Merge pull request 'Решение по базовый SQL' (#39) from ebelykh into main

Reviewed-on: https://gitea.de-infra.servehttp.com/de-infrastructure/DWH/pulls/39
2026-01-24 07:37:01 +04:00
parent 1a608757b2 0a4db28644
commit 1012c43304
25 changed files with 475 additions and 0 deletions
@@ -0,0 +1,20 @@
 --Задача 1068
 SELECT p.product_name, s.year, s.price
 FROM Sales s
 JOIN Product p
 ON s.product_id = p.product_id;
 --Задача 1378
 SELECT EmployeeUNI.unique_id,
       Employees.name
 FROM Employees
 LEFT JOIN EmployeeUNI
 ON Employees.id = EmployeeUNI.id;      
 --Задача 577
 SELECT e.name, b.bonus
 FROM Employee e
 LEFT JOIN Bonus b
 ON e.empId = b.empId
 WHERE b.bonus < 1000
   OR b.bonus IS NULL;
@@ -0,0 +1,233 @@
 CREATE TABLE users (
    id INT PRIMARY KEY,
    name TEXT,
    age INT,
    email TEXT,
    registration_date DATE
 );
 INSERT INTO users VALUES
 (1, 'Alice', 25, 'alice@mail.com', '2023-01-10'),
 (2, 'Bob', 30, 'bob@gmail.com', '2023-02-05'),
 (3, 'Charlie', 22, 'charlie@mail.com', '2023-02-20'),
 (4, 'Diana', 28, 'diana@mail.com', '2023-03-01'),
 (5, 'Ethan', 35, 'ethan@gmail.com', '2023-03-10');
 SELECT * FROM users ORDER BY id;
 CREATE TABLE courses (
    id INT PRIMARY KEY,
    title TEXT,
    category TEXT,
    created_at DATE
 );
 INSERT INTO courses VALUES
 (1, 'SQL для начинающих', 'data', '2023-01-01'),
 (2, 'Python для анализа данных', 'programming', '2023-01-15'),
 (3, 'BI с нуля', 'business', '2023-03-01');
 SELECT * FROM courses ORDER BY id;
 CREATE TABLE lessons (
    id INT PRIMARY KEY,
    course_id INT,
    title TEXT,
    duration_min INT,
    FOREIGN KEY (course_id) REFERENCES courses(id)
 );
 INSERT INTO lessons VALUES
 (1, 1, 'SELECT и FROM', 10),
 (2, 1, 'JOIN', 15),
 (3, 2, 'Pandas', 20),
 (4, 3, 'Основы BI', 12),
 (5, 3, 'Метрики и дашборды', 18);
 SELECT * FROM lessons ORDER BY id;
 CREATE TABLE enrollments (
    id INT PRIMARY KEY,
    user_id INT,
    course_id INT,
    enrolled_at DATE,
    FOREIGN KEY (user_id) REFERENCES users(id),
    FOREIGN KEY (course_id) REFERENCES courses(id)
 );
 INSERT INTO enrollments VALUES
 (1, 1, 1, '2023-01-15'),
 (2, 1, 2, '2023-02-01'),
 (3, 2, 1, '2023-01-20'),
 (4, 3, 2, '2023-03-05'),
 (5, 4, 3, '2023-04-01');
 SELECT * FROM enrollments ORDER BY id;
 CREATE TABLE lesson_views (
    id INT PRIMARY KEY,
    user_id INT,
    lesson_id INT,
    viewed_at TIMESTAMP,
    FOREIGN KEY (user_id) REFERENCES users(id),
    FOREIGN KEY (lesson_id) REFERENCES lessons(id)
 );
 INSERT INTO lesson_views VALUES
 (1, 1, 1, '2023-01-16 10:00:00'),
 (2, 1, 2, '2023-01-16 10:15:00'),
 (3, 2, 1, '2023-01-21 09:00:00'),
 (4, 3, 3, '2023-03-06 12:00:00'),
 (5, 4, 4, '2023-04-02 10:00:00'),
 (6, 4, 5, '2023-04-03 10:00:00');
 SELECT * FROM lesson_views ORDER BY id;
 --Создаем materialized view c названием user_activity_summary
 DROP MATERIALIZED VIEW IF EXISTS user_activity_summary;
 CREATE MATERIALIZED VIEW user_activity_summary AS
 WITH
 enr AS (
  SELECT
    user_id,
    COUNT(*) AS enrollment_count
  FROM enrollments
  GROUP BY user_id
 ),
 views AS (
  SELECT
    user_id,
    COUNT(DISTINCT lesson_id) AS viewed_lessons_count,
    MIN(viewed_at) AS first_view,
    MAX(viewed_at) AS last_view
  FROM lesson_views
  GROUP BY user_id
 ),
 possible AS (
  SELECT
    e.user_id,
    COUNT(l.id) AS possible_lessons
  FROM enrollments e
  JOIN lessons l ON l.course_id = e.course_id
  GROUP BY e.user_id
 )
 SELECT
  u.id AS user_id,
  u.name,
  enr.enrollment_count,
  COALESCE(views.viewed_lessons_count, 0) AS viewed_lessons_count,
  views.last_view,
  views.first_view,
  ROUND(
    COALESCE(views.viewed_lessons_count, 0)::numeric
    / possible.possible_lessons * 100,
    2
  ) || '%' AS engagement_rate
 FROM users u
 JOIN enr ON enr.user_id = u.id
 JOIN possible ON possible.user_id = u.id
 LEFT JOIN views ON views.user_id = u.id
 ORDER BY u.id;
 --Проверка
 SELECT * FROM user_activity_summary ORDER BY user_id;
 --Создаем materialized view c названием course_summary
 DROP MATERIALIZED VIEW IF EXISTS course_summary;
 CREATE MATERIALIZED VIEW course_summary AS
 WITH
 -- 1) сколько уроков в каждом курсе
 lessons_cnt AS (
  SELECT
    course_id,
    COUNT(*) AS lessons_count
  FROM lessons
  GROUP BY course_id
 ),
 -- 2) сколько уникальных пользователей записано на курс
 users_cnt AS (
  SELECT
    course_id,
    COUNT(DISTINCT user_id) AS unique_users
  FROM enrollments
  GROUP BY course_id
 ),
 -- 3) просмотры по курсу (через lessons -> course_id)
 views_cnt AS (
  SELECT
    l.course_id,
    COUNT(lv.id) AS total_views,
    MIN(lv.viewed_at) AS first_viewed_at,
    MAX(lv.viewed_at) AS last_viewed_at
  FROM lessons l
  LEFT JOIN lesson_views lv ON lv.lesson_id = l.id
  GROUP BY l.course_id
 )
 SELECT
  c.id AS course_id,
  c.title AS course_title,
  COALESCE(u.unique_users, 0) AS unique_users,
  COALESCE(ls.lessons_count, 0) AS lessons_count,
  COALESCE(v.total_views, 0) AS total_views,
  ROUND(
    COALESCE(v.total_views, 0)::numeric / NULLIF(COALESCE(u.unique_users, 0), 0),
    2
  ) AS avg_views_per_user,
  v.first_viewed_at,
  v.last_viewed_at
 FROM courses c
 LEFT JOIN users_cnt u ON u.course_id = c.id
 LEFT JOIN lessons_cnt ls ON ls.course_id = c.id
 LEFT JOIN views_cnt v ON v.course_id = c.id
 ORDER BY c.id;
 SELECT * FROM course_summary ORDER BY course_id;
 --Создаем materialized view c названием platform_summary
 DROP MATERIALIZED VIEW IF EXISTS platform_summary;
 CREATE MATERIALIZED VIEW platform_summary AS
 SELECT
  (SELECT COUNT(*) FROM users) AS total_users,
  (SELECT COUNT(*) FROM courses) AS total_courses,
  (SELECT COUNT(*) FROM lessons) AS total_lessons,
  (SELECT COUNT(DISTINCT user_id) FROM lesson_views) AS users_with_views,
  ROUND(
    (SELECT COUNT(*) FROM lessons)::numeric
    / (SELECT COUNT(*) FROM courses),
    2
  ) AS avg_lessons_per_course,
  ROUND(
    (SELECT COUNT(*) FROM lesson_views)::numeric
    / (SELECT COUNT(*) FROM lessons),
    2
  ) AS avg_views_per_lesson;
  SELECT * FROM platform_summary;
 --Доп. задание: EXPLAIN
 EXPLAIN SELECT * FROM user_activity_summary;
 EXPLAIN SELECT * FROM course_summary;
@@ -0,0 +1,72 @@
 --Задача 1
 В варианте А: WHERE фильтрует товары и убирает те, которые не в наличии, потом эти товары(строки)участвуют в группировке, в варианте В - HAVING фильтрует уже сгруппированные данные(категории)
 --Задача 2356
 SELECT teacher_id,
       COUNT(DISTINCT subject_id) AS cnt
 FROM teacher
 GROUP BY teacher_id;
 --Задача 1581
 SELECT customer_id,
       COUNT(v.visit_id) AS count_no_trans
 FROM visits v
 LEFT JOIN transactions t
 ON v.visit_id = t.visit_id
 WHERE t.transaction_id IS NULL
 GROUP BY customer_id;
 --Задача 1141 
 SELECT activity_date AS day,
       COUNT(DISTINCT user_id) AS active_users
 FROM Activity
 WHERE activity_date BETWEEN '2019-06-28' AND '2019-07-27'
 GROUP BY activity_date;
 --Задача 596
 SELECT class
 FROM Courses
 GROUP BY class
 HAVING COUNT(student) >= 5;
 --Задача 1075
 SELECT project_id,
       ROUND(AVG(experience_years), 2) AS average_years
 FROM Project p
 JOIN Employee e
 ON p.employee_id = e.employee_id
 GROUP BY project_id;
 --Задача 1729
 SELECT user_id, 
       COUNT (follower_id) AS followers_count 
 FROM followers 
 GROUP BY user_id
 ORDER BY user_id;
 --Задача 1633
 SELECT
    r.contest_id,
    ROUND(
        COUNT(r.user_id) * 100.0 / (SELECT COUNT(*) FROM Users),
        2
    ) AS percentage
 FROM Register r
 GROUP BY r.contest_id
 ORDER BY percentage DESC, r.contest_id ASC;
 --Задача 1251
 SELECT
    p.product_id,
    COALESCE(
        ROUND(
             SUM(u.units * p.price) * 1.0 / NULLIF(SUM(u.units), 0),
            2
        ),
        0
    ) AS average_price
 FROM Prices p
 LEFT JOIN UnitsSold u
    ON p.product_id = u.product_id
    AND u.purchase_date BETWEEN p.start_date AND p.end_date
 GROUP BY p.product_id;
@@ -0,0 +1,43 @@
 --Задача 1757
 SELECT product_id
 FROM Products
 WHERE low_fats = 'Y' AND recyclable = 'Y';
 --Задача 584
 SELECT name
 FROM Customer
 WHERE referee_id!= 2 OR referee_id IS NULL;
 --Задача 595
 SELECT name, population, area
 FROM World
 WHERE area >= 3000000
   OR population >= 25000000;
 --Задача 1148 
 SELECT DISTINCT author_id AS id
 FROM Views
 WHERE author_id = viewer_id
 ORDER BY id; 
 --Задача 1683 
 SELECT tweet_id
 FROM Tweets
 WHERE CHAR_LENGTH(content) > 15;
 --Задача 620
 SELECT id, movie, description, rating
 FROM Cinema
 WHERE id % 2 = 1
  AND description != 'boring'
 ORDER BY rating DESC;
 --Задача 1667
 SELECT
  user_id,
  CONCAT(
    UPPER(SUBSTR(name, 1, 1)),
    LOWER(SUBSTR(name, 2))
  ) AS name
 FROM Users
 ORDER BY user_id;
@@ -0,0 +1,33 @@
 --Задача 1
  CREATE TABLE products_extended (
  id INT PRIMARY KEY,
  name VARCHAR(100) NOT NULL,
  category VARCHAR(50),
  price DECIMAL(6,2),
  in_stock BOOLEAN DEFAULT true,
  email_support VARCHAR
 );
 --Задача 2 Вариант с DEFAULT (in_stock не указываем)
 INSERT INTO products_extended (id, name, category, price, email_support)
 VALUES
 (1, 'Mi Band 7', 'smartwatch', 49.00, 'miband@xiaomi.com'),
 (2, 'Surface Pro', 'tablet', 1299.00, 'surface@microsoft.com');
 --Задача 3
 ALTER TABLE products_extended  
 ADD COLUMN rating DECIMAL(3,2), 
 DROP COLUMN email_support;
 --Задача 4
 UPDATE products_extended
 SET price = price * 1.1
 WHERE name = 'Mi Band 7';
 --Задача 5(удаляет данные/таблицу)
 TRUNCATE TABLE products_extended;
 DROP TABLE products_extended;
@@ -0,0 +1,54 @@
 SELECT
 name,
 category,
  price,
  price * 1.10 AS price_with_markup,
  price * 1.20 AS price_with_vat,
  COALESCE(email_support, 'нет почты') AS status
 FROM products_extended
 WHERE in_stock = true
  AND category NOT IN ('smartwatch', 'ebook_reader')
  AND price BETWEEN 300 AND 1300;
 SELECT
  name,
  category,
  email_support,
  price * 1.25 AS price_25,
  price > 1000 AS premium
 FROM products_extended
 WHERE (price < 150 OR price > 1200)
  AND email_support IS NOT NULL;
 SELECT
  id,
  name,
  category,
  price
 FROM products_extended
 WHERE category IN ('smartphone', 'laptop', 'tablet')
  AND name NOT LIKE '%i%'
  AND price BETWEEN 500 AND 1300
 ORDER BY id;
 SELECT
  name,
  category,
  price,
  'нет поддержки' AS comment
 FROM products_extended
 WHERE in_stock = true
  AND email_support IS NULL
  AND price < 800;
 SELECT
  name,
  category,
  price,
  price > 1000 AS premium
 FROM products_extended
 WHERE (name LIKE '%Pro' OR name LIKE '%X%')
  AND in_stock = true
  AND price > 700;
@@ -0,0 +1,20 @@
 --Задача 1211
 SELECT
    query_name,
    ROUND(AVG(rating * 1.0 / position), 2) AS quality,
    ROUND(AVG(CASE WHEN rating < 3 THEN 1 ELSE 0 END) * 100,2) AS poor_query_percentage
 FROM Queries
 GROUP BY query_name;
 --Задача 1193
 SELECT
    TO_CHAR(trans_date, 'YYYY-MM') AS month,
    country,
    COUNT(*) AS trans_count,
    SUM(CASE WHEN state = 'approved' THEN 1 ELSE 0 END) AS approved_count,
    SUM(amount) AS trans_total_amount,
    SUM(CASE WHEN state = 'approved' THEN amount ELSE 0 END) AS approved_total_amount
 FROM Transactions
 GROUP BY
    TO_CHAR(trans_date, 'YYYY-MM'),
    country;