인프런 커뮤니티 질문&답변

UNNEST

1) array_exercises 테이블에서 각 영화(title)별로 장르를(genres) unnest 해서 보여주세요

SELECT title, genre
FROM advanced.array_exercises
CROSS JOIN UNNEST(genres) AS genre

2) array_exercieses 테이블에서 각 영화(title) 별로 배우 (actor)와 배역(character)을 보여주세요. 배우와 배역은 별도의 컬럼으로 나와야 합니다.

SELECT title,
actor_info.actor,
actor_info.character,
FROM advanced.array_exercises
CROSS JOIN UNNEST(actors) AS actor_info;

3) array_exercises 테이블에서 각 영화(title) 별로 배우(actor), 배역(character), 장르(genre)를 출력하세요. 한 row 에 배우, 배역, 장르가 모두 표시되어야 합니다.

SELECT 
  title, 
  actor_info.actor,
  actor_info.character,
  genre,
FROM advanced.array_exercises
CROSS JOIN UNNEST(actors) AS actor_info
CROSS JOIN UNNEST(genres) AS genre;

4) 앱 로그 데이터(app_logs)의 배열을 풀어주세요.

SELECT 
  user_id,
  event_date,
  event_name,
  user_pseudo_id,
  params.key AS key,
  params.value.string_value AS string_value,
  params.value.int_value AS int_value,
FROM advanced.app_logs
CROSS JOIN UNNEST(event_params) AS params
ORDER BY event_date;

PIVOT

1) orders 테이블에서 유저(user_id)별로 주문금액(amount)의 합계를 PIVOT 해주세요 날짜(order_date)를 행(Row)으로, user_id를 열(Column)으로 만들어야 합니다.

SELECT
  order_date,
  SUM(IF(user_id=1, amount, 0)) AS user_1,
  SUM(IF(user_id=2, amount, 0)) AS user_2,
  SUM(IF(user_id=3, amount, 0)) AS user_3
FROM advanced.orders
GROUP BY order_date
ORDER BY order_date ASC

2) orders 테이블에서 날짜(order_date)별로 유저들의 주문금액(amount)의 합계를 PIVOT 해주세요. user_id를 행으로, order_date를 열으로 만들어야 합니다.

SELECT 
  user_id,
  SUM(IF(order_date = '2023-05-01', amount, 0)) AS `2023-05-01`,
  SUM(IF(order_date = '2023-05-02', amount, 0)) AS `2023-05-02`,
  SUM(IF(order_date = '2023-05-03', amount, 0)) AS `2023-05-03`,
  SUM(IF(order_date = '2023-05-04', amount, 0)) AS `2023-05-04`,
  SUM(IF(order_date = '2023-05-05', amount, 0)) AS `2023-05-05`
FROM advanced.orders
GROUP BY user_id
ORDER BY user_id;

3) orders 테이블에서 사용자(user_id)별, 날짜(order_date)별로 주문이 있다면 1, 없다면 0으로 PIVOT 해주세요. user_id를 행으로, order_date를 열로 만들고 주문을 많이 해도 1로 처리합니다.

SELECT 
  user_id,
  MAX(IF(order_date = "2023-05-01",1,0)) AS `2023-05-01`,
  MAX(IF(order_date = "2023-05-02",1,0)) AS `2023-05-02`,
  MAX(IF(order_date = "2023-05-03",1,0)) AS `2023-05-03`,
  MAX(IF(order_date = "2023-05-04",1,0)) AS `2023-05-04`,
  MAX(IF(order_date = "2023-05-05",1,0)) AS `2023-05-05`
FROM advanced.orders
GROUP BY user_id
ORDER BY user_id

4) user_id = 32888 이 카트 추가하기 (click_cart)를 누를 때 어떤 음식(food_id)을 담았나요?

WITH base AS (
SELECT 
	event_date,
	event_name,
	user_pseudo_id,
	event_timestamp,
	user_id,
	MAX(IF(param.key = "firebase_screen", param.value.string_value, NULL)) AS firebase_screen,
  MAX(IF(param.key = "food_id", param.value.int_value, NULL)) AS food_id,
  MAX(IF(param.key = "session_id", param.value.string_value, NULL)) AS session_id
FROM advanced.app_logs
CROSS JOIN UNNEST(event_params) AS param
WHERE event_date = "2022-08-01"
GROUP BY ALL
)
SELECT 
	select_date,
	COUNT(user_id) AS user_cnt
FROM base
WHERE 
	event_name = "click_cart" 
GROUP BY event_date

3. 퍼널

WITH base AS (
  SELECT
    event_date,
    event_timestamp,
    event_name,
    user_id,
    user_pseudo_id,
    platform,
    -- event_param
    MAX(IF(event_param.key = "firebase_screen", event_param.value.string_value, NULL)) AS firebase_screen,
    -- MAX(IF(event_param.key = "food_id", event_param.value.int_value, NULL)) AS food_id,
    MAX(IF(event_param.key = "session_id", event_param.value.string_value, NULL)) AS session_id
  FROM advanced.app_logs
  CROSS JOIN UNNEST(event_params) AS event_param
  WHERE
    -- event_date = "2022-08-01" # 적은 데이터로 쿼리를 작성하기 위해 만들어둔 조건
    event_date BETWEEN "2022-08-01" AND "2022-08-18"
  GROUP BY ALL
), filter_event_and_concat_event_and_screen AS (
  -- (1) event_name + screen (필요한 이벤트만 WHERE 조건에 걸어서 사용)
  SELECT
    * EXCEPT(event_name, firebase_screen, event_timestamp),
    CONCAT(event_name, "-", firebase_screen) AS event_name_with_screen,
    DATETIME(TIMESTAMP_MICROS(event_timestamp), 'Asia/Seoul') AS event_datetime
  FROM base
  WHERE
    event_name IN ("screen_view", "click_payment")
), 
funnel AS (
  SELECT
    event_date,
    event_name_with_screen,
    CASE 
      WHEN event_name_with_screen = "screen_view-welcome" THEN 1
      WHEN event_name_with_screen = "screen_view-home" THEN 2
      WHEN event_name_with_screen = "screen_view-food_category" THEN 3
      WHEN event_name_with_screen = "screen_view-restaurant" THEN 4
      WHEN event_name_with_screen = "screen_view-cart" THEN 5
      WHEN event_name_with_screen = "click_payment-cart" THEN 6
    ELSE NULL
    END AS step_number,
    COUNT(DISTINCT user_pseudo_id) AS cnt
  FROM filter_event_and_concat_event_and_screen
  GROUP BY ALL
  HAVING step_number IS NOT NULL
  )

SELECT 
  event_date,
  MAX(IF(funnel.event_name_with_screen = 'screen_view-welcome', cnt, null)) as `screen_view-welcome`,
  MAX(IF(funnel.event_name_with_screen = 'screen_view-home', cnt, null)) as `screen_view-home`,
  MAX(IF(funnel.event_name_with_screen = 'screen_view-food_category', cnt, null)) as `screen_view-food_category`,
  MAX(IF(funnel.event_name_with_screen = 'screen_view-restaurant', cnt, null)) as `screen_view-restaurant`,
  MAX(IF(funnel.event_name_with_screen = 'screen_view-cart', cnt, null)) as `screen_view-cart`,
  MAX(IF(funnel.event_name_with_screen = 'click_payment-cart', cnt, null)) as `click_payment-cart`
FROM funnel 
GROUP BY ALL
ORDER BY event_date