Python collections模块详解 - 5大专用容器入门教程

from collections import Counter, defaultdict, OrderedDict, deque, namedtuple

import collections

collections.Counter([1, 2, 3])
collections.defaultdict(list)

from collections import Counter, defaultdict, OrderedDict, deque, namedtuple

# Counter: 计数
counter = Counter("abracadabra")
print(f"Counter: {counter}")
print(f"最常见的3个: {counter.most_common(3)}")

# defaultdict: 默认值字典
dd = defaultdict(list)
dd["fruits"].append("apple")
dd["fruits"].append("banana")
print(f"\ndefaultdict: {dict(dd)}")

# OrderedDict: 有序字典
od = OrderedDict()
od["first"] = 1
od["second"] = 2
od["third"] = 3
print(f"\nOrderedDict: {od}")

# deque: 双端队列
dq = deque([1, 2, 3])
dq.appendleft(0)
dq.append(4)
print(f"\ndeque: {dq}")

# namedtuple: 命名元组
Point = namedtuple("Point", ["x", "y"])
p = Point(3, 4)
print(f"\nnamedtuple: {p}, x={p.x}, y={p.y}")

Counter: Counter({'a': 5, 'b': 2, 'r': 2, 'c': 1, 'd': 1})
最常见的3个: [('a', 5), ('b', 2), ('r', 2)]

defaultdict: {'fruits': ['apple', 'banana']}

OrderedDict: OrderedDict([('first', 1), ('second', 2), ('third', 3)])

deque: deque([0, 1, 2, 3, 4])

namedtuple: Point(x=3, y=4), x=3, y=4

from collections import Counter, defaultdict, deque, namedtuple

# 场景1：统计词频 -> Counter
text = "the quick brown fox jumps over the lazy dog the fox"
word_freq = Counter(text.split())
print("词频统计:")
for word, count in word_freq.most_common(3):
    print(f"  {word}: {count}")

# 场景2：分组数据 -> defaultdict
students = [("A班", "张三"), ("B班", "李四"), ("A班", "王五"), ("B班", "赵六")]
classes = defaultdict(list)
for cls, name in students:
    classes[cls].append(name)
print(f"\n分组结果: {dict(classes)}")

# 场景3：滑动窗口 -> deque
def moving_average(data, window_size):
    window = deque(maxlen=window_size)
    averages = []
    for value in data:
        window.append(value)
        if len(window) == window_size:
            averages.append(sum(window) / window_size)
    return averages

data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
print(f"\n移动平均(窗口3): {moving_average(data, 3)}")

词频统计:
  the: 3
  fox: 2
  quick: 1

分组结果: {'A班': ['张三', '王五'], 'B班': ['李四', '赵六']}

移动平均(窗口3): [2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]

from collections import Counter, defaultdict, namedtuple

# 定义数据结构
Record = namedtuple("Record", ["date", "category", "amount"])

# 模拟交易数据
transactions = [
    Record("2024-01-01", "餐饮", 35),
    Record("2024-01-01", "交通", 15),
    Record("2024-01-02", "餐饮", 42),
    Record("2024-01-02", "购物", 128),
    Record("2024-01-02", "餐饮", 28),
    Record("2024-01-03", "交通", 8),
    Record("2024-01-03", "餐饮", 55),
]

# 按类别分组统计
category_totals = defaultdict(int)
category_counts = Counter()

for t in transactions:
    category_totals[t.category] += t.amount
    category_counts[t.category] += 1

print("消费统计:")
print(f"{'类别':6s} {'次数':4s} {'总额':6s} {'平均':6s}")
print("-" * 28)
for category in category_totals:
    total = category_totals[category]
    count = category_counts[category]
    avg = total / count
    print(f"{category:6s} {count:4d} {total:6d} {avg:6.1f}")

消费统计:
类别   次数 总额   平均
----------------------------
餐饮      4    160   40.0
交通      2     23   11.5
购物      1    128  128.0