不调用pyspark中的聚合函数对数据进行分组

data = [
    {'name': 'Alice', 'age': 25, 'gender': 'female'},
    {'name': 'Bob', 'age': 30, 'gender': 'male'},
    {'name': 'Charlie', 'age': 25, 'gender': 'male'},
    {'name': 'Dave', 'age': 35, 'gender': 'male'},
    {'name': 'Eve', 'age': 30, 'gender': 'female'}
]

groups = {}
for item in data:
    key = item['age']  # 以年龄作为键进行分组
    if key in groups:
        groups[key].append(item)
    else:
        groups[key] = [item]

# 打印分组结果
for key, group in groups.items():
    print(f"Age {key}:")
    for item in group:
        print(f"  {item['name']} ({item['gender']})")

SELECT age, COUNT(*) as count
FROM data
GROUP BY age