code added

ankurbhambri · ankurbhambri · commit 1598de5f9991 · 2024-06-09T05:40:46.000+05:30
diff --git a/array_json.sql b/array_json.sql
@@ -21,14 +21,14 @@ VALUES
 ('Atlanta', '{TV,"Wireless Internet","Air conditioning","Smoke detector","Carbon monoxide detector",Essentials,"Lock on bedroom door",Hangers,Iron,"Fire extinguisher"}');
 
 
--- Count array length of column values
-SELECT city, array_length(string_to_array(array_values, ','), 1) AS number_of_amenities
-FROM arrayTable;
-
 -- Convert a comma-separated string into an array using string_to_array.
 SELECT string_to_array('TV,Wireless Internet,Air conditioning', ',') AS amenities_array;
 
 
+-- Count array length of column values
+SELECT city, array_length(string_to_array(array_values, ','), 1) AS number_of_amenities
+FROM arrayTable;
+
 -- Count the number of unique values in array_values column across all entries.
 SELECT COUNT(DISTINCT unnest(string_to_array(array_values, ','))) AS unique_amenities_count
 FROM arrayTable;
diff --git a/consequitive.sql b/consequitive.sql
@@ -1,4 +1,5 @@
 -- Using a CTE to calculate the most and least expensive products in each category
+
 WITH cte AS (
     SELECT
         name, 
@@ -11,7 +12,6 @@ WITH cte AS (
         LAST_VALUE(model) OVER (PARTITION BY category ORDER BY price DESC RANGE BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS least_expensive_product_name
     FROM products
 )
--- Select the category, model, price, most expensive product, and least expensive product from the CTE
 SELECT 
     category, 
     model, 
@@ -21,6 +21,7 @@ SELECT
 FROM cte;
 
 -- Query to find users who have logged in consecutively 3 or more times
+
 SELECT DISTINCT repeated_names
 FROM (
     SELECT *,
diff --git a/tricky_questions/Marketing_Campaign_Success.sql b/tricky_questions/Marketing_Campaign_Success.sql
@@ -1,3 +1,16 @@
+-- https://platform.stratascratch.com/coding/514-marketing-campaign-success-advanced?code_type=1
+
+/*
+
+You have a table of in-app purchases by user. Users that make their first in-app purchase are placed in a marketing campaign where they see call-to-actions for more in-app purchases. 
+Find the number of users that made additional in-app purchases due to the success of the marketing campaign.
+
+
+The marketing campaign doesn't start until one day after the initial in-app purchase so users that only made one or multiple purchases on the first day do not count, 
+nor do we count users that over time purchase only the products they purchased on the first day.
+
+*/
+
 with cte as (
     select *, 
         rank() over(partition by user_id order by created_at) as rn 
diff --git a/tricky_questions/Median_Employee_Salary.sql b/tricky_questions/Median_Employee_Salary.sql
@@ -1,15 +1,57 @@
-with cte as (
-  select *,
-  row_number() over(partition by company order by salary desc) rw,
-  count(1) over(partition by company order by salary desc RANGE BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) as scn
- from salaries
-), even_odd as (
-  SELECT *
-  FROM cte
-  WHERE scn % 2 = 0 AND rw IN (scn / 2, (scn / 2) + 1)
-  union all
-  SELECT *
-  FROM cte
-  WHERE scn % 2 <> 0 and rw = (scn + 1) / 2
+/*
+
+The Employee table holds all employees. The employee table has three columns: Employee Id, Company Name, and Salary.
+
++-----+------------+--------+
+|Id   | Company    | Salary |
++-----+------------+--------+
+|1    | A          | 2341   |
+|2    | A          | 341    |
+|3    | A          | 15     |
+|4    | A          | 15314  |
+|5    | A          | 451    |
+|6    | A          | 513    |
+|7    | B          | 15     |
+|8    | B          | 13     | 
+|9    | B          | 1154   |
+|10   | B          | 1345   |
+|11   | B          | 1221   |
+|12   | B          | 234    |
+|13   | C          | 2345   |
+|14   | C          | 2645   |
+|15   | C          | 2645   |
+|16   | C          | 2652   |
+|17   | C          | 65     |
++-----+------------+--------+
+
+Write a SQL query to find the median salary of each company. Bonus points if you can solve it without using any built-in SQL functions.
+
++-----+------------+--------+
+|Id   | Company    | Salary |
++-----+------------+--------+
+|5    | A          | 451    |
+|6    | A          | 513    |
+|12   | B          | 234    |
+|9    | B          | 1154   |
+|14   | C          | 2645   |
++-----+------------+--------+
+
+*/
+WITH cte AS (
+    SELECT *,
+           ROW_NUMBER() OVER (PARTITION BY company ORDER BY salary DESC) AS rw,
+           COUNT(1) OVER (PARTITION BY company ORDER BY salary DESC RANGE BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) AS scn
+    FROM salaries
+),
+even_odd AS (
+    SELECT *
+    FROM cte
+    WHERE scn % 2 = 0 AND rw IN (scn / 2, (scn / 2) + 1)
+    UNION ALL
+    SELECT *
+    FROM cte
+    WHERE scn % 2 <> 0 AND rw = (scn + 1) / 2
 )
-SELECT id, company, salary FROM even_odd group by company, salary, id
+SELECT id, company, salary
+FROM even_odd
+GROUP BY company, salary, id;
diff --git a/tricky_questions/amazon_questions.sql b/tricky_questions/amazon_questions.sql
@@ -73,7 +73,7 @@ create table events
 
 with cte as (
 	select 
-		INITCAP(e.status) status, -- to make it capital
+		INITCAP(e.status) status, -- to make first char capital
 		Concat(a.first_name, ' ', a.last_name) customer,
 		string_agg(distinct b.name, ', ') campaign,
 		count(1) total,
diff --git a/tricky_questions/meta.sql b/tricky_questions/meta.sql
@@ -0,0 +1,155 @@
+ /*
+
+ The following schema is a subset of a relational database of a grocery store
+ chain. This chain sells many products of different product classes to its
+ customers across its different stores. It also conducts many different
+ promotion campaigns.
+ 
+ The relationship between the four tables we want to analyze is depicted below:
+ 
+       # sales                                # products
+       +------------------+---------+         +---------------------+---------+
+       | product_id       | INTEGER |>--------| product_id          | INTEGER |
+       | store_id         | INTEGER |    +---<| product_class_id    | INTEGER |
+       | customer_id      | INTEGER |    |    | brand_name          | VARCHAR |
+  +---<| promotion_id     | INTEGER |    |    | product_name        | VARCHAR |
+  |    | store_sales      | DECIMAL |    |    | is_low_fat_flg      | TINYINT |
+  |    | store_cost       | DECIMAL |    |    | is_recyclable_flg   | TINYINT |
+  |    | units_sold       | DECIMAL |    |    | gross_weight        | DECIMAL |
+  |    | transaction_date | DATE    |    |    | net_weight          | DECIMAL |
+  |    +------------------+---------+    |    +---------------------+---------+
+  |                                      |
+  |    # promotions                      |    # product_classes
+  |    +------------------+---------+    |    +---------------------+---------+
+  +----| promotion_id     | INTEGER |    +----| product_class_id    | INTEGER |
+       | promotion_name   | VARCHAR |         | product_subcategory | VARCHAR |
+       | media_type       | VARCHAR |         | product_category    | VARCHAR |
+       | cost             | DECIMAL |         | product_department  | VARCHAR |
+       | start_date       | DATE    |         | product_family      | VARCHAR |
+       | end_date         | DATE    |         +---------------------+---------+
+       +------------------+---------+
+
+ Question 1
+
+ -- What percent of all products in the grocery chain's catalog
+ -- are both low fat and recyclable?
+ 
+
+ EXPECTED OUTPUT:
+ Note: Please use the column name(s) specified in the expected output in your solution.
+ +----------------------------+
+ | pct_low_fat_and_recyclable |
+ +----------------------------+
+ |         15.384615384615385 |
+ +----------------------------+
+
+Question 2
+
+ -- What are the top five (ranked in decreasing order)
+ -- single-channel media types that correspond to the most money
+ -- the grocery chain had spent on its promotional campaigns?
+
+ Single Media Channel Types are promotions that contain only one media type.
+
+ EXPECTED OUPTUT:
+ Note: Please use the column name(s) specified in the expected output in your solution.
+ +---------------------------+------------+
+ | single_channel_media_type | total_cost |
+ +---------------------------+------------+
+ | In-Store Coupon           | 70800.0000 |
+ | Street Handout            | 70627.0000 |
+ | Radio                     | 60192.0000 |
+ | Sunday Paper              | 56994.0000 |
+ | Product Attachment        | 50815.0000 |
+ +---------------------------+------------+
+
+Question 3
+
+  -- Of sales that had a valid promotion, the VP of marketing
+ -- wants to know what % of transactions occur on either
+ -- the very first day or the very last day of a promotion campaign.
+ 
+ 
+ EXPECTED OUTPUT:
+ Note: Please use the column name(s) specified in the expected output in your solution.
+ +-------------------------------------------------------------+
+ | pct_of_transactions_on_first_or_last_day_of_valid_promotion |
+ +-------------------------------------------------------------+
+ |                                         41.9047619047619048 |
+ +-------------------------------------------------------------+
+
+
+Question 4
+
+-- The CMO is interested in understanding how the sales of different
+ -- product families are affected by promotional campaigns.
+ -- To do so, for each of the available product families,
+ -- show the total number of units sold,
+ -- as well as the ratio of units sold that had a valid promotion
+ -- to units sold without a promotion,
+ -- ordered by increasing order of total units sold.
+ 
+ 
+ EXPECTED OUTPUT
+ Note: Please use the column name(s) specified in the expected output in your solution.
+ +----------------+------------------+--------------------------------------------------+
+ | product_family | total_units_sold | ratio_units_sold_with_promo_to_sold_without_promo|
+ +----------------+------------------+--------------------------------------------------+
+ | Drink          |          43.0000 |                           0.79166666666666666667 |
+ | Non-Consumable |         176.0000 |                           0.76000000000000000000 |
+ | Food           |         564.0000 |                           0.75155279503105590062 |
+ +----------------+------------------+--------------------------------------------------+
+
+
+Question 5
+
+-- The VP of Sales feels that some product categories don't sell
+ -- and can be completely removed from the inventory.
+ -- As a first pass analysis, they want you to find what percentage
+ -- of product categories have never been sold.
+ 
+ EXPECTED OUTPUT:
+ Note: Please use the column name(s) specified in the expected output in your solution.
+ +-----------------------------------+
+ | pct_product_categories_never_sold |
+ +-----------------------------------+
+ |               13.8888888888888889 |
+ +-----------------------------------+
+
+ */
+
+
+1.
+
+select count(case when is_low_fat_flg = 1 and is_recyclable_flg = 1 then 1 end) * 100.0 / count(*) from products
+
+2. 
+
+select media_type as single_channel_media_type, sum(cost) total_cost 
+from promotions where media_type not like '%,%'
+group by media_type 
+order by 2 desc 
+limit 5
+
+3.
+
+select count(case when transaction_date=start_date or transaction_date=end_date then 1 end) * 100.0 / count(*) pct_of_transactions_on_first_or_last_day_of_valid_promotion 
+from sales s join promotions p on s.promotion_id=p.promotion_id
+
+
+4. 
+
+select product_family, sum(units_sold) as total_units_sold,
+sum(case when s.promotion_id != 0 then units_sold end) * 1.0 / sum(case when s.promotion_id = 0 then units_sold end) * 1.0 ratio_units_sold_with_promo_to_sold_without_promo 
+from sales s join products p on s.product_id=p.product_id
+join product_classes pc on pc.product_class_id=p.product_class_id
+group by product_family
+
+
+5.
+
+select (tc - count(distinct pc.product_category)) * 100.0 / tc  
+from (select count(distinct product_category) tc from product_classes),
+sales s
+join products p on s.product_id=p.product_id 
+join product_classes pc on pc.product_class_id=p.product_class_id
diff --git a/tricky_questions/yt-assignment.sql b/tricky_questions/yt-assignment.sql
@@ -31,4 +31,6 @@ Note - Data is not provided for these tables, you can insert some dummy data if
     At a time, one student can be active in one batch only. One Student can not be transferred more than four times.
     Calculate each students attendance percentage for all the sessions.
 
-*/
+*/
+
+-- TODO
