diff --git a/02_activities/assignments/Cohort_8/Bookstore ERD.pdf b/02_activities/assignments/Cohort_8/Bookstore ERD.pdf new file mode 100644 index 000000000..8ce5272a3 Binary files /dev/null and b/02_activities/assignments/Cohort_8/Bookstore ERD.pdf differ diff --git a/02_activities/assignments/Cohort_8/asn1_logical_data_model.png b/02_activities/assignments/Cohort_8/asn1_logical_data_model.png new file mode 100644 index 000000000..f9629065e Binary files /dev/null and b/02_activities/assignments/Cohort_8/asn1_logical_data_model.png differ diff --git a/02_activities/assignments/Cohort_8/assignment1.sql b/02_activities/assignments/Cohort_8/assignment1.sql index c992e3205..017053054 100644 --- a/02_activities/assignments/Cohort_8/assignment1.sql +++ b/02_activities/assignments/Cohort_8/assignment1.sql @@ -4,17 +4,24 @@ --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, 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. */ - +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), @@ -22,11 +29,23 @@ filtered by customer IDs between 8 and 10 (inclusive) using either: 1. two conditions using AND 2. one condition using BETWEEN */ + -- option 1 +SELECT *, + quantity * cost_to_customer_per_qty AS price +FROM customer_purchases +WHERE customer_id >= 8 + AND customer_id <= 10; + + -- option 2 +SELECT *, + quantity * cost_to_customer_per_qty AS price +FROM customer_purchases +WHERE customer_id BETWEEN 8 AND 10; --CASE @@ -35,19 +54,46 @@ Using the product table, write a query that outputs the product_id and product_n 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 LOWER(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.*, + vba.* +FROM vendor AS v +INNER JOIN vendor_booth_assignments AS vba + ON v.vendor_id = vba.vendor_id +ORDER BY + v.vendor_name, + vba.market_date; /* SECTION 3 */ @@ -56,7 +102,11 @@ vendor_id field they both have in common, and sorts the result by vendor_name, t /* 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(*) AS times_rented +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 @@ -64,7 +114,23 @@ 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_first_name, + c.customer_last_name, + SUM(cp.quantity * cp.cost_to_customer_per_qty) AS total_spent +FROM customer AS c +JOIN customer_purchases AS cp + ON c.customer_id = cp.customer_id +GROUP BY + c.customer_id, + c.customer_first_name, + c.customer_last_name +HAVING + total_spent > 2000 +ORDER BY + c.customer_last_name, + c.customer_first_name; --Temp Table /* 1. Insert the original vendor table into a temp.new_vendor and then add a 10th vendor: @@ -78,6 +144,15 @@ When inserting the new vendor, you need to appropriately align the columns to be VALUES(col1,col2,col3,col4,col5) */ +DROP TABLE IF EXISTS new_vendor; +CREATE TEMPORARY TABLE new_vendor AS +SELECT * FROM vendor; + +INSERT INTO new_vendor (vendor_id, vendor_name, vendor_type, vendor_owner_first_name, vendor_owner_last_name) +VALUES (10, 'Thomas''s Superfood Store', 'Fresh Focused', 'Thomas', 'Rosenthal'); + + +SELECT * FROM new_vendor ORDER BY vendor_id; -- Date diff --git a/02_activities/assignments/Cohort_8/assignment2.sql b/02_activities/assignments/Cohort_8/assignment2.sql index c2743d3b7..8a828c72d 100644 --- a/02_activities/assignments/Cohort_8/assignment2.sql +++ b/02_activities/assignments/Cohort_8/assignment2.sql @@ -11,7 +11,6 @@ SELECT product_name || ', ' || product_size|| ' (' || product_qty_type || ')' FROM product - But wait! The product table has some bad data (a few NULL values). Find the NULLs and then using COALESCE, replace the NULL with a blank for the first column with nulls, and 'unit' for the second column with nulls. @@ -21,7 +20,18 @@ 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, + product_size, + product_qty_type +FROM product +WHERE product_name IS NULL + OR product_size IS NULL + OR product_qty_type IS NULL;*/ + +SELECT + product_name || ', ' || COALESCE(product_size, '') || ' (' || COALESCE(product_qty_type, 'unit') || ')' +FROM product; --Windowed Functions @@ -35,17 +45,46 @@ each new market date for each customer, or select only the unique market dates p 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 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 + customer_id, + market_date, + DENSE_RANK() OVER ( + PARTITION BY customer_id + ORDER BY market_date DESC + ) AS reverse_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 * FROM customer_purchases LIMIT 1; +SELECT + customer_id, + product_id, + vendor_id, + market_date, + quantity, + cost_to_customer_per_qty, + transaction_time, + COUNT(*) OVER ( + PARTITION BY customer_id, product_id + ) AS times_purchased +FROM customer_purchases; -- String manipulations /* 1. Some product names in the product table have descriptions like "Jar" or "Organic". @@ -58,12 +97,24 @@ Remove any trailing or leading whitespaces. Don't just use a case statement for | Habanero Peppers - Organic | Organic | 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_id, + product_name, + product_size +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. @@ -75,7 +126,41 @@ 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. */ +--1 +WITH daily_sales AS ( + SELECT + market_date, + SUM(quantity * cost_to_customer_per_qty) AS total_sales + FROM customer_purchases + GROUP BY market_date +) + +--2 +, ranked_sales AS ( + SELECT + market_date, + total_sales, + RANK() OVER (ORDER BY total_sales DESC) AS sales_rank_desc, + RANK() OVER (ORDER BY total_sales ASC) AS sales_rank_asc + FROM daily_sales +) + +--3 +SELECT + market_date, + total_sales, + 'Highest Sales Day' AS sales_type +FROM ranked_sales +WHERE sales_rank_desc = 1 + +UNION +SELECT + market_date, + total_sales, + 'Lowest Sales Day' AS sales_type +FROM ranked_sales +WHERE sales_rank_asc = 1; /* SECTION 3 */ @@ -91,7 +176,26 @@ 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 DISTINCT + v.vendor_name, + p.product_name, + vi.original_price + FROM vendor_inventory vi + JOIN vendor v ON vi.vendor_id = v.vendor_id + JOIN product p ON vi.product_id = p.product_id +), +distinct_customers AS ( + SELECT COUNT(DISTINCT customer_id) AS total_customers + FROM customer +) +SELECT + vp.vendor_name, + vp.product_name, + 5 * vp.original_price * dc.total_customers AS potential_revenue +FROM vendor_products vp +CROSS JOIN distinct_customers dc +ORDER BY potential_revenue DESC; -- INSERT /*1. Create a new table "product_units". @@ -99,11 +203,42 @@ 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 + product_id, + product_name, + product_size, + product_category_id, + product_qty_type, + CURRENT_TIMESTAMP AS snapshot_timestamp +FROM product +WHERE product_qty_type = 'unit'; + +--Verify the product_units table was created +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 ( + product_id, + product_name, + product_size, + product_category_id, + product_qty_type, + snapshot_timestamp +) +VALUES ( + (SELECT MAX(product_id) + 1 FROM product_units), + 'Chocolate Chip Cookies', + '12 oz', + 3, -- Assuming 3 is the baked goods category + 'unit', + CURRENT_TIMESTAMP +); +SELECT * FROM product_units ORDER BY product_id DESC LIMIT 5; -- DELETE @@ -111,6 +246,9 @@ 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.*/ +DELETE FROM product_units WHERE product_id = 24; + +SELECT * FROM product_units WHERE product_id = 24; -- UPDATE @@ -131,5 +269,44 @@ 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. */ +--Add the column +ALTER TABLE product_units +ADD current_quantity INT; +--Verify column added +SELECT * FROM product_units LIMIT 1; + +--Find products in product_units that have NO vendor_inventory data +SELECT pu.product_id, pu.product_name +FROM product_units pu +LEFT JOIN vendor_inventory vi ON pu.product_id = vi.product_id +WHERE vi.product_id IS NULL +GROUP BY pu.product_id, pu.product_name; + +--Write the UPDATE with COALESCE to handle NULLs +/*UPDATE product_units +SET current_quantity = ( + SELECT COALESCE(vi.quantity, 0) + FROM vendor_inventory vi + WHERE vi.product_id = product_units.product_id + ORDER BY vi.market_date DESC + LIMIT 1 +);*/ + +UPDATE product_units +SET current_quantity = COALESCE( + ( + SELECT quantity + FROM vendor_inventory vi + WHERE vi.product_id = product_units.product_id + ORDER BY market_date DESC + LIMIT 1 + ), + 0 +); + +--Verify the UPDATE worked +SELECT product_id, product_name, current_quantity +FROM product_units +ORDER BY product_id;