Skip to content

Second 25 queries of TPC-DS #660

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
resetius merged 1 commit into from
Dec 21, 2023
Merged

Second 25 queries of TPC-DS #660

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 28 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q26.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
-- start query 1 in stream 0 using template query26.tpl and seed 1930872976
select item.i_item_id,
avg(cs_quantity) agg1,
avg(cs_list_price) agg2,
avg(cs_coupon_amt) agg3,
avg(cs_sales_price) agg4
from {{catalog_sales}} as catalog_sales
cross join {{customer_demographics}} as customer_demographics
cross join {{date_dim}} as date_dim
cross join {{item}} as item
cross join {{promotion}} as promotion
where cs_sold_date_sk = d_date_sk and
cs_item_sk = i_item_sk and
cs_bill_cdemo_sk = cd_demo_sk and
cs_promo_sk = p_promo_sk and
cd_gender = 'F' and
cd_marital_status = 'S' and
cd_education_status = 'College' and
(p_channel_email = 'N' or p_channel_event = 'N') and
d_year = 1998
group by item.i_item_id
order by item.i_item_id
limit 100;

-- end query 1 in stream 0 using template query26.tpl
30 changes: 30 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q27.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
-- start query 1 in stream 0 using template query27.tpl and seed 2017787633
select item.i_item_id,
store.s_state, grouping(store.s_state) g_state,
avg(ss_quantity) agg1,
avg(ss_list_price) agg2,
avg(ss_coupon_amt) agg3,
avg(ss_sales_price) agg4
from {{store_sales}} as store_sales
cross join {{customer_demographics}} as customer_demographics
cross join {{date_dim}} as date_dim
cross join {{store}} as store
cross join {{item}} as item
where ss_sold_date_sk = d_date_sk and
ss_item_sk = i_item_sk and
ss_store_sk = s_store_sk and
ss_cdemo_sk = cd_demo_sk and
cd_gender = 'F' and
cd_marital_status = 'U' and
cd_education_status = '2 yr Degree' and
d_year = 2000 and
s_state in ('AL','IN', 'SC', 'NY', 'OH', 'FL')
group by rollup (item.i_item_id, store.s_state)
order by item.i_item_id
,store.s_state
limit 100;

-- end query 1 in stream 0 using template query27.tpl
56 changes: 56 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q28.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
-- start query 1 in stream 0 using template query28.tpl and seed 444293455
select *
from (select avg(ss_list_price) B1_LP
,count(ss_list_price) B1_CNT
,count(distinct ss_list_price) B1_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 0 and 5
and (ss_list_price between 73 and 73+10
or ss_coupon_amt between 7826 and 7826+1000
or ss_wholesale_cost between 70 and 70+20)) B1 cross join
(select avg(ss_list_price) B2_LP
,count(ss_list_price) B2_CNT
,count(distinct ss_list_price) B2_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 6 and 10
and (ss_list_price between 152 and 152+10
or ss_coupon_amt between 2196 and 2196+1000
or ss_wholesale_cost between 56 and 56+20)) B2 cross join
(select avg(ss_list_price) B3_LP
,count(ss_list_price) B3_CNT
,count(distinct ss_list_price) B3_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 11 and 15
and (ss_list_price between 53 and 53+10
or ss_coupon_amt between 3430 and 3430+1000
or ss_wholesale_cost between 13 and 13+20)) B3 cross join
(select avg(ss_list_price) B4_LP
,count(ss_list_price) B4_CNT
,count(distinct ss_list_price) B4_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 16 and 20
and (ss_list_price between 182 and 182+10
or ss_coupon_amt between 3262 and 3262+1000
or ss_wholesale_cost between 20 and 20+20)) B4 cross join
(select avg(ss_list_price) B5_LP
,count(ss_list_price) B5_CNT
,count(distinct ss_list_price) B5_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 21 and 25
and (ss_list_price between 85 and 85+10
or ss_coupon_amt between 3310 and 3310+1000
or ss_wholesale_cost between 37 and 37+20)) B5 cross join
(select avg(ss_list_price) B6_LP
,count(ss_list_price) B6_CNT
,count(distinct ss_list_price) B6_CNTD
from {{store_sales}} as store_sales
where ss_quantity between 26 and 30
and (ss_list_price between 180 and 180+10
or ss_coupon_amt between 12592 and 12592+1000
or ss_wholesale_cost between 22 and 22+20)) B6
limit 100;

-- end query 1 in stream 0 using template query28.tpl
50 changes: 50 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q29.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
-- start query 1 in stream 0 using template query29.tpl and seed 2031708268
select
item.i_item_id
,item.i_item_desc
,store.s_store_id
,store.s_store_name
,stddev_samp(ss_quantity) as store_sales_quantity
,stddev_samp(sr_return_quantity) as store_returns_quantity
,stddev_samp(cs_quantity) as catalog_sales_quantity
from
{{store_sales}} as store_sales
cross join {{store_returns}} as store_returns
cross join {{catalog_sales}} as catalog_sales
cross join {{date_dim}} d1
cross join {{date_dim}} d2
cross join {{date_dim}} d3
cross join {{store}} as store
cross join {{item}} as item
where
d1.d_moy = 4
and d1.d_year = 1998
and d1.d_date_sk = ss_sold_date_sk
and i_item_sk = ss_item_sk
and s_store_sk = ss_store_sk
and ss_customer_sk = sr_customer_sk
and ss_item_sk = sr_item_sk
and ss_ticket_number = sr_ticket_number
and sr_returned_date_sk = d2.d_date_sk
and d2.d_moy between 4 and 4 + 3
and d2.d_year = 1998
and sr_customer_sk = cs_bill_customer_sk
and sr_item_sk = cs_item_sk
and cs_sold_date_sk = d3.d_date_sk
and d3.d_year in (1998,1998+1,1998+2)
group by
item.i_item_id
,item.i_item_desc
,store.s_store_id
,store.s_store_name
order by
item.i_item_id
,item.i_item_desc
,store.s_store_id
,store.s_store_name
limit 100;

-- end query 1 in stream 0 using template query29.tpl
39 changes: 39 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q30.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
$customer_total_return =
(select web_returns.wr_returning_customer_sk as ctr_customer_sk
,customer_address.ca_state as ctr_state,
sum(wr_return_amt) as ctr_total_return
from {{web_returns}} as web_returns
cross join {{date_dim}} as date_dim
cross join {{customer_address}} as customer_address
where wr_returned_date_sk = d_date_sk
and d_year =2000
and wr_returning_addr_sk = ca_address_sk
group by web_returns.wr_returning_customer_sk
,customer_address.ca_state);

$avg_total_return_by_state =
(select ctr_state, avg(ctr_total_return) avg_return
from $customer_total_return
group by ctr_state);

-- start query 1 in stream 0 using template query30.tpl and seed 1819994127
select c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
,c_last_review_date,ctr_total_return
from $customer_total_return ctr1
join $avg_total_return_by_state ctr2 on ctr1.ctr_state = ctr2.ctr_state
cross join {{customer_address}} as customer_address
cross join {{customer}} as customer
where ctr1.ctr_total_return > 1.2*ctr2.avg_return
and ca_address_sk = c_current_addr_sk
and ca_state = 'GA'
and ctr1.ctr_customer_sk = c_customer_sk
order by c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
,c_last_review_date,ctr_total_return
limit 100;

-- end query 1 in stream 0 using template query30.tpl
61 changes: 61 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q31.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
$ss =
(select customer_address.ca_county ca_county, date_dim.d_qoy d_qoy, date_dim.d_year d_year,sum(ss_ext_sales_price) as store_sales
from {{store_sales}} as store_sales
cross join {{date_dim}} as date_dim
cross join {{customer_address}} as customer_address
where ss_sold_date_sk = d_date_sk
and ss_addr_sk=ca_address_sk
group by customer_address.ca_county,date_dim.d_qoy, date_dim.d_year);

$ws =
(select customer_address.ca_county ca_county,date_dim.d_qoy d_qoy, date_dim.d_year d_year,sum(ws_ext_sales_price) as web_sales
from {{web_sales}} as web_sales
cross join {{date_dim}} as date_dim
cross join {{customer_address}} as customer_address
where ws_sold_date_sk = d_date_sk
and ws_bill_addr_sk=ca_address_sk
group by customer_address.ca_county,date_dim.d_qoy, date_dim.d_year);

-- start query 1 in stream 0 using template query31.tpl and seed 1819994127
select
ss1.ca_county
,ss1.d_year
,ws2.web_sales/ws1.web_sales web_q1_q2_increase
,ss2.store_sales/ss1.store_sales store_q1_q2_increase
,ws3.web_sales/ws2.web_sales web_q2_q3_increase
,ss3.store_sales/ss2.store_sales store_q2_q3_increase
from
$ss ss1
cross join $ss ss2
cross join $ss ss3
cross join $ws ws1
cross join $ws ws2
cross join $ws ws3
where
ss1.d_qoy = 1
and ss1.d_year = 1999
and ss1.ca_county = ss2.ca_county
and ss2.d_qoy = 2
and ss2.d_year = 1999
and ss2.ca_county = ss3.ca_county
and ss3.d_qoy = 3
and ss3.d_year = 1999
and ss1.ca_county = ws1.ca_county
and ws1.d_qoy = 1
and ws1.d_year = 1999
and ws1.ca_county = ws2.ca_county
and ws2.d_qoy = 2
and ws2.d_year = 1999
and ws1.ca_county = ws3.ca_county
and ws3.d_qoy = 3
and ws3.d_year =1999
and case when ws1.web_sales > 0 then ws2.web_sales/ws1.web_sales else null end
> case when ss1.store_sales > 0 then ss2.store_sales/ss1.store_sales else null end
and case when ws2.web_sales > 0 then ws3.web_sales/ws2.web_sales else null end
> case when ss2.store_sales > 0 then ss3.store_sales/ss2.store_sales else null end
order by ss1.d_year;

-- end query 1 in stream 0 using template query31.tpl
35 changes: 35 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q32.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
$avg_discount_by_item = (
select
item.i_item_sk i_item_sk,
avg(cs_ext_discount_amt) as avg_discout
from
{{catalog_sales}} as catalog_sales
cross join {{date_dim}} as date_dim
cross join {{item}} as item
where cast (d_date as date) between cast('2002-03-29' as date) and
(cast('2002-03-29' as date) + DateTime::IntervalFromDays(90))
and d_date_sk = cs_sold_date_sk
group by item.i_item_sk
);

-- start query 1 in stream 0 using template query32.tpl and seed 2031708268
select sum(cs_ext_discount_amt) as `excess discount amount`
from
{{catalog_sales}} cs
cross join {{item}} as item
cross join {{date_dim}} as date_dim
join $avg_discount_by_item adi on cs.cs_item_sk = adi.i_item_sk
where
i_manufact_id = 66
and item.i_item_sk = cs.cs_item_sk
and cast (d_date as date) between cast('2002-03-29' as date) and
(cast('2002-03-29' as date) + DateTime::IntervalFromDays(90))
and d_date_sk = cs_sold_date_sk
and cs_ext_discount_amt
> 1.3 * adi.avg_discout
limit 100;

-- end query 1 in stream 0 using template query32.tpl
82 changes: 82 additions & 0 deletions ydb/library/benchmarks/queries/tpcds/yql/q33.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,82 @@
{% include 'header.sql.jinja' %}

-- NB: Subquerys
$ss = (
select
item.i_manufact_id i_manufact_id,sum(ss_ext_sales_price) total_sales
from
{{store_sales}} as store_sales cross join
{{date_dim}} as date_dim cross join
{{customer_address}} as customer_address cross join
{{item}} as item
where
item.i_manufact_id in (select
i_manufact_id
from
{{item}} as item
where i_category in ('Home'))
and ss_item_sk = i_item_sk
and ss_sold_date_sk = d_date_sk
and d_year = 1998
and d_moy = 5
and ss_addr_sk = ca_address_sk
and ca_gmt_offset = -6
group by item.i_manufact_id);

$cs = (
select
item.i_manufact_id i_manufact_id,sum(cs_ext_sales_price) total_sales
from
{{catalog_sales}} as catalog_sales cross join
{{date_dim}} as date_dim cross join
{{customer_address}} as customer_address cross join
{{item}} as item
where
item.i_manufact_id in (select
i_manufact_id
from
{{item}} as item
where i_category in ('Home'))
and cs_item_sk = i_item_sk
and cs_sold_date_sk = d_date_sk
and d_year = 1998
and d_moy = 5
and cs_bill_addr_sk = ca_address_sk
and ca_gmt_offset = -6
group by item.i_manufact_id);

$ws = (
select
item.i_manufact_id i_manufact_id,sum(ws_ext_sales_price) total_sales
from
{{web_sales}} as web_sales cross join
{{date_dim}} as date_dim cross join
{{customer_address}} as customer_address cross join
{{item}} as item
where
item.i_manufact_id in (select
i_manufact_id
from
{{item}} as item
where i_category in ('Home'))
and ws_item_sk = i_item_sk
and ws_sold_date_sk = d_date_sk
and d_year = 1998
and d_moy = 5
and ws_bill_addr_sk = ca_address_sk
and ca_gmt_offset = -6
group by item.i_manufact_id);


-- start query 1 in stream 0 using template query33.tpl and seed 1930872976
select i_manufact_id ,sum(total_sales) total_sales
from (select * from $ss
union all
select * from $cs
union all
select * from $ws) tmp1
group by i_manufact_id
order by total_sales
limit 100;

-- end query 1 in stream 0 using template query33.tpl
Loading