Initial submission of assignment 2

02_activities/assignments/Microcredential_Cohort/Assignment2.md

@@ -56,7 +56,8 @@ 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...
+Type 1 = addresses are overwritten
+Type 2 = addresses are retained
 ```
 
 ***

02_activities/assignments/Microcredential_Cohort/assignment2.sql

@@ -23,7 +23,9 @@ Edit the appropriate columns -- you're making two edits -- and the NULL rows wil
 All the other rows will remain the same. */
 --QUERY 1
 
-
+SELECT 
+product_name || ', ' || coalesce(product_size,'') || ' (' || IFNULL(product_qty_type, "unit") || ')'
+FROM product;
 
 
 --END QUERY
@@ -42,6 +44,12 @@ Filter the visits to dates before April 29, 2022. */
 --QUERY 2
 
 
+SELECT DISTINCT
+	market_date,
+	customer_id,
+	dense_rank() OVER(PARTITION BY customer_id ORDER BY market_date ASC) as date_rank
+FROM  customer_purchases
+WHERE date(market_date) < date('2022-04-29');
 
 
 --END QUERY
@@ -54,6 +62,18 @@ HINT: Do not use the previous visit dates filter. */
 --QUERY 3
 
 
+SELECT x.*
+	,x.customer_id
+FROM (
+	SELECT DISTINCT
+		customer_id
+		,market_date
+		,dense_rank() OVER(PARTITION BY customer_id ORDER BY market_date DESC) as date_rank
+	FROM customer_purchases
+	) x
+	INNER JOIN customer_purchases cp
+		on cp.customer_id = x.customer_id
+	WHERE x.date_rank = 1;
 
 
 --END QUERY
@@ -66,8 +86,20 @@ You can make this a running count by including an ORDER BY within the PARTITION
 Filter the visits to dates before April 29, 2022. */
 --QUERY 4
 
-
-
+SELECT x.*
+	, x.customer_id
+FROM (
+	SELECT 
+		customer_id
+		,market_date
+		,product_id
+		,count(*) OVER(PARTITION BY customer_id, product_id ORDER BY market_date ASC) as times_purchased_product 
+	FROM customer_purchases
+
+	) x
+INNER JOIN customer_purchases cp
+	on x.customer_id = cp.customer_id
+WHERE date(x.market_date) < date('2022-04-29');
 
 --END QUERY
 
@@ -85,7 +117,15 @@ 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. */
 --QUERY 5
 
-
+SELECT 
+	product_id
+	,product_name
+	,CASE
+		WHEN instr(product_name,' - ') > 0 THEN substr(product_name,(instr(product_name,' - ')+3))
+		ELSE NULL
+		END product_description
+FROM product
+;
 
 
 --END QUERY
@@ -94,7 +134,17 @@ Hint: you might need to use INSTR(product_name,'-') to find the hyphens. INSTR w
 /* 2. Filter the query to show any product_size value that contain a number with REGEXP. */
 --QUERY 6
 
-
+SELECT 
+	product_id
+	,product_name
+	,CASE
+		WHEN instr(product_name,' - ') > 0 THEN substr(product_name,(instr(product_name,' - ')+3))
+		ELSE NULL
+		END product_description
+	,product_size 
+FROM product
+WHERE product_size REGEXP '[0-9]'
+;
 
 
 --END QUERY
@@ -111,9 +161,40 @@ HINT: There are a possibly a few ways to do this query, but if you're struggling
 with a UNION binding them. */
 --QUERY 7
 
-
-
-
+SELECT
+	market_date,
+	total_sales,
+	rn_max AS [row_number]
+
+FROM (
+    SELECT
+		market_date,
+		SUM(quantity * cost_to_customer_per_qty) AS total_sales,
+		ROW_NUMBER() OVER (ORDER BY SUM(quantity * cost_to_customer_per_qty) DESC) AS rn_max
+
+	FROM customer_purchases
+	GROUP BY market_date
+) x
+WHERE rn_max = 1
+
+UNION
+
+SELECT
+	market_date,
+	total_sales,
+	rn_min
+
+FROM (
+	SELECT
+		market_date
+		,SUM(quantity * cost_to_customer_per_qty) AS total_sales
+		,ROW_NUMBER() OVER (ORDER BY SUM(quantity * cost_to_customer_per_qty) ASC) AS rn_min
+	FROM customer_purchases
+	GROUP BY market_date
+) 
+WHERE rn_min = 1;
+
+
 --END QUERY
 
 
@@ -132,7 +213,39 @@ How many customers are there (y).
 Before your final group by you should have the product of those two queries (x*y).  */
 --QUERY 8
 
+DROP TABLE IF EXISTS temp.vendor_products;
+DROP TABLE IF EXISTS temp.customers;
+
+-- how many distinct vendors and product names are there
+CREATE TEMP TABLE IF NOT EXISTS temp.vendor_products AS
+SELECT DISTINCT
+	vi.vendor_id
+	,vi.product_id
+	,vi.original_price
+	,p.product_name
+	,v.vendor_name
+FROM vendor_inventory as vi
+LEFT JOIN product AS p
+	ON vi.product_id = p.product_id
+INNER JOIN vendor as v
+	ON vi.vendor_id = v.vendor_id;
+
+-- how many unique customers
+CREATE TEMP TABLE IF NOT EXISTS temp.customers AS
+SELECT DISTINCT
+	customer_id
+FROM customer;
+
+SELECT * FROM temp.vendor_products;
+SELECT * FROM temp.customers;
 
+SELECT 
+	vendor_name
+	,product_name
+	,original_price * 5 AS revenue_per_product
+FROM temp.vendor_products JOIN temp.customers
+GROUP BY vendor_name,product_name;
+
 
 
 --END QUERY
@@ -145,8 +258,19 @@ It should use all of the columns from the product table, as well as a new column
 Name the timestamp column `snapshot_timestamp`. */
 --QUERY 9
 
+DROP TABLE IF EXISTS product_units;
 
-
+CREATE TABLE  product_units AS
+SELECT
+	product_id 
+	,product_name
+	,product_size
+	,product_category_id
+	,product_qty_type
+	,datetime('now') AS CURRENT_TIMESTAMP
+FROM product
+WHERE product_qty_type = 'unit'
+;
 
 --END QUERY
 
@@ -155,8 +279,11 @@ Name the timestamp column `snapshot_timestamp`. */
 This can be any product you desire (e.g. add another record for Apple Pie). */
 --QUERY 10
 
-
-
+INSERT INTO product_units
+	(product_id, product_name, product_size, product_category_id, product_qty_type, current_timestamp)
+VALUES
+	(999, 'Garlic Bread', 'Large', 4, 'unit', datetime('now'))
+;
 
 --END QUERY
 
@@ -167,7 +294,9 @@ This can be any product you desire (e.g. add another record for Apple Pie). */
 HINT: If you don't specify a WHERE clause, you are going to have a bad time.*/
 --QUERY 11
 
-
+DELETE  
+FROM product_units
+WHERE product_id = 999
 
 
 --END QUERY
@@ -191,10 +320,22 @@ Finally, make sure you have a WHERE statement to update the right row,
 When you have all of these components, you can run the update statement. */
 --QUERY 12
 
+ALTER TABLE product_units
+ADD current_quantity INT;
 
-
+UPDATE product_units
+SET current_quantity = coalesce (
+(
+		SELECT quantity
+		FROM (
+			SELECT
+				product_id
+				,quantity
+				,row_number() OVER(PARTITION BY product_id ORDER BY market_date DESC) AS rn_max
+			FROM vendor_inventory
+	)x
+	WHERE x.product_id = product_units.product_id AND rn_max = 1
+	)
+	,0);
 
 --END QUERY
-
-
-