akavalek · akavalek · Aug 11, 2025 · Aug 16, 2025 · Aug 18, 2025
diff --git a/02_activities/assignments/AAK One Entity-Relationship Diagram.drawio.png b/02_activities/assignments/AAK One Entity-Relationship Diagram.drawio.png
diff --git a/02_activities/assignments/AAK assignment-two diagram 1.png b/02_activities/assignments/AAK assignment-two diagram 1.png
diff --git a/02_activities/assignments/AAK assignment-two diagram 2.png b/02_activities/assignments/AAK assignment-two diagram 2.png
diff --git a/02_activities/assignments/Assignment2.md b/02_activities/assignments/Assignment2.md
@@ -14,10 +14,10 @@
     * Open a private window in your browser. Copy and paste the link to your pull request into the address bar. Make sure you can see your pull request properly. This helps the technical facilitator and learning support staff review your submission easily.
 
 Checklist:
-- [ ] Create a branch called `assignment-two`.
-- [ ] Ensure that the repository is public.
-- [ ] Review [the PR description guidelines](https://github.com/UofT-DSI/onboarding/blob/main/onboarding_documents/submissions.md#guidelines-for-pull-request-descriptions) and adhere to them.
-- [ ] Verify that the link is accessible in a private browser window.
+- [X] Create a branch called `assignment-two`.
+- [X] Ensure that the repository is public.
+- [X] Review [the PR description guidelines](https://github.com/UofT-DSI/onboarding/blob/main/onboarding_documents/submissions.md#guidelines-for-pull-request-descriptions) and adhere to them.
+- [X] Verify that the link is accessible in a private browser window.
 
 If you encounter any difficulties or have questions, please don't hesitate to reach out to our team via our Slack at `#cohort-6-help`. Our Technical Facilitators and Learning Support staff are here to help you navigate any challenges.
 
@@ -54,7 +54,36 @@ The store wants to keep customer addresses. Propose two architectures for the CU
 **HINT:** search type 1 vs type 2 slowly changing dimensions. 
 
 ```
-Your answer...
+My answer:
+
+Type 1 - will overwrite changes. We will only see the most recent address for each customer.
+Below is the suggested columns for that:
+- customer_id
+- customer_first_name
+- customer_last_name
+- unit
+- street
+- city
+- province
+- postal_code
+- country
+
+
+Type 2- will keep all records and timestamp every row, allowing you to access the most recent address on file, but also the historical addresses for any given customer.
+Below is the suggested columns for that:
+- customer_id
+- customer_first_name
+- customer_last_name
+- unit
+- street
+- city
+- province
+- postal_code
+- country
+- date_updated
+- most_recent_address (Y/N column)
+
+
 ```
 
 ***

diff --git a/02_activities/assignments/assignment1.sql b/02_activities/assignments/assignment1.sql
@@ -4,21 +4,22 @@
 
 --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, 
+/* 2. Write a query that displays all of the columns and 10 rows from the customer 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), 
@@ -27,46 +28,89 @@ filtered by vendor IDs between 8 and 10 (inclusive) using either:
 	2.  one condition using BETWEEN
 */
 -- option 1
-
+select *
+,(quantity * cost_to_customer_per_qty) as price
+from customer_purchases where vendor_id <=10 and vendor_id >=8;
 
 -- 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. 
 Using the product table, write a query that outputs the product_id and product_name
 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 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 
+v.vendor_id
+,v.vendor_name
+,v.vendor_type
+,v.vendor_owner_first_name
+,v.vendor_owner_last_name
+,vba.booth_number
+,vba.market_date
+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 */
 
 -- AGGREGATE
 /* 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(vendor_id)
+from vendor_booth_assignments 
+group by vendor_id;
 
 
 /* 2. The Farmer’s Market Customer Appreciation Committee wants to give a bumper 
 sticker to everyone who has ever spent more than $2000 at the market. Write a query that generates a list 
 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_last_name
+,c.customer_first_name
+,sum(cp.quantity * cp.cost_to_customer_per_qty) as spend
+from customer c
+left join customer_purchases cp on c.customer_id = cp.customer_id
+group by c.customer_id
+having spend > 2000
+order by c.customer_last_name, c.customer_first_name;
 
 
 
@@ -81,16 +125,18 @@ When inserting the new vendor, you need to appropriately align the columns to be
 -> To insert the new row use VALUES, specifying the value you want for each column:
 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','Thomas','Rosenthal');
 -- Date
 /*1. Get the customer_id, month, and year (in separate columns) of every purchase in the customer_purchases table.
 
 HINT: you might need to search for strfrtime modifers sqlite on the web to know what the modifers for month 
 and year are! */
 
-
+-- 
 
 /* 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. 

diff --git a/02_activities/assignments/assignment2.sql b/02_activities/assignments/assignment2.sql
@@ -20,7 +20,9 @@ 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 
+product_name || ', ' || coalesce(product_size,'')|| ' (' || coalesce(product_qty_type,'unit') || ')'
+FROM product;
 
 --Windowed Functions
 /* 1. Write a query that selects from the customer_purchases table and numbers each customer’s  
@@ -32,18 +34,37 @@ 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 * from customer_purchases;
+
+select distinct
+customer_id
+,market_date
+,dense_rank()over(partition by customer_id ORDER BY market_date asc) as 'visit_number'
+from customer_purchases;
+--group by customer_id, market_date
+
+
 
 
 /* 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 distinct
+customer_id
+,market_date
+,dense_rank()over(partition by customer_id ORDER BY market_date desc) as 'visit_number'
+from customer_purchases;
+--group by customer_id, market_date;
 
 
 /* 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 
+*,
+count(product_id) over(partition by customer_id, product_id order by market_date,transaction_time asc) as 'purchase_number'
+from customer_purchases;
 
 -- String manipulations
 /* 1. Some product names in the product table have descriptions like "Jar" or "Organic". 
@@ -57,24 +78,65 @@ 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
+*
+,trim(
+	case
+	when product_name like '%-%' then substr(product_name, instr(product_name,'-')+1)
+	else  null 
+	end) as description
+from product;
 
 /* 2. Filter the query to show any product_size value that contain a number with REGEXP. */
-
+select
+*
+,trim(
+	case
+	when product_name like '%-%' then substr(product_name, instr(product_name,'-')+1)
+	else  null 
+	end) as description
+from product 
+where product_size REGEXP '[0-9]';
 
 
 -- UNION
 /* 1. Using a UNION, write a query that displays the market dates with the highest and lowest total sales.
 
 HINT: There are a possibly a few ways to do this query, but if you're struggling, try the following: 
-1) Create a CTE/Temp Table to find sales values grouped dates; 
+1) Create a CTE/Temp Table to find sales values grouped dates 
 2) Create another CTE/Temp table with a rank windowed function on the previous query to create 
-"best day" and "worst day"; 
+"best day" and "worst day"
 3) Query the second temp table twice, once for the best day, once for the worst day, 
 with a UNION binding them. */
 
-
-
+drop table if exists temp.best_worst_selling_days;
+
+create temp table temp.best_worst_selling_days as 	
+select
+q1.market_date
+,q1.daily_sales
+,dense_rank() over(order by q1.daily_sales desc) as best_selling_day
+,dense_rank() over(order by q1.daily_sales asc) as worst_selling_day
+from
+	(select
+	market_date
+	,sum(quantity * cost_to_customer_per_qty) as daily_sales
+	from customer_purchases
+	group by market_date) q1;
+
+select 
+market_date
+,daily_sales
+,'best selling day' as description
+from temp.best_worst_selling_days where best_selling_day = 1
+union all 
+select 
+market_date
+,daily_sales
+,'worst selling day' as description
+from temp.best_worst_selling_days where worst_selling_day = 1;
+
+
 
 /* SECTION 3 */
 
@@ -90,25 +152,54 @@ How many customers are there (y).
 Before your final group by you should have the product of those two queries (x*y).  */
 
 
+select 
+p.product_name
+,v.vendor_name
+,sum( 5* x.original_price) as sales_revenue
+from 
+	(select distinct 
+	vi.product_id
+	,vi.vendor_id
+	,c.customer_id
+	,vi.original_price 
+	from vendor_inventory vi
+	cross join customer c) x	
+left join vendor v on v.vendor_id = x.vendor_id
+left join product p on p.product_id = x.product_id
+group by p.product_name, v.vendor_name;
+
+
 
 -- INSERT
 /*1.  Create a new table "product_units". 
 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`. */
 
+drop table if exists product_units;
 
+create table product_units as
+select *
+,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). */
 
+--select * from product_units;
+
+insert into product_units values 
+(10,'Eggs','1 dozen',6,'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_id = 10 
+and snapshot_timestamp = (select min(snapshot_timestamp) from product_units);
+
 
 
 -- UPDATE
@@ -128,6 +219,18 @@ 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;
 
 
+with updated_quantity as
+	(select *
+	,row_number()over(partition by product_id order by market_date desc) as market_date_rank
+	from vendor_inventory)
+update product_units
+	set current_quantity = coalesce
+	((select uq.quantity
+	from updated_quantity uq
+	where uq.product_id = product_units.product_id and uq.market_date_rank = 1),0);
 
+