Shopify data engineering internship challenge 2024

sql/task1.sql

@@ -1,14 +1,34 @@
 -- Problem 1: Retrieve all products in the Sports category
 -- Write an SQL query to retrieve all products in a specific category.
+SELECT *
+FROM Products
+INNER JOIN Categories ON Products.category_id = Categories.category_id
+WHERE Categories.category_name LIKE '%Sports%';
 
 -- Problem 2: Retrieve the total number of orders for each user
 -- Write an SQL query to retrieve the total number of orders for each user.
 -- The result should include the user ID, username, and the total number of orders.
+SELECT Users.user_id, Users.username, COUNT(Orders.order_id) AS total_orders
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+GROUP BY Users.user_id;
+
 
 -- Problem 3: Retrieve the average rating for each product
 -- Write an SQL query to retrieve the average rating for each product.
 -- The result should include the product ID, product name, and the average rating.
+SELECT Products.product_id, Products.product_name, AVG(Reviews.rating) AS average_rating
+FROM Products
+INNER JOIN Reviews ON Products.product_id = Reviews.product_id
+GROUP BY Products.product_id;
+
 
 -- Problem 4: Retrieve the top 5 users with the highest total amount spent on orders
 -- Write an SQL query to retrieve the top 5 users with the highest total amount spent on orders.
 -- The result should include the user ID, username, and the total amount spent.
+SELECT Users.user_id, Users.username, SUM(Orders.total_amount) AS total_amount_spent
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+GROUP BY Users.user_id
+ORDER BY total_amount_spent DESC
+LIMIT 5;

sql/task2.sql

@@ -2,18 +2,42 @@
 -- Write an SQL query to retrieve the products with the highest average rating.
 -- The result should include the product ID, product name, and the average rating.
 -- Hint: You may need to use subqueries or common table expressions (CTEs) to solve this problem.
+SELECT Products.product_id, Products.product_name, AVG(Reviews.rating) AS average_rating
+FROM Products
+INNER JOIN Reviews ON Products.product_id = Reviews.product_id
+GROUP BY Products.product_id
+ORDER BY average_rating DESC
+LIMIT 1;
 
 -- Problem 6: Retrieve the users who have made at least one order in each category
 -- Write an SQL query to retrieve the users who have made at least one order in each category.
 -- The result should include the user ID and username.
 -- Hint: You may need to use subqueries or joins to solve this problem.
+SELECT Users.user_id, Users.username
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+INNER JOIN Order_Items ON Orders.order_id = Order_Items.order_id
+INNER JOIN Products ON Order_Items.product_id = Products.product_id
+INNER JOIN Categories ON Products.category_id = Categories.category_id
+GROUP BY Users.user_id
+HAVING COUNT(DISTINCT Categories.category_id) = (SELECT COUNT(*) FROM Categories);
+
+
 
 -- Problem 7: Retrieve the products that have not received any reviews
 -- Write an SQL query to retrieve the products that have not received any reviews.
 -- The result should include the product ID and product name.
 -- Hint: You may need to use subqueries or left joins to solve this problem.
+SELECT Products.product_id, Products.product_name
+FROM Products
+LEFT JOIN Reviews ON Products.product_id = Reviews.product_id
+WHERE Reviews.review_id IS NULL;
 
 -- Problem 8: Retrieve the users who have made consecutive orders on consecutive days
 -- Write an SQL query to retrieve the users who have made consecutive orders on consecutive days.
 -- The result should include the user ID and username.
--- Hint: You may need to use subqueries or window functions to solve this problem.
+-- Hint: You may need to use subqueries or window functions to solve this problem.
+SELECT DISTINCT Users.user_id, Users.username
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+WHERE Orders.order_date = DATE_SUB(Orders.order_date, INTERVAL 1 DAY)

sql/task3.sql

@@ -2,18 +2,45 @@
 -- Write an SQL query to retrieve the top 3 categories with the highest total sales amount.
 -- The result should include the category ID, category name, and the total sales amount.
 -- Hint: You may need to use subqueries, joins, and aggregate functions to solve this problem.
+SELECT Categories.category_id, Categories.category_name, SUM(Orders.total_amount) AS total_sales_amount
+FROM Categories
+INNER JOIN Products ON Categories.category_id = Products.category_id
+INNER JOIN Order_Items ON Products.product_id = Order_Items.product_id
+INNER JOIN Orders ON Order_Items.order_id = Orders.order_id
+GROUP BY Categories.category_id
+ORDER BY total_sales_amount DESC
+LIMIT 3;
 
 -- Problem 10: Retrieve the users who have placed orders for all products in the Toys & Games
 -- Write an SQL query to retrieve the users who have placed orders for all products in the Toys & Games
 -- The result should include the user ID and username.
 -- Hint: You may need to use subqueries, joins, and aggregate functions to solve this problem.
+SELECT Users.user_id, Users.username
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+INNER JOIN Order_Items ON Orders.order_id = Order_Items.order_id
+INNER JOIN Products ON Order_Items.product_id = Products.product_id
+INNER JOIN Categories ON Products.category_id = Categories.category_id
+WHERE Categories.category_name LIKE '%Toys & Games%'
+GROUP BY Users.user_id
+
 
 -- Problem 11: Retrieve the products that have the highest price within each category
 -- Write an SQL query to retrieve the products that have the highest price within each category.
 -- The result should include the product ID, product name, category ID, and price.
 -- Hint: You may need to use subqueries, joins, and window functions to solve this problem.
+SELECT Products.product_id, Products.product_name, Products.category_id, Products.price
+FROM Products
+INNER JOIN Categories ON Products.category_id = Categories.category_id
+WHERE Products.price = (SELECT MAX(Products.price) FROM Products WHERE Products.category_id = Categories.category_id);
 
 -- Problem 12: Retrieve the users who have placed orders on consecutive days for at least 3 days
 -- Write an SQL query to retrieve the users who have placed orders on consecutive days for at least 3 days.
 -- The result should include the user ID and username.
 -- Hint: You may need to use subqueries, joins, and window functions to solve this problem.
+SELECT DISTINCT Users.user_id, Users.username
+FROM Users
+INNER JOIN Orders ON Users.user_id = Orders.user_id
+WHERE Orders.order_date BETWEEN CURRENT_DATE - INTERVAL '3 DAYS' AND CURRENT_DATE - INTERVAL '1 DAY';
+
+