ABA搜索词-新增字段DD50、DD100、DD200

Pyspark_job/dwd/dwd_st_asin_measure.py

@@ -175,7 +175,7 @@ class DwdStMeasure(Templates):
         self.df_asin_bs = self.spark.sql(sql).cache()
         self.df_asin_bs.show(10)
 
-        sql = f"select asin, asin_title, asin_price, parent_asin " \
+        sql = f"select asin, asin_title, asin_price, parent_asin, asin_bought_month " \
               f"from dim_asin_detail where site_name='{self.site_name}' and date_type='{self.date_type.replace('_old', '')}' and date_info='{self.date_info}';"
         print("sql:", sql)
         self.df_asin_detail = self.spark.sql(sql).cache()
@@ -413,17 +413,34 @@ class DwdStMeasure(Templates):
                 df_st_asin_agg, on=['asin'], how='left'
             )
         elif cal_type == "st":
+            # 计算搜索词DD占比
+            df_asin_bought_month = self.df_asin_detail.select('asin', 'asin_bought_month').join(
+                self.df_asin_amazon_orders, on=['asin'], how='left'
+            ).withColumn(
+                "asin_bought_month", F.coalesce(F.col("asin_bought_month"), F.col("asin_amazon_orders"))
+            ).drop("asin_amazon_orders")
+
             df_st_asin_agg = self.df_st_asin_duplicated.select("search_term", "asin").join(
                 self.df_asin_self, on='asin', how='left'
+            ).join(
+                df_asin_bought_month, on='asin', how='left'
             ).withColumn(
                 "is_self_asin",
                 F.when(F.col("is_self_asin").isNotNull(), F.col("is_self_asin")).otherwise(F.lit(0))
             ).groupby(['search_term']).agg(
                 F.sum('is_self_asin').alias("st_self_asin_counts"),
-                F.count('asin').alias("st_total_asin_counts")
+                F.count('asin').alias("st_total_asin_counts"),
+                F.sum(F.when(F.col("asin_bought_month") >= 50, 1).otherwise(0)).alias("st_dd50_counts"),
+                F.sum(F.when(F.col("asin_bought_month") >= 100, 1).otherwise(0)).alias("st_dd100_counts"),
+                F.sum(F.when(F.col("asin_bought_month") >= 200, 1).otherwise(0)).alias("st_dd200_counts")
+            ).withColumn(
+                'st_self_asin_proportion', F.round(F.col('st_self_asin_counts') / F.col('st_total_asin_counts'), 4)
+            ).withColumn(
+                'st_dd50_proportion', F.round(F.col('st_dd50_counts') / F.col('st_total_asin_counts'), 4)
+            ).withColumn(
+                'st_dd100_proportion', F.round(F.col('st_dd100_counts') / F.col('st_total_asin_counts'), 4)
             ).withColumn(
-                'st_self_asin_proportion',
-                F.round(F.col('st_self_asin_counts') / F.col('st_total_asin_counts'), 4)
+                'st_dd200_proportion', F.round(F.col('st_dd200_counts') / F.col('st_total_asin_counts'), 4)
             )
             df = df.join(
                 df_st_asin_agg, on=['search_term'], how='left'
@@ -725,4 +742,4 @@ if __name__ == '__main__':
     date_type = sys.argv[2]  # 参数2：类型：day/week/4_week/month/quarter
     date_info = sys.argv[3]  # 参数3：年-月-日/年-周/年-月/年-季, 比如: 2022-1
     handle_obj = DwdStMeasure(site_name=site_name, date_type=date_type, date_info=date_info)
-    handle_obj.run()
+    handle_obj.run()
\ No newline at end of file

Pyspark_job/dwt/dwt_aba_st_analytics.py

@@ -181,7 +181,10 @@ class DwtAbaStAnalytics(Templates):
             st_zr_counts,
             st_sp_counts,
             st_self_asin_counts,
-            st_self_asin_proportion
+            st_self_asin_proportion,
+            st_dd50_proportion,
+            st_dd100_proportion,
+            st_dd200_proportion
         from dwd_st_measure
         where site_name = '{self.site_name}' 
         and date_type = '{self.date_type}' 
@@ -903,7 +906,10 @@ class DwtAbaStAnalytics(Templates):
             "st_self_asin_proportion",
             "lang",
             "asin_movie_type_count",
-            "is_hidden_cate"
+            "is_hidden_cate",
+            "st_dd50_proportion",
+            "st_dd100_proportion",
+            "st_dd200_proportion"
         )
 
         # 空值处理