Skip to Main Content
Data Science Using Python and R
book

Data Science Using Python and R

by Chantal D. Larose, Daniel T. Larose
April 2019
Beginner to intermediate content levelBeginner to intermediate
240 pages
6h 47m
English
Wiley
Content preview from Data Science Using Python and R

Chapter 14ASSOCIATION RULES

14.1 INTRODUCTION TO ASSOCIATION RULES

Association rules seek to uncover associations among the variables and take the form “If antecedent, then consequent,” along with a measure of the support and confidence associated with the rule. For example, a particular supermarket may find that of the 1000 customers shopping on a Thursday night, 200 bought diapers, and of the 200 who bought diapers, 50 bought beer. Thus, the association rule would be: “If buy diapers, then buy beer,” with a support of 50/1000 = 5% and a confidence of 50/200 = 25%.

The daunting problem that awaits any such algorithm is the curse of dimensionality: The number of possible association rules grows exponentially in the number of attributes. Specifically, if there are k attributes, we limit ourselves to binary attributes, we account only for the positive cases (e.g. buy diapers = yes), there are on the order of k ∙ 2k − 1 possible association rules.1 Consider that a typical application for association rules is market basket analysis and that there may be thousands of binary attributes (buy beer? buy popcorn? buy milk? buy bread? etc.), the search problem appears at first glance to be utterly hopeless. For example, suppose that a tiny convenience store has only 100 different items and a customer could either buy or not buy any combination of those 100 items. Then, there are 2100 ≅ 1.27 × 1030 possible association rules that await your intrepid search algorithm. Thankfully, however, ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Practical Data Science with Python 3: Synthesizing Actionable Insights from Data

Practical Data Science with Python 3: Synthesizing Actionable Insights from Data

Ervin Varga
Python Data Science Essentials - Third Edition

Python Data Science Essentials - Third Edition

Alberto Boschetti, Luca Massaron, Pietro Marinelli, Matteo Malosetti

Publisher Resources

ISBN: 9781119526810Purchase book