diff --git a/02_activities/assignments/Microcredential_Cohort/Bookstore_logical_model.pdf b/02_activities/assignments/Microcredential_Cohort/Bookstore_logical_model.pdf new file mode 100644 index 000000000..117a7aad3 Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/Bookstore_logical_model.pdf differ diff --git a/02_activities/assignments/Microcredential_Cohort/ERDIAGRAM.pdf b/02_activities/assignments/Microcredential_Cohort/ERDIAGRAM.pdf new file mode 100644 index 000000000..10d44547a Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/ERDIAGRAM.pdf differ diff --git a/02_activities/assignments/Microcredential_Cohort/PROMPT3.pdf b/02_activities/assignments/Microcredential_Cohort/PROMPT3.pdf new file mode 100644 index 000000000..dd55d17ff Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/PROMPT3.pdf differ diff --git a/02_activities/assignments/Microcredential_Cohort/assignment1.sql b/02_activities/assignments/Microcredential_Cohort/assignment1.sql index 2ec561e2a..16584a881 100644 --- a/02_activities/assignments/Microcredential_Cohort/assignment1.sql +++ b/02_activities/assignments/Microcredential_Cohort/assignment1.sql @@ -6,7 +6,8 @@ --SELECT /* 1. Write a query that returns everything in the customer table. */ --QUERY 1 - +SELECT * +FROM customer; @@ -16,7 +17,10 @@ /* 2. Write a query that displays all of the columns and 10 rows from the customer table, sorted by customer_last_name, then customer_first_ name. */ --QUERY 2 - +SELECT * +FROM customer +ORDER BY customer_last_name, customer_first_name +LIMIT 10; @@ -27,7 +31,10 @@ sorted by customer_last_name, then customer_first_ name. */ /* 1. Write a query that returns all customer purchases of product IDs 4 and 9. Limit to 25 rows of output. */ --QUERY 3 - +SELECT * +FROM customer_purchases +WHERE product_id IN (4, 9) +LIMIT 25; @@ -42,7 +49,11 @@ filtered by customer IDs between 8 and 10 (inclusive) using either: Limit to 25 rows of output. */ --QUERY 4 - +SELECT *, + quantity * cost_to_customer_per_qty AS price +FROM customer_purchases +WHERE customer_id BETWEEN 8 AND 10 +LIMIT 25; @@ -55,7 +66,13 @@ 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.” */ --QUERY 5 - +SELECT product_id, + product_name, + CASE + WHEN product_qty_type = 'unit' THEN 'unit' + ELSE 'bulk' + END AS prod_qty_type_condensed +FROM product; @@ -66,7 +83,17 @@ if the product_qty_type is “unit,” and otherwise displays the word “bulk. 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. */ --QUERY 6 - +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; @@ -78,7 +105,18 @@ contains the word “pepper” (regardless of capitalization), and otherwise out vendor_id field they both have in common, and sorts the result by market_date, then vendor_name. Limit to 24 rows of output. */ --QUERY 7 - +SELECT v.vendor_id, + v.vendor_name, + v.vendor_type, + v.vendor_owner_first_name, + v.vendor_owner_last_name, + vba.booth_number, + vba.market_date +FROM vendor AS v +INNER JOIN vendor_booth_assignments AS vba + ON v.vendor_id = vba.vendor_id +ORDER BY vba.market_date, v.vendor_name +LIMIT 24; @@ -92,7 +130,11 @@ Limit to 24 rows of output. */ /* 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. */ --QUERY 8 - +SELECT vendor_id, + COUNT(*) AS times_rented +FROM vendor_booth_assignments +GROUP BY vendor_id +ORDER BY vendor_id; @@ -105,7 +147,15 @@ 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. */ --QUERY 9 - +SELECT c.customer_last_name, + c.customer_first_name, + SUM(cp.quantity * cp.cost_to_customer_per_qty) AS total_spent +FROM customer AS c +INNER JOIN customer_purchases AS cp + ON c.customer_id = cp.customer_id +GROUP BY c.customer_id +HAVING total_spent > 2000 +ORDER BY c.customer_last_name, c.customer_first_name; @@ -124,10 +174,17 @@ When inserting the new vendor, you need to appropriately align the columns to be VALUES(col1,col2,col3,col4,col5) */ --QUERY 10 - - - - +CREATE TEMPORARY TABLE temp.new_vendor AS +SELECT * FROM vendor; + +INSERT INTO temp.new_vendor + (vendor_id, vendor_name, vendor_type, + vendor_owner_first_name, vendor_owner_last_name) +VALUES + (10, 'Thomass Superfood Store', 'Fresh Focused', + 'Thomas', 'Rosenthal'); + +SELECT * FROM temp.new_vendor; --END QUERY @@ -138,7 +195,11 @@ HINT: you might need to search for strfrtime modifers sqlite on the web to know and year are! Limit to 25 rows of output. */ --QUERY 11 - +SELECT customer_id, + STRFTIME('%m', market_date) AS purchase_month, + STRFTIME('%Y', market_date) AS purchase_year +FROM customer_purchases +LIMIT 25; @@ -152,7 +213,13 @@ HINTS: you will need to AGGREGATE, GROUP BY, and filter... but remember, STRFTIME returns a STRING for your WHERE statement... AND be sure you remove the LIMIT from the previous query before aggregating!! */ --QUERY 12 - +SELECT customer_id, + SUM(quantity * cost_to_customer_per_qty) AS total_spent +FROM customer_purchases +WHERE STRFTIME('%m', market_date) = '04' + AND STRFTIME('%Y', market_date) = '2022' +GROUP BY customer_id +ORDER BY customer_id; diff --git a/02_activities/assignments/Microcredential_Cohort/assignment2.sql b/02_activities/assignments/Microcredential_Cohort/assignment2.sql index 4079c18ae..b2a96969a 100644 --- a/02_activities/assignments/Microcredential_Cohort/assignment2.sql +++ b/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, '') || ' (' || COALESCE(product_qty_type, 'unit') || ')' +FROM product; --END QUERY @@ -40,7 +42,19 @@ 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(). Filter the visits to dates before April 29, 2022. */ --QUERY 2 - +SELECT + customer_id, + market_date, + vendor_id, + product_id, + quantity, + cost_to_customer_per_qty, + DENSE_RANK() OVER ( + PARTITION BY customer_id + ORDER BY market_date + ) AS visit_number +FROM customer_purchases +WHERE market_date < '2022-04-29'; @@ -52,7 +66,22 @@ then write another query that uses this one as a subquery (or temp table) and fi only the customer’s most recent visit. HINT: Do not use the previous visit dates filter. */ --QUERY 3 - +SELECT * +FROM ( + SELECT + customer_id, + market_date, + vendor_id, + product_id, + quantity, + cost_to_customer_per_qty, + DENSE_RANK() OVER ( + PARTITION BY customer_id + ORDER BY market_date DESC + ) AS visit_number_desc + FROM customer_purchases +) AS ranked_visits +WHERE visit_number_desc = 1; @@ -65,7 +94,19 @@ customer_purchases table that indicates how many different times that customer h You can make this a running count by including an ORDER BY within the PARTITION BY if desired. Filter the visits to dates before April 29, 2022. */ --QUERY 4 - +SELECT + customer_id, + market_date, + vendor_id, + product_id, + quantity, + cost_to_customer_per_qty, + COUNT(*) OVER ( + PARTITION BY customer_id, product_id + ORDER BY market_date + ) AS purchase_count_running +FROM customer_purchases +WHERE market_date < '2022-04-29'; @@ -84,7 +125,14 @@ 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_name, + CASE + WHEN INSTR(product_name, '-') > 0 + THEN TRIM(SUBSTR(product_name, INSTR(product_name, '-') + 1)) + ELSE NULL + END AS description +FROM product; @@ -93,7 +141,16 @@ 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_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]'; @@ -110,7 +167,30 @@ 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. */ --QUERY 7 - +WITH daily_sales AS ( + SELECT + market_date, + ROUND(SUM(quantity * cost_to_customer_per_qty), 2) AS total_sales + FROM customer_purchases + GROUP BY market_date +), +ranked_sales AS ( + SELECT + market_date, + total_sales, + RANK() OVER (ORDER BY total_sales DESC) AS rank_best, + RANK() OVER (ORDER BY total_sales ASC) AS rank_worst + FROM daily_sales +) +SELECT market_date, total_sales, 'Best Day' AS label +FROM ranked_sales +WHERE rank_best = 1 + +UNION + +SELECT market_date, total_sales, 'Worst Day' AS label +FROM ranked_sales +WHERE rank_worst = 1; @@ -131,7 +211,23 @@ 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). */ --QUERY 8 - +SELECT + v.vendor_name, + p.product_name, + vi.original_price, + COUNT(DISTINCT c.customer_id) AS num_customers, + 5 * COUNT(DISTINCT c.customer_id) * vi.original_price AS total_revenue +FROM ( + SELECT DISTINCT vendor_id, product_id, original_price + FROM vendor_inventory +) AS vi +CROSS JOIN ( + SELECT DISTINCT customer_id FROM customer +) AS c +JOIN vendor v ON v.vendor_id = vi.vendor_id +JOIN product p ON p.product_id = vi.product_id +GROUP BY v.vendor_name, p.product_name, vi.original_price +ORDER BY v.vendor_name, p.product_name; @@ -144,7 +240,12 @@ 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`. */ --QUERY 9 - +CREATE TABLE IF NOT EXISTS product_units AS +SELECT + *, + CURRENT_TIMESTAMP AS snapshot_timestamp +FROM product +WHERE product_qty_type = 'unit'; @@ -154,7 +255,22 @@ Name the timestamp column `snapshot_timestamp`. */ /*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). */ --QUERY 10 - +INSERT INTO product_units ( + product_id, + product_name, + product_size, + product_category_id, + product_qty_type, + snapshot_timestamp +) +VALUES ( + 999, + 'Apple Pie', + 'whole', + 1, + 'unit', + CURRENT_TIMESTAMP +); @@ -166,7 +282,13 @@ 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 + AND snapshot_timestamp = ( + SELECT MIN(snapshot_timestamp) + FROM product_units + WHERE product_id = 999 + ); @@ -190,9 +312,21 @@ 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. */ --QUERY 12 +ALTER TABLE product_units +ADD current_quantity INT; - - +UPDATE product_units +SET current_quantity = ( + SELECT COALESCE(vi.quantity, 0) + FROM vendor_inventory vi + WHERE vi.product_id = product_units.product_id + AND vi.market_date = ( + SELECT MAX(vi2.market_date) + FROM vendor_inventory vi2 + WHERE vi2.product_id = product_units.product_id + ) + LIMIT 1 +); --END QUERY