Canonical results for tpcds s1 (#11402)

Author: iddqdex

ydb/library/benchmarks/gen_queries/consts.yql

@@ -28,3 +28,5 @@ $scale_factor = 1;
 
 $round = ($x, $y) -> { return Math::Round($x, $y); };
 $upscale = ($x) -> { return $x; };
+
+$todecimal = ($x, $p, $s) -> { return cast($x as double); };

ydb/library/benchmarks/gen_queries/consts_decimal.yql

@@ -28,3 +28,4 @@ $scale_factor = 1;
 
 $round = ($x,$y) -> {return $x;};
 $upscale = ($x) -> { return cast($x as decimal(35,9)); };
+$todecimal = ($x, $p, $s) -> { return cast(cast($x as string?) as decimal($p,$s)); };

ydb/library/benchmarks/queries/tpcds/pg/q41.sql

@@ -14,7 +14,7 @@ select  distinct(i_product_name)
         (i_category = 'Women' and
         (i_color = 'brown' or i_color = 'honeydew') and
         (i_units = 'Bunch' or i_units = 'Ton') and
-        (i_size = 'petite' or i_size = 'large')
+        (i_size = 'N/A' or i_size = 'small')
         ) or
         (i_category = 'Men' and
         (i_color = 'floral' or i_color = 'deep') and
@@ -35,7 +35,7 @@ select  distinct(i_product_name)
         (i_category = 'Women' and
         (i_color = 'cyan' or i_color = 'papaya') and
         (i_units = 'Cup' or i_units = 'Dram') and
-        (i_size = 'petite' or i_size = 'large')
+        (i_size = 'N/A' or i_size = 'small')
         ) or
         (i_category = 'Men' and
         (i_color = 'orange' or i_color = 'frosted') and

ydb/library/benchmarks/queries/tpcds/pg/q66.sql

@@ -196,7 +196,7 @@ select
  	and cs_ship_mode_sk = sm_ship_mode_sk
         and d_year = 2001
  	and t_time between 30838 AND 30838+28800
- 	and sm_carrier in ('MSC','BARIAN')
+ 	and sm_carrier in ('DHL','BARIAN')
      group by
         w_warehouse_name
  	,w_warehouse_sq_ft

ydb/library/benchmarks/queries/tpcds/pg/q71.sql

@@ -35,7 +35,7 @@ select i_brand_id brand_id, i_brand brand,t_hour,t_minute,
    and time_sk = t_time_sk
    and (t_meal_time = 'breakfast' or t_meal_time = 'dinner')
  group by i_brand, i_brand_id,t_hour,t_minute
- order by ext_price desc nulls first, i_brand_id nulls first, t_hour,t_minute
+ order by ext_price desc nulls last, i_brand_id nulls first
  limit 1000
  ;
 

ydb/library/benchmarks/queries/tpcds/pg/q76.sql

@@ -3,19 +3,19 @@
 select  channel, col_name, d_year, d_qoy, i_category, COUNT(*) sales_cnt, SUM(ext_sales_price) sales_amt FROM (
         SELECT 'store' as channel, 'ss_store_sk' col_name, d_year, d_qoy, i_category, ss_ext_sales_price ext_sales_price
          FROM {{store_sales}}, {{item}}, {{date_dim}}
-         WHERE ss_addr_sk IS NULL
+         WHERE ss_store_sk IS NULL
            AND ss_sold_date_sk=d_date_sk
            AND ss_item_sk=i_item_sk
         UNION ALL
         SELECT 'web' as channel, 'ws_ship_customer_sk' col_name, d_year, d_qoy, i_category, ws_ext_sales_price ext_sales_price
          FROM {{web_sales}}, {{item}}, {{date_dim}}
-         WHERE ws_web_page_sk IS NULL
+         WHERE ws_ship_customer_sk IS NULL
            AND ws_sold_date_sk=d_date_sk
            AND ws_item_sk=i_item_sk
         UNION ALL
         SELECT 'catalog' as channel, 'cs_ship_addr_sk' col_name, d_year, d_qoy, i_category, cs_ext_sales_price ext_sales_price
          FROM {{catalog_sales}}, {{item}}, {{date_dim}}
-         WHERE cs_warehouse_sk IS NULL
+         WHERE cs_ship_addr_sk IS NULL
            AND cs_sold_date_sk=d_date_sk
            AND cs_item_sk=i_item_sk) foo
 GROUP BY channel, col_name, d_year, d_qoy, i_category

ydb/library/benchmarks/queries/tpcds/pg/q83.sql

@@ -50,11 +50,11 @@ with sr_items as
  group by i_item_id)
   select  sr_items.item_id
        ,sr_item_qty
-       ,sr_item_qty/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 sr_dev
+       ,cast(sr_item_qty as double)/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 sr_dev
        ,cr_item_qty
-       ,cr_item_qty/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 cr_dev
+       ,cast(cr_item_qty as double)/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 cr_dev
        ,wr_item_qty
-       ,wr_item_qty/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 wr_dev
+       ,cast(wr_item_qty as double)/(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 * 100 wr_dev
        ,(sr_item_qty+cr_item_qty+wr_item_qty)/3.0 average
  from sr_items
      ,cr_items

ydb/library/benchmarks/queries/tpcds/pg/q85.sql

@@ -9,7 +9,7 @@ select  substr(r_reason_desc,1,20) reason
  where ws_web_page_sk = wp_web_page_sk
    and ws_item_sk = wr_item_sk
    and ws_order_number = wr_order_number
-   and ws_sold_date_sk = d_date_sk and d_year = 2001
+   and ws_sold_date_sk = d_date_sk and d_year = 2000
    and cd1.cd_demo_sk = wr_refunded_cdemo_sk
    and cd2.cd_demo_sk = wr_returning_cdemo_sk
    and ca_address_sk = wr_refunded_addr_sk

ydb/library/benchmarks/queries/tpcds/yql/q15.sql

@@ -3,12 +3,8 @@
 -- NB: Subquerys
 
 -- start query 1 in stream 0 using template query15.tpl and seed 1819994127
-$todecimal = ($x) -> {
-  return cast(cast($x as string?) as decimal(7,2))
-};
-
 select  customer_address.ca_zip
-       ,sum($todecimal(cs_sales_price))
+       ,sum($todecimal(cs_sales_price, 7, 2))
  from {{catalog_sales}} as catalog_sales
      cross join {{customer}} as customer
      cross join {{customer_address}} as customer_address

ydb/library/benchmarks/queries/tpcds/yql/q18.sql

@@ -3,10 +3,10 @@
 -- TODO this commit should be reverted upon proper fix for https://github.com/ydb-platform/ydb/issues/7565
 -- NB: Subquerys
 -- start query 1 in stream 0 using template query18.tpl and seed 1978355063
-select  item.i_item_id,
-        customer_address.ca_country,
-        customer_address.ca_state,
-        customer_address.ca_county,
+select  item.i_item_id i_item_id,
+        customer_address.ca_country ca_country,
+        customer_address.ca_state ca_state,
+        customer_address.ca_county ca_county,
         avg( cast(cs_quantity as float)) agg1,
         avg( cast(cs_list_price as float)) agg2,
         avg( cast(cs_coupon_amt as float)) agg3,
@@ -34,10 +34,10 @@ select  item.i_item_id,
        ca_state in ('MS','IN','ND'
                    ,'OK','NM','VA','MS')
  group by rollup (item.i_item_id, customer_address.ca_country, customer_address.ca_state, customer_address.ca_county)
- order by customer_address.ca_country,
-        customer_address.ca_state,
-        customer_address.ca_county,
-	item.i_item_id, agg6
+ order by ca_country,
+        ca_state,
+        ca_county,
+	i_item_id, agg6
  limit 100;
 
 -- end query 1 in stream 0 using template query18.tpl