Book Image

Data Augmentation with Python

By : Duc Haba
Book Image

Data Augmentation with Python

By: Duc Haba

Overview of this book

Data is paramount in AI projects, especially for deep learning and generative AI, as forecasting accuracy relies on input datasets being robust. Acquiring additional data through traditional methods can be challenging, expensive, and impractical, and data augmentation offers an economical option to extend the dataset. The book teaches you over 20 geometric, photometric, and random erasing augmentation methods using seven real-world datasets for image classification and segmentation. You’ll also review eight image augmentation open source libraries, write object-oriented programming (OOP) wrapper functions in Python Notebooks, view color image augmentation effects, analyze safe levels and biases, as well as explore fun facts and take on fun challenges. As you advance, you’ll discover over 20 character and word techniques for text augmentation using two real-world datasets and excerpts from four classic books. The chapter on advanced text augmentation uses machine learning to extend the text dataset, such as Transformer, Word2vec, BERT, GPT-2, and others. While chapters on audio and tabular data have real-world data, open source libraries, amazing custom plots, and Python Notebook, along with fun facts and challenges. By the end of this book, you will be proficient in image, text, audio, and tabular data augmentation techniques.
Table of Contents (17 chapters)
Part 1: Data Augmentation
Part 2: Image Augmentation
Part 3: Text Augmentation
Part 4: Audio Data Augmentation
Part 5: Tabular Data Augmentation

Exploring and visualizing tabular data

Tabular augmentation is more challenging than image, text, and audio augmentation. The primary reason is that you need to build a CNN or RNN model to see the effect of the synthetic data.

Pluto will spend more time explaining his journey to investigate the real-world Bank Fraud and World Series datasets than implementing the tabular augmentation functions using the DeltaPy library. Once you understand the data visualization process, you can apply it to other tabular datasets.

Fun fact

Typically, Pluto starts a chapter by writing code in the Python Notebook for that chapter. It consists of around 150 to 250 combined code and text cells. They are unorganized collections of research notes and try-and-error Python code cells. Once Pluto proves that the concepts and techniques are working correctly through coding, he starts writing the chapter. As part of the writing progress, he cleans and refactors the Python Notebook with wrapper functions...