Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Simplifying Data Engineering and Analytics with Delta

You're reading from  Simplifying Data Engineering and Analytics with Delta

Product type Book
Published in Jul 2022
Publisher Packt
ISBN-13 9781801814867
Pages 334 pages
Edition 1st Edition
Languages
Concepts
Author (1):
Anindita Mahapatra Anindita Mahapatra
Profile icon Anindita Mahapatra

Table of Contents (18) Chapters

Preface Section 1 – Introduction to Delta Lake and Data Engineering Principles
Chapter 1: Introduction to Data Engineering Chapter 2: Data Modeling and ETL Chapter 3: Delta – The Foundation Block for Big Data Section 2 – End-to-End Process of Building Delta Pipelines
Chapter 4: Unifying Batch and Streaming with Delta Chapter 5: Data Consolidation in Delta Lake Chapter 6: Solving Common Data Pattern Scenarios with Delta Chapter 7: Delta for Data Warehouse Use Cases Chapter 8: Handling Atypical Data Scenarios with Delta Chapter 9: Delta for Reproducible Machine Learning Pipelines Chapter 10: Delta for Data Products and Services Section 3 – Operationalizing and Productionalizing Delta Pipelines
Chapter 11: Operationalizing Data and ML Pipelines Chapter 12: Optimizing Cost and Performance with Delta Chapter 13: Managing Your Data Journey Other Books You May Enjoy

Applying sampling techniques to address class imbalance

Let's look at a scenario where there's a cell culture dataset that is being analyzed using machine learning (ML) algorithms to predict the onset of cancer. Most cells are normal; a small percentage may be abnormal. The two primary classes here are "normal" and "abnormal." This is an imbalanced dataset. This applies to multi-class datasets as well. An imbalance occurs when one or more classes have low proportions in the training data compared to other classes. Since the ML process involves "learning" from the dataset, there is a lot to learn about the normal scenarios and very little about the cancer ones. Most ML algorithms for classification are designed and demonstrated on problems that assume an equal distribution of classes and are designed to maximize accuracy and reduce error. The consequence of this imbalanced dataset is that the model is biased. Sometimes, it goes undetected and...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime}