Method _fast_code_diversity

data/database.py:2045–2071

Fast approximation of code diversity using simple metrics Returns diversity score (higher = more diverse)

(self, code1: str, code2: str)

        return total_diversity / max(1, comparisons)

    def _fast_code_diversity(self, code1: str, code2: str) -> float:
        """
        Fast approximation of code diversity using simple metrics

        Returns diversity score (higher = more diverse)
        """
        if code1 == code2:
            return 0.0

        # Length difference (scaled to reasonable range)
        len1, len2 = len(code1), len(code2)
        length_diff = abs(len1 - len2)

        # Line count difference
        lines1 = code1.count("\n")
        lines2 = code2.count("\n")
        line_diff = abs(lines1 - lines2)

        # Simple character set difference
        chars1 = set(code1)
        chars2 = set(code2)
        char_diff = len(chars1.symmetric_difference(chars2))

        # Combine metrics (scaled to match original edit distance range)
        diversity = length_diff * 0.1 + line_diff * 10 + char_diff * 0.5

        return diversity

    def _get_cached_diversity(self, program: Program) -> float:
        """