diff --git a/02_activities/assignments/ERDs.pdf b/02_activities/assignments/ERDs.pdf new file mode 100644 index 000000000..8d5207e60 Binary files /dev/null and b/02_activities/assignments/ERDs.pdf differ diff --git a/02_activities/assignments/assignment1.sql b/02_activities/assignments/assignment1.sql index 2e89fa7af..6481202d3 100644 --- a/02_activities/assignments/assignment1.sql +++ b/02_activities/assignments/assignment1.sql @@ -5,21 +5,25 @@ --SELECT /* 1. Write a query that returns everything in the customer table. */ - +select * from customer; /* 2. Write a query that displays all of the columns and 10 rows from the cus- tomer table, sorted by customer_last_name, then customer_first_ name. */ +select * from customer +order by customer_last_name, customer_first_name +limit 10; --WHERE /* 1. Write a query that returns all customer purchases of product IDs 4 and 9. */ -- option 1 +select * from customer_purchases where product_id = 4 or product_id = 9; -- option 2 - +select * from customer_purchases where product_id in (4,9); /*2. Write a query that returns all customer purchases and a new calculated column 'price' (quantity * cost_to_customer_per_qty), filtered by vendor IDs between 8 and 10 (inclusive) using either: @@ -28,10 +32,13 @@ filtered by vendor IDs between 8 and 10 (inclusive) using either: */ -- option 1 +select *, (quantity * cost_to_customer_per_qty) as price from customer_purchases +where vendor_id >= 8 and vendor_id <= 10; -- option 2 - +select *, (quantity * cost_to_customer_per_qty) as price from customer_purchases +where vendor_id between 8 and 10; --CASE /* 1. Products can be sold by the individual unit or by bulk measures like lbs. or oz. @@ -39,19 +46,36 @@ Using the product table, write a query that outputs the product_id and product_n columns and add a column called prod_qty_type_condensed that displays the word “unit” if the product_qty_type is “unit,” and otherwise displays the word “bulk.” */ - +select product_id, product_name, + case + when product_qty_type = 'unit' then 'unit' + else 'bulk' + end as prod_qty_type_condensed +from product; /* 2. We want to flag all of the different types of pepper products that are sold at the market. add a column to the previous query called pepper_flag that outputs a 1 if the product_name contains the word “pepper” (regardless of capitalization), and otherwise outputs 0. */ +select product_id, product_name, + case + when product_qty_type = 'unit' then 'unit' + else 'bulk' + end as prod_qty_type_condensed, + case + when lower(product_name) LIKE '%pepper%' then 1 + else 0 + end as pepper_flag +from product; --JOIN /* 1. Write a query that INNER JOINs the vendor table to the vendor_booth_assignments table on the vendor_id field they both have in common, and sorts the result by vendor_name, then market_date. */ - +select * from vendor v +inner join vendor_booth_assignments vba on v.vendor_id = vba.vendor_id +order by v.vendor_name, vba.market_date; /* SECTION 3 */ @@ -60,6 +84,9 @@ vendor_id field they both have in common, and sorts the result by vendor_name, t /* 1. Write a query that determines how many times each vendor has rented a booth at the farmer’s market by counting the vendor booth assignments per vendor_id. */ +select vendor_id, count(*) as booth_rental_count +from vendor_booth_assignments +group by vendor_id; /* 2. The Farmer’s Market Customer Appreciation Committee wants to give a bumper @@ -68,6 +95,14 @@ of customers for them to give stickers to, sorted by last name, then first name. HINT: This query requires you to join two tables, use an aggregate function, and use the HAVING keyword. */ +select c.customer_id, c.customer_first_name, c.customer_last_name, +sum(cp.quantity * cp.cost_to_customer_per_qty) as total_spent +from customer c +join customer_purchases cp + on c.customer_id = cp.customer_id +group by c.customer_id, c.customer_first_name, c.customer_last_name +having sum(cp.quantity * cp.cost_to_customer_per_qty) > 2000 +order by c.customer_last_name, c.customer_first_name; --Temp Table @@ -82,6 +117,12 @@ When inserting the new vendor, you need to appropriately align the columns to be VALUES(col1,col2,col3,col4,col5) */ +create table temp.new_vendor as +select * from vendor; + +insert into temp.new_vendor (vendor_id, vendor_name, vendor_type, vendor_owner_first_name, vendor_owner_last_name) +values (10, 'Thomass Superfood Store', 'Fresh Focused store', 'Thomas', 'Rosenthal'); + -- Date @@ -90,7 +131,10 @@ VALUES(col1,col2,col3,col4,col5) HINT: you might need to search for strfrtime modifers sqlite on the web to know what the modifers for month and year are! */ - +select customer_id, + strftime('%m', market_date) as month, + strftime('%Y', market_date) as year +from customer_purchases; /* 2. Using the previous query as a base, determine how much money each customer spent in April 2022. Remember that money spent is quantity*cost_to_customer_per_qty. @@ -98,3 +142,8 @@ Remember that money spent is quantity*cost_to_customer_per_qty. HINTS: you will need to AGGREGATE, GROUP BY, and filter... but remember, STRFTIME returns a STRING for your WHERE statement!! */ +select customer_id, sum(quantity * cost_to_customer_per_qty) as total_spent +from customer_purchases +where strftime('%Y', market_date) = '2022' + and strftime('%m', market_date) = '04' +group by customer_id; diff --git a/02_activities/assignments/assignment2.sql b/02_activities/assignments/assignment2.sql index 5ad40748a..4c219b434 100644 --- a/02_activities/assignments/assignment2.sql +++ b/02_activities/assignments/assignment2.sql @@ -20,6 +20,13 @@ The `||` values concatenate the columns into strings. Edit the appropriate columns -- you're making two edits -- and the NULL rows will be fixed. All the other rows will remain the same.) */ +select * from product +where product_size is null or product_qty_type is null; + +select product_name || ', ' || + coalesce(product_size, '') || ' (' || + coalesce(product_qty_type, 'unit') || ')' as formatted_product +from product; --Windowed Functions @@ -32,17 +39,37 @@ each new market date for each customer, or select only the unique market dates p (without purchase details) and number those visits. HINT: One of these approaches uses ROW_NUMBER() and one uses DENSE_RANK(). */ +select customer_id, market_date, + row_number() over ( + partition by customer_id + order by market_date + ) as visit_number +from customer_purchases; /* 2. Reverse the numbering of the query from a part so each customer’s most recent visit is labeled 1, then write another query that uses this one as a subquery (or temp table) and filters the results to only the customer’s most recent visit. */ +select * from ( + select customer_id, market_date, + row_number() over ( + partition by customer_id + order by market_date desc + ) AS visit_number + from customer_purchases +) as ranked_visits +where visit_number = 1; /* 3. Using a COUNT() window function, include a value along with each row of the customer_purchases table that indicates how many different times that customer has purchased that product_id. */ +select customer_id, product_id, market_date, quantity, cost_to_customer_per_qty, + count(*) over ( + partition by customer_id, product_id + ) as times_purchased +from customer_purchases; -- String manipulations @@ -57,10 +84,18 @@ Remove any trailing or leading whitespaces. Don't just use a case statement for Hint: you might need to use INSTR(product_name,'-') to find the hyphens. INSTR will help split the column. */ +select product_id, product_name, + trim(substr( + product_name, + instr(product_name, '-') + 1 + )) as description +from product; /* 2. Filter the query to show any product_size value that contain a number with REGEXP. */ +select product_id, product_name, product_size from product +where product_size regexp '[0-9]'; -- UNION @@ -73,6 +108,26 @@ HINT: There are a possibly a few ways to do this query, but if you're struggling 3) Query the second temp table twice, once for the best day, once for the worst day, with a UNION binding them. */ +-- Get highest and lowest sales days +select market_date, total_sales from ( + select + market_date, + SUM(quantity * cost_to_customer_per_qty) as total_sales + from customer_purchases + group by market_date + order by total_sales desc + limit 1 +) +union +select market_date, total_sales from ( + select + market_date, + SUM(quantity * cost_to_customer_per_qty) as total_sales + from customer_purchases + group by market_date + order by total_sales asc + limit 1 +); @@ -89,6 +144,13 @@ Think a bit about the row counts: how many distinct vendors, product names are t How many customers are there (y). Before your final group by you should have the product of those two queries (x*y). */ +select v.vendor_name, p.product_name, + count(distinct c.customer_id) * 5 * vi.original_price as total_revenue +from vendor_inventory vi +cross join customer c +join vendor v on vi.vendor_id = v.vendor_id +join product p on vi.product_id = p.product_id +group by v.vendor_name, p.product_name, vi.original_price; -- INSERT @@ -97,18 +159,30 @@ This table will contain only products where the `product_qty_type = 'unit'`. It should use all of the columns from the product table, as well as a new column for the `CURRENT_TIMESTAMP`. Name the timestamp column `snapshot_timestamp`. */ +-- Create the new table with the extra column +create table product_units as +select product_id, product_name, product_size, product_qty_type, + product_category_id, CURRENT_TIMESTAMP as snapshot_timestamp +from product +where product_qty_type = 'unit'; /*2. Using `INSERT`, add a new row to the product_units table (with an updated timestamp). This can be any product you desire (e.g. add another record for Apple Pie). */ +insert into product_units ( + product_id, product_name, product_size, product_qty_type, + product_category_id, snapshot_timestamp +) +values (999, 'Apple Pie', '12"', '3', 'unit', CURRENT_TIMESTAMP); -- DELETE /* 1. Delete the older record for the whatever product you added. HINT: If you don't specify a WHERE clause, you are going to have a bad time.*/ - +delete from product_units +where product_name = 'apple pie' and snapshot_timestamp is null; -- UPDATE @@ -128,6 +202,21 @@ Finally, make sure you have a WHERE statement to update the right row, you'll need to use product_units.product_id to refer to the correct row within the product_units table. When you have all of these components, you can run the update statement. */ +ALTER TABLE product_units +ADD current_quantity INT; + +update product_units +set current_quantity = coalesce( + (select T1.quantity + from vendor_inventory as T1 + where T1.product_id = product_units.product_id + and T1.market_date = ( + select MAX(T2.market_date) + from vendor_inventory as T2 + where T2.product_id = product_units.product_id + ) + ), 0 +);