diff --git a/02_activities/assignments/Cohort_8/Assignment-two_1-3.pdf b/02_activities/assignments/Cohort_8/Assignment-two_1-3.pdf new file mode 100644 index 000000000..885aefcdb Binary files /dev/null and b/02_activities/assignments/Cohort_8/Assignment-two_1-3.pdf differ diff --git a/02_activities/assignments/Cohort_8/SQL A-1 Part 1.pdf b/02_activities/assignments/Cohort_8/SQL A-1 Part 1.pdf new file mode 100644 index 000000000..b03c1af39 Binary files /dev/null and b/02_activities/assignments/Cohort_8/SQL A-1 Part 1.pdf differ diff --git a/02_activities/assignments/Cohort_8/assignment1.sql b/02_activities/assignments/Cohort_8/assignment1.sql index c992e3205..b533c64af 100644 --- a/02_activities/assignments/Cohort_8/assignment1.sql +++ b/02_activities/assignments/Cohort_8/assignment1.sql @@ -5,16 +5,31 @@ --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 = 4 +AND product_id = 9 + /*2. Write a query that returns all customer purchases and a new calculated column 'price' (quantity * cost_to_customer_per_qty), @@ -24,9 +39,29 @@ filtered by customer IDs between 8 and 10 (inclusive) using either: */ -- option 1 +SELECT +quantity, +customer_id, +cost_to_customer_per_qty, +quantity * cost_to_customer_per_qty AS price + +FROM customer_purchases + +WHERE + customer_id >= 8 AND customer_id <= 10; + -- option 2 +SELECT +quantity, +customer_id, +cost_to_customer_per_qty, +quantity * cost_to_customer_per_qty AS price + +FROM customer_purchases + +WHERE customer_id BETWEEN 8 AND 10; --CASE @@ -35,19 +70,48 @@ 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 product_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 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 * + +FROM vendor + +INNER JOIN vendor_booth_assignments + ON vendor.vendor_id = vendor_booth_assignments.vendor_id + ORDER BY vendor_name, market_date; /* SECTION 3 */ @@ -56,7 +120,13 @@ 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 num_of_booth +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 +134,19 @@ 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 * + ,SUM(quantity*cost_to_customer_per_qty) AS total_spend + +FROM customer_purchases AS cp + INNER JOIN customer AS c + ON cp.customer_id = c.customer_id + +GROUP BY customer_first_name, customer_last_name + +HAVING total_spend > 2000 +ORDER BY +customer_last_name, customer_first_name; --Temp Table /* 1. Insert the original vendor table into a temp.new_vendor and then add a 10th vendor: @@ -78,19 +160,18 @@ When inserting the new vendor, you need to appropriately align the columns to be VALUES(col1,col2,col3,col4,col5) */ +DROP TABLE IF EXISTS temp.new_vendor; +CREATE TABLE temp.new_vendor AS --- Date -/*1. Get the customer_id, month, and year (in separate columns) of every purchase in the customer_purchases table. +SELECT * -HINT: you might need to search for strfrtime modifers sqlite on the web to know what the modifers for month -and year are! */ +FROM vendor; +INSERT INTO temp.new_vendor (vendor_id, vendor_name, vendor_type, vendor_owner_first_name, vendor_owner_last_name) +VALUES (10, 'Thomas Superfood Store', 'Fresh Focused Store', 'Thomas', 'Rental'); -/* 2. Using the previous query as a base, determine how much money each customer spent in April 2022. -Remember that money spent is quantity*cost_to_customer_per_qty. +SELECT * FROM new_vendor; -HINTS: you will need to AGGREGATE, GROUP BY, and filter... -but remember, STRFTIME returns a STRING for your WHERE statement!! */ diff --git a/02_activities/assignments/Cohort_8/assignment2.sql b/02_activities/assignments/Cohort_8/assignment2.sql index c2743d3b7..5f6e7e3d7 100644 --- a/02_activities/assignments/Cohort_8/assignment2.sql +++ b/02_activities/assignments/Cohort_8/assignment2.sql @@ -6,22 +6,17 @@ We tell them, no problem! We can produce a list with all of the appropriate details. Using the following syntax you create our super cool and not at all needy manager a list: - -SELECT +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. -**HINT**: keep the syntax the same, but edited the correct components with the string. -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 * +,NULLIF(product_size,'NULL') as product_size_null +,coalesce(NULLIF(product_size,'NULL'),'') as balnk_product_size +,NULLIF(product_qty_type,'NULL') as product_qty_type_null +,coalesce(NULLIF(product_qty_type,'NULL'),'unit') as unit_product_qty_type +FROM product; --Windowed Functions @@ -34,6 +29,11 @@ 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 + customer_id, + market_date, + DENSE_RANK() OVER (PARTITION BY customer_id ORDER BY market_date ASC) 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, @@ -41,11 +41,24 @@ then write another query that uses this one as a subquery (or temp table) and fi only the customer’s most recent visit. */ +SELECT * FROM ( + SELECT + customer_id, + market_date, + DENSE_RANK() OVER (PARTITION BY customer_id ORDER BY market_date DESC) as visit_number + FROM customer_purchases +) +WHERE visit_number = 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 + customer_id, + product_id, + COUNT(product_id) OVER (PARTITION BY customer_id, product_id) as purchase_count +FROM customer_purchases; -- String manipulations /* 1. Some product names in the product table have descriptions like "Jar" or "Organic". @@ -58,11 +71,14 @@ 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. */ - - - /* 2. Filter the query to show any product_size value that contain a number with REGEXP. */ +SELECT *, +CASE WHEN INSTR(product_name,'-') > 0 + THEN LTRIM(RTRIM(SUBSTR(product_name,INSTR(product_name,'-')+1))) + ELSE NULL END AS description +FROM product +WHERE product_size REGEXP '[0-9]'; -- UNION @@ -71,10 +87,30 @@ Hint: you might need to use INSTR(product_name,'-') to find the hyphens. INSTR w HINT: There are a possibly a few ways to do this query, but if you're struggling, try the following: 1) Create a CTE/Temp Table to find sales values grouped dates; 2) Create another CTE/Temp table with a rank windowed function on the previous query to create -"best day" and "worst day"; +"best day" and "worst day"; 3) Query the second temp table twice, once for the best day, once for the worst day, with a UNION binding them. */ +WITH DailySales AS ( + SELECT + market_date, + SUM(quantity * cost_to_customer_per_qty) as total_sales + FROM customer_purchases + GROUP BY market_date +) +SELECT * FROM ( + SELECT market_date, total_sales, 'Highest Sales' as category + FROM DailySales + ORDER BY total_sales DESC + LIMIT 1 +) +UNION +SELECT * FROM ( + SELECT market_date, total_sales, 'Lowest Sales' as category + FROM DailySales + ORDER BY total_sales ASC + LIMIT 1 +); @@ -92,6 +128,22 @@ How many customers are there (y). Before your final group by you should have the product of those two queries (x*y). */ +WITH CustomerCount AS ( + SELECT COUNT(DISTINCT customer_id) as cust_count FROM customer +), +UniqueProducts AS ( + SELECT DISTINCT vendor_id, product_id, original_price + FROM vendor_inventory +) +SELECT + v.vendor_name, + p.product_name, + (up.original_price * 5 * cc.cust_count) as potential_revenue +FROM UniqueProducts up +JOIN vendor v ON up.vendor_id = v.vendor_id +JOIN product p ON up.product_id = p.product_id +CROSS JOIN CustomerCount cc; + -- INSERT /*1. Create a new table "product_units". @@ -99,11 +151,15 @@ 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'; +-- Next, insert a new row (e.g., a new Apple Pie record). -/*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 (9999, 'Apple Pie', 'Large', 1, 'unit', CURRENT_TIMESTAMP); -- DELETE @@ -111,6 +167,9 @@ 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_name = 'Apple Pie' +AND product_id != 999; -- UPDATE @@ -131,5 +190,22 @@ 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. */ +-- Step 1: Add the column +ALTER TABLE product_units +ADD current_quantity INT; +-- Step 2: Update the column with the most recent inventory quantity +UPDATE product_units +SET current_quantity = ( + SELECT COALESCE(quantity, 0) + FROM vendor_inventory vi + WHERE vi.product_id = product_units.product_id + ORDER BY market_date DESC + LIMIT 1 +) +WHERE EXISTS ( + SELECT 1 + FROM vendor_inventory vi + WHERE vi.product_id = product_units.product_id +);