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

Reinforcing learning through Python Notebook

Pluto uses the Python Notebook to reinforce our understanding of text augmentation. He uses the batch function to display text in batches. This works similarly to the batch functions for images. In other words, it randomly selects new records and transforms them using the augmentation methods.

Fun fact

Pluto recommends running the batch functions repeatedly to gain a deeper insight into the text augmentation methods. There are thousands of text records in the Twitter and Amazon datasets. Each time you run the batch functions, it displays different records from the dataset.

As with the image augmentation implementation, the wrapper functions use the Nlpaug library under the hood. The wrapper function allows you to focus on the text transformation concepts and not be distracted by the library implementation. You can use another text augmentation library, and the wrapper function input and output will remain the same.

Pluto could...