How to build a recommendation system
Have you ever wondered how Amazon was breaking in your wallet by suggesting products that you couldn’t resist buying? How Netflix found this awesome movie that you love? Well, it’s all part of the magic that goes into their recommendation systems. These recommenders are developed to find patterns in your preferences, search for similar patterns in other people and make relevant suggestions that will encourage you to spend more on the company’s products and services. In this post, I’ll explain the basic idea behind a recommender system and how to build a simple one based on book reviews of the 1 million book ratings database.
R: Scraping the Release Dates of Github Projects
In theory the release dates should be accessible through the github API but the few that I looked at weren’t returning any data so I scraped the data together.
Nine Laws of Data Mining
Data mining is the creation of new knowledge in natural or artificial form, by using business knowledge to discover and interpret patterns in data.
1st Law: ‘Business Goals Law’: Business objectives are the origin of every data mining solution
2nd Law: ‘Business Knowledge Law’: Business knowledge is central to every step of the data mining process
3rd Law: ‘Data Preparation Law’: Data preparation is more than half of every data mining process
4th Law: ‘NFL-DM’: The right model for a given application can only be discovered by experiment or ‘There is No Free Lunch for the Data Miner’
5th Law: ‘Watkins’ Law’: There are always patterns
6th Law: ‘Insight Law’: Data mining amplifies perception in the business domain
7th Law: ‘Prediction Law’: Prediction increases information locally by generalisation
8th Law: ‘Value Law’: The value of data mining results is not determined by the accuracy or stability of predictive models
9th Law: ‘Law of Change’: All patterns are subject to change
Shiny finally has a colour picker – use colourInput to select colours in Shiny apps
Shiny has many useful input controls, but there was one that was always missing until today – a colour picker. The package shinyjs now has a colourInput() function and, of course, a corresponding updateColourInput(). There have been many times when I wanted to allow users in a Shiny app to select a colour, and I’ve seen that feature being requested multiple times on different online boards, so I decided to make my own such input control.