225 lines
8.7 KiB
Python
225 lines
8.7 KiB
Python
#统计分析 数据访问层（动态查询 + 聚合）
|
||
from os.path import join
|
||
from typing import Optional
|
||
|
||
from sqlalchemy import and_, case, func
|
||
from sqlalchemy.orm import Session
|
||
|
||
from model.wl_class_model import Class_
|
||
from model.wl_emp_model import Emp
|
||
from model.wl_score_model import Score
|
||
from model.wl_student_model import Student
|
||
from scheme.wl_statistics_scheme import AgeCompareOp, SortOrder
|
||
|
||
# stu_gender 字段的实际取值，确认数据库里存的到底是什么后改这两行即可
|
||
MALE_VALUE = "男"
|
||
FEMALE_VALUE = "女"
|
||
|
||
|
||
|
||
|
||
# ---- 2.6.1.1 动态年龄范围查询 ----
|
||
# 比较条件 -> SQLAlchemy 表达式工厂，动态拼接 where 条件
|
||
_AGE_OP_FACTORY = {
|
||
AgeCompareOp.gt: lambda v1, v2: Student.stu_age > v1,
|
||
AgeCompareOp.ge: lambda v1, v2: Student.stu_age >= v1,
|
||
AgeCompareOp.lt: lambda v1, v2: Student.stu_age < v1,
|
||
AgeCompareOp.le: lambda v1, v2: Student.stu_age <= v1,
|
||
AgeCompareOp.eq: lambda v1, v2: Student.stu_age == v1,
|
||
AgeCompareOp.between: lambda v1, v2: Student.stu_age.between(v1, v2),
|
||
}
|
||
|
||
class StatisticDao:
|
||
|
||
@staticmethod
|
||
def search_students_by_age(db: Session, op: AgeCompareOp,
|
||
value: int, value2: Optional[int] = None):
|
||
if op == AgeCompareOp.between:
|
||
if value2 is None:
|
||
raise ValueError("区间查询（between）需要同时提供上界 value2")
|
||
if value > value2:
|
||
raise ValueError("区间查询的下界不能大于上界")
|
||
|
||
condition = _AGE_OP_FACTORY[op](value, value2)
|
||
return db.query(Student) \
|
||
.filter(Student.is_deleted == 0, condition) \
|
||
.order_by(Student.stu_age) \
|
||
.all()
|
||
@staticmethod
|
||
def statistic_classes_count(db: Session):
|
||
"""每个班级的总人数 + 按性别细分的分布（含 0 人的空班级）"""
|
||
result=[]
|
||
for c in db.query(Class_).filter(Class_.is_deleted==0).all():
|
||
students=[s for s in c.students if s.is_deleted == 0]
|
||
result.append({
|
||
"class_id":c.class_id,
|
||
"total":len(students),
|
||
"male_count":sum(1 for s in students if s.stu_gender==MALE_VALUE),
|
||
"female_count":sum(1 for s in students if s.stu_gender==FEMALE_VALUE)
|
||
})
|
||
return result
|
||
# 另一个版本的写法，效率更高
|
||
# male = func.sum(case((Student.stu_gender == MALE_VALUE, 1), else_=0))
|
||
# female = func.sum(case((Student.stu_gender == FEMALE_VALUE, 1), else_=0))
|
||
#
|
||
# return db.query(
|
||
# WlClass.class_id.label("class_id"),
|
||
# func.count(Student.stu_id).label("total"),
|
||
# male.label("male_count"),
|
||
# female.label("female_count"),
|
||
# ).select_from(WlClass) \
|
||
# .outerjoin(
|
||
# Student,
|
||
# # 逻辑删除的过滤条件必须写在 ON 里，写进 where 会把空班级整行滤掉
|
||
# and_(Student.class_id == WlClass.class_id, Student.is_deleted == 0),
|
||
# ) \
|
||
# .filter(WlClass.is_deleted == 0) \
|
||
# .group_by(WlClass.class_id) \
|
||
# .order_by(WlClass.class_id) \
|
||
# .all()
|
||
|
||
@staticmethod
|
||
def query_score_by_line(db:Session,score_line:float):
|
||
result=[]
|
||
for s in db.query(Student).filter(Student.is_deleted==0).all():
|
||
if all(sc.score>score_line for sc in s.scores):
|
||
result.append({
|
||
"stu_no":s.stu_no,
|
||
"stu_name":s.stu_name,
|
||
"scores": [{"exam_order":i.exam_order,"score":i.score} for i in s.scores]
|
||
})
|
||
return result
|
||
|
||
@staticmethod
|
||
def query_by_fail_count(db:Session,fail_count:int):
|
||
result=[]
|
||
students=db.query(Student).filter(Student.is_deleted==0).all()
|
||
for stu in students:
|
||
if len([sc for sc in stu.scores if sc.score<60])>fail_count:
|
||
result.append({
|
||
"stu_name":stu.stu_name,
|
||
"class_id":stu.class_id,
|
||
"scores":[{"exam_order":i.exam_order,"score":i.score} for i in stu.scores]
|
||
})
|
||
return result
|
||
|
||
@staticmethod
|
||
def get_class_avg_score(db: Session, sort_order: SortOrder | None = None):
|
||
"""每次考试每个班级的平均分，支持按平均分动态升/降序"""
|
||
avg_score = func.avg(Score.score).label("avg_score")
|
||
|
||
q = db.query(
|
||
Student.class_id.label("class_id"),
|
||
Score.exam_order.label("exam_order"),
|
||
avg_score,
|
||
).select_from(Score) \
|
||
.join(Score.student) \
|
||
.filter(Student.is_deleted == 0, Student.class_id.isnot(None)) \
|
||
.group_by(Student.class_id, Score.exam_order)
|
||
|
||
# 动态排序：传了方向就按平均分排，没传则按班级 + 考试序次排
|
||
if sort_order == SortOrder.desc:
|
||
q = q.order_by(avg_score.desc())
|
||
elif sort_order == SortOrder.asc:
|
||
q = q.order_by(avg_score.asc())
|
||
else:
|
||
q = q.order_by(Student.class_id, Score.exam_order)
|
||
|
||
return q.all()
|
||
|
||
@staticmethod
|
||
def get_info_by_rank(db:Session,rank:int):
|
||
q=(db.query(
|
||
Student.stu_name,
|
||
Student.class_id,
|
||
Emp.offer_time,
|
||
Emp.company_name
|
||
).select_from(Student) \
|
||
.join(Student.emp)) \
|
||
.filter(Student.is_deleted==0, Emp.is_deleted==0) \
|
||
.order_by(Emp.salary.desc())\
|
||
.limit(rank)
|
||
|
||
return q.all()
|
||
@staticmethod
|
||
def get_emp_time(db:Session):
|
||
"""每个学生的就业时长（天）= offer下发时间 - 就业开放时间
|
||
"""
|
||
emp_total_time = func.coalesce(
|
||
# 未就业学生左外连接后 Emp 列为 NULL，DATEDIFF 也返回 NULL，统一兜成 0
|
||
func.datediff(Emp.offer_time, Emp.emp_open_time),
|
||
0,
|
||
).label('emp_total_time')
|
||
|
||
# 逻辑删除条件写在 ON 里，写进 where 会变成 INNER JOIN，未就业学生会被滤掉
|
||
q=db.query(
|
||
Student.stu_name,
|
||
emp_total_time,
|
||
).select_from(Student) \
|
||
.outerjoin(Emp, and_(Student.stu_no == Emp.stu_no, Emp.is_deleted == 0)) \
|
||
.filter(Student.is_deleted==0)
|
||
|
||
return q.all()
|
||
|
||
@staticmethod
|
||
def get_class_avg_emp_time(db:Session, sort_order: SortOrder | None = None):
|
||
"""每个班级的平均就业时长（天）= offer下发时间 - 就业开放时间
|
||
|
||
口径：
|
||
- 以班级表为主表左外连接，保证没有任何就业学生的班级也出现在结果里
|
||
- 只统计已进入就业阶段（emp_open_time 非空）且已拿到 offer（offer_time 非空）的学生
|
||
- 该班可统计的人数为 0 时 AVG 返回 NULL，出参里 avg_emp_time 给 None，即"无就业学生"
|
||
"""
|
||
emp_time = func.datediff(Emp.offer_time, Emp.emp_open_time)
|
||
# AVG 和 COUNT(表达式) 都会自动忽略 NULL，所以没 offer 时间的学生不参与分子也不占分母
|
||
avg_emp_time = func.avg(emp_time).label("avg_emp_time")
|
||
# 用 COUNT(表达式) 而不是 COUNT(*)，它正好是平均值的分母
|
||
emp_stu_count = func.count(emp_time).label("emp_stu_count")
|
||
|
||
q = db.query(
|
||
Class_.class_id.label("class_id"),
|
||
avg_emp_time,
|
||
emp_stu_count,
|
||
).select_from(Class_) \
|
||
.outerjoin(
|
||
Student,
|
||
# 逻辑删除的过滤条件必须写在 ON 里，写进 where 会把空班级整行滤掉
|
||
and_(Student.class_id == Class_.class_id, Student.is_deleted == 0),
|
||
) \
|
||
.outerjoin(
|
||
Emp,
|
||
and_(
|
||
Emp.stu_no == Student.stu_no,
|
||
Emp.is_deleted == 0,
|
||
Emp.emp_open_time.isnot(None),
|
||
Emp.offer_time.isnot(None),
|
||
),
|
||
) \
|
||
.group_by(Class_.class_id)
|
||
|
||
# 动态排序逻辑与 get_class_avg_score 保持一致
|
||
if sort_order == SortOrder.desc:
|
||
# MySQL 里 DESC 时 NULL 排最后，"无就业学生"的班级自然落到末尾
|
||
q = q.order_by(avg_emp_time.desc())
|
||
elif sort_order == SortOrder.asc:
|
||
q = q.order_by(avg_emp_time.asc())
|
||
else:
|
||
q = q.order_by(Class_.class_id)
|
||
|
||
return [
|
||
{
|
||
"class_id": r.class_id,
|
||
# AVG 出来是 Decimal，转 float 并按天保留 1 位小数；None 表示该班无就业学生
|
||
"avg_emp_time": round(float(r.avg_emp_time), 1)
|
||
if r.avg_emp_time is not None else None,
|
||
"emp_stu_count": r.emp_stu_count,
|
||
}
|
||
for r in q.all()
|
||
]
|
||
|
||
|
||
|
||
|
||
|
||
|