def merge_trusting_system1_unhidden(system1, system2, wildcard, ratio=0.8): from validate_frequency import number_of_matches for (s1,s2) in zip(system1,system2): n = number_of_matches(wildcard, s1) if float(n) / len(s1) <= ratio: yield s1 else: yield s2
def convert(system, tag='PHI', ratio=0.5, suppchar='_'): from validate_frequency import number_of_matches for line in system: line = line.strip() n = number_of_matches(suppchar, line) yield (line, tag if float(n) / len(line) >= ratio else '')