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

Interaction augmentation

Interaction techniques are used in ML and statistical modeling to capture the relationships between two or more features in a dataset for augmentation. The goal is to create new augmentation data that captures the interaction between existing components, which can help improve model performance and provide additional insights into the data. You can apply these techniques to cross-sectional or time-specific data, including normalizing, discretizing, and autoregression models.

Pluto has selected two out of seven methods for a hands-on Python programming demonstration. As with the transformation augmentation methods, the coding is repetitive. Thus, Pluto will provide fun challenges for the other five interaction augmentation techniques.

Pluto will start with the regression method, then the operator method.

Regression augmentation

The regression method uses the lowess smoother function to smooth the curve of the data by locally weighting the observations...