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

Transforming augmentation

Before digging into the tabular augmentation methods, Pluto will reiterate that he will not build a neural network model to test if the augmentation benefits the particular dataset. In addition, the pattern for writing the wrapper functions follows the previous practice: using the chosen library to do the critical augmentation step.

As the Python Notebook notes, the DeltaPy library’s dependency is the fbprofet and pystan libraries. The three libraries are in beta and may be unstable. Pluto has repeatedly tested the Python code. Once the libraries have been loaded, the code works flawlessly.

Tabular transformation is a collection of techniques that take one variable and generate a new dataset based on the transformation method. It applies to both cross-section and time series data. The DeltaPy library defines 14 functions for transformation.

These transformation techniques include the operations functions used in present information, the smoothing...