品类调研改为node_id分类

Pyspark_job/dwt/dwt_bs_top100_change_rate.py

@@ -52,7 +52,7 @@ class DwtBsTop100ChangeRate(object):
 
     # 跨月对齐主键：分类多归属（同 current_id 挂多个父级路径=多行），只用 current_id 会 1:N 串行。
     # current_id + parent_id_join（根→直接父级的完整路径）= 每行唯一（已实测 2026-05 分区无重复）。
-    JOIN_KEYS = ['asin_bs_cate_current_id', 'asin_bs_cate_parent_id_join']
+    JOIN_KEYS = ['asin_node_current_id', 'asin_node_parent_id_join']
 
     def __init__(self, site_name, date_type, date_info):
         self.site_name = site_name
@@ -101,10 +101,10 @@ class DwtBsTop100ChangeRate(object):
         return df
 
     def read_data(self):
-        # 本期额外带 level（落表用，便于后端/排查），对比期只要指标值
+        # 本期额外带 level + leaf_node（落表用，便于后端/前端按叶子筛），对比期只要指标值
         metric_cols = [m for m, _ in self.METRICS]
         base_sql = f"""
-            select {', '.join(self.JOIN_KEYS + ['level'] + metric_cols)}
+            select {', '.join(self.JOIN_KEYS + ['level', 'leaf_node'] + metric_cols)}
             from {self.source_tb}
             where site_name='{self.site_name}' and date_type='{self.date_type}' and date_info='{self.date_info}'
         """
@@ -181,7 +181,7 @@ class DwtBsTop100ChangeRate(object):
         for m, _ in self.METRICS:
             rate_cols.append(f"{m}_ym_rate")
             rate_cols.append(f"{m}_lm_rate")
-        out_cols = self.JOIN_KEYS + ['level'] + rate_cols
+        out_cols = self.JOIN_KEYS + ['level', 'leaf_node'] + rate_cols
 
         self.df_save = self.df_save.select(*out_cols) \
             .withColumn("site_name", F.lit(self.site_name)) \

Pyspark_job/sqoop_export/dwt_bs_top100.py

@@ -78,8 +78,8 @@ if __name__ == '__main__':
     # 导出列 = 86 业务列 + 3 分区列（列名与 Hive dwt_bs_top100 一致, sqoop 按名映射 PG 同名列）
     export_cols = [
         # 维度 / 键
-        "asin_bs_cate_current_id", "asin_bs_cate_parent_id", "asin_bs_cate_parent_id_join",
-        "level", "cur_category_name",
+        "asin_node_current_id", "asin_node_parent_id", "asin_node_parent_id_join",
+        "level", "cur_category_name", "leaf_node",
         # 销量类
         "asin_amazon_orders_sum", "asin_bsr_orders_sum", "asin_bsr_orders_sum_new", "asin_bsr_orders_sum_brand",
         "asin_bsr_orders_mean", "asin_bsr_orders_mean_new", "asin_bsr_orders_mean_brand", "asin_bsr_orders_sum_parent",

Pyspark_job/sqoop_export/dwt_bs_top100_change_rate.py

@@ -78,7 +78,7 @@ if __name__ == '__main__':
 
     # 导出列 = join键2 + level + 28 变化率列 + 3 分区列（列名与 Hive dwt_bs_top100_change_rate 一致）
     export_cols = [
-        "asin_bs_cate_current_id", "asin_bs_cate_parent_id_join", "level",
+        "asin_node_current_id", "asin_node_parent_id_join", "level", "leaf_node",
         "asin_amazon_orders_sum_ym_rate", "asin_amazon_orders_sum_lm_rate",
         "asin_bsr_orders_sum_ym_rate", "asin_bsr_orders_sum_lm_rate",
         "asin_bsr_orders_mean_ym_rate", "asin_bsr_orders_mean_lm_rate",