高效Python列表匹配：利用哈希表优化大数据量对象关联

class Person:
    def __init__(self, name, age, district, house_number):
        self.name = name
        self.age = age
        self.district = district
        self.house_number = house_number

    def __repr__(self):
        return f"Person(name='{self.name}', age={self.age}, district='{self.district}', house_number={self.house_number}')"

# 假设 men 和 women 列表以及 min_age 变量已预先定义并填充
# 例如:
# men = [Person("Alex", 35, "District 1", 101), Person("Bob", 28, "District 2", 205), ...]
# women = [Person("Alice", 32, "District 1", 101), Person("Betty", 27, "District 2", 205), ...]
# min_age = 30

# 假设 men, women 列表和 min_age 变量已定义
men_new = []
women_new = []

# 第一步：筛选符合年龄条件的男性
for man in men:
    if man.age > min_age:
        men_new.append(man)

# 第二步：为筛选出的男性匹配对应的女性
for man in men_new:
    # 这一步是性能瓶颈
    # 每次循环都需要遍历整个 women 列表
    for woman in women:
        if woman.district == man.district and woman.house_number == man.house_number:
            women_new.append(woman)
            break # 找到即退出内层循环

house_to_woman = {}
for woman in women:
    # 使用 (district, house_number) 元组作为键，确保唯一性
    house_key = (woman.district, woman.house_number)
    house_to_woman[house_key] = woman

# 这一步的复杂度是 O(N)，其中 N 是 women 列表的长度。

men_new = []
women_new = []

for man in men:
    if man.age > min_age:
        # 添加符合条件的男性
        men_new.append(man)

        # 构建哈希查找的键
        house_key = (man.district, man.house_number)

        # 从哈希表中 O(1) 平均时间复杂度查找对应的女性
        # 假设每个男性都有对应的女性，且数据完整性良好
        women_new.append(house_to_woman[house_key])

# 这一步的复杂度是 O(N_men + M)，其中 N_men 是 men 列表的长度，M 是 men_new 的长度。
# 由于字典查找的平均时间复杂度是 O(1)，因此总的匹配操作效率极高。

import random

class Person:
    def __init__(self, name, age, district, house_number):
        self.name = name
        self.age = age
        self.district = district
        self.house_number = house_number

    def __repr__(self):
        return f"Person(name='{self.name}', age={self.age}, district='{self.district}', house_number={self.house_number}')"

# 示例数据生成函数 (模拟大数据量)
def generate_people_data(num_districts, houses_per_district):
    men_list = []
    women_list = []

    person_id_counter = 0
    for d_idx in range(num_districts):
        district_name = f"District_{d_idx + 1}"
        for h_idx in range(1, houses_per_district + 1):
            # 确保每个房屋有一男一女
            man_age = random.randint(20, 60)
            woman_age = random.randint(20, 60)

            men_list.append(Person(f"Man_{person_id_counter}", man_age, district_name, h_idx))
            women_list.append(Person(f"Woman_{person_id_counter}", woman_age, district_name, h_idx))
            person_id_counter += 1

    # 随机打乱列表顺序以模拟实际情况
    random.shuffle(men_list)
    random.shuffle(women_list)

    return men_list, women_list

# --- 主程序逻辑 ---
# 生成模拟数据
NUM_DISTRICTS = 100
HOUSES_PER_DISTRICT = 1000
men, women = generate_people_data(NUM_DISTRICTS, HOUSES_PER_DISTRICT)
min_age = 30

print(f"生成了 {len(men)} 对男女数据。")
print(f"筛选年龄阈值: {min_age}")

# 优化解决方案
men_new_optimized = []
women_new_optimized = []

# 步骤一：构建女性信息哈希表
house_to_woman = {}
for woman in women:
    house_key = (woman.district, woman.house_number)
    house_to_woman[house_key] = woman

# 步骤二：筛选男性并进行高效匹配
for man in men:
    if man.age > min_age:
        men_new_optimized.append(man)
        house_key = (man.district, man.house_number)

        # 安全查找，以防数据不一致（虽然本问题假设一致）
        if house_key in house_to_woman:
            women_new_optimized.append(house_to_woman[house_key])
        else:
            # 处理未找到匹配女性的情况，例如记录错误或跳过
            print(f"警告: 未找到 {man.district} 区域 {man.house_number} 号房屋的女性。")

print(f"筛选并匹配后，找到 {len(men_new_optimized)} 对男女。")

# 验证结果（可选，只打印前几对）
print("\n--- 匹配结果示例 (前5对) ---")
for i in range(min(5, len(men_new_optimized))):
    print(f"男: {men_new_optimized[i]}, 女: {women_new_optimized[i]}")
    # 验证是否在同一房屋
    assert men_new_optimized[i].district == women_new_optimized[i].district
    assert men_new_optimized[i].house_number == women_new_optimized[i].house_number