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

Mapping augmentation

The mapping method uses ML and data analysis to summarize and reduce the dimensionality of data for augmentation. It can be done via unsupervised or supervised learning. Some examples of mapping methods include eigendecomposition and PCA. PCA is a statistical procedure that transforms a set of correlated variables into uncorrelated variables called principal components.

In the DeltaPy library, there are seven mapping methods for tabular augmentation. Pluto has done a few implementations in the Python Notebook, but he will not explain the coding here. The Python wrapper function is repetitive and can easily be applied to any mapping method. The functions are as follows:

  • Eigendecomposition (ED) is a form of PCA for tabular augmentation. In ED, the eigenvectors are the covariance matrix of the data, and the corresponding eigenvalues represent the amount of variance by each component. ED includes linear discriminant analysis (LDA), singular value decomposition...