Uploading Assignment 2 for proper repo pr

02_activities/assignments/Assignment2.md

@@ -55,6 +55,78 @@ The store wants to keep customer addresses. Propose two architectures for the CU
 
 ```
 Your answer...
+
+Here's my proposal for two CUSTOMER_ADDRESS tables:
+
+TYPE 1 - This would overwrite changes to the customer address directly, it would not retain history, but would keep table record counts lean.
+
+In practice, a customer would have 1 record (not showing all fields):
+__________________________________
+| customer_id | customer_address | 
+|-------------|------------------|
+| 123         |Address1          | 
+
+
+When a new address is added (for example Address 2), the existing records is updated via UPDATE statement on the applicable address/country/postal etc. fields.
+
+
+After the update, it would look like:
+__________________________________
+| customer_id | customer_address | 
+|-------------|------------------|
+| 123         |Address2          | 
+
+
+The table itself would be:
+- customer_id (int)
+- customer_address (varchar (255))
+- customer_address_unit (varchar(80))
+- postal_zip (varchar(14))
+- state_province (varchar(3))
+- country (varchar(80))
+- country_code (varchar (3))
+
+
+
+TYPE 2 - This would add a new row/record for every new address a customer has. This would maintain existing rows for historical purposes. Compared to Type 1 proposition, this has two additional fields:
+    - effective_date would show when the new address is added
+    - current_flag would indicate if that records is the current address of the customer
+
+In practice, a customer could have 3 addresses (not showing all fields):
+__________________________________________________________________
+| customer_id | customer_address | effective_date | current_flag |
+|-------------|------------------|----------------|--------------|
+| 123         |Address1          | 2024-01-01     | NULL         |
+| 123         |Address2          | 2024-02-01     | NULL         |   
+| 123         |Address3          | 2025-01-01     | Y            |
+
+When a new address is added (for example Address 4):
+1. The existing current_flag would be changed to NULL for address 3
+2. A new record is inserted for customer 123 with Address 4, today's date, and current_flag = 'Y'
+
+After the update, it would look like:
+__________________________________________________________________
+| customer_id | customer_address | effective_date | current_flag |
+|-------------|------------------|----------------|--------------|
+| 123         |Address1          | 2024-01-01     | NULL         |
+| 123         |Address2          | 2024-02-01     | NULL         |   
+| 123         |Address3          | 2025-01-01     | NULL         |
+| 123         |Address4          | 2025-04-27     | Y            |
+
+
+The table itself would be:
+- customer_id (int)
+- customer_address (varchar (255))
+- customer_address_unit (varchar(80))
+- postal_zip (varchar(14))
+- state_province (varchar(3))
+- country (varchar(80))
+- country_code (varchar (3))
+- effective_date (date)
+- current_flag (varchar(1))
+
+
+
 ```
 
 ***

02_activities/assignments/assignment2.sql

@@ -20,6 +20,10 @@ 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
@@ -32,17 +36,75 @@ 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 customer_visits
+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. */
 
+-- Recent visit is 1 (reverse order). Just add DESC to order by for market_date
+SELECT
+	customer_id
+	,market_date
+	,ROW_NUMBER() OVER (
+		PARTITION BY customer_id
+		ORDER BY market_date DESC
+	) AS customer_visits
+FROM  (
+	SELECT DISTINCT	
+		customer_id
+		,market_date
+	FROM customer_purchases
+	)
+
+
+-- Only get most recent visit
+SELECT *
+FROM (
+	SELECT
+		customer_id
+		,market_date
+		,ROW_NUMBER() OVER (
+			PARTITION BY customer_id
+			ORDER BY market_date DESC
+		) AS customer_visits
+	FROM  (
+		SELECT DISTINCT	
+			customer_id
+			,market_date
+		FROM customer_purchases
+		)
+	)
+WHERE customer_visits = 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
+	*
+	,COUNT(*) OVER (
+		PARTITION BY customer_id, product_id 
+		ORDER BY market_date, transaction_time
+		) AS product_purchase_count
+FROM customer_purchases
+ORDER BY customer_id, product_id, market_date, transaction_time;
+
 
 
 -- String manipulations
@@ -57,10 +119,22 @@ 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. */
 
+--Need to add +2 in SUBSTR because of the hyphen and the space after
+SELECT 
+	*
+	,TRIM(IIF(INSTR(product_name, '-') > 0, SUBSTR(product_name, INSTR(product_name, '-') + 2), NULL)) AS description 
+FROM product;
+
 
 
 /* 2. Filter the query to show any product_size value that contain a number with REGEXP. */
 
+SELECT 
+	*
+	,TRIM(IIF(INSTR(product_name, '-') > 0, SUBSTR(product_name, INSTR(product_name, '-') + 2), NULL)) AS description 
+FROM product
+WHERE product_size REGEXP '[0-9]';
+
 
 
 -- UNION
@@ -73,6 +147,35 @@ 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. */
 
+SELECT 
+	* 
+FROM
+	(--Get worst date (lowest sales)
+	SELECT 
+		market_date
+		,SUM(quantity * cost_to_customer_per_qty) AS 'total_sales'
+		,'worst day' AS 'sales_performance'
+	FROM customer_purchases
+	GROUP BY market_date
+	ORDER BY total_sales ASC
+	LIMIT 1
+	) 
+
+UNION
+
+SELECT 
+	* 
+FROM
+	(--Get best date (most sales)
+	SELECT 
+		market_date
+		,SUM(quantity * cost_to_customer_per_qty) AS 'total_sales'
+		,'best day' AS 'sales_performance'
+	FROM customer_purchases
+	GROUP BY market_date
+	ORDER BY total_sales DESC
+	LIMIT 1
+	);
 
 
 
@@ -89,6 +192,43 @@ 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).  */
 
+-- There are 3 vendors in vendor_inventory (vendor_id 4, 7, 8) and they have 8 products altogether.
+-- There are 26 customers. We should expect the total records of customers purchasing to be (8*26) = 208.
+
+-- Aggregate to find total sales per product_name
+SELECT
+	vendor_name
+	,product_name
+	,SUM(amount_to_sell)
+FROM ( 
+	-- Get all valid combinations of products and vendors from vendor_inventory
+	SELECT 
+		v.vendor_id
+		,v.vendor_name
+		,vi.product_id
+		,cp.product_name
+		,vi.original_price
+		,(vi.original_price * 5) AS amount_to_sell
+	FROM vendor v
+	INNER JOIN (
+		SELECT DISTINCT 
+			vendor_id
+			,product_id
+			,original_price
+		FROM vendor_inventory 
+		) vi
+		ON	v.vendor_id = vi.vendor_id
+
+	-- Get all combinations of customers and products and join on relevant product_ids
+	INNER JOIN (	
+		SELECT * 
+		FROM customer c
+		CROSS JOIN product p
+		) cp
+		ON vi.product_id = cp.product_id
+	)
+GROUP BY product_name;
+
 
 
 -- INSERT
@@ -97,18 +237,73 @@ 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`. */
 
+--Get table format for product
+PRAGMA table_info(product);
+
+--From this, we see the names and types as:
+--	name				type
+--	product_id			int(11)
+--	product_name		varchar(45)
+--	product_size		varchar(45)
+--	product_category_id	int(11)
+--	product_qty_type	varchar(45)
+
+
+
+-- Delete table in case it already exists
+DROP TABLE IF EXISTS product_units;
+
+--Copy table format/columns of product, include snapshot_timestamp column
+CREATE TABLE product_units (
+	product_id INT(11)
+	,product_name VARCHAR(45)
+	,product_size VARCHAR(45)
+	,product_category_id INT(11)
+	,product_qty_type VARCHAR(45)
+	,snapshot_timestamp TEXT
+	);
+
+--Insert 'unit' values, as well as the timestamp
+INSERT INTO product_units
+	SELECT 
+		*
+		,strftime('%Y-%m-%d %H:%M:%S', datetime('now')) AS 'snapshot_timestamp'
+	FROM product
+	WHERE product_qty_type = 'unit';
+
+-- Checking if results look good	
+SELECT * FROM product_units;
+
 
 
 /*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 VALUES(
+	24
+	,'Anchovy Martini'
+	,'30 oz'
+	,3
+	,'unit'
+	,strftime('%Y-%m-%d %H:%M:%S', datetime('now'))
+	);
+
+-- Checking if results look good		
+SELECT * FROM product_units;
+
 
 
 -- 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 = 'Anchovy Martini';
+
+-- Checking if results look good	
+SELECT * FROM product_units;
+
 
 
 -- UPDATE
@@ -128,6 +323,46 @@ 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;
+
+DROP TABLE IF EXISTS temp_latest_inventory;
+
+-- Get modified version of product_units as a temp table to join values 
+CREATE TEMP TABLE temp_latest_inventory AS 
+	-- Get all product_ids with current_quantity. It's set to 0 if it's not for the max date (Oct 13, 2023)
+	SELECT 
+		pu.*
+		,vi_latest.*
+		,COALESCE(vi_latest.quantity,0) AS latest_quantity
+	FROM product_units pu
+	LEFT JOIN (
+		-- Inventory of latest date. If no record, means they were not available on that date
+		SELECT vi.*
+			,vi_latest_date.max_market_date
+		FROM vendor_inventory vi
+		INNER JOIN (
+			-- Get the latest date for each product
+			SELECT 
+				MAX(market_date) AS max_market_date
+			FROM vendor_inventory vi
+		) vi_latest_date
+		ON vi.market_date = vi_latest_date.max_market_date
+	) vi_latest
+	ON pu.product_id = vi_latest.product_id;
+
+SELECT * FROM temp_latest_inventory;
+
+-- Update statement for current_quantity, join on product_id
+UPDATE product_units 
+SET current_quantity = (
+	SELECT latest_quantity	
+	FROM temp_latest_inventory
+	WHERE product_units.product_id = temp_latest_inventory.product_id
+	);
+
+-- Checking if results look good		
+SELECT * FROM product_units;