WorkBuddy
71bf723a10
P1-1 schema/ORM 漂移: - 新增 0006 迁移: 回填后 drop 幽灵列 predictions.cutoff_at, 并幂等重建 ix_match_stats_available_at / ix_predictions_cutoff_at - models.py 为 MatchStats / Prediction 声明上述两个索引, 使 autogenerate 不再误建议删除 P1-2 迁移对历史越界数据不安全: - 0004 在建 CHECK 约束前先 op.execute 清洗越界行 (负数进球/置信度越界/非法 1x2/mode),避免 ALTER 中途失败 导致迁移卡在半完成状态 P1-3 回测缓存污染: - predict_match / _predict_single 新增 use_cache 参数, use_cache=False 时既不读也不写进程内缓存 - run_backtest 显式传 use_cache=False,避免 settle 到旧记录 P1-5 understat 关系属性访问: - MatchRepository.find_by_teams_and_date 加 selectinload(Match.stats) P1-6 日期键构造不统一: - bzzoiro 抽取 _to_date()/_match_key() 统一去重键构造, 消除 str(date) 与 isoformat() 的隐式格式依赖
213 lines
10 KiB
Python
213 lines
10 KiB
Python
"""6 张表 ORM: leagues / teams / matches / match_stats / predictions / injuries。"""
|
|
from __future__ import annotations
|
|
|
|
from datetime import date, datetime, timezone
|
|
|
|
from sqlalchemy import (
|
|
Boolean,
|
|
CheckConstraint,
|
|
Date,
|
|
DateTime,
|
|
Float,
|
|
ForeignKey,
|
|
Index,
|
|
Integer,
|
|
String,
|
|
Text,
|
|
func,
|
|
)
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
from sqlalchemy.orm import Mapped, mapped_column, relationship
|
|
|
|
from src.db.base import Base
|
|
|
|
|
|
def _utcnow() -> datetime:
|
|
return datetime.now(timezone.utc)
|
|
|
|
|
|
class League(Base):
|
|
__tablename__ = "leagues"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
code: Mapped[str] = mapped_column(String(20), unique=True, nullable=False)
|
|
name: Mapped[str] = mapped_column(String(100), nullable=False)
|
|
country: Mapped[str | None] = mapped_column(String(50))
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
|
|
matches: Mapped[list["Match"]] = relationship(back_populates="league")
|
|
|
|
|
|
class Team(Base):
|
|
__tablename__ = "teams"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
name: Mapped[str] = mapped_column(String(120), unique=True, nullable=False)
|
|
name_zh: Mapped[str | None] = mapped_column(String(60))
|
|
team_type: Mapped[str] = mapped_column(String(20), default="club")
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
|
|
home_matches: Mapped[list["Match"]] = relationship(foreign_keys="Match.home_team_id", back_populates="home_team")
|
|
away_matches: Mapped[list["Match"]] = relationship(foreign_keys="Match.away_team_id", back_populates="away_team")
|
|
|
|
|
|
class Match(Base):
|
|
__tablename__ = "matches"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
league_id: Mapped[int] = mapped_column(ForeignKey("leagues.id"), nullable=False)
|
|
season: Mapped[str | None] = mapped_column(String(12))
|
|
home_team_id: Mapped[int] = mapped_column(ForeignKey("teams.id"), nullable=False)
|
|
away_team_id: Mapped[int] = mapped_column(ForeignKey("teams.id"), nullable=False)
|
|
match_date: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
|
|
match_date_date: Mapped[date] = mapped_column(
|
|
"match_date_date",
|
|
Date,
|
|
nullable=False,
|
|
index=True,
|
|
)
|
|
match_status: Mapped[str] = mapped_column(String(20), default="scheduled")
|
|
home_goals: Mapped[int | None] = mapped_column(Integer)
|
|
away_goals: Mapped[int | None] = mapped_column(Integer)
|
|
home_ht_goals: Mapped[int | None] = mapped_column(Integer)
|
|
away_ht_goals: Mapped[int | None] = mapped_column(Integer)
|
|
match_stage: Mapped[str | None] = mapped_column(String(100))
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow, onupdate=_utcnow)
|
|
|
|
league: Mapped[League] = relationship(back_populates="matches", lazy="selectin")
|
|
# lazy="selectin": 这些关系在业务里几乎总是一起读取(切片/回测/展示)。
|
|
# 默认的 lazy="select" 在 async SQLAlchemy 下,于 session 之外或未显式
|
|
# eager-load 时访问会抛 MissingGreenlet —— 已因此导致 form/stats/h2h
|
|
# 三个专家切片静默失败。统一改为预加载,从根上消除这类问题。
|
|
home_team: Mapped[Team] = relationship(
|
|
foreign_keys=[home_team_id], back_populates="home_matches", lazy="selectin"
|
|
)
|
|
away_team: Mapped[Team] = relationship(
|
|
foreign_keys=[away_team_id], back_populates="away_matches", lazy="selectin"
|
|
)
|
|
stats: Mapped["MatchStats | None"] = relationship(
|
|
back_populates="match", cascade="all, delete-orphan", lazy="selectin"
|
|
)
|
|
predictions: Mapped[list["Prediction"]] = relationship(back_populates="match", cascade="all, delete-orphan")
|
|
|
|
__table_args__ = (
|
|
Index("ix_matches_league_date", "league_id", match_date.desc()),
|
|
Index("ix_matches_home_date", "home_team_id", match_date.desc()),
|
|
Index("ix_matches_away_date", "away_team_id", match_date.desc()),
|
|
Index("ix_matches_status_date", "match_status", match_date.desc()),
|
|
Index(
|
|
"ix_matches_unique",
|
|
"league_id",
|
|
"home_team_id",
|
|
"away_team_id",
|
|
"match_date_date",
|
|
unique=True,
|
|
),
|
|
)
|
|
|
|
|
|
class MatchStats(Base):
|
|
__tablename__ = "match_stats"
|
|
|
|
match_id: Mapped[int] = mapped_column(ForeignKey("matches.id", ondelete="CASCADE"), primary_key=True)
|
|
home_xg: Mapped[float | None] = mapped_column(Float)
|
|
away_xg: Mapped[float | None] = mapped_column(Float)
|
|
home_shots: Mapped[int | None] = mapped_column(Integer)
|
|
away_shots: Mapped[int | None] = mapped_column(Integer)
|
|
home_shots_on_target: Mapped[int | None] = mapped_column(Integer)
|
|
away_shots_on_target: Mapped[int | None] = mapped_column(Integer)
|
|
home_corners: Mapped[int | None] = mapped_column(Integer)
|
|
away_corners: Mapped[int | None] = mapped_column(Integer)
|
|
home_possession: Mapped[float | None] = mapped_column(Float)
|
|
home_yellow_cards: Mapped[int | None] = mapped_column(Integer)
|
|
away_yellow_cards: Mapped[int | None] = mapped_column(Integer)
|
|
home_red_cards: Mapped[int | None] = mapped_column(Integer)
|
|
away_red_cards: Mapped[int | None] = mapped_column(Integer)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow, onupdate=_utcnow)
|
|
# 数据血缘:追踪统计数据的来源和可用时间
|
|
source: Mapped[str | None] = mapped_column(String(30)) # bzzoiro / understat
|
|
source_record_id: Mapped[str | None] = mapped_column(String(100))
|
|
retrieved_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
available_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
|
|
match: Mapped[Match] = relationship(back_populates="stats")
|
|
|
|
__table_args__ = (
|
|
# 数据血缘时间过滤查询用(按 available_at 取「赛前已可得」的统计)
|
|
Index("ix_match_stats_available_at", "available_at"),
|
|
)
|
|
|
|
|
|
class Injury(Base):
|
|
"""球员伤停记录(api-football 数据源)。"""
|
|
__tablename__ = "injuries"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
player_id: Mapped[int | None] = mapped_column(Integer, index=True)
|
|
player_name: Mapped[str] = mapped_column(String(120), nullable=False)
|
|
team_id: Mapped[int | None] = mapped_column(ForeignKey("teams.id"), index=True)
|
|
fixture_id: Mapped[int | None] = mapped_column(Integer)
|
|
league_id: Mapped[int | None] = mapped_column(Integer)
|
|
injury_type: Mapped[str | None] = mapped_column(String(50)) # Missing Fixture / Suspended
|
|
reason: Mapped[str | None] = mapped_column(String(200))
|
|
injury_date: Mapped[date | None] = mapped_column(Date, index=True)
|
|
return_date: Mapped[date | None] = mapped_column(Date)
|
|
retrieved_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
|
|
team: Mapped["Team | None"] = relationship()
|
|
|
|
__table_args__ = (
|
|
Index("ix_injuries_player_fixture", "player_id", "fixture_id", "injury_type", unique=True),
|
|
Index("ix_injuries_team_date", "team_id", "injury_date"),
|
|
)
|
|
|
|
|
|
class Prediction(Base):
|
|
__tablename__ = "predictions"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
|
match_id: Mapped[int] = mapped_column(ForeignKey("matches.id"), nullable=False)
|
|
provider: Mapped[str] = mapped_column(String(30), nullable=False)
|
|
model: Mapped[str] = mapped_column(String(80), nullable=False)
|
|
prompt_version: Mapped[str] = mapped_column(String(20), nullable=False, default="v1")
|
|
prompt_tokens: Mapped[int | None] = mapped_column(Integer)
|
|
completion_tokens: Mapped[int | None] = mapped_column(Integer)
|
|
latency_ms: Mapped[int | None] = mapped_column(Integer)
|
|
pred_home_goals: Mapped[float | None] = mapped_column(Float)
|
|
pred_away_goals: Mapped[float | None] = mapped_column(Float)
|
|
pred_1x2: Mapped[str | None] = mapped_column(String(3))
|
|
subjective_confidence: Mapped[float | None] = mapped_column(Float) # LLM 主观置信度,非概率
|
|
reasoning: Mapped[str | None] = mapped_column(Text)
|
|
raw_response: Mapped[dict | None] = mapped_column(JSONB)
|
|
# multi-agent 模式: 各专家报告
|
|
mode: Mapped[str] = mapped_column(String(20), nullable=False, default="single")
|
|
agent_outputs: Mapped[dict | None] = mapped_column(JSONB)
|
|
# 预测状态: success / failed / degraded
|
|
status: Mapped[str] = mapped_column(String(20), nullable=False, default="success")
|
|
# 时间语义:区分比赛时间、预测创建时间、数据截止时间
|
|
match_kickoff_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
prediction_created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
prediction_cutoff_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
|
|
input_hash: Mapped[str | None] = mapped_column(String(64))
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=_utcnow)
|
|
actual_home_goals: Mapped[int | None] = mapped_column(Integer)
|
|
actual_away_goals: Mapped[int | None] = mapped_column(Integer)
|
|
settled: Mapped[bool] = mapped_column(Boolean, default=False)
|
|
|
|
match: Mapped[Match] = relationship(back_populates="predictions")
|
|
|
|
__table_args__ = (
|
|
Index("ix_predictions_match", "match_id"),
|
|
Index("ix_predictions_provider_model", "provider", "model"),
|
|
# 数据截止时间过滤查询用(按 prediction_cutoff_at 取「赛前已生成」的预测)
|
|
Index("ix_predictions_cutoff_at", "prediction_cutoff_at"),
|
|
# 数据库级约束:最后一道防线
|
|
CheckConstraint("pred_home_goals >= 0", name="ck_pred_home_goals_nonneg"),
|
|
CheckConstraint("pred_away_goals >= 0", name="ck_pred_away_goals_nonneg"),
|
|
CheckConstraint("subjective_confidence >= 0 AND subjective_confidence <= 1", name="ck_confidence_range"),
|
|
CheckConstraint("pred_1x2 IN ('1', 'X', '2')", name="ck_pred_1x2_enum"),
|
|
CheckConstraint("mode IN ('single', 'multi')", name="ck_mode_enum"),
|
|
CheckConstraint("status IN ('success', 'failed', 'degraded')", name="ck_status_enum"),
|
|
)
|