聚合和分组

1、准备数据库环境，比之前增加了price字段

class Publisher(models.Model):
    name = models.CharField(max_length=32)

    def __str__(self):
        return '<Publisher: {} - {}>'.format(self.pk, self.name)

class Book(models.Model):
    title = models.CharField(max_length=32)
    price = models.DecimalField(max_digits=5,decimal_places=2)  #最大999.99
    publisher = models.ForeignKey('Publisher',related_name='books',related_query_name='book',on_delete=models.CASCADE)

    def __str__(self):
        return '<Book: {} - {}>'.format(self.pk, self.title)

class Author(models.Model):
    name = models.CharField(max_length=32)
    books = models.ManyToManyField('Book')  #多对多创建，后面是要关联的表Book类

 聚合

import os

if __name__ == '__main__':
    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "about_orm.settings")
    import django

    django.setup()

    from app01 import models

    from django.db.models import Max,Min,Sum,Avg,Count

    # ret = models.Book.objects.aggregate(Max('price')) #aggregate本身就是聚合
    ret = models.Book.objects.all().aggregate(Min('price'),Avg('price'),max=Max('price')) #aggregate本身就是聚合
    # print(ret) #{'price__max': Decimal('99.00'), 'price__min': Decimal('10.00'), 'price__avg': 68.5}

分组

import os

if __name__ == '__main__':
    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "about_orm.settings")
    import django

    django.setup()

    from app01 import models

    from django.db.models import Max,Min,Sum,Avg,Count

    # ret = models.Book.objects.aggregate(Max('price')) #aggregate本身就是聚合
    ret = models.Book.objects.all().aggregate(Min('price'),Avg('price'),max=Max('price')) #aggregate本身就是聚合
    # print(ret) #{'price__max': Decimal('99.00'), 'price__min': Decimal('10.00'), 'price__avg': 68.5}

    # 按照出版社进行分组,聚合字段不再我这，我用跨表book__price  最后的values是取我的querySet里面的字段和对应的值
    ret = models.Publisher.objects.annotate(Avg('book__price')).values() #annotate:注释 把做完的结果塞到对象里面了
    # print(ret)

    #按照书做分组 再以publisher__name做二次分组
    # ret = models.Book.objects.values('publisher__name').annotate(avg=Avg('price'))
    # # print(ret)
    # for i in ret:
    #     print(i)

    #统计一本书作者的个数
    # ret = models.Book.objects.annotate(author_num=Count('author'))
    # for i in ret:
    #     print(i.author_num)

    # 统计出每个出版社买的最便宜的书的价格
    # 方法一：
    # ret = models.Publisher.objects.annotate(Min('book__price')).values()
    # for i in ret:
    #     print(i)

    #方法二：按照书分组 指定values，指定以publisher做了分组的字段
    # ret = models.Book.objects.values('publisher').annotate(Min('price'))
    # for i in ret:
    #     print(i)

    #统计不止一个作者的图书
    # ret = models.Book.objects.annotate(count=Count('author')).filter(count__gt=1)
    # for i in ret:
    #     print(i)  #<Book: 2 - 葵花宝典>

 

我们在这里先复习一下SQL语句的分组。

假设现在有一张公司职员表：

 我们使用原生SQL语句，按照部门分组求平均工资：

select dept,AVG(salary) from employee group by dept;

ORM查询:

from django.db.models import Avg
Employee.objects.values("dept").annotate(avg=Avg("salary").values("dept", "avg")

连表查询的分组：

SQL查询：

select dept.name,AVG(salary) from employee inner join dept on (employee.dept_id=dept.id) group by dept_id;

ORM查询：

from django.db.models import Avg
models.Dept.objects.annotate(avg=Avg("employee__salary")).values("name", "avg")

更多示例：

示例1：统计每一本书的作者个数

>>> book_list = models.Book.objects.all().annotate(author_num=Count("author"))
>>> for obj in book_list:
...     print(obj.author_num)
...
2
1
1

示例2：统计出每个出版社买的最便宜的书的价格

>>> publisher_list = models.Publisher.objects.annotate(min_price=Min("book__price"))
>>> for obj in publisher_list:
...     print(obj.min_price)
...     
9.90
19.90

方法二：

>>> models.Book.objects.values("publisher__name").annotate(min_price=Min("price"))
<QuerySet [{'publisher__name': '沙河出版社', 'min_price': Decimal('9.90')}, {'publisher__name': '人民出版社', 'min_price': Decimal('19.90')}]>

示例3：统计不止一个作者的图书

>>> models.Book.objects.annotate(author_num=Count("author")).filter(author_num__gt=1)
<QuerySet [<Book: 番茄物语>]>

示例4：根据一本图书作者数量的多少对查询集 QuerySet进行排序

>>> models.Book.objects.annotate(author_num=Count("author")).order_by("author_num")
<QuerySet [<Book: 香蕉物语>, <Book: 橘子物语>, <Book: 番茄物语>]>

示例5：查询各个作者出的书的总价格

>>> models.Author.objects.annotate(sum_price=Sum("book__price")).values("name", "sum_price")
<QuerySet [{'name': '小精灵', 'sum_price': Decimal('9.90')}, {'name': '小仙女', 'sum_price': Decimal('29.80')}, {'name': '小魔女', 'sum_price': Decimal('9.90')}]>