(input_path)
for emdb_id, predicted_file, gt_file, execution_time in results:
evaluator.evaluate(emdb_id, predicted_file, gt_file, execution_time)
evaluator.create_report(output_path, time() - start_time)
