Exploring and visualizing tabular data
Tabular augmentation is more challenging than image, text, and audio augmentation. The primary reason is that you need to build a CNN or RNN model to see the effect of the synthetic data.
Pluto will spend more time explaining his journey to investigate the real-world Bank Fraud and World Series datasets than implementing the tabular augmentation functions using the DeltaPy library. Once you understand the data visualization process, you can apply it to other tabular datasets.
Fun fact
Typically, Pluto starts a chapter by writing code in the Python Notebook for that chapter. It consists of around 150 to 250 combined code and text cells. They are unorganized collections of research notes and try-and-error Python code cells. Once Pluto proves that the concepts and techniques are working correctly through coding, he starts writing the chapter. As part of the writing progress, he cleans and refactors the Python Notebook with wrapper functions...
