Homework

03_homework/homework_1.md

@@ -75,4 +75,6 @@ Please do not pick the exact same tables that I have already diagramed. For exam
 	- These are the tables that are connected
 	-  ![01_farmers_market_conceptual_model.png](./images/01_farmers_market_conceptual_model.png)
 - The column names can be found in a few spots (DB Schema window in the bottom right, the Database Structure tab in the main window by expanding each table entry, at the top of the Browse Data tab in the main window)
-
+
+- My answer here:
+- https://github.com/zrasi/sql/blob/homework/03_homework/images/Zarrin_sql_homework_1.png

03_homework/homework_2.sql

@@ -1,42 +1,78 @@
 --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 customer_id, customer_first_name, customer_last_name, customer_zip
+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. */
 -- option 1
+SELECT *
+FROM customer_purchases
+WHERE product_id IN (4, 9);
 
 -- option 2
+SELECT *
+FROM customer_purchases
+WHERE product_id = 4 OR product_id = 9;
 
 /*2. Write a query that returns all customer purchases and a new calculated column 'price' (quantity * cost_to_customer_per_qty), 
 filtered by vendor IDs between 8 and 10 (inclusive) using either:
 	1.  two conditions using AND
 	2.  one condition using BETWEEN
 */
 -- option 1
-
+SELECT *, (quantity * cost_to_customer_per_qty) AS price
+FROM customer_purchases
+WHERE vendor_id >= 8 AND vendor_id <= 10;
 
 -- option 2
+SELECT *, (quantity * cost_to_customer_per_qty) AS price
+FROM customer_purchases
+WHERE vendor_id BETWEEN 8 AND 10;
+
 
 --CASE
 /* 1. Products can be sold by the individual unit or by bulk measures like lbs. or oz. 
 Using the product table, write a query that outputs the product_id and product_name
 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 prod_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 UPPER(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 v
+INNER JOIN vendor_booth_assignments vba ON v.vendor_id = vba.vendor_id
+ORDER BY v.vendor_name, vba.market_date;

03_homework/homework_3.sql

@@ -1,7 +1,9 @@
 -- AGGREGATE
 /* 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 booth_rental_count
+FROM vendor_booth_assignments
+GROUP BY vendor_id;
 
 
 /* 2. The Farmer’s Market Customer Appreciation Committee wants to give a bumper 
@@ -10,6 +12,16 @@ 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 c.customer_id, c.customer_first_name, c.customer_last_name,
+		SUM(cp.quantity * cp.cost_to_customer_per_qty) AS total_spent
+FROM customer c
+JOIN customer_purchases cp
+ON c.customer_id = cp.customer_id
+GROUP BY
+		c.customer_id, c.customer_first_name, c.customer_last_name
+HAVING
+		total_spent > 2000
+ORDER BY c.customer_last_name, c.customer_first_name;
 
 
 --Temp Table
@@ -23,7 +35,15 @@ When inserting the new vendor, you need to appropriately align the columns to be
 -> To insert the new row use VALUES, specifying the value you want for each column:
 VALUES(col1,col2,col3,col4,col5) 
 */
+DROP TABLE IF EXISTS new_vendor;
+
+CREATE TEMPORARY TABLE new_vendor AS
+SELECT * FROM vendor;
+
+INSERT INTO new_vendor (vendor_id, vendor_name, vendor_type, vendor_owner_first_name, vendor_owner_last_name)
+Values (10, 'Thomas Superfood Store', 'a Fresh Focused store', 'Thomas', 'Rosenthal');
 
+SELECT * FROM new_vendor;
 
 
 -- Date
@@ -32,9 +52,19 @@ VALUES(col1,col2,col3,col4,col5)
 HINT: you might need to search for strfrtime modifers sqlite on the web to know what the modifers for month 
 and year are! */
 
+SELECT  customer_id,
+		strftime('%m', market_date) AS month,
+		strftime('%Y', market_date) AS year
+FROM customer_purchases;
+
 /* 2. Using the previous query as a base, determine how much money each customer spent in April 2019. 
 Remember that money spent is quantity*cost_to_customer_per_qty. 
 
 HINTS: you will need to AGGREGATE, GROUP BY, and filter...
 but remember, STRFTIME returns a STRING for your WHERE statement!! */
+SELECT  customer_id, market_date,
+		SUM(quantity * cost_to_customer_per_qty) AS total_spent
+FROM  customer_purchases
+WHERE strftime('%m', market_date) = '04' AND strftime('%Y', market_date) = '2019'
+GROUP BY customer_id;
 

03_homework/homework_4.sql

@@ -1,40 +1,173 @@
--- COALESCE
-/* 1. Our favourite manager wants a detailed long list of products, but is afraid of tables! 
-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 
-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 problem, and 'unit' for the second problem. 
-
-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.) */
-
-
-
-
---Windowed Functions
-/* 1. Write a query that selects from the customer_purchases table and numbers each customer’s  
-visits to the farmer’s market (labeling each market date with a different number). 
-Each customer’s first visit is labeled 1, second visit is labeled 2, etc. 
-
-You can either display all rows in the customer_purchases table, with the counter changing on
-each new market date for each customer, or select only the unique market dates per customer 
-(without purchase details) and number those visits. 
-HINT: One of these approaches uses ROW_NUMBER() and one uses DENSE_RANK(). */
-
-
-/* 2. Reverse the numbering of the query from a part so each customer’s most recent visit is labeled 1, 
-then write another query that uses this one as a subquery (or temp table) and filters the results to 
-only the customer’s most recent visit. */
-
-
-/* 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. */
+-- COALESCE
+/* 1. Our favourite manager wants a detailed long list of products, but is afraid of tables! 
+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 
+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 problem, and 'unit' for the second problem. 
+
+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 
+product_name || ', ' || coalesce(product_size, '') || ' (' || coalesce(product_qty_type, 'unit') || ')'
+FROM product;
+
+
+--Windowed Functions
+/* 1. Write a query that selects from the customer_purchases table and numbers each customer’s  
+visits to the farmer’s market (labeling each market date with a different number). 
+Each customer’s first visit is labeled 1, second visit is labeled 2, etc. 
+
+You can either display all rows in the customer_purchases table, with the counter changing on
+each new market date for each customer, or select only the unique market dates per customer 
+(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,
+    row_number() OVER (PARTITION BY customer_id ORDER BY market_date) AS visit_number
+FROM 
+    customer_purchases;*/
+
+SELECT 
+    customer_id,
+    market_date,
+    dense_rank() OVER (PARTITION BY customer_id ORDER BY market_date) 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, 
+then write another query that uses this one as a subquery (or temp table) and filters the results to 
+only the customer’s most recent visit. */
+
+SELECT
+	customer_id,
+	market_date,
+	row_number() OVER (PARTITION BY customer_id ORDER BY market_date DESC) AS visit_number
+FROM 
+	customer_purchases;
+
+
+SELECT customer_id, market_date, visit_number
+FROM 
+	( 
+		SELECT 
+			customer_id,
+			market_date,
+			row_number() OVER (PARTITION BY customer_id ORDER BY market_date DESC) AS visit_number
+		FROM 
+			customer_purchases
+
+	) AS recent_visits
+
+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(DISTINCT market_date) AS purchase_count
+FROM
+		customer_purchases
+GROUP BY
+		customer_id, product_id;
+
+-- I tried the code below, but I am getting error that DISTICT is not supported for window function.	
+/*SELECT 
+    customer_id,
+    product_id,
+    COUNT(DISTINCT market_date) 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". 
+These are separated from the product name with a hyphen. 
+Create a column using SUBSTR (and a couple of other commands) that captures these, but is otherwise NULL. 
+Remove any trailing or leading whitespaces. Don't just use a case statement for each product! 
+
+| product_name               | description |
+|----------------------------|-------------|
+| Habanero Peppers - Organic | Organic     |
+
+Hint: you might need to use INSTR(product_name,'-') to find the hyphens. INSTR will help split the column. */
+
+SELECT 
+    product_name,
+	CASE
+		WHEN instr(product_name, '-') = 0 THEN NULL
+		ELSE TRIM(SUBSTR(product_name, INSTR(product_name, '-') + 1)) 
+	END	AS description
+FROM 
+    product;
+
+/* 2. Filter the query to show any product_size value that contain a number with REGEXP. */
+
+SELECT
+	product_name,
+	product_size
+FROM
+	product
+WHERE
+	product_size REGEXP '[0-9]';
+
+-- UNION;
+
+/* 1. Using a UNION, write a query that displays the market dates with the highest and lowest total sales.
+
+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"; 
+3) Query the second temp table twice, once for the best day, once for the worst day, 
+with a UNION binding them. */
+
+WITH daily_sales 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 sales_rank_desc,
+		RANK() OVER (ORDER BY total_sales ASC) AS sales_rank_asc
+	FROM
+		daily_sales
+)
+SELECT
+	market_date,
+	total_sales
+FROM
+	ranked_sales
+WHERE
+	sales_rank_desc = 1
+UNION
+SELECT
+	market_date,
+	total_sales
+FROM
+	ranked_sales
+WHERE
+	sales_rank_asc = 1;
+
+