年度流量选品-增加变体销量相关指标

Pyspark_job/doris_handle/dwt_flow_asin_month.py

@@ -732,7 +732,13 @@ EXTRA_COLUMNS = (
     "bought_month_9, bought_month_10, bought_month_11, bought_month_12, "
     "bought_month_q1, bought_month_q2, bought_month_q3, bought_month_q4, "
     "total_appear_month, bought_month_peak, peak_month_arr, "
-    "is_periodic_flag, is_seasonal_flag, bsr_seen_count_total, nsr_seen_count_total"
+    "is_periodic_flag, is_seasonal_flag, bsr_seen_count_total, nsr_seen_count_total, "
+    "variation_bought_month_total, bought_month_total_yoy, variation_bought_month_total_yoy, "
+    "variation_bought_month_1, variation_bought_month_2, variation_bought_month_3, variation_bought_month_4, "
+    "variation_bought_month_5, variation_bought_month_6, variation_bought_month_7, variation_bought_month_8, "
+    "variation_bought_month_9, variation_bought_month_10, variation_bought_month_11, variation_bought_month_12, "
+    "variation_bought_month_q1, variation_bought_month_q2, variation_bought_month_q3, variation_bought_month_q4, "
+    "variation_bought_month_peak, variation_peak_month_arr"
 )
 
 
@@ -765,7 +771,28 @@ CREATE TABLE IF NOT EXISTS `dwt`.`{table_name}`
     `is_periodic_flag`      INT,
     `is_seasonal_flag`      INT,
     `bsr_seen_count_total`  INT,
-    `nsr_seen_count_total`  INT
+    `nsr_seen_count_total`  INT,
+    `variation_bought_month_total`      INT,
+    `bought_month_total_yoy`            DECIMAL(20,4),
+    `variation_bought_month_total_yoy`  DECIMAL(20,4),
+    `variation_bought_month_1`          INT,
+    `variation_bought_month_2`          INT,
+    `variation_bought_month_3`          INT,
+    `variation_bought_month_4`          INT,
+    `variation_bought_month_5`          INT,
+    `variation_bought_month_6`          INT,
+    `variation_bought_month_7`          INT,
+    `variation_bought_month_8`          INT,
+    `variation_bought_month_9`          INT,
+    `variation_bought_month_10`         INT,
+    `variation_bought_month_11`         INT,
+    `variation_bought_month_12`         INT,
+    `variation_bought_month_q1`         INT,
+    `variation_bought_month_q2`         INT,
+    `variation_bought_month_q3`         INT,
+    `variation_bought_month_q4`         INT,
+    `variation_bought_month_peak`       INT,
+    `variation_peak_month_arr`          ARRAY<INT>
 ) ENGINE=OLAP
 UNIQUE KEY(`asin`)
 COMMENT '流量选品年度聚合指标'
@@ -793,13 +820,19 @@ def sync_extra_table(spark, site_name, date_info):
             total_appear_month,
             bought_month_peak,
             peak_month_arr,
-            is_periodic_flag, is_seasonal_flag, bsr_seen_count_total, nsr_seen_count_total
+            is_periodic_flag, is_seasonal_flag, bsr_seen_count_total, nsr_seen_count_total,
+            variation_bought_month_total, bought_month_total_yoy, variation_bought_month_total_yoy,
+            variation_bought_month_1, variation_bought_month_2, variation_bought_month_3, variation_bought_month_4,
+            variation_bought_month_5, variation_bought_month_6, variation_bought_month_7, variation_bought_month_8,
+            variation_bought_month_9, variation_bought_month_10, variation_bought_month_11, variation_bought_month_12,
+            variation_bought_month_q1, variation_bought_month_q2, variation_bought_month_q3, variation_bought_month_q4,
+            variation_bought_month_peak, variation_peak_month_arr
         FROM dwt_flow_asin_year
         WHERE site_name = '{site_name}' AND date_info = '{date_info}'
     """
     df_raw = spark.sql(sqlQuery=sql)
 
-    # total_appear_month / peak_month_arr 在 Hive 那边存的是逗号拼接的 STRING
+    # total_appear_month / peak_month_arr / variation_peak_month_arr 在 Hive 那边存的是逗号拼接的 STRING
     df_extra = df_raw.withColumn(
         'total_appear_month', F.split(F.col('total_appear_month'), ',')
     ).withColumn(
@@ -812,6 +845,12 @@ def sync_extra_table(spark, site_name, date_info):
         'peak_month_arr', F.expr("transform(peak_month_arr, x -> cast(x as int))")
     ).withColumn(
         'peak_month_arr', F.to_json(F.col('peak_month_arr'))
+    ).withColumn(
+        'variation_peak_month_arr', F.split(F.col('variation_peak_month_arr'), ',')
+    ).withColumn(
+        'variation_peak_month_arr', F.expr("transform(variation_peak_month_arr, x -> cast(x as int))")
+    ).withColumn(
+        'variation_peak_month_arr', F.to_json(F.col('variation_peak_month_arr'))
     ).repartition(20, 'asin').cache()
 
     row_count = df_extra.count()
@@ -1159,6 +1198,27 @@ CREATE TABLE IF NOT EXISTS `selection`.`{table_name}`
     `peak_month_arr`              ARRAY<INT>       NULL,
     `is_periodic_flag`            INT              NULL,
     `is_seasonal_flag`            INT              NULL,
+    `variation_bought_month_total`      INT              NULL,
+    `bought_month_total_yoy`            DECIMAL(20,4)    NULL,
+    `variation_bought_month_total_yoy`  DECIMAL(20,4)    NULL,
+    `variation_bought_month_1`          INT              NULL,
+    `variation_bought_month_2`          INT              NULL,
+    `variation_bought_month_3`          INT              NULL,
+    `variation_bought_month_4`          INT              NULL,
+    `variation_bought_month_5`          INT              NULL,
+    `variation_bought_month_6`          INT              NULL,
+    `variation_bought_month_7`          INT              NULL,
+    `variation_bought_month_8`          INT              NULL,
+    `variation_bought_month_9`          INT              NULL,
+    `variation_bought_month_10`         INT              NULL,
+    `variation_bought_month_11`         INT              NULL,
+    `variation_bought_month_12`         INT              NULL,
+    `variation_bought_month_q1`         INT              NULL,
+    `variation_bought_month_q2`         INT              NULL,
+    `variation_bought_month_q3`         INT              NULL,
+    `variation_bought_month_q4`         INT              NULL,
+    `variation_bought_month_peak`       INT              NULL,
+    `variation_peak_month_arr`          ARRAY<INT>       NULL,
     INDEX idx_title      (`title`)      USING INVERTED PROPERTIES("parser" = "english") COMMENT '标题倒排索引',
     INDEX idx_title_stem (`title_stem`) USING INVERTED PROPERTIES("parser" = "english") COMMENT '标题词干倒排索引',
     INDEX idx_title_stem_15 (`title_stem_15`) USING INVERTED PROPERTIES("parser" = "english") COMMENT '标题词干前15个词倒排索引',
@@ -1317,7 +1377,16 @@ SELECT
     agg.bought_month_peak,
     agg.peak_month_arr,
     COALESCE(uma.is_periodic_flag, agg.is_periodic_flag, 0) AS is_periodic_flag,
-    COALESCE(uma.is_seasonal_flag, agg.is_seasonal_flag, 0) AS is_seasonal_flag
+    COALESCE(uma.is_seasonal_flag, agg.is_seasonal_flag, 0) AS is_seasonal_flag,
+    COALESCE(agg.variation_bought_month_total, 0) AS variation_bought_month_total,
+    agg.bought_month_total_yoy,
+    agg.variation_bought_month_total_yoy,
+    agg.variation_bought_month_1, agg.variation_bought_month_2,  agg.variation_bought_month_3,  agg.variation_bought_month_4,
+    agg.variation_bought_month_5, agg.variation_bought_month_6,  agg.variation_bought_month_7,  agg.variation_bought_month_8,
+    agg.variation_bought_month_9, agg.variation_bought_month_10, agg.variation_bought_month_11, agg.variation_bought_month_12,
+    agg.variation_bought_month_q1, agg.variation_bought_month_q2, agg.variation_bought_month_q3, agg.variation_bought_month_q4,
+    agg.variation_bought_month_peak,
+    agg.variation_peak_month_arr
 FROM `dwt`.`{site_name}_flow_asin_365day` f
 LEFT JOIN `dwt`.`{site_name}_flow_asin_365day_extra` agg ON f.asin = agg.asin
 -- ===== 利润率 =====