Python defaultdict默认字典详解 - 数据分组与嵌套字典教程

from collections import defaultdict

# 创建defaultdict
dd = defaultdict(default_factory)

# 常用工厂函数
dd = defaultdict(list)      # 默认值为空列表
dd = defaultdict(int)       # 默认值为0
dd = defaultdict(set)       # 默认值为空集合
dd = defaultdict(str)       # 默认值为空字符串
dd = defaultdict(lambda: "N/A")  # 自定义默认值

from collections import defaultdict

# 普通dict的问题
data = [("水果", "苹果"), ("蔬菜", "白菜"), ("水果", "香蕉")]

# 方式1：普通dict需要判断键是否存在
groups_dict = {}
for category, item in data:
    if category not in groups_dict:
        groups_dict[category] = []
    groups_dict[category].append(item)
print(f"普通dict: {groups_dict}")

# 方式2：使用setdefault
groups_setdefault = {}
for category, item in data:
    groups_setdefault.setdefault(category, []).append(item)
print(f"setdefault: {groups_setdefault}")

# 方式3：使用defaultdict（最简洁）
groups_dd = defaultdict(list)
for category, item in data:
    groups_dd[category].append(item)
print(f"defaultdict: {dict(groups_dd)}")

普通dict: {'水果': ['苹果', '香蕉'], '蔬菜': ['白菜']}
setdefault: {'水果': ['苹果', '香蕉'], '蔬菜': ['白菜']}
defaultdict: {'水果': ['苹果', '香蕉'], '蔬菜': ['白菜']}

from collections import defaultdict

# int工厂函数：计数器
counter = defaultdict(int)
words = ["apple", "banana", "apple", "cherry", "banana", "apple"]
for word in words:
    counter[word] += 1
print(f"计数器: {dict(counter)}")

# set工厂函数：去重分组
unique_groups = defaultdict(set)
pairs = [("A", 1), ("A", 2), ("B", 1), ("A", 1), ("B", 3)]
for key, value in pairs:
    unique_groups[key].add(value)
print(f"去重分组: {dict(unique_groups)}")

# 自定义工厂函数
config = defaultdict(lambda: "未配置")
config["host"] = "localhost"
print(f"\n已配置的键: {config['host']}")
print(f"未配置的键: {config['port']}")

计数器: {'apple': 3, 'banana': 2, 'cherry': 1}
去重分组: {'A': {1, 2}, 'B': {1, 3}}

已配置的键: localhost
未配置的键: 未配置

from collections import defaultdict

# 嵌套defaultdict：二维分组
def nested_dict():
    """创建嵌套的defaultdict"""
    return defaultdict(list)

# 按年份和月份分组
sales_data = [
    ("2024", "01", "产品A", 100),
    ("2024", "01", "产品B", 200),
    ("2024", "02", "产品A", 150),
    ("2023", "12", "产品A", 80),
    ("2023", "12", "产品B", 120),
]

# 二级分组
sales_by_month = defaultdict(nested_dict)
for year, month, product, amount in sales_data:
    sales_by_month[year][month].append((product, amount))

# 输出结果
print("销售数据分组:")
for year in sorted(sales_by_month.keys()):
    print(f"  {year}年:")
    for month in sorted(sales_by_month[year].keys()):
        items = sales_by_month[year][month]
        total = sum(a for _, a in items)
        print(f"    {month}月: {len(items)}笔, 总额{total}")

# 多级聚合：使用defaultdict(int)汇总
yearly_totals = defaultdict(int)
for year, month, product, amount in sales_data:
    yearly_totals[year] += amount

print(f"\n年度汇总: {dict(yearly_totals)}")

销售数据分组:
  2023年:
    12月: 2笔, 总额200
  2024年:
    01月: 2笔, 总额300
    02月: 1笔, 总额150

年度汇总: {'2024': 450, '2023': 200}