Assignment two

.gitignore

@@ -1,3 +1,4 @@
 .DS_Store
 .vscode/
 .sqbpro
+*.db-journal

02_activities/assignments/Assignment2.md

@@ -54,7 +54,9 @@ 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 is the overwrite approach. Our table is the same CUSTOMER_ADDRESS table and we would update the columns AddressID, CustomerID, Street, City, State, and Zipcode with each change/update. We wil not preserve old addresses only the most recent (MAX) one will be kept
+
+Type 2 will retain changes through adding a new row to track the historical data. We would add rows to the type 1 approach, thus having a table that includes the following fields:  AddressID, CustomerID, Street, City, State, and Zipcode with the addition of EffectiveDate and CurrentFlag, underscoring when the update was last current and whether or not it is current now. This allows us to retain the old, historical address data while leveraging the current, most up to date address information in the same table. 
 ```
 
 ***

02_activities/assignments/assignment2.sql

@@ -20,6 +20,11 @@ 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')  || ')' 
+AS details
+FROM product;
 
 
 --Windowed Functions
@@ -32,18 +37,33 @@ 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 *, 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. */
 
+WITH recent_visit AS (SELECT *,
+    ROW_NUMBER() 
+    OVER (PARTITION BY customer_id ORDER BY market_date DESC) 
+    AS ranked
+    FROM customer_purchases
+)
+SELECT *
+FROM recent_visit
+WHERE ranked = 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) 
+AS time_purchase
+FROM customer_purchases;
 
 -- String manipulations
 /* 1. Some product names in the product table have descriptions like "Jar" or "Organic". 
@@ -57,11 +77,26 @@ 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,
+  CASE
+    WHEN INSTR(product_name, '-') > 0 
+    THEN TRIM(
+      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 product_name, product_size,
+  CASE
+    WHEN INSTR(product_name, '-') > 0 
+    THEN TRIM(
+      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.
@@ -73,6 +108,25 @@ 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. */
 
+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,
+    RANK() OVER (ORDER BY total_sales ASC)  AS rank_low,
+    RANK() OVER (ORDER BY total_sales DESC) AS rank_high
+  FROM daily_sales
+)
+SELECT market_date, total_sales,'worst' AS day_type
+FROM ranked_sales
+WHERE rank_low = 1
+
+UNION
+
+SELECT market_date, total_sales,'best' AS day_type
+FROM ranked_sales
+WHERE rank_high = 1;
 
 
 
@@ -89,27 +143,56 @@ 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).  */
 
+WITH vendor_products AS (
+  SELECT vi.vendor_id, vi.product_id, vi.original_price
+  FROM vendor_inventory AS vi),
 
+joined AS (
+  SELECT vp.vendor_id, vp.product_id, vp.original_price, c.customer_id
+  FROM vendor_products AS vp
+  CROSS JOIN customer AS c)
+
+SELECT v.vendor_name, p.product_name, SUM(5 * e.original_price) AS money_made
+FROM joined AS e
+  JOIN vendor  AS v ON v.vendor_id  = e.vendor_id
+  JOIN product AS p ON p.product_id = e.product_id
+GROUP BY v.vendor_name, p.product_name
+ORDER BY v.vendor_name, p.product_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`. */
 
-
+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). */
 
-
+INSERT INTO product_units
+  (product_id,
+   product_name,
+   product_size,
+   product_category_id,
+   product_qty_type,
+   snapshot_timestamp)
+VALUES (7, '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_id = 7
+  AND snapshot_timestamp <>
+    (SELECT MAX(snapshot_timestamp)
+      FROM product_units
+      WHERE product_id = 7);
 
 -- UPDATE
 /* 1.We want to add the current_quantity to the product_units table. 
@@ -128,6 +211,14 @@ 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 vi.quantity
+    FROM vendor_inventory AS vi
+    WHERE vi.product_id = product_units.product_id
+    ORDER BY vi.market_date DESC
+    LIMIT 1),0);
 

04_this_cohort/live_code/module_4/string_manipulations.sql

@@ -0,0 +1,48 @@
+-- string manipulations
+
+SELECT DISTINCT
+
+LTRIM('                THOMAS ROSENTHAL                 ') as [ltrim]
+,RTRIM('                THOMAS ROSENTHAL                 ') as [rtrim]
+,TRIM('                THOMAS ROSENTHAL                 ') as [trimmed]
+,LTRIM(RTRIM('                THOMAS ROSENTHAL                 ')) as [both]
+
+--replace
+,REPLACE('THOMAS ROSENTHAL', ' ', ' WILLIAM ' ) -- add my middle name between first name and last name
+,REPLACE('THOMAS ROSENTHAL', 'a','') -- case sensitive
+,REPLACE('THOMAS ROSENTHAL', 'A','') -- replaces both A's
+,REPLACE(REPLACE(customer_first_name, 'a',''),'e','') as new_customer_first_name
+
+,UPPER(customer_first_name) as [upper]
+,LOWER(customer_first_name) as [lower]
+
+--concat
+,customer_first_name || ' ' || customer_last_name as customer_name
+,UPPER(customer_first_name) || ' ' || UPPER(customer_last_name) || ' ' || customer_postal_code as upper_cust_name
+
+
+FROM customer;
+
+SELECT DISTINCT
+customer_last_name
+,SUBSTR(customer_last_name,4) -- any length from the 4th character
+,substr(customer_last_name,4,2) 
+,substr(customer_last_name, -5,4) -- counting from the right
+,substr(customer_last_name,1,2) -- results with 2 characters
+,substr(customer_last_name,0,2) -- results with 1 character instead of 2
+
+--length
+,length(customer_last_name)
+
+
+,'THOMAS
+
+ROSENTHAL'
+
+,replace('THOMAS
+
+ROSENTHAL', char(10), ' ' ) -- removing all instances of the line break from the string
+
+FROM customer
+
+WHERE customer_last_name REGEXP '(a)$' -- filtering to only end in a

04_this_cohort/live_code/module_5/CROSS_JOIN.sql

@@ -0,0 +1,15 @@
+--CROSS JOIN
+
+DROP TABLE IF EXISTS temp.sizes;
+CREATE TEMP TABLE IF NOT EXISTS temp.sizes (size TEXT);
+
+INSERT INTO temp.sizes
+VALUES('small'),
+('medium'),
+('large');
+
+SELECT * FROM temp.sizes;
+
+SELECT product_name, size
+FROM product
+CROSS JOIN temp.sizes

04_this_cohort/live_code/module_5/FIRST_VIEW.sql

@@ -0,0 +1,21 @@
+-- VIEW
+
+-- vendor daily sales
+DROP VIEW IF EXISTS vendor_daily_sales;
+CREATE VIEW IF NOT EXISTS vendor_daily_sales AS
+
+	SELECT 
+	md.market_date
+	,market_day
+	,market_year
+	,vendor_name
+	,SUM(quantity*cost_to_customer_per_qty) as sales
+
+
+	FROM market_date_info md
+	INNER JOIN customer_purchases cp
+		ON md.market_date = cp.market_date
+	INNER JOIN vendor v
+		ON v.vendor_id = cp.vendor_id
+
+	GROUP BY cp.market_date, v.vendor_id

04_this_cohort/live_code/module_5/INSERT_UPDATE_DELETE.sql

@@ -0,0 +1,21 @@
+--INSERT UPDATE AND DELETE
+
+DROP TABLE IF EXISTS temp.product_expanded;
+CREATE TEMP TABLE product_expanded AS 
+	SELECT * FROM product;
+
+INSERT INTO product_expanded
+VALUES(26, 'Almonds', '1 lb',1, 'lbs');
+
+--update our new record product_size to 1/2 kg
+UPDATE product_expanded
+--SELECT * FROM product_expanded
+SET product_size = '1/2 kg', product_qty_type = 'kg'
+WHERE product_id = 26;
+
+-- delete our almonds
+DELETE FROM product_expanded
+--SELECT * FROM product_expanded
+WHERE product_id = 26;
+
+SELECT * from product_expanded

04_this_cohort/live_code/module_5/INSERT_UPDATE_FOR_DYNAMIC_VIEW.sql

@@ -0,0 +1,5 @@
+UPDATE new_customer_purchases
+SET market_date = DATE('now')
+
+INSERT INTO market_date_info
+VALUES('2025-04-23','Wednesday','17','2025','8:00 AM','2:00 PM', 'nothing interesting','Spring', '20','28',0,0);

04_this_cohort/live_code/module_5/LIVE_DYNAMIC_VIEW.sql

@@ -0,0 +1,40 @@
+--VIEW
+-- THIS ONLY WORKS IF YOU HAVE THE PROPER STEPS
+-- IMPORT as csv 
+-- ?? update the market date info table to also have todays date!
+-- UPDATING THE NEW DATA TO "TODAY" in the where statement
+
+
+DROP VIEW IF EXISTS vendor_daily_sales;
+CREATE VIEW IF NOT EXISTS vendor_daily_sales AS
+
+	SELECT 
+	md.market_date
+	,market_day
+	,market_year
+	,vendor_name
+	,SUM(quantity*cost_to_customer_per_qty) as sales
+
+	-- want to update the VIEW
+	-- need to bring in the new data 
+	-- new data is called new_customer_purchases
+	--but we want the old data too!
+	--....use a union to combine old and new
+
+	FROM market_date_info md
+
+	INNER JOIN (
+		SELECT * FROM 
+		customer_purchases 
+		UNION 
+		SELECT * FROM 
+		new_customer_purchases ) as cp
+			ON md.market_date = cp.market_date
+	INNER JOIN vendor v
+		ON v.vendor_id = cp.vendor_id
+
+	-- we want TODAYS data only
+	WHERE md.market_date = date('now')
+
+	GROUP BY cp.market_date, v.vendor_id
+

04_this_cohort/live_code/module_5/SELF_JOIN.sql

@@ -0,0 +1,22 @@
+-- SELF JOIN
+drop table if exists temp.employees;
+create temp table temp.employees
+(
+emp_id int,
+emp_name text,
+mgr_id int
+);
+
+insert into temp.employees
+Values(1,'Thomas',3)
+,(2,'Laura',4)
+,(3,'Rohan',null)
+,(4,'Jennie',3);
+
+
+SELECT * FROM temp.employees
+
+select a.emp_name,b.emp_name as mgr_name 
+from temp.employees a
+left join temp.employees b
+	on a.mgr_id = b.emp_id

04_this_cohort/live_code/module_5/VIEW_IN_ANOTHER_QUERY.sql

@@ -0,0 +1,12 @@
+-- using a view in another query
+SELECT 
+market_year
+,market_week
+,vendor_name
+,SUM(sales) as weekly_sales
+
+FROM vendor_daily_sales
+
+GROUP BY market_year
+,market_week
+,vendor_name