修复品牌培育分数排序问题

api/recommend.py

@@ -25,6 +25,7 @@ async def recommend(request: RecommendRequest, backgroundTasks: BackgroundTasks)
     if request.product_code in products_in_oreder:
         recommend_list = recommend_model.get_recommend_list_by_gbdtlr(request.product_code, recall_count=request.recall_cust_count)
     else:
+        print("走这了")
         recommend_list = recommend_model.get_recommend_list_by_item2vec(request.product_code, recall_count=request.recall_cust_count)
     recommend_data = recommend_model.get_recommend_and_delivery(recommend_list, delivery_count=request.delivery_count)
     request_data = []

api_test.py

@@ -3,10 +3,10 @@ import json
 
 url = "http://127.0.0.1:7960/brandcultivation/api/v1/recommend"
 payload = {
-    "city_uuid": "00000000000000000000000011445301",
-    "product_code": "440298",
-    "recall_cust_count": 1000,
-    "delivery_count": 2000,
+    "city_uuid": "00000000000000000000000011440801",
+    "product_code": "430121",
+    "recall_cust_count": 30,
+    "delivery_count": 500,
     "cultivacation_id": "10000001",
     "limit_cycle_name": "202502W2(02.10-02.16)"
 }

models/item2vec/inference.py

@@ -50,7 +50,7 @@ class Item2VecModel:
         recommend_cust = (
             order_data.groupby(["cust_code"], as_index=False)["sale_qty"].sum()
             .query("sale_qty > 0")
-            .sort_values(["sale_qty"], ascending=[False])
+            .sort_values(["sale_qty", "cust_code"], ascending=[False, True])
         )
         
         # 对销量进行归一化