Skip to Content
Hands-On Automated Machine Learning
book

Hands-On Automated Machine Learning

by Sibanjan Das, Umit Mert Cakmak
April 2018
Beginner to intermediate content levelBeginner to intermediate
282 pages
6h 52m
English
Packt Publishing
Content preview from Hands-On Automated Machine Learning

Detecting and treating univariate outliers

As the names imply, univariate outliers are based on a single attribute in a dataset. Univariate outliers are discovered using box plots and by seeing the distribution of the values of an attribute. However, when we build AutoML pipelines, we don't have the privilege to visualize the data distribution. Instead, the AutoML system should be able to detect the outliers and treat them by itself.

So, we can deploy any of the following three methods for automated univariate outlier detection and treatment:

  • Interquartile range and filtering
  • Winsorizing
  • Trimming

Let's create a dummy outlier dataset to demonstrate the outlier detection and treatment method:

%matplotlib inlineimport numpy as npimport matplotlib.pyplot ...
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

Automated Machine Learning

Automated Machine Learning

Adnan Masood
R: Unleash Machine Learning Techniques

R: Unleash Machine Learning Techniques

Raghav Bali, Dipanjan Sarkar, Brett Lantz, Cory Lesmeister

Publisher Resources

ISBN: 9781788629898Supplemental Content