for_Mysql.sql

for_Mysql.sql

@@ -0,0 +1,115 @@
+-- zepto project
+create database zepto;
+
+use zepto;
+
+drop table if exists zepto_v2;
+
+select * from zepto_v3;
+
+ALTER TABLE zepto_v3 RENAME TO zepto;
+
+-- data exploration
+-- count of rows
+select count(*) from zepto;
+
+-- sample data
+SELECT * FROM zepto LIMIT 10;
+
+-- null values
+SELECT * FROM zepto WHERE name IS NULL OR
+category IS NULL OR
+mrp IS NULL OR
+discountPercent IS NULL OR
+discountedSellingPrice IS NULL OR
+weightInGms IS NULL OR
+availableQuantity IS NULL OR
+outOfStock IS NULL OR
+quantity IS NULL;
+
+-- different product categories
+SELECT DISTINCT category FROM zepto ORDER BY category;
+
+-- product names present multiple times
+SELECT name, COUNT(*) AS "Number of Entries" FROM zepto
+GROUP BY name HAVING COUNT(*) > 1 ORDER BY COUNT(*) DESC;
+
+
+
+-- data cleaning
+-- products with price = 0
+SELECT * FROM zepto
+WHERE mrp = 0 OR discountedSellingPrice = 0;
+
+DELETE FROM zepto
+WHERE mrp = 0;
+
+SET SQL_SAFE_UPDATES = 0;
+
+DELETE FROM zepto
+WHERE CAST(mrp AS DECIMAL(10,2)) = 0;
+
+-- convert paise to rupees
+UPDATE zepto
+SET mrp = mrp / 100.0,
+discountedSellingPrice = discountedSellingPrice / 100.0;
+
+SELECT mrp, discountedSellingPrice FROM zepto;
+
+
+
+-- data analysis
+-- Q1. Find the top 10 best-value products based on the discount percentage.
+SELECT DISTINCT name, mrp, discountPercent
+FROM zepto
+ORDER BY discountPercent DESC
+LIMIT 10;
+
+-- Q2.What are the Products with High MRP but Out of Stock
+SELECT DISTINCT name,mrp
+FROM zepto
+WHERE outOfStock = "TRUE" and mrp > 300
+ORDER BY mrp DESC;
+
+-- Q3.Calculate Estimated Revenue for each category
+SELECT category,
+SUM(discountedSellingPrice * availableQuantity) AS total_revenue
+FROM zepto
+GROUP BY category
+ORDER BY total_revenue;
+
+-- Q4. Find all products where MRP is greater than ₹500 and discount is less than 10%.
+SELECT DISTINCT name, mrp, discountPercent
+FROM zepto
+WHERE mrp > 500 AND discountPercent < 10
+ORDER BY mrp DESC, discountPercent DESC;
+
+-- Q5. Identify the top 5 categories offering the highest average discount percentage.
+SELECT category,
+ROUND(AVG(discountPercent),2) AS avg_discount
+FROM zepto
+GROUP BY category
+ORDER BY avg_discount DESC
+LIMIT 5;
+
+-- Q6. Find the price per gram for products above 100g and sort by best value.
+SELECT DISTINCT name, weightInGms, discountedSellingPrice,
+ROUND(discountedSellingPrice/weightInGms,2) AS price_per_gram
+FROM zepto
+WHERE weightInGms >= 100
+ORDER BY price_per_gram;
+
+-- Q7.Group the products into categories like Low, Medium, Bulk.
+SELECT DISTINCT name, weightInGms,
+CASE WHEN weightInGms < 1000 THEN 'Low'
+	WHEN weightInGms < 5000 THEN 'Medium'
+	ELSE 'Bulk'
+	END AS weight_category
+FROM zepto;
+
+-- Q8.What is the Total Inventory Weight Per Category 
+SELECT category,
+SUM(weightInGms * availableQuantity) AS total_weight
+FROM zepto
+GROUP BY category
+ORDER BY total_weight;