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


Tabular augmentation is a technique that can improve the accuracy of ML models by increasing the amount of data used. It adds columns or rows to a dataset generated by existing features or data from other sources. It increases the available input data, allowing the model to make more accurate predictions. Tabular augmentation adds new information not currently included in the dataset, increasing the model’s utility. Tabular augmentation is beneficial when used with other ML techniques, such as DL, to improve the accuracy and performance of predictive models.

Pluto downloaded the real-world Bank Fraud and World Series datasets from the Kaggle website. He wrote most of the code in the Python Notebook for visualizing large datasets using various graphs, such as histograms, heatmaps, correlograms, and waffle and joy plots. He did this because understanding the datasets is essential before augmenting them. However, he didn’t write a CNN or RNN model to verify the...