如何为Python爱好字典去重并保留字母排序？

方案一：排序后去重（兼容原有逻辑） #

修改现有sort_dictionary函数，在对爱好者列表排序后，通过遍历过滤重复项。由于排序后的重复元素是连续的，用集合记录已出现的元素即可高效去重，同时保留排序后的顺序。

def deduplicate_sorted_list(lst):
    seen = set()
    unique_lst = []
    for name in lst:
        if name not in seen:
            seen.add(name)
            unique_lst.append(name)
    return unique_lst

def sort_dictionary(dict: dict) -> dict:
    return {k: deduplicate_sorted_list(sorted(v)) for k, v in dict.items()}

def create_dictionary_with_hobbies(data: str) -> dict:
    """Create dictionary about hobbies and their hobbyists ie. {hobby1: [name1, name2, ...], hobby2: [...]}."""
    result = {}
    for line in data.split('\n'):
        name, hobby = line.split(":")
        result.setdefault(hobby, []).append(name)
        result = sort_dictionary(result)
    return result 

if __name__ == '__main__':
    sample_data = """Jack:crafting\nPeter:hiking\nWendy:gaming\nMonica:tennis\nChris:origami\nSophie:sport\nMonica:design\nCarmen:sport\nChris:sport\nMonica:skateboarding\nCarmen:cooking\nWendy:photography\nMonica:tennis\nCooper:yoga\nWendy:sport\nCooper:movies\nMonica:theatre\nCooper:yoga\nChris:gaming\nMolly:fishing\nJack:skateboarding\nWendy:fishing\nJack:drawing\nMonica:baking\nSophie:baking\nAlfred:driving\nAlfred:shopping\nAlfred:crafting\nJack:drawing\nCarmen:shopping\nCarmen:driving\nPeter:drawing\nCarmen:shopping\nWendy:fitness\nAlfred:travel\nJack:origami\nSophie:design\nJack:pets\nCarmen:dance\nAlfred:baking\nSophie:sport\nPeter:gaming\nJack:skateboarding\nCooper:football\nAlfred:sport\nCooper:fitness\nChris:yoga\nWendy:football\nMolly:design\nJack:hiking\nMonica:pets\nCarmen:photography\nJack:baking\nPeter:driving\nChris:driving\nCarmen:driving\nPeter:theatre\nMolly:hiking\nWendy:puzzles\nJack:crafting\nPeter:photography\nCarmen:theatre\nSophie:crafting\nCarmen:cooking\nAlfred:gaming\nPeter:theatre\nCooper:hiking\nChris:football\nChris:pets\nJack:football\nMonica:skateboarding\nChris:driving\nCarmen:pets\nCooper:gaming\nChris:hiking\nJack:cooking\nPeter:fishing\nJack:gaming\nPeter:origami\nCarmen:movies\nSophie:driving\nJack:sport\nCarmen:theatre\nWendy:shopping\nCarmen:pets\nWendy:gaming\nSophie:football\nWendy:theatre\nCarmen:football\nMolly:theatre\nPeter:theatre\nMonica:flowers\nMolly:skateboarding\nPeter:driving\nSophie:travel\nMonica:photography\nCooper:cooking\nJack:fitness\nPeter:cooking\nChris:gaming"""
    print(create_dictionary_with_hobbies(sample_data))

方案二：源头去重（性能更优） #

直接用集合存储每个爱好对应的爱好者，集合会自动过滤重复元素，最后再将集合转为排序后的列表。这种方式避免了先添加重复元素再去重的冗余操作，数据量大时性能更出色。

def create_dictionary_with_hobbies(data: str) -> dict:
    """Create dictionary about hobbies and their hobbyists ie. {hobby1: [name1, name2, ...], hobby2: [...]}."""
    result = {}
    for line in data.split('\n'):
        name, hobby = line.split(":")
        # 用集合存储，自动去重
        result.setdefault(hobby, set()).add(name)
    # 将每个爱好的集合转为排序后的列表
    return {k: sorted(v) for k, v in result.items()}

if __name__ == '__main__':
    sample_data = """Jack:crafting\nPeter:hiking\nWendy:gaming\nMonica:tennis\nChris:origami\nSophie:sport\nMonica:design\nCarmen:sport\nChris:sport\nMonica:skateboarding\nCarmen:cooking\nWendy:photography\nMonica:tennis\nCooper:yoga\nWendy:sport\nCooper:movies\nMonica:theatre\nCooper:yoga\nChris:gaming\nMolly:fishing\nJack:skateboarding\nWendy:fishing\nJack:drawing\nMonica:baking\nSophie:baking\nAlfred:driving\nAlfred:shopping\nAlfred:crafting\nJack:drawing\nCarmen:shopping\nCarmen:driving\nPeter:drawing\nCarmen:shopping\nWendy:fitness\nAlfred:travel\nJack:origami\nSophie:design\nJack:pets\nCarmen:dance\nAlfred:baking\nSophie:sport\nPeter:gaming\nJack:skateboarding\nCooper:football\nAlfred:sport\nCooper:fitness\nChris:yoga\nWendy:football\nMolly:design\nJack:hiking\nMonica:pets\nCarmen:photography\nJack:baking\nPeter:driving\nChris:driving\nCarmen:driving\nPeter:theatre\nMolly:hiking\nWendy:puzzles\nJack:crafting\nPeter:photography\nCarmen:theatre\nSophie:crafting\nCarmen:cooking\nAlfred:gaming\nPeter:theatre\nCooper:hiking\nChris:football\nChris:pets\nJack:football\nMonica:skateboarding\nChris:driving\nCarmen:pets\nCooper:gaming\nChris:hiking\nJack:cooking\nPeter:fishing\nJack:gaming\nPeter:origami\nCarmen:movies\nSophie:driving\nJack:sport\nCarmen:theatre\nWendy:shopping\nCarmen:pets\nWendy:gaming\nSophie:football\nWendy:theatre\nCarmen:football\nMolly:theatre\nPeter:theatre\nMonica:flowers\nMolly:skateboarding\nPeter:driving\nSophie:travel\nMonica:photography\nCooper:cooking\nJack:fitness\nPeter:cooking\nChris:gaming"""
    print(create_dictionary_with_hobbies(sample_data))

效果验证 #

两种方案运行后，crafting对应的列表会变成['Alfred', 'Jack', 'Sophie']，所有重复姓名都被去除，同时保持字母升序排列。

内容的提问来源于stack exchange，提问作者Zaraza_21