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


At first glance, text augmentation seems counterintuitive and problematic because the techniques inject errors into the text. Still, DL based on CNNs or RNNs recognizes patterns regardless of a few misspellings or synonym replacements. Furthermore, many published scholarly papers have described the benefits of text augmentation to increase prediction or forecast accuracy.

In Chapter 5, you learned about three Character augmentation techniques, OCR, Keyboard, and Random. In addition, the six Word augmentation techniques are the Misspell, Split, Random, Synonyms, Antonyms, and Reserved words. There are more text augmentation methods in the Nlgaug, NLTK, Gensim, TextBlob, and Augly libraries.

Implementing the text augmentation methods using a Python Notebook is deceptively simple. This is because Pluto built a solid foundation layer in Chapter 1 with an object-oriented class and learned how to extend the object with decorator as he discovered new augmentation techniques...