diff --git a/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt1.png b/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt1.png new file mode 100644 index 000000000..d5261f76c Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt1.png differ diff --git a/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt2.png b/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt2.png new file mode 100644 index 000000000..79f7d9911 Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/Assignment2Prompt2.png differ diff --git a/02_activities/assignments/Microcredential_Cohort/assignment1.sql b/02_activities/assignments/Microcredential_Cohort/assignment1.sql index 2ec561e2a..861a32d0f 100644 --- a/02_activities/assignments/Microcredential_Cohort/assignment1.sql +++ b/02_activities/assignments/Microcredential_Cohort/assignment1.sql @@ -7,7 +7,8 @@ /* 1. Write a query that returns everything in the customer table. */ --QUERY 1 - +SELECT * +FROM customer; --END QUERY @@ -17,7 +18,10 @@ sorted by customer_last_name, then customer_first_ name. */ --QUERY 2 - +SELECT * +FROM customer +ORDER BY customer_last_name ASC, customer_first_name ASC +LIMIT 10; --END QUERY @@ -28,7 +32,10 @@ sorted by customer_last_name, then customer_first_ name. */ Limit to 25 rows of output. */ --QUERY 3 - +SELECT * +FROM customer_purchases +WHERE product_id in (4,9) +LIMIT 25; --END QUERY @@ -43,7 +50,11 @@ 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; --END QUERY @@ -56,7 +67,15 @@ columns and add a column called prod_qty_type_condensed that displays the word 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; --END QUERY @@ -67,6 +86,22 @@ add a column to the previous query called pepper_flag that outputs a 1 if the pr 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; @@ -79,6 +114,13 @@ vendor_id field they both have in common, and sorts the result by market_date, t Limit to 24 rows of output. */ --QUERY 7 +SELECT * + +FROM vendor as v +INNER JOIN vendor_booth_assignments as vba + on v.vendor_id = vba.vendor_id +ORDER BY vba.market_date ASC, v.vendor_name ASC +LIMIT 24; @@ -93,6 +135,14 @@ Limit to 24 rows of output. */ at the farmer’s market by counting the vendor booth assignments per vendor_id. */ --QUERY 8 +SELECT vendor_id, +booth_number, +COUNT (* ) as booth_rental_count + +FROM vendor_booth_assignments + +GROUP BY vendor_id, booth_number +ORDER BY vendor_id, booth_number; @@ -105,6 +155,25 @@ 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 cp.customer_id, +customer_first_name, +customer_last_name, +SUM(quantity* cost_to_customer_per_qty) AS total_spend + +FROM customer as c +INNER JOIN customer_purchases as cp + ON c.customer_id = cp.customer_id + +GROUP BY + c.customer_id, + c.customer_last_name, -- weirdly the query fails when not grouped by names depite having the id + c.customer_first_name + +HAVING SUM(quantity* cost_to_customer_per_qty) > 2000 + +ORDER BY + c.customer_last_name, + c.customer_first_name; @@ -124,9 +193,17 @@ When inserting the new vendor, you need to appropriately align the columns to be VALUES(col1,col2,col3,col4,col5) */ --QUERY 10 +DROP TABLE IF EXISTS temp.new_vendor; +CREATE 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 @@ -139,6 +216,12 @@ 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; @@ -153,6 +236,17 @@ 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 money_spent + +FROM customer_purchases + +WHERE strftime('%Y', market_date) = '2022' + AND strftime('%m', market_date) = '04' + + +GROUP BY customer_id; + diff --git a/02_activities/assignments/Microcredential_Cohort/assignment2.sql b/02_activities/assignments/Microcredential_Cohort/assignment2.sql index 4079c18ae..66f749f6d 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 +42,14 @@ 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 *, +DENSE_RANK() OVER ( + PARTITION BY customer_id + ORDER BY market_date + ) AS visit_number +FROM customer_purchases +WHERE market_date < '2022-04-29' +ORDER BY customer_id, market_date ASC; @@ -52,10 +61,26 @@ 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 + customer_id, + market_date as most_recent_visit +FROM ( + SELECT + customer_id, + market_date, + ROW_NUMBER() OVER ( + PARTITION BY customer_id + ORDER BY market_date DESC + ) AS visit_number + FROM ( + SELECT DISTINCT + customer_id, + market_date + FROM customer_purchases + ) AS unique_visits +) AS numbered_visits +WHERE visit_number = 1 +ORDER BY customer_id; --END QUERY @@ -65,8 +90,18 @@ 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, + product_id, + quantity, + COUNT(*) OVER ( + PARTITION BY customer_id, product_id + ORDER BY market_date + ) AS product_purchase_running_count +FROM customer_purchases +WHERE market_date < '2022-04-29' +ORDER BY customer_id, product_id, market_date; --END QUERY @@ -85,7 +120,19 @@ 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; --END QUERY @@ -94,8 +141,21 @@ 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]'; --END QUERY @@ -111,7 +171,42 @@ HINT: There are a possibly a few ways to do this query, but if you're struggling with a UNION binding them. */ --QUERY 7 - +WITH sales_by_date 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 DESC + ) AS highest_sales_rank, + RANK() OVER ( + ORDER BY total_sales ASC + ) AS lowest_sales_rank + FROM sales_by_date +) + +SELECT + market_date, + total_sales, + 'Highest Sales' AS sales_type +FROM ranked_sales +WHERE highest_sales_rank = 1 + +UNION + +SELECT + market_date, + total_sales, + 'Lowest Sales' AS sales_type +FROM ranked_sales +WHERE lowest_sales_rank = 1; --END QUERY @@ -133,7 +228,39 @@ Before your final group by you should have the product of those two queries (x*y --QUERY 8 - +WITH vendor_products AS ( + SELECT DISTINCT + vendor_id, + product_id, + original_price + FROM vendor_inventory +), + +vendor_product_customer 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 * vpc.original_price) AS total_sales +FROM vendor_product_customer AS vpc +JOIN vendor AS v + ON vpc.vendor_id = v.vendor_id +JOIN product AS p + ON vpc.product_id = p.product_id +GROUP BY + v.vendor_name, + p.product_name +ORDER BY + v.vendor_name, + p.product_name; --END QUERY @@ -144,9 +271,19 @@ 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 product_units AS +SELECT + *, + CURRENT_TIMESTAMP AS snapshot_timestamp +FROM product +WHERE 1 = 0; - - +INSERT INTO product_units +SELECT + *, + CURRENT_TIMESTAMP AS snapshot_timestamp +FROM product +WHERE product_qty_type = 'unit'; --END QUERY @@ -154,7 +291,13 @@ 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 +SELECT + *, + CURRENT_TIMESTAMP AS snapshot_timestamp +FROM product +WHERE product_name = 'Apple Pie' +LIMIT 1; @@ -166,7 +309,13 @@ 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_name = 'Apple Pie' + AND snapshot_timestamp < ( + SELECT MAX(snapshot_timestamp) + FROM product_units + WHERE product_name = 'Apple Pie' + ); @@ -190,9 +339,26 @@ 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 = COALESCE( + ( + SELECT + quantity + FROM vendor_inventory + WHERE vendor_inventory.product_id = product_units.product_id + ORDER BY market_date DESC + LIMIT 1 + ), + 0 +); + +SELECT + * +FROM product_units +ORDER BY product_id; --END QUERY diff --git a/02_activities/assignments/Microcredential_Cohort/vendor-booth-assgn.jpeg b/02_activities/assignments/Microcredential_Cohort/vendor-booth-assgn.jpeg new file mode 100644 index 000000000..d4f4138e9 Binary files /dev/null and b/02_activities/assignments/Microcredential_Cohort/vendor-booth-assgn.jpeg differ