Histogrammen

Zakelijke data analyseren in SQL

Michel Semaan

Data Scientist

Histogrammen - overzicht

Histogram: visualiseert de frequentie van elke waarde in een dataset

Frequentietabel

orders  users
------  -----
1       7
2       42
3       65
...     ...

Histogram van orders per user

Zakelijke data analyseren in SQL

Histogrammen - query (I)

WITH user_orders AS (
  SELECT
    user_id,
    COUNT(DISTINCT order_id) AS orders
  FROM meals
  JOIN orders ON meals.meal_id = orders.meal_id
  GROUP BY user_id)

SELECT orders, COUNT(DISTINCT user_id) AS users FROM user_orders GROUP BY orders ORDER BY orders ASC;
Zakelijke data analyseren in SQL

Histogrammen - query (II)

WITH user_revenues AS (
  SELECT
    user_id,
    SUM(meal_price * order_quantity) AS revenue
  FROM meals
  JOIN orders ON meals.meal_id = orders.meal_id
  GROUP BY user_id)

SELECT ROUND(revenue :: NUMERIC, -2) AS revenue_100, COUNT(DISTINCT user_id) AS users FROM user_revenues GROUP BY revenue_100 ORDER BY revenue_100 ASC;
Zakelijke data analyseren in SQL

Histogrammen plotten

Microsoft Excel

Google Spreadsheets

matplotlib

ggplot2

Zakelijke data analyseren in SQL

Wat vertellen histogrammen je?

U-vormig histogram

U-vormig histogram

  • Veel users met lage en hoge omzet; weinig met mediane omzet

Normaal histogram

Normaal histogram

  • Veel users met mediane omzet; weinig met lage of hoge omzet
Zakelijke data analyseren in SQL

Histogrammen

Zakelijke data analyseren in SQL

Preparing Video For Download...