fix: 调整数据大盘 DAU 为开始比价和开始领券口径

app/admin/repositories/stats.py

@@ -13,6 +13,7 @@ from sqlalchemy.orm import Session
 
 from app.models.ad_feed_reward import AdFeedRewardRecord
 from app.models.ad_reward import AdRewardRecord
+from app.models.analytics_event import AnalyticsEvent
 from app.models.comparison import ComparisonRecord
 from app.models.coupon_state import CouponPromptEngagement
 from app.models.cps_order import CpsOrder
@@ -35,6 +36,8 @@ REGULAR_TASK_EXCLUDED_BIZ_TYPES = (
 )
 MEITUAN_CPS_INVALID_STATUSES = ("4", "5")
 MEITUAN_CPS_SETTLED_STATUS = "6"
+COMPARE_START_EVENT = "real_compare_start"
+COUPON_START_EVENT = "real_coupon_start"
 JD_CPS_INVALID_CODES = {
     "2", "3", "4", "5", "6", "7", "8", "9", "11", "13", "14", "19", "20", "21",
     "22", "23", "25", "26", "27", "28", "29", "30", "31", "34", "35", "36",
@@ -50,14 +53,31 @@ def _beijing_today_start_utc() -> datetime:
 
 
 def today_dau(db: Session) -> int:
-    """今日活跃用户数(DAU):北京时区今天 0 点后登录过(last_login_at)。
+    """今日活跃用户数(DAU):登录 + 开始比价 + 开始领券,按用户去重。
 
     广告收益报表复用这个函数;历史窗口 DAU 由 dashboard_overview 的 period 口径另算。
     """
+    today_bj = datetime.now(_BEIJING).date()
     today_start = _beijing_today_start_utc()
-    return int(
-        db.execute(select(func.count(User.id)).where(User.last_login_at >= today_start)).scalar_one()
+    tomorrow_start = today_start + timedelta(days=1)
+    login_user_ids = _id_set(
+        db,
+        select(User.id).where(User.last_login_at >= today_start, User.last_login_at < tomorrow_start),
     )
+    compare_start_user_ids = _event_user_ids(
+        db, (COMPARE_START_EVENT,), today_start, tomorrow_start
+    )
+    coupon_event_user_ids = _event_user_ids(
+        db, (COUPON_START_EVENT,), today_start, tomorrow_start
+    )
+    coupon_claim_user_ids = _id_set(
+        db,
+        select(CouponPromptEngagement.user_id).where(
+            CouponPromptEngagement.engage_date == today_bj,
+            CouponPromptEngagement.engage_type == "claim_started",
+        ),
+    )
+    return len(login_user_ids | compare_start_user_ids | coupon_event_user_ids | coupon_claim_user_ids)
 
 
 def _default_period_end() -> date:
@@ -96,6 +116,24 @@ def _date_range(date_from: date, date_to: date) -> list[date]:
     return [date_from + timedelta(days=i) for i in range(days + 1)]
 
 
+def _id_set(db: Session, stmt) -> set[int]:
+    return {int(v) for v in db.execute(stmt).scalars().all() if v is not None}
+
+
+def _event_user_ids(
+    db: Session, event_names: tuple[str, ...], start_utc: datetime, end_utc: datetime
+) -> set[int]:
+    return _id_set(
+        db,
+        select(AnalyticsEvent.user_id).where(
+            AnalyticsEvent.user_id.is_not(None),
+            AnalyticsEvent.event.in_(event_names),
+            AnalyticsEvent.created_at >= start_utc,
+            AnalyticsEvent.created_at < end_utc,
+        ),
+    )
+
+
 def _commission_rate_percent(raw: str | None) -> Decimal | None:
     """美团 commissionRate 原值: "300"=3%, "10"=0.1%;也兼容 "3%"。"""
     if raw is None:
@@ -226,17 +264,22 @@ def dashboard_overview(
     login_user_ids = _user_id_set(
         select(User.id).where(User.last_login_at >= start_utc, User.last_login_at < end_utc)
     )
-    compare_user_ids = _user_id_set(
-        select(ComparisonRecord.user_id).where(*period_comparison_conds)
+    compare_start_user_ids = _event_user_ids(
+        db, (COMPARE_START_EVENT,), start_utc, end_utc
     )
-    coupon_user_ids = _user_id_set(
+    coupon_event_user_ids = _event_user_ids(
+        db, (COUPON_START_EVENT,), start_utc, end_utc
+    )
+    coupon_claim_user_ids = _user_id_set(
         select(CouponPromptEngagement.user_id).where(
             CouponPromptEngagement.engage_date >= period_from,
             CouponPromptEngagement.engage_date <= period_to,
             CouponPromptEngagement.engage_type == "claim_started",
         )
     )
-    period_active_user_ids = login_user_ids | compare_user_ids | coupon_user_ids
+    period_active_user_ids = (
+        login_user_ids | compare_start_user_ids | coupon_event_user_ids | coupon_claim_user_ids
+    )
     period_retained_new_user_ids = period_new_user_ids & period_active_user_ids
     period_retention_rate = (
         round(len(period_retained_new_user_ids) / len(period_new_user_ids), 4)
@@ -258,10 +301,13 @@ def dashboard_overview(
                 User.last_login_at < day_end_utc,
             )
         )
-        daily_compare_user_ids = _user_id_set(
-            select(ComparisonRecord.user_id).where(*daily_comparison_conds)
+        daily_compare_start_user_ids = _event_user_ids(
+            db, (COMPARE_START_EVENT,), day_start_utc, day_end_utc
         )
-        daily_coupon_user_ids = _user_id_set(
+        daily_coupon_event_user_ids = _event_user_ids(
+            db, (COUPON_START_EVENT,), day_start_utc, day_end_utc
+        )
+        daily_coupon_claim_user_ids = _user_id_set(
             select(CouponPromptEngagement.user_id).where(
                 CouponPromptEngagement.engage_date == cur_date,
                 CouponPromptEngagement.engage_type == "claim_started",
@@ -271,7 +317,10 @@ def dashboard_overview(
             {
                 "date": cur_date,
                 "active_users": len(
-                    daily_login_user_ids | daily_compare_user_ids | daily_coupon_user_ids
+                    daily_login_user_ids
+                    | daily_compare_start_user_ids
+                    | daily_coupon_event_user_ids
+                    | daily_coupon_claim_user_ids
                 ),
                 "new_users": _count(
                     User,
@@ -430,8 +479,8 @@ def dashboard_overview(
                 "retained_new_users": len(period_retained_new_user_ids),
                 "retention_rate": period_retention_rate,
                 "retention_note": (
-                    "近似口径:登录(last_login_at)+已上报比价记录+领券claim_started;"
-                    "尚不包含未完成上报的比价开始事件"
+                    "口径:登录(last_login_at)+开始比价(real_compare_start)+"
+                    "开始领券(real_coupon_start/claim_started),按用户去重"
                 ),
             },
             "comparison": {