Skip to content

UofT-DSI | SQL - Assignment 2 #2

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

Open
akorade wants to merge 8 commits into
base: main
Choose a base branch
from
Open

UofT-DSI | SQL - Assignment 2 #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ac5914f
Add Bookstore ER diagram for Assignment 2
akorade Nov 13, 2025
e2baf21
Add employee shift entities to bookstore ER diagram
akorade Nov 13, 2025
4eccbf3
Add SQL examples for type 1 and type 2 address tables
akorade Nov 14, 2025
11b5111
assignment 2 sql : Add solutions for window functions and string mani…
akorade Nov 14, 2025
f005c34
Complete string manipulation and UNION queries for assignment 2
akorade Nov 18, 2025
b7cf3ec
Add revenue calculation query for vendors and products
akorade Nov 18, 2025
7022cc8
Add product_units table with timestamp and current_quantity updates
akorade Nov 19, 2025
782bab6
Refactor product description extraction and update revenue calculatio…
akorade Nov 19, 2025
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
144 changes: 144 additions & 0 deletions ...ivities/assignments/Cohort_8/Assignment 2 - Prompt 1 + Prompt 2- Bookstore ER Diagram.mmd
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,144 @@
erDiagram
CUSTOMER ||--o{ "ORDER" : places
EMPLOYEE ||--o{ "ORDER" : handles
"ORDER" ||--o{ SALES : contains
BOOK ||--o{ SALES : "sold in"
DATE_DIM ||--o{ "ORDER" : "order date"

BOOK_CATEGORY ||--o{ BOOK : "categorizes"

BOOK ||--o{ BOOK_SUPPLIER : "is supplied by"
SUPPLIER ||--o{ BOOK_SUPPLIER : "supplies"

BOOK ||--o{ INVENTORY_TRANSACTION : "movement"
DATE_DIM ||--o{ INVENTORY_TRANSACTION : "txn date"

EMPLOYEE ||--o{ EMPLOYEE_SHIFT : "assigned"
SHIFT ||--o{ EMPLOYEE_SHIFT : "shift info"
DATE_DIM ||--o{ EMPLOYEE_SHIFT : "shift date"

CUSTOMER {
int customer_id PK
string first_name
string last_name
string email
string phone
string loyalty_number
string address_line1
string address_line2
string city
string province_state
string postal_code
date created_at
}

EMPLOYEE {
int employee_id PK
string first_name
string last_name
string role
date hire_date
string email
string phone
boolean is_active
}

SHIFT {
int shift_id PK
string shift_name "Morning, Evening"
time start_time
time end_time
}

EMPLOYEE_SHIFT {
int emp_shift_id PK
int employee_id FK
int shift_id FK
int date_key FK
boolean is_confirmed
string notes
}

"ORDER" {
int order_id PK
int customer_id FK
int employee_id FK
int order_date_key FK
string order_status
string payment_method
decimal order_subtotal
decimal order_tax
decimal order_total
}

SALES {
int sales_id PK
int order_id FK
int book_id FK
int quantity
decimal unit_price
decimal discount_amount
decimal line_total
}

BOOK {
int book_id PK
string isbn
string title
string author
int category_id FK
decimal list_price
date published_date
boolean is_active
}

BOOK_CATEGORY {
int category_id PK
string category_name
string description
}

SUPPLIER {
int supplier_id PK
string supplier_name
string contact_name
string email
string phone
string address_line1
string address_line2
string city
string province_state
string postal_code
}

BOOK_SUPPLIER {
int book_id FK
int supplier_id FK
decimal supplier_price
int lead_time_days
boolean is_primary
}

INVENTORY_TRANSACTION {
int txn_id PK
int book_id FK
int date_key FK
string txn_type "RECEIPT, SALE, RETURN, ADJUSTMENT"
int quantity_change "positive or negative"
int order_id FK "for sales"
int supplier_id FK "for receipts (optional)"
string notes
}

DATE_DIM {
int date_key PK
date full_date
int year
int quarter
int month
string month_name
int day
string day_name
boolean is_weekend
boolean is_holiday
}
Binary file added ...signments/Cohort_8/Assignment 2 - Prompt 1 + Prompt 2- Bookstore ER Diagram.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
37 changes: 35 additions & 2 deletions 02_activities/assignments/Cohort_8/Assignment2.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,8 +53,41 @@ 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...
```sql
/*
TYPE 1 (Overwrite Changes)
- Only one address per customer,
*/
CREATE TABLE CUSTOMER_ADDRESS (
customer_id INTEGER PRIMARY KEY,
address_line1 TEXT NOT NULL,
address_line2 TEXT,
city TEXT NOT NULL,
province_state TEXT NOT NULL,
postal_code TEXT NOT NULL,
country TEXT NOT NULL,
last_updated_at TEXT DEFAULT (datetime('now')),
FOREIGN KEY (customer_id) REFERENCES CUSTOMER(customer_id)
);

/*
TYPE 2 (Keep History)
- One customer can have multiple address records over time.
*/
CREATE TABLE CUSTOMER_ADDRESS (
customer_address_id INTEGER PRIMARY KEY AUTOINCREMENT,
customer_id INTEGER NOT NULL,
address_line1 TEXT NOT NULL,
address_line2 TEXT,
city TEXT NOT NULL,
province_state TEXT NOT NULL,
postal_code TEXT NOT NULL,
country TEXT NOT NULL,
valid_from_date TEXT NOT NULL, -- ISO date like '2025-01-15'
valid_to_date TEXT, -- NULL means currently active
is_current INTEGER NOT NULL DEFAULT 1, -- 1 = current, 0 = historical
FOREIGN KEY (customer_id) REFERENCES CUSTOMER(customer_id)
);
```

***
Expand Down
142 changes: 128 additions & 14 deletions 02_activities/assignments/Cohort_8/assignment2.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,15 @@ 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
COALESCE(product_name, '')
|| ', ' ||
COALESCE(product_size, '')
|| ' (' ||
COALESCE(product_qty_type, 'unit')
|| ')'
AS product_details
FROM product;

--Windowed Functions
/* 1. Write a query that selects from the customer_purchases table and numbers each customer’s
Expand All @@ -32,18 +40,50 @@ 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,
DENSE_RANK() OVER (
PARTITION BY customer_id
ORDER BY market_date
) AS visit_number
FROM (
SELECT DISTINCT customer_id, market_date
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. */


CREATE TEMP TABLE temp_customer_visits AS
Copy link
Copy Markdown

@monzchan monzchan Nov 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good attempt. The question requires reversing numbering based on the distinct visit list from above. Here used the raw customer_purchases may cause duplicate rows and incorrect visit numbering. consider this:
WITH visits AS (
SELECT
customer_id,
market_date,
ROW_NUMBER() OVER (
PARTITION BY customer_id
ORDER BY market_date DESC
) AS visit_number
FROM (
SELECT DISTINCT customer_id, market_date
FROM customer_purchases
) x
)
SELECT customer_id, market_date
FROM visits
WHERE visit_number = 1;

SELECT
customer_id,
market_date,
ROW_NUMBER() OVER (
PARTITION BY customer_id
ORDER BY market_date DESC
) AS visit_number
FROM customer_purchases;
SELECT
customer_id,
market_date
FROM temp_customer_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,
customer_purchases.*,
product.product_name,
COUNT(*) OVER (
PARTITION BY customer_id, customer_purchases.product_id
) AS times_customer_bought_product
FROM customer_purchases
INNER JOIN product
ON customer_purchases.product_id = product.product_id;

-- String manipulations
/* 1. Some product names in the product table have descriptions like "Jar" or "Organic".
Expand All @@ -57,11 +97,16 @@ 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_name,
TRIM(SUBSTR(product_name, NULLIF(INSTR(product_name, '-'), 0) + 1)) AS description
Copy link
Copy Markdown

@monzchan monzchan Nov 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If the product name has no hyphen, student formula incorrectly extracts the entire product_name instead of returning NULL, producing wrong descriptions.
CASE WHEN INSTR(product_name, '-') > 0 THEN
TRIM(SUBSTR(product_name, INSTR(product_name, '-') + 1))
ELSE NULL END

FROM product;

/* 2. Filter the query to show any product_size value that contain a number with REGEXP. */


SELECT *
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.
Expand All @@ -72,8 +117,36 @@ HINT: There are a possibly a few ways to do this query, but if you're struggling
"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. */


-- Step 1: Create CTE for daily sales
WITH daily_sales AS (
SELECT
market_date,
SUM(quantity * cost_to_customer_per_qty) AS total_sales
FROM customer_purchases
GROUP BY market_date
),
ranked_sales AS (
SELECT
market_date,
total_sales,
# ranking twice will correctly return all tied days
RANK() OVER (ORDER BY total_sales DESC) AS best_rank,
RANK() OVER (ORDER BY total_sales ASC) AS worst_rank
FROM daily_sales
)
SELECT
market_date,
total_sales,
'Best day' AS day_type
FROM ranked_sales
WHERE best_rank = 1
UNION
SELECT
market_date,
total_sales,
'Worst day' AS day_type
FROM ranked_sales
WHERE worst_rank = 1


/* SECTION 3 */
Expand All @@ -88,27 +161,49 @@ Remember, CROSS JOIN will explode your table rows, so CROSS JOIN should likely b
Think a bit about the row counts: how many distinct vendors, product names are there (x)?
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,
customer_count * 5 * vi.original_price AS total_revenue
Copy link
Copy Markdown

@monzchan monzchan Nov 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SUM(5 * vi.original_price) AS total_revenue

FROM (
SELECT DISTINCT
vendor_id,
product_id,
original_price
FROM vendor_inventory) AS vi
CROSS JOIN (
-- Get all unique customers
SELECT COUNT(DISTINCT customer_id) as customer_count
FROM customer
) c
INNER JOIN vendor v ON vi.vendor_id = v.vendor_id
INNER JOIN product p ON vi.product_id = p.product_id
GROUP BY v.vendor_name, p.product_name, vi.original_price;

-- 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`. */


CREATE TABLE product_units AS
SELECT
product.*,
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_category_id, product_qty_type, snapshot_timestamp)
VALUES (9999, 'Test Product', '1 unit', 1, '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 = 9999


-- UPDATE
Expand All @@ -128,6 +223,25 @@ 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 latest_inventory AS (
SELECT product_id,
quantity,
ROW_NUMBER() OVER (
PARTITION BY product_id
ORDER BY market_date DESC
) AS rn
FROM vendor_inventory)
UPDATE product_units
SET current_quantity = COALESCE((
SELECT vi.quantity
FROM latest_inventory vi
WHERE vi.product_id = product_units.product_id AND vi.rn = 1
), 0);

-- SELECT Statements for reference
SELECT * FROM product_units;