fix(growth): require a 1000-view baseline on the rate board

Keep small-base videos on the delta board only, and raise the smoothing prior to 1000 so videos that just clear the floor do not dominate the ranking.

DEVELOPMENT.md

@@ -608,7 +608,7 @@ interaction_rate = (like + coin + favorite) / max(view, 1)
 
 - 查询前一有效快照而不是填补缺失日期；
 - 缺失日期在图表中断开；
-- 增速榜要求播放基数至少 200；
+- 增速榜要求播放基数至少 1000；
 - 互动率榜要求播放至少 100；
 - 样本不足两天的视频明确标注，不伪造增长数据。
 

config.docker.example.jsonc

@@ -108,6 +108,6 @@
     "video_shrink_minutes": 60,
     "shrink_minutes": null,
     "home_growth_days": "auto",
-    "growth_rate_prior": 500,
+    "growth_rate_prior": 1000,
   },
 }

config.example.jsonc

@@ -124,6 +124,6 @@
     // "auto" = 7 日有数据用 7，否则 1
     "home_growth_days": "auto",
     // 增速榜排序：Δ / (基线 + prior)。卡片上的百分比仍是 Δ / 基线。
-    "growth_rate_prior": 500,
+    "growth_rate_prior": 1000,
   },
 }

project.md

@@ -681,14 +681,14 @@ d7 = (view_today - view_{today-7}) / 实际间隔天数
 r7 = (view_today - view_{today-7}) / max(view_{today-7}, 1)
 d1_published_today = view_today - 0          # 只进增量榜，不计算增速
 d1_imported_today  = view_today - view_open   # 需同日第二次采样
-sort_rate = Δ / (基线 + analytics.growth_rate_prior)  # 默认 prior=500，只用于增速榜排序
+sort_rate = Δ / (基线 + analytics.growth_rate_prior)  # 默认 prior=1000，只用于增速榜排序
 ```
 
 | 榜 | 口径 | 基数门槛 |
 |---|---|---|
 | 累计热度 | §8.1 | — |
 | 近 7 天播放增量 | `d7(view)` | — |
-| 近 7 天增速 | `r7(view)` | `view >= 200` |
+| 近 7 天增速 | `r7(view)` | 基线播放 `>= 1000` |
 | 互动率 | `(like+coin+fav)/view` | `view >= 100` |
 | 单项榜 | 7 项直接排序 | — |
 | UP 榜 | 按 `up_mid` 聚合 Σ/AVG | — |

reaction_board/analytics.py

@@ -34,7 +34,7 @@ DEFAULT_HEAT_WEIGHTS: dict[str, float] = {
 }
 
 MIN_VIEW_FOR_INTERACTION = 100
-MIN_VIEW_FOR_GROWTH_RATE = 200
+MIN_VIEW_FOR_GROWTH_RATE = 1000
 MIN_EFFICIENCY_DURATION = 600
 DEFAULT_MATURITY_DAYS = 2
 DEFAULT_SHRINK_MINUTES = 120.0

reaction_board/config.py

@@ -52,7 +52,7 @@ DEFAULT_ANALYTICS: dict[str, Any] = {
     "video_shrink_minutes": 60,
     "shrink_minutes": None,
     "home_growth_days": "auto",
-    "growth_rate_prior": 500,
+    "growth_rate_prior": 1000,
 }
 
 DEFAULT_CONFIG: dict[str, Any] = {
@@ -595,7 +595,7 @@ def _build_config(data: Mapping[str, Any], path: Path, *, secrets_path: Path) ->
         ),
         home_growth_days=home_growth_days,
         growth_rate_prior=_as_int(
-            analytics_raw.get("growth_rate_prior", 500),
+            analytics_raw.get("growth_rate_prior", 1000),
             "analytics.growth_rate_prior",
             minimum=0,
         ),

reaction_board/web/queries.py

@@ -59,6 +59,19 @@ def _chunks(values: Sequence[int], size: int = 400) -> Iterable[Sequence[int]]:
         yield values[index:index + size]
 
 
+def _growth_baseline_view(item: Mapping[str, Any]) -> int | None:
+    """增速分母：当前播放减去区间增量。zero 基线的增量等于当前播放，结果为 0。"""
+    growth = item.get("growth") or {}
+    current = (item.get("metrics") or {}).get("view")
+    delta = growth.get("delta")
+    if current is None or delta is None:
+        return None
+    try:
+        return int(current) - int(delta)
+    except (TypeError, ValueError):
+        return None
+
+
 def _date_minus(day: str, days: int) -> str:
     return (date.fromisoformat(day) - timedelta(days=int(days))).isoformat()
 
@@ -1036,7 +1049,7 @@ class DashboardQueries:
                         item for item in items
                         if item.get("growth", {}).get("baseline") != "zero"
                         and item.get("growth", {}).get("rate") is not None
-                        and (item["metrics"] or {}).get("view", 0) >= MIN_VIEW_FOR_GROWTH_RATE
+                        and (_growth_baseline_view(item) or 0) >= MIN_VIEW_FOR_GROWTH_RATE
                     ]
 
             rate_prior = max(0, int(analytics.growth_rate_prior))
@@ -1087,8 +1100,8 @@ class DashboardQueries:
                 available = False
                 if growth_days == 1 and sort == "growth_rate":
                     reason = (
-                        "近 1 日增速需要前一日快照，或更早发布的新入库当天至少两次成功采样；"
+                        "近 1 日增速需要基线播放至少 "
-                        "当日发布不计入增速"
+                        f"{MIN_VIEW_FOR_GROWTH_RATE}；当日发布不计入增速"
                     )
                 elif growth_days == 1:
                     reason = (

reaction_board/web/static/views/about.js

@@ -50,7 +50,7 @@ export async function renderAbout(root) {
         <li><strong>播放 / 投币 / 收藏 / 评论</strong>：直接取当日快照；弹幕与转发不单列，已并入“互动”。</li>
         <li><strong>互动</strong>：点赞 + 投币 + 收藏。综合热度也使用全部七项指标，按配置权重加权。</li>
         <li><strong>互动率</strong>：(点赞 + 投币 + 收藏) / 播放；播放不足 100 不计算。</li>
-        <li><strong>播放增速</strong>：卡片上的百分比是增量 / 基线播放。排序用增量 / (基线 + ${analytics.growth_rate_prior})，避免小基数霸榜。当日发布没有基线，不进增速榜。</li>
+        <li><strong>播放增速</strong>：卡片上的百分比是增量 / 基线播放。基线播放不足 1000 不进增速榜。排序用增量 / (基线 + ${analytics.growth_rate_prior})。当日发布没有基线，不进增速榜。</li>
         <li><strong>综合热度</strong>：每项先 <code>log1p</code>，再按中位数与 IQR 做稳健标准化，最后加权求和。分数只用于同一批数据内排序，不能跨日期比较。</li>
         <li><strong>内容效率</strong>：播放 / 内容小时。内容小时 = 视频总时长（多 P 为各 P 之和）÷ 3600。榜单里的单条视频用收缩后的估计：<code>(播放 + κ·μ₀) / (小时 + κ)</code>，κ 默认 ${analytics.video_shrink_minutes} 分钟、μ₀ 为全库播放/小时；详情页保留原始播放/小时。</li>
         <li><strong>互动效率</strong>：互动 / 内容小时，互动口径与收缩方式同上。</li>

reaction_board/web/static/views/rankings.js

@@ -187,8 +187,8 @@ function growthNote(sort, growthDays, prior) {
       ? `百分比是真实相对增量；排序按平滑增速（基线 + ${strength}）。`
       : "百分比是真实相对增量；排序按平滑增速。";
     const cold = Number(growthDays) === 1
-      ? "当日发布不进增速榜。更早发布的新入库按入库时播放量起算，需要当天至少两次采样。"
+      ? "基线播放不足 1000、以及当日发布，不进增速榜。"
-      : "";
+      : "基线播放不足 1000 不进增速榜。";
     return `<div class="section-note">${smooth}${cold}</div>`;
   }
   if (sort !== "growth" || Number(growthDays) !== 1) return "";

tests/test_config.py

@@ -146,7 +146,7 @@ def test_analytics_defaults_and_validation():
         assert cfg.analytics.video_shrink_minutes == 60
         assert cfg.analytics.shrink_minutes is None
         assert cfg.analytics.home_growth_days == "auto"
-        assert cfg.analytics.growth_rate_prior == 500
+        assert cfg.analytics.growth_rate_prior == 1000
         assert cfg.schedule.recent_snapshot_minutes == 60
         assert cfg.schedule.recent_video_days == 2
         assert cfg.schedule.snapshot_at == "23:15"
@@ -160,7 +160,7 @@ def test_analytics_defaults_and_validation():
             "video_shrink_minutes": 30,
             "shrink_minutes": 90,
             "home_growth_days": 1,
-            "growth_rate_prior": 1000,
+            "growth_rate_prior": 2000,
         }
         data["schedule"] = {
             "discover_minutes": 30,
@@ -178,7 +178,7 @@ def test_analytics_defaults_and_validation():
         assert cfg.analytics.video_shrink_minutes == 30
         assert cfg.analytics.shrink_minutes == 90
         assert cfg.analytics.home_growth_days == 1
-        assert cfg.analytics.growth_rate_prior == 1000
+        assert cfg.analytics.growth_rate_prior == 2000
         assert cfg.schedule.recent_snapshot_minutes == 15
         assert cfg.schedule.recent_video_days == 3
 

tests/test_web_queries.py

@@ -492,7 +492,7 @@ def test_about_payload():
                 "video_shrink_minutes": 60,
                 "shrink_minutes": None,
                 "home_growth_days": "auto",
-                "growth_rate_prior": 500,
+                "growth_rate_prior": 1000,
             }
             assert about["heat_weights"]["view"] == 0.30
             assert about["followers"]["videos_total"] == 3
@@ -758,8 +758,8 @@ def test_same_day_growth_baselines():
 
             rate = q.list_videos(sort="growth_rate", growth_days=1, page_size=20)
             rate_aids = {item["aid"] for item in rate["items"]}
-            assert 103 not in rate_aids
+            assert 103 not in rate_aids and 105 not in rate_aids
-            assert 101 in rate_aids and 105 in rate_aids
+            assert 101 in rate_aids
 
             seven = q.list_videos(sort="growth", growth_days=7)
             seven_aids = {item["aid"] for item in seven["items"]}
@@ -782,7 +782,7 @@ def test_same_day_growth_baselines():
 
 
 def test_growth_rate_sort_uses_prior():
-    """小基数的真实增速可以更高，排序分用基线 + prior，不按 raw rate 排。"""
+    """基线不足 1000 不进增速榜；达标后按基线 + prior 排序，不按 raw rate。"""
     with tempfile.TemporaryDirectory() as tmp:
         db, q = setup(tmp)
         try:
@@ -791,7 +791,9 @@ def test_growth_rate_sort_uses_prior():
             previous_day = DATES[-2]
             start = int(day_bounds(latest)[0])
             pub = int(day_bounds("2026-09-01")[0])
-            for aid, views in ((301, (80, 512)), (302, (2000, 4000))):
+            # 301：80→512，真实 +540%，基线低于 1000，只留在增量榜。
+            # 304：1000→2500，真实增速高于 302，平滑后应排在 302 后面。
+            for aid, views in ((301, (80, 512)), (302, (5000, 10000)), (304, (1000, 2500))):
                 repo.upsert_from_fav(
                     resource(aid, up_mid=1, up_name="UP A", pubdate=pub),
                     FOLDER.media_id, was_added=True, now=start,
@@ -807,11 +809,16 @@ def test_growth_rate_sort_uses_prior():
             DASHBOARD_CACHE.clear()
             ranked = q.list_videos(sort="growth_rate", growth_days=1, page_size=20)
             order = [item["aid"] for item in ranked["items"]]
-            assert ranked["growth_rate_prior"] == 500
+            assert ranked["growth_rate_prior"] == 1000
-            assert order.index(302) < order.index(301)
+            assert 301 not in order
-            small = next(item for item in ranked["items"] if item["aid"] == 301)
+            assert order.index(302) < order.index(304)
-            assert abs(small["growth"]["rate"] - 432 / 80) < 1e-12
+            modest = next(item for item in ranked["items"] if item["aid"] == 304)
-            assert small["growth"]["delta"] == 432
+            assert abs(modest["growth"]["rate"] - 1500 / 1000) < 1e-12
+
+            growth = q.list_videos(sort="growth", growth_days=1, page_size=20)
+            grown = next(item for item in growth["items"] if item["aid"] == 301)
+            assert grown["growth"]["delta"] == 432
+            assert abs(grown["growth"]["rate"] - 432 / 80) < 1e-12
         finally:
             db.close()