Third 25 queries of TPC-DS

ydb/library/benchmarks/queries/tpcds/yql/q51.sql

@@ -0,0 +1,51 @@
+{% include 'header.sql.jinja' %}
+
+-- start query 1 in stream 0 using template query51.tpl and seed 1819994127
+$web_v1 = (
+select
+  web_sales.ws_item_sk item_sk, date_dim.d_date as d_date,
+  sum(sum(ws_sales_price))
+      over (partition by web_sales.ws_item_sk order by date_dim.d_date rows between unbounded preceding and current row) cume_sales
+from {{web_sales}} as web_sales
+cross join
+     {{date_dim}} as date_dim
+where ws_sold_date_sk=d_date_sk
+  and d_month_seq between 1214 and 1214+11
+  and ws_item_sk is not NULL
+group by web_sales.ws_item_sk, date_dim.d_date);
+
+$store_v1 = (
+select
+  store_sales.ss_item_sk item_sk, date_dim.d_date as d_date,
+  sum(sum(ss_sales_price))
+      over (partition by store_sales.ss_item_sk order by date_dim.d_date rows between unbounded preceding and current row) cume_sales
+from {{store_sales}} as store_sales
+cross join
+    {{date_dim}} as date_dim
+where ss_sold_date_sk=d_date_sk
+  and d_month_seq between 1214 and 1214+11
+  and ss_item_sk is not NULL
+group by store_sales.ss_item_sk, date_dim.d_date);
+
+ select  *
+from (select item_sk
+     ,d_date
+     ,web_sales
+     ,store_sales
+     ,max(web_sales)
+         over (partition by item_sk order by d_date rows between unbounded preceding and current row) web_cumulative
+     ,max(store_sales)
+         over (partition by item_sk order by d_date rows between unbounded preceding and current row) store_cumulative
+     from (select case when web.item_sk is not null then web.item_sk else store.item_sk end item_sk
+                 ,case when web.d_date is not null then web.d_date else store.d_date end d_date
+                 ,web.cume_sales web_sales
+                 ,store.cume_sales store_sales
+           from $web_v1 as web full outer join $store_v1 as store on (web.item_sk = store.item_sk
+                                                          and web.d_date = store.d_date)
+          )x )y
+where web_cumulative > store_cumulative
+order by item_sk
+        ,d_date
+limit 100;
+
+-- end query 1 in stream 0 using template query51.tpl

ydb/library/benchmarks/queries/tpcds/yql/q52.sql

@@ -0,0 +1,26 @@
+{% include 'header.sql.jinja' %}
+
+-- start query 1 in stream 0 using template query52.tpl and seed 1819994127
+select  dt.d_year
+ 	,item.i_brand_id brand_id
+ 	,item.i_brand brand
+ 	,sum(ss_ext_sales_price) ext_price
+ from {{date_dim}} dt
+ cross join
+      {{store_sales}} as store_sales
+ cross join
+      {{item}} as item
+ where dt.d_date_sk = store_sales.ss_sold_date_sk
+    and store_sales.ss_item_sk = item.i_item_sk
+    and item.i_manager_id = 1
+    and dt.d_moy=12
+    and dt.d_year=2000
+ group by dt.d_year
+ 	,item.i_brand
+ 	,item.i_brand_id
+ order by dt.d_year
+ 	,ext_price desc
+ 	,brand_id
+limit 100 ;
+
+-- end query 1 in stream 0 using template query52.tpl

ydb/library/benchmarks/queries/tpcds/yql/q53.sql

@@ -0,0 +1,33 @@
+{% include 'header.sql.jinja' %}
+
+-- start query 1 in stream 0 using template query53.tpl and seed 1819994127
+select  * from
+(select item.i_manufact_id as i_manufact_id,
+sum(ss_sales_price) sum_sales,
+avg(sum(ss_sales_price)) over (partition by item.i_manufact_id) avg_quarterly_sales
+from {{item}} as item
+cross join {{store_sales}} as store_sales
+cross join {{date_dim}} as date_dim
+cross join {{store}} as store
+where ss_item_sk = i_item_sk and
+ss_sold_date_sk = d_date_sk and
+ss_store_sk = s_store_sk and
+d_month_seq in (1212,1212+1,1212+2,1212+3,1212+4,1212+5,1212+6,1212+7,1212+8,1212+9,1212+10,1212+11) and
+((i_category in ('Books','Children','Electronics') and
+i_class in ('personal','portable','reference','self-help') and
+i_brand in ('scholaramalgamalg #14','scholaramalgamalg #7',
+		'exportiunivamalg #9','scholaramalgamalg #9'))
+or(i_category in ('Women','Music','Men') and
+i_class in ('accessories','classical','fragrances','pants') and
+i_brand in ('amalgimporto #1','edu packscholar #1','exportiimporto #1',
+		'importoamalg #1')))
+group by item.i_manufact_id, date_dim.d_qoy ) tmp1
+where case when avg_quarterly_sales > 0
+	then abs (sum_sales - avg_quarterly_sales)/ avg_quarterly_sales
+	else null end > 0.1
+order by avg_quarterly_sales,
+	 sum_sales,
+	 i_manufact_id
+limit 100;
+
+-- end query 1 in stream 0 using template query53.tpl

ydb/library/benchmarks/queries/tpcds/yql/q54.sql

@@ -0,0 +1,71 @@
+{% include 'header.sql.jinja' %}
+
+-- start query 1 in stream 0 using template query54.tpl and seed 1930872976
+$d_month_seq_begin = (select distinct d_month_seq+1
+                                 from   {{date_dim}} as date_dim where d_year = 2000 and d_moy = 2);
+$d_month_seq_end = (select distinct d_month_seq+3
+                                 from   {{date_dim}} as date_dim where d_year = 2000 and d_moy = 2);
+
+$my_customers = (
+ select distinct c_customer_sk
+        , c_current_addr_sk
+ from
+        ( select cs_sold_date_sk sold_date_sk,
+                 cs_bill_customer_sk customer_sk,
+                 cs_item_sk item_sk
+          from   {{catalog_sales}} as catalog_sales
+          union all
+          select ws_sold_date_sk sold_date_sk,
+                 ws_bill_customer_sk customer_sk,
+                 ws_item_sk item_sk
+          from   {{web_sales}} as web_sales
+         ) cs_or_ws_sales
+cross join
+         {{item}} as item
+cross join
+         {{date_dim}} as date_dim
+cross join
+         {{customer}} as customer
+ where   sold_date_sk = d_date_sk
+         and item_sk = i_item_sk
+         and i_category = 'Books'
+         and i_class = 'business'
+         and c_customer_sk = cs_or_ws_sales.customer_sk
+         and d_moy = 2
+         and d_year = 2000
+ );
+
+$my_revenue = (
+ select my_customers.c_customer_sk,
+        sum(ss_ext_sales_price) as revenue
+ from   $my_customers as my_customers
+ cross join
+        {{store_sales}} as store_sales
+cross join
+        {{customer_address}} as customer_address
+cross join
+        {{store}} as store
+cross join
+        {{date_dim}} as date_dim
+ where  my_customers.c_current_addr_sk = customer_address.ca_address_sk
+        and ca_county = s_county
+        and ca_state = s_state
+        and ss_sold_date_sk = d_date_sk
+        and c_customer_sk = ss_customer_sk
+        and d_month_seq between $d_month_seq_begin
+                           and  $d_month_seq_end
+ group by my_customers.c_customer_sk
+ );
+
+ $segments =
+ (select cast((revenue/50) as int) as segment
+  from   $my_revenue
+ );
+
+  select  segment, count(*) as num_customers, segment*50 as segment_base
+ from $segments
+ group by segment
+ order by segment, num_customers
+ limit 100;
+
+-- end query 1 in stream 0 using template query54.tpl

ydb/library/benchmarks/queries/tpcds/yql/q55.sql

@@ -0,0 +1,18 @@
+{% include 'header.sql.jinja' %}
+
+-- start query 1 in stream 0 using template query55.tpl and seed 2031708268
+select  item.i_brand_id brand_id, item.i_brand brand,
+ 	sum(ss_ext_sales_price) ext_price
+ from {{date_dim}} as date_dim
+ cross join {{store_sales}} as store_sales
+ cross join {{item}} as item
+ where d_date_sk = ss_sold_date_sk
+ 	and ss_item_sk = i_item_sk
+ 	and i_manager_id=13
+ 	and d_moy=11
+ 	and d_year=1999
+ group by item.i_brand, item.i_brand_id
+ order by ext_price desc, brand_id
+limit 100 ;
+
+-- end query 1 in stream 0 using template query55.tpl

ydb/library/benchmarks/queries/tpcds/yql/q56.sql

@@ -0,0 +1,4 @@
+{% include 'header.sql.jinja' %}
+
+-- TODO: where is it?
+select 1;

ydb/library/benchmarks/queries/tpcds/yql/q57.sql

@@ -0,0 +1,54 @@
+{% include 'header.sql.jinja' %}
+
+-- NB: Subquerys
+$v1 = (
+ select item.i_category i_category, item.i_brand i_brand,
+        call_center.cc_name cc_name,
+        date_dim.d_year d_year, date_dim.d_moy d_moy,
+        sum(cs_sales_price) sum_sales,
+        avg(sum(cs_sales_price)) over
+          (partition by item.i_category, item.i_brand,
+                     call_center.cc_name, date_dim.d_year)
+          avg_monthly_sales,
+        rank() over
+          (partition by item.i_category, item.i_brand,
+                     call_center.cc_name
+           order by date_dim.d_year, date_dim.d_moy) rn
+ from {{item}} as item
+ cross join {{catalog_sales}} as catalog_sales
+ cross join  {{date_dim}} as date_dim
+ cross join {{call_center}} as call_center
+ where cs_item_sk = i_item_sk and
+       cs_sold_date_sk = d_date_sk and
+       cc_call_center_sk= cs_call_center_sk and
+       (
+         d_year = 1999 or
+         ( d_year = 1999-1 and d_moy =12) or
+         ( d_year = 1999+1 and d_moy =1)
+       )
+ group by item.i_category, item.i_brand,
+          call_center.cc_name , date_dim.d_year, date_dim.d_moy);
+$v2 = (
+ select v1.i_category i_category, v1.i_brand i_brand
+        ,v1.d_year d_year, v1.d_moy d_moy
+        ,v1.avg_monthly_sales avg_monthly_sales
+        ,v1.sum_sales sum_sales, v1_lag.sum_sales psum, v1_lead.sum_sales nsum
+ from $v1 v1 cross join $v1 v1_lag cross join $v1 v1_lead
+ where v1.i_category = v1_lag.i_category and
+       v1.i_category = v1_lead.i_category and
+       v1.i_brand = v1_lag.i_brand and
+       v1.i_brand = v1_lead.i_brand and
+       v1. cc_name = v1_lag. cc_name and
+       v1. cc_name = v1_lead. cc_name and
+       v1.rn = v1_lag.rn + 1 and
+       v1.rn = v1_lead.rn - 1);
+-- start query 1 in stream 0 using template query57.tpl and seed 2031708268
+  select  *
+ from $v2
+ where  d_year = 1999 and
+        avg_monthly_sales > 0 and
+        case when avg_monthly_sales > 0 then abs(sum_sales - avg_monthly_sales) / avg_monthly_sales else null end > 0.1
+ order by sum_sales - avg_monthly_sales, avg_monthly_sales
+ limit 100;
+
+-- end query 1 in stream 0 using template query57.tpl

ydb/library/benchmarks/queries/tpcds/yql/q58.sql

@@ -0,0 +1,65 @@
+{% include 'header.sql.jinja' %}
+
+-- NB: Subquerys
+$week_seq = (select d_week_seq
+                                      from {{date_dim}} as date_dim
+                                      where d_date = '1998-02-21');
+$ss_items =
+ (select item.i_item_id item_id
+        ,sum(ss_ext_sales_price) ss_item_rev
+ from {{store_sales}} as store_sales
+     cross join {{item}} as item
+     cross join {{date_dim}} as date_dim
+ where ss_item_sk = i_item_sk
+   and d_date in (select d_date
+                  from {{date_dim}} as date_dim
+                  where d_week_seq = $week_seq)
+   and ss_sold_date_sk   = d_date_sk
+ group by item.i_item_id);
+$cs_items =
+ (select item.i_item_id item_id
+        ,sum(cs_ext_sales_price) cs_item_rev
+  from {{catalog_sales}} as catalog_sales
+      cross join {{item}} as item
+      cross join {{date_dim}} as date_dim
+ where cs_item_sk = i_item_sk
+  and  d_date in (select d_date
+                  from {{date_dim}} as date_dim
+                  where d_week_seq = $week_seq)
+  and  cs_sold_date_sk = d_date_sk
+ group by item.i_item_id);
+$ws_items =
+ (select item.i_item_id item_id
+        ,sum(ws_ext_sales_price) ws_item_rev
+  from {{web_sales}} as web_sales
+      cross join {{item}} as item
+      cross join {{date_dim}} as date_dim
+ where ws_item_sk = i_item_sk
+  and  d_date in (select d_date
+                  from {{date_dim}} as date_dim
+                  where d_week_seq =$week_seq)
+  and ws_sold_date_sk   = d_date_sk
+ group by item.i_item_id);
+-- start query 1 in stream 0 using template query58.tpl and seed 1819994127
+  select  ss_items.item_id
+       ,ss_item_rev
+       ,ss_item_rev/((ss_item_rev+cs_item_rev+ws_item_rev)/3) * 100 ss_dev
+       ,cs_item_rev
+       ,cs_item_rev/((ss_item_rev+cs_item_rev+ws_item_rev)/3) * 100 cs_dev
+       ,ws_item_rev
+       ,ws_item_rev/((ss_item_rev+cs_item_rev+ws_item_rev)/3) * 100 ws_dev
+       ,(ss_item_rev+cs_item_rev+ws_item_rev)/3 average
+ from $ss_items ss_items cross join $cs_items cs_items cross join $ws_items ws_items
+ where ss_items.item_id=cs_items.item_id
+   and ss_items.item_id=ws_items.item_id
+   and ss_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev
+   and ss_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev
+   and cs_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev
+   and cs_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev
+   and ws_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev
+   and ws_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev
+ order by item_id
+         ,ss_item_rev
+ limit 100;
+
+-- end query 1 in stream 0 using template query58.tpl

ydb/library/benchmarks/queries/tpcds/yql/q59.sql

@@ -0,0 +1,48 @@
+{% include 'header.sql.jinja' %}
+
+-- NB: Subquerys
+$wss =
+ (select date_dim.d_week_seq d_week_seq,
+        store_sales.ss_store_sk ss_store_sk,
+        sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales,
+        sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales,
+        sum(case when (d_day_name='Tuesday') then ss_sales_price else  null end) tue_sales,
+        sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales,
+        sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales,
+        sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales,
+        sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales
+ from {{store_sales}} as store_sales
+ cross join {{date_dim}} as date_dim
+ where d_date_sk = ss_sold_date_sk
+ group by date_dim.d_week_seq,store_sales.ss_store_sk
+ );
+-- start query 1 in stream 0 using template query59.tpl and seed 1819994127
+  select  s_store_name1,s_store_id1,d_week_seq1
+       ,sun_sales1/sun_sales2,mon_sales1/mon_sales2
+       ,tue_sales1/tue_sales2,wed_sales1/wed_sales2,thu_sales1/thu_sales2
+       ,fri_sales1/fri_sales2,sat_sales1/sat_sales2
+ from
+ (select s_store_name s_store_name1,wss.d_week_seq d_week_seq1
+        ,s_store_id s_store_id1,sun_sales sun_sales1
+        ,mon_sales mon_sales1,tue_sales tue_sales1
+        ,wed_sales wed_sales1,thu_sales thu_sales1
+        ,fri_sales fri_sales1,sat_sales sat_sales1
+  from $wss wss cross join {{store}} as store cross join {{date_dim}} d
+  where d.d_week_seq = wss.d_week_seq and
+        ss_store_sk = s_store_sk and
+        d_month_seq between 1205 and 1205 + 11) y cross join
+ (select s_store_name s_store_name2,wss.d_week_seq d_week_seq2
+        ,s_store_id s_store_id2,sun_sales sun_sales2
+        ,mon_sales mon_sales2,tue_sales tue_sales2
+        ,wed_sales wed_sales2,thu_sales thu_sales2
+        ,fri_sales fri_sales2,sat_sales sat_sales2
+  from $wss wss cross join {{store}} as store cross join {{date_dim}} d
+  where d.d_week_seq = wss.d_week_seq and
+        ss_store_sk = s_store_sk and
+        d_month_seq between 1205+ 12 and 1205 + 23) x
+ where s_store_id1=s_store_id2
+   and d_week_seq1=d_week_seq2-52
+ order by s_store_name1,s_store_id1,d_week_seq1
+limit 100;
+
+-- end query 1 in stream 0 using template query59.tpl