跳至正文

字典和集合

字典 (Dictionary)​

字典是以键值对形式存储数据的可变数据结构。

创建字典​

# 空字典
empty = {}
empty = dict()

# 带值的字典
person = {
    "name": "홍길동",
    "age": 25,
    "city": "서울"
}

# dict() 函数
person = dict(name="홍길동", age=25, city="서울")

# 从列表转换
pairs = [("name", "홍길동"), ("age", 25)]
person = dict(pairs)

# 创建键
keys = ["a", "b", "c"]
values = [1, 2, 3]
result = dict(zip(keys, values))
print(result)  # {'a': 1, 'b': 2, 'c': 3}

# 用 fromkeys 设置默认值
keys = ["a", "b", "c"]
result = dict.fromkeys(keys, 0)
print(result)  # {'a': 0, 'b': 0, 'c': 0}

访问字典​

person = {"name": "홍길동", "age": 25, "city": "서울"}

# 通过键访问
print(person["name"])  # 홍길동
print(person["age"])   # 25

# get() 方法（安全）
print(person.get("name"))     # 홍길동
print(person.get("phone"))    # None（键不存在）
print(person.get("phone", "없음"))  # 없음（默认值）

# 检查键是否存在
print("name" in person)   # True
print("phone" in person)  # False

# 所有键、值、键值对
print(person.keys())      # dict_keys(['name', 'age', 'city'])
print(person.values())    # dict_values(['홍길동', 25, '서울'])
print(person.items())     # dict_items([('name', '홍길동'), ...])

# 转换为列表
keys_list = list(person.keys())
values_list = list(person.values())

修改字典​

person = {"name": "홍길동", "age": 25}

# 添加/修改值
person["city"] = "서울"     # 添加
person["age"] = 26          # 修改
print(person)

# update() - 添加/修改多个值
person.update({"age": 27, "job": "개발자"})
print(person)

person.update(age=28, phone="010-1234-5678")
print(person)

# setdefault - 仅在键不存在时添加
person.setdefault("city", "부산")  # 如果已存在则忽略
print(person["city"])  # 서울（保持现有值）

person.setdefault("hobby", "독서")  # 不存在则添加
print(person["hobby"])  # 독서

# 删除值
del person["hobby"]    # 按键删除
age = person.pop("age")  # 删除并返回值
print(age)  # 28

# 删除最后一项（Python 3.7+ 保持插入顺序）
item = person.popitem()
print(item)  # ('phone', '010-1234-5678')

# 清空全部
person.clear()
print(person)  # {}

遍历字典​

person = {"name": "홍길동", "age": 25, "city": "서울"}

# 遍历键
for key in person:
    print(key)

# 显式使用键
for key in person.keys():
    print(key)

# 遍历值
for value in person.values():
    print(value)

# 遍历键值对（最常用）
for key, value in person.items():
    print(f"{key}: {value}")

# 带索引
for index, (key, value) in enumerate(person.items()):
    print(f"{index+1}. {key}: {value}")

字典推导式​

# 基本形式
squares = {x: x**2 for x in range(1, 6)}
print(squares)  # {1: 1, 2: 4, 3: 9, 4: 16, 5: 25}

# 带条件
even_squares = {x: x**2 for x in range(1, 11) if x % 2 == 0}
print(even_squares)  # {2: 4, 4: 16, 6: 36, 8: 64, 10: 100}

# 字符串长度
words = ["apple", "banana", "cherry"]
lengths = {word: len(word) for word in words}
print(lengths)  # {'apple': 5, 'banana': 6, 'cherry': 6}

# 交换键和值
original = {"a": 1, "b": 2, "c": 3}
swapped = {v: k for k, v in original.items()}
print(swapped)  # {1: 'a', 2: 'b', 3: 'c'}

# 条件转换
scores = {"홍길동": 85, "김철수": 92, "이영희": 78}
grades = {name: "Pass" if score >= 80 else "Fail"
          for name, score in scores.items()}
print(grades)

嵌套字典​

# 学生信息
students = {
    "2024001": {
        "name": "홍길동",
        "age": 20,
        "scores": {"math": 85, "english": 90}
    },
    "2024002": {
        "name": "김철수",
        "age": 21,
        "scores": {"math": 92, "english": 88}
    }
}

# 访问
print(students["2024001"]["name"])  # 홍길동
print(students["2024001"]["scores"]["math"])  # 85

# 遍历
for student_id, info in students.items():
    print(f"ID: {student_id}")
    print(f"이름: {info['name']}")
    avg = sum(info['scores'].values()) / len(info['scores'])
    print(f"평균: {avg:.1f}")
    print()

集合 (Set)​

集合是不允许重复的无序集合。

创建集合​

# 空集合（注意：{} 是字典！）
empty = set()

# 带值的集合
numbers = {1, 2, 3, 4, 5}
fruits = {"사과", "바나나", "체리"}

# 重复项会自动删除
numbers = {1, 2, 2, 3, 3, 3}
print(numbers)  # {1, 2, 3}

# 从其他类型转换
numbers = set([1, 2, 2, 3, 4, 4, 5])
print(numbers)  # {1, 2, 3, 4, 5}

chars = set("hello")
print(chars)  # {'h', 'e', 'l', 'o'} - 重复项已删除

集合操作​

# 添加元素
fruits = {"사과", "바나나"}
fruits.add("체리")
print(fruits)  # {'사과', '바나나', '체리'}

# 添加多个元素
fruits.update(["포도", "멜론"])
print(fruits)

# 删除元素
fruits.remove("바나나")  # 不存在会报错
fruits.discard("수박")   # 不存在不报错
popped = fruits.pop()    # 删除任意元素
fruits.clear()           # 清空全部

# 检查是否包含
numbers = {1, 2, 3, 4, 5}
print(3 in numbers)      # True
print(10 in numbers)     # False

# 长度
print(len(numbers))      # 5

集合运算​

a = {1, 2, 3, 4, 5}
b = {4, 5, 6, 7, 8}

# 并集（union）
print(a | b)            # {1, 2, 3, 4, 5, 6, 7, 8}
print(a.union(b))       # 相同结果

# 交集（intersection）
print(a & b)            # {4, 5}
print(a.intersection(b))  # 相同结果

# 差集（difference）
print(a - b)            # {1, 2, 3}
print(a.difference(b))  # 相同结果

# 对称差集（symmetric difference）
print(a ^ b)            # {1, 2, 3, 6, 7, 8}
print(a.symmetric_difference(b))  # 相同结果

# 子集/超集
small = {1, 2}
large = {1, 2, 3, 4}
print(small.issubset(large))      # True
print(large.issuperset(small))    # True
print(small.isdisjoint({5, 6}))   # True（无交集）

集合推导式​

# 基本形式
squares = {x**2 for x in range(1, 6)}
print(squares)  # {1, 4, 9, 16, 25}

# 带条件
even_nums = {x for x in range(1, 11) if x % 2 == 0}
print(even_nums)  # {2, 4, 6, 8, 10}

# 字符串处理
text = "hello world"
unique_chars = {c.upper() for c in text if c.isalpha()}
print(unique_chars)  # {'H', 'E', 'L', 'O', 'W', 'R', 'D'}

frozenset（不可变集合）​

# 不可变集合
immutable = frozenset([1, 2, 3, 4, 5])
print(immutable)

# 无法修改
# immutable.add(6)  # ❌ AttributeError

# 可用作字典键
data = {
    frozenset([1, 2]): "group1",
    frozenset([3, 4]): "group2"
}
print(data[frozenset([1, 2])])  # group1

实战示例​

词频分析​

def word_frequency(text):
    """计算词频"""
    # 转换为小写并分割
    words = text.lower().split()

    # 计算频率
    frequency = {}
    for word in words:
        frequency[word] = frequency.get(word, 0) + 1

    # 按频率排序
    sorted_freq = sorted(frequency.items(),
                        key=lambda x: x[1],
                        reverse=True)

    return dict(sorted_freq)

text = """
Python is a popular programming language.
Python is easy to learn.
Many developers use Python.
"""

result = word_frequency(text)
print("=== 단어 빈도 ===")
for word, count in result.items():
    print(f"{word}: {count}회")

电话簿​

class PhoneBook:
    def __init__(self):
        self.contacts = {}

    def add(self, name, phone):
        """添加联系人"""
        self.contacts[name] = phone
        print(f"{name} 추가됨")

    def get(self, name):
        """获取联系人"""
        return self.contacts.get(name, "등록되지 않음")

    def update(self, name, phone):
        """更新联系人"""
        if name in self.contacts:
            self.contacts[name] = phone
            print(f"{name} 수정됨")
        else:
            print(f"{name}을 찾을 수 없음")

    def remove(self, name):
        """删除联系人"""
        if name in self.contacts:
            del self.contacts[name]
            print(f"{name} 삭제됨")
        else:
            print(f"{name}을 찾을 수 없음")

    def list_all(self):
        """列出所有联系人"""
        if not self.contacts:
            print("등록된 연락처가 없습니다")
            return

        print("\n=== 전화번호부 ===")
        for name, phone in sorted(self.contacts.items()):
            print(f"{name}: {phone}")

# 使用示例
phonebook = PhoneBook()
phonebook.add("홍길동", "010-1234-5678")
phonebook.add("김철수", "010-2345-6789")
phonebook.list_all()
print(f"\n홍길동: {phonebook.get('홍길동')}")

去重和分析​

def analyze_data(data):
    """分析数据"""
    # 去重
    unique = set(data)

    # 统计
    stats = {
        "전체": len(data),
        "고유값": len(unique),
        "중복": len(data) - len(unique),
        "최대": max(data),
        "최소": min(data),
        "중복값": [x for x in unique if data.count(x) > 1]
    }

    return stats

data = [1, 2, 2, 3, 3, 3, 4, 5, 5]
result = analyze_data(data)

print("=== 데이터 분석 ===")
for key, value in result.items():
    print(f"{key}: {value}")

学生成绩管理​

class GradeManager:
    def __init__(self):
        self.students = {}

    def add_student(self, name):
        """添加学生"""
        if name not in self.students:
            self.students[name] = {}
            print(f"{name} 추가됨")

    def add_score(self, name, subject, score):
        """添加成绩"""
        if name not in self.students:
            self.add_student(name)
        self.students[name][subject] = score

    def get_average(self, name):
        """计算平均分"""
        if name not in self.students or not self.students[name]:
            return 0
        scores = self.students[name].values()
        return sum(scores) / len(scores)

    def get_subject_average(self, subject):
        """按科目计算平均分"""
        scores = [student[subject]
                 for student in self.students.values()
                 if subject in student]
        if not scores:
            return 0
        return sum(scores) / len(scores)

    def get_ranking(self):
        """计算排名"""
        averages = {name: self.get_average(name)
                   for name in self.students}
        return sorted(averages.items(),
                     key=lambda x: x[1],
                     reverse=True)

    def show_report(self):
        """显示成绩单"""
        print("\n=== 성적표 ===")
        for name, scores in self.students.items():
            print(f"\n{name}:")
            for subject, score in scores.items():
                print(f"  {subject}: {score}점")
            print(f"  평균: {self.get_average(name):.1f}점")

# 使用示例
manager = GradeManager()
manager.add_score("홍길동", "수학", 85)
manager.add_score("홍길동", "영어", 90)
manager.add_score("김철수", "수학", 92)
manager.add_score("김철수", "영어", 88)

manager.show_report()

print("\n=== 순위 ===")
for rank, (name, avg) in enumerate(manager.get_ranking(), 1):
    print(f"{rank}. {name}: {avg:.1f}점")

标签系统​

class TagSystem:
    def __init__(self):
        self.items = {}  # {item_id: {tags}}
        self.tags = {}   # {tag: {item_ids}}

    def add_item(self, item_id, tags):
        """添加项目和标签"""
        self.items[item_id] = set(tags)
        for tag in tags:
            if tag not in self.tags:
                self.tags[tag] = set()
            self.tags[tag].add(item_id)

    def find_by_tag(self, tag):
        """按标签查找项目"""
        return self.tags.get(tag, set())

    def find_by_tags(self, tags, mode="any"):
        """按多个标签查找"""
        if not tags:
            return set()

        tag_sets = [self.tags.get(tag, set()) for tag in tags]

        if mode == "any":  # OR 条件
            return set.union(*tag_sets) if tag_sets else set()
        else:  # AND 条件
            return set.intersection(*tag_sets) if tag_sets else set()

    def get_related_tags(self, tag):
        """查找相关标签"""
        items = self.find_by_tag(tag)
        related = set()
        for item in items:
            related.update(self.items[item])
        related.discard(tag)
        return related

# 使用示例
tags = TagSystem()
tags.add_item("post1", ["python", "tutorial", "beginner"])
tags.add_item("post2", ["python", "advanced", "performance"])
tags.add_item("post3", ["javascript", "tutorial", "beginner"])

print("Python 태그:", tags.find_by_tag("python"))
print("Tutorial + Beginner:", tags.find_by_tags(["tutorial", "beginner"], "all"))
print("Python 관련 태그:", tags.get_related_tags("python"))

常见问题​

Q1. 什么类型可以作为字典的键？​

A: 只允许不可变（immutable）类型

# ✅ 允许
d = {
    "string": 1,
    42: 2,
    3.14: 3,
    (1, 2): 4,
    frozenset([1, 2]): 5
}

# ❌ 不允许
# d = {[1, 2]: 1}  # 列表不允许
# d = {{1, 2}: 1}  # 集合不允许
# d = {{"a": 1}: 1}  # 字典不允许

Q2. 字典有顺序吗？​

A: Python 3.7+ 保持插入顺序

# Python 3.7+
d = {"c": 3, "a": 1, "b": 2}
print(list(d.keys()))  # ['c', 'a', 'b'] - 插入顺序

# 如需排序，显式指定
sorted_d = dict(sorted(d.items()))
print(list(sorted_d.keys()))  # ['a', 'b', 'c']

Q3. 集合不能通过索引访问吗？​

A: 是的，因为无序所以无法通过索引访问

s = {1, 2, 3}
# print(s[0])  # ❌ TypeError

# 转换为列表或使用循环
s_list = list(s)
print(s_list[0])  # ✅

for item in s:  # ✅
    print(item)

Q4. 如何为字典值设置默认值？​

A: 使用 defaultdict

from collections import defaultdict

# 普通字典
normal = {}
# normal["key"] += 1  # ❌ KeyError

# defaultdict
counter = defaultdict(int)  # 默认值 0
counter["key"] += 1  # ✅
print(counter["key"])  # 1

groups = defaultdict(list)  # 默认值 []
groups["a"].append(1)  # ✅
print(groups)  # {'a': [1]}

下一步​

你已掌握字典和集合！

核心总结：
✅ 字典：键值对，快速查找
✅ 集合：去重，集合运算
✅ 推导式实现简洁创建
✅ 实战应用（频率分析、标签系统等）

下一步：在条件语句和循环中学习如何控制程序流程！