Python 入门教程（五）：字典与集合

1
# 键值对：{键: 值, ...}
2
student = {
3
    "name": "小明",
4
    "age": 18,
5
    "major": "计算机科学",
6
    "scores": {"python": 90, "cpp": 85},   # 字典可以嵌套
7
}
8

9
print(student["name"])            # 小明
10
print(student["scores"]["python"])   # 90（链式访问嵌套）
11

12
# 空字典
13
empty = {}
14
also_empty = dict()
15

16
# dict() 构造
17
ages = dict(小明=18, 小红=17)      # {'小明': 18, '小红': 17}
18
pairs = dict([("a", 1), ("b", 2)]) # {'a': 1, 'b': 2}

1
text = """python is simple and python is powerful
2
learn python and code python"""
3

4
# 方法：setdefault 计数
5
freq = {}
6
for word in text.split():
7
    freq.setdefault(word, 0)
8
    freq[word] += 1
9

10
# 按次数降序输出 Top 3
11
for word, count in sorted(freq.items(), key=lambda x: x[1], reverse=True)[:3]:
12
    print(f"{word}: {count} 次")
13
# python: 4 次
14
# and: 2 次
15
# is: 2 次

1
contacts = {
2
    "小明": {"phone": "138xxxx", "city": "北京", "tags": ["同学", "编程组"]},
3
    "小红": {"phone": "139xxxx", "city": "上海", "tags": ["同学"]},
4
}
5

6
def show(name):
7
    info = contacts.get(name)
8
    if info is None:
9
        print(f"没有 {name} 的联系方式")
10
        return
11
    tags = "/".join(info["tags"])
12
    print(f"{name}｜{info['phone']}｜{info['city']}｜标签: {tags}")
13

14
def search_by_city(city):
15
    found = [n for n, i in contacts.items() if i["city"] == city]
16
    print(f"{city} 的联系人: {found}")
17

18
show("小明")           # 小明｜138xxxx｜北京｜标签: 同学/编程组
19
search_by_city("上海")  # 上海 的联系人: ['小红']

1
# 花括号内是元素（不是键值对）就是集合
2
fruits = {"apple", "banana", "apple", "cherry"}
3
print(fruits)          # {'apple', 'banana', 'cherry'} 自动去重！
4
print(len(fruits))     # 3
5

6
# ⚠️ 空花括号是字典不是集合！
7
empty_dict = {}
8
empty_set = set()      # 空集合必须用 set()
9

10
# 从列表去重（最常用场景）
11
nums = [1, 3, 2, 3, 1, 5]
12
unique = list(set(nums))
13
print(unique)          # [1, 2, 3, 5]（顺序不保证！）
14

15
# 去重且保序的写法
16
unique_ordered = list(dict.fromkeys(nums))
17
print(unique_ordered)  # [1, 3, 2, 5] ✓ 保持原序

1
class_a = {"python", "cpp", "java", "go"}
2
class_b = {"python", "java", "rust", "js"}
3

4
# 交集：都选了的课
5
print(class_a & class_b)          # {'python', 'java'}
6
print(class_a.intersection(class_b))   # 同上
7

8
# 并集：所有人选过的课
9
print(class_a | class_b)          # {'python','cpp','java','go','rust','js'}
10

11
# 差集：A 选了 B 没选的
12
print(class_a - class_b)          # {'cpp', 'go'}
13

14
# 对称差：只有一方选了的（并集 - 交集）
15
print(class_a ^ class_b)          # {'cpp', 'go', 'rust', 'js'}
16

17
# 子集与超集
18
print({"python"} <= class_a)      # True 子集判断
19
print(class_a.issubset(class_a | class_b))   # True

1
import time
2

3
big_list = list(range(1_000_000))
4
big_set = set(big_list)
5

6
t1 = time.time()
7
for _ in range(100):
8
    999_999 in big_list
9
t2 = time.time()
10
for _ in range(100):
11
    999_999 in big_set
12
t3 = time.time()
13

14
print(f"列表查找: {(t2-t1)*1000:.1f}ms")
15
print(f"集合查找: {(t3-t2)*1000:.1f}ms")   # 快百倍以上