turns-00050.parquet:28691
4aea1c5cf5966af066f4ca17degenerate_repetitionAbsentFinal dense release
USER
You are a database expert and SQL optimizer. You will be given a SQL query and its rewritten variant. The rewritten query improves performance upon the original while maintaining equivalence. Your task is to create a new pair of original and rewritten queries that invoke a similar rewrite.
[ORIGINAL QUERY]```select i_item_id,ca_country,ca_state,ca_county,avg( cast(cs_quantity as decimal(12,2))) agg1,avg( cast(cs_list_price as decimal(12,2))) agg2,avg( cast(cs_coupon_amt as decimal(12,2))) agg3,avg( cast(cs_sales_price as decimal(12,2))) agg4,avg( cast(cs_net_profit as decimal(12,2))) agg5,avg( cast(c_birth_year as decimal(12,2))) agg6,avg( cast(cd1.cd_dep_count as decimal(12,2))) agg7 from catalog_sales,customer_demographics cd1,customer_demographics cd2,customer,customer_address,date_dim,item where cs_sold_date_sk = d_date_sk and cs_item_sk = i_item_sk and cs_bill_cdemo_sk = cd1.cd_demo_sk and cs_bill_customer_sk = c_customer_sk and cd1.cd_gender = 'F' and cd1.cd_education_status = 'Primary' and c_current_cdemo_sk = cd2.cd_demo_sk and c_current_addr_sk = ca_address_sk and c_birth_month in (1,3,7,11,10,4) and d_year = 2001 and ca_state in ('AL','MO','TN','GA','MT','IN','CA') group by rollup (i_item_id,ca_country,ca_state,ca_county) order by ca_country,ca_state,ca_county,i_item_id limit 100; ```
[REWRITTEN QUERY]```with catalog_sales_filtered as (select * from catalog_sales where cs_sold_date_sk in (select d_date_sk from date_dim where d_year = 2001)) select i_item_id,ca_country,ca_state,ca_county,avg( cast(cs_quantity as decimal(12,2))) agg1,avg( cast(cs_list_price as decimal(12,2))) agg2,avg( cast(cs_coupon_amt as decimal(12,2))) agg3,avg( cast(cs_sales_price as decimal(12,2))) agg4,avg( cast(cs_net_profit as decimal(12,2))) agg5,avg( cast(c_birth_year as decimal(12,2))) agg6,avg( cast(cd1.cd_dep_count as decimal(12,2))) agg7 from catalog_sales_filtered,customer_demographics cd1,customer_demographics cd2,customer,customer_address,date_dim,item where cs_sold_date_sk = d_date_sk and cs_item_sk = i_item_sk and cs_bill_cdemo_sk = cd1.cd_demo_sk and cs_bill_customer_sk = c_customer_sk and cd1.cd_gender = 'F' and cd1.cd_education_status = 'Primary' and c_current_cdemo_sk = cd2.cd_demo_sk and c_current_addr_sk = ca_address_sk and c_birth_month in (1,3,7,11,10,4) and d_year = 2001 and ca_state in ('AL','MO','TN','GA','MT','IN','CA') group by rollup (i_item_id,ca_country,ca_state,ca_county) order by ca_country,ca_state,ca_county,i_item_id limit 100;```
Now, consider the TPC-DS schema and create a new original and equivalent rewritten query pair such that the rewrite operation is similar to the provided demonstration.Keep the following points in mind while creating the new query pair:
1. The original query must not have any CTEs.
2. The original query must make use of the following fact tables: ['web_sales']. Below is the join graph for these fact tables:
['web_sales(ws_bill_hdemo_sk) references household_demographics(hd_demo_sk);', 'web_sales(ws_bill_customer_sk) references customer(c_customer_sk);', 'web_sales(ws_sold_date_sk) references date_dim(d_date_sk);']
4. The original query must employ 1 joins.
5. The original query must employ the following operators in its WHERE clause: [].
6. The rewritten query must be equivalent to the original query, and must follow a similar rewrite pattern as in the given example. Enclose the original and rewritten queries within ``` and ```.ASSISTANT
Sure! Here is a new pair of original and rewritten SQL queries using the TPC-DS schema and incorporating a similar rewrite pattern to the given example:
[ORIGINAL QUERY]
```sql
SELECT ws_item_sk, c_customer_id, AVG(CAST(ws_quantity AS DECIMAL(12, 2))) avg_quantity, AVG(CAST(ws_sales_price AS DECIMAL(12, 2))) avg_sales_price
FROM web_sales, customer
WHERE ws_bill_customer_sk = c_customer_sk AND ws_sold_date_sk = (SELECT d_date_sk FROM date_dim WHERE d_year = 2001)
GROUP BY ws_item_sk, c_customer_id
ORDER BY ws_item_sk, c_customer_id
LIMIT 100;
```
[REWRITTEN QUERY]
```sql
WITH web_sales_filtered AS (
SELECT *
FROM web_sales
WHERE ws_sold_date_sk IN (SELECT d_date_sk FROM date_dim WHERE d_year = 2001)
)
SELECT ws_item_sk, c_customer_id, AVG(CAST(ws_quantity AS DECIMAL(12, 2))) avg_quantity, AVG(CAST(ws_sales_price AS DECIMAL(12, 2))) avg_sales_price
FROM web_sales_filtered, customer
WHERE ws_bill_customer_sk = c_customer_sk
GROUP BY ws_item_sk, c_customer_id
ORDER BY ws_item_sk, c_customer_id
LIMIT 100;
```
Explanation:
- The original query selects average quantities and sales prices from the `web_sales` and `customer` tables, filtering records where the `ws_sold_date_sk` is equal to the date key of the year 2001.
- The rewritten query improves performance by pre-filtering the `web_sales` table using a Common Table Expression (CTE) to only include records from the year 2001, akin to the rewrite demonstrated in the given query example.