Add Geo suffix and Adpingid column to 投手明细

Package now renders as pkg_GEO, where GEO is the region with the highest
total spend for that package. The new Adpingid column shows the
top-spending Adping within that region, so label and id stay consistent.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

build_data.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python3
-# 从 xlsx 重算 data.json。取数规则见 README 注释：
-#   平台消耗统计: B=Date, C=Adpingid, D=包名, I=花费
-#   投手:        B=Adpingid, L=Media Buyer投放人
-#   @某某 == 某某；未填投放人的 Adpingid 丢弃；exclude.json 里的包名永久剔除。
+# 从 xlsx 重算 data.json。
+#   平台消耗统计: B=Date, C=Adpingid, D=包名, E=地区, I=花费
+#   投手:        B=Adpingid, D=pkg, L=Media Buyer投放人
+# 规则：@某某 == 某某；未填投放人的 Adpingid 丢弃；exclude.json 里的包名永久剔除（精确匹配）。
+# 每个 package 明细：Geo 后缀 = 该 package 花费最高的地区；Adpingid = 该地区内花费最高的 Adping。
 import openpyxl, collections, json, datetime, os, sys
 
 HERE = os.path.dirname(os.path.abspath(__file__))
@@ -18,7 +19,7 @@ def key(v):
 
 wb = openpyxl.load_workbook(SRC, data_only=True)
 
-# --- 投手表：Adpingid -> 投放人；同时收集需按 Adping 剔除的 id ---
+# --- 投手表：Adpingid -> 投放人 ---
 amap, dropped_ids = {}, set()
 for r in wb['投手'].iter_rows(min_row=2, values_only=True):
     adp, pkg, buyer, status = r[1], r[3], r[11], r[0]
@@ -38,14 +39,15 @@ owned = collections.Counter(amap.values())   # 每位投手名下的 Adpingid
 # --- 平台消耗统计 ---
 rows = []
 for r in wb['平台消耗统计'].iter_rows(min_row=2, values_only=True):
-    d, adp, pkg, spend = r[1], r[2], r[3], r[8]
+    d, adp, pkg, geo, spend = r[1], r[2], r[3], r[4], r[8]
     if d is None or adp is None or not isinstance(d, datetime.datetime):
         continue
     try:
         s = float(spend) if spend is not None else 0.0
     except (TypeError, ValueError):
         s = 0.0
-    rows.append((d.date(), key(adp), (str(pkg).strip() if pkg else '(未知)'), s))
+    rows.append((d.date(), key(adp), (str(pkg).strip() if pkg else '(未知)'),
+                 (str(geo).strip() if geo else ''), s))
 
 if not rows:
     sys.exit('ERROR: 平台消耗统计 无有效数据行')
@@ -53,32 +55,55 @@ if not rows:
 end = max(r[0] for r in rows)
 start = end - datetime.timedelta(days=WINDOW_DAYS - 1)
 
-buyers = collections.defaultdict(lambda: collections.defaultdict(float))
+pkg_spend = collections.defaultdict(float)   # (buyer, pkg)             -> spend
+geo_spend = collections.defaultdict(float)   # (buyer, pkg, geo)        -> spend
+ga_spend  = collections.defaultdict(float)   # (buyer, pkg, geo, adping) -> spend
 ids = collections.defaultdict(set)
 unmatched = collections.defaultdict(float)
 excluded_spend, excluded_rows = 0.0, 0
 
-for d, adp, pkg, s in rows:
+for d, adp, pkg, geo, s in rows:
     if not (start <= d <= end):
         continue
     if pkg in EXCL or adp in dropped_ids:
         excluded_spend += s; excluded_rows += 1
         continue
-    if adp in amap:
-        buyers[amap[adp]][pkg] += s
-        ids[amap[adp]].add(adp)
-    else:
+    b = amap.get(adp)
+    if b is None:
         unmatched[(adp, pkg)] += s
+        continue
+    pkg_spend[(b, pkg)] += s
+    geo_spend[(b, pkg, geo)] += s
+    ga_spend[(b, pkg, geo, adp)] += s
+    ids[b].add(adp)
+
+by_buyer = collections.defaultdict(dict)
+for (b, pkg), v in pkg_spend.items():
+    by_buyer[b][pkg] = v
 
 out = []
-for b, pk in buyers.items():
+for b, pk in by_buyer.items():
+    pkgs = []
+    for pkg, v in sorted(pk.items(), key=lambda x: -x[1])[:5]:
+        # 花费最高的地区，再取该地区内花费最高的 Adpingid
+        top_geo = max((g for (bb, pp, g) in geo_spend if bb == b and pp == pkg),
+                      key=lambda g: geo_spend[(b, pkg, g)])
+        top_adp = max((a for (bb, pp, g, a) in ga_spend
+                       if bb == b and pp == pkg and g == top_geo),
+                      key=lambda a: ga_spend[(b, pkg, top_geo, a)])
+        pkgs.append({
+            "pkg": pkg,
+            "geo": top_geo,
+            "label": f"{pkg}_{top_geo}" if top_geo else pkg,
+            "adping": top_adp,
+            "spend": round(v, 4),
+        })
     out.append({
         "name": b, "@name": b,
         "total": round(sum(pk.values()), 4),
-        "active_ids": len(ids[b]),      # 本周期内有消耗的 Adpingid 数
-        "owned_ids": owned[b],          # 名下负责的 Adpingid 总数
-        "pkgs": [{"pkg": k, "spend": round(v, 4)}
-                 for k, v in sorted(pk.items(), key=lambda x: -x[1])[:5]],
+        "active_ids": len(ids[b]),
+        "owned_ids": owned[b],
+        "pkgs": pkgs,
     })
 out.sort(key=lambda x: -x['total'])
 
@@ -90,7 +115,8 @@ data = {
         "generated_at": datetime.date.today().isoformat(),
         "date_range": f"{start:%Y/%m/%d}-{end:%Y/%m/%d}",
         "note": "投放人以「投手」表 Media Buyer 列为准，@某某 已与某某合并计算；"
-                "未填写投放人的 Adpingid 不计入；exclude.json 所列包名已排除。",
+                "未填写投放人的 Adpingid 不计入；exclude.json 所列包名已排除。"
+                "Package 后缀为该 Package 花费最高的投放地区，Adpingid 为该地区内花费最高的 Adping。",
     },
     "grand_total": round(sum(b['total'] for b in out), 4),
     "week34_id_count": sum(len(v) for v in ids.values()),
@@ -104,4 +130,6 @@ print(f"窗口 {start} -> {end}")
 print(f"排除包名命中 {excluded_rows} 行，剔除花费 {excluded_spend:.2f}")
 print(f"合计 {data['grand_total']:.2f} / Adpingid {data['week34_id_count']}")
 for b in out:
-    print(f"  {b['name']:6s} {b['total']:10.2f}")
+    print(f"  {b['name']:6s} {b['total']:10.2f}  在投{b['active_ids']:3d}/负责{b['owned_ids']:3d}")
+    for p in b['pkgs']:
+        print(f"      {p['label']:52s} {p['adping']:>10s} {p['spend']:9.2f}")