util.py

import constants as cst
import re
import datetime


def get_file_name(file):
    return re.match(cst.FILE_NAME_PATTERN, file).group(1)

def now():
    return datetime.datetime.now().strftime("%Y%m%d_%H%M%S")

def get_escaped_name(problem):
    return problem.replace("-", "_").replace(".", "")


def parse_relevant_features(data_file_name):
    search = re.search('\D+_(\d+)_', data_file_name)
    if not search:
        raise ValueError("wrong file format!")
    dims_count = int(search.group(1))
    return dims_count


def collect_params(f):
    params = []
    # relevant features 2 - 30
    # for rf in range(cst.RELEVANT_FEATURES_LOWER_BOUND, cst.RELEVANT_FEATURES_UPPER_BOUND):
    for rf in cst.RELEVANT_FEATURES_RANGE_LIST:
        # cubes 1 - 10
        # for c in range(cst.CUBES_LOWER_BOUND, cst.CUBES_UPPER_BOUND):
        for c in cst.INTERACTION_NUMBER_RANGE_LIST:
            # cube types complete, incomplete, incomplete overlapping
            for t in cst.INTERACTION_TYPES_RANGE_LIST:
                if (c == 1 or rf / c < 2) and t != 'c':
                    continue
                dataset_name = 'cubes_' + '{0:02d}'.format(rf) + '_' \
                       + '{0:02d}'.format(c) + '_' \
                       + t
                param = f(dataset_name, rf, c, t)
                print('collected param:', param)
                if type(param) == list:
                    params.extend(param)
                else:
                    params.append(param)
    return params