What this book covers

Chapter 1, Machine Learning and the Idea of Automation, covers a brief introduction to machine learning, the difference between classification and regression tasks, an overview of automation and why it is needed, and the machine learning options in the Python ecosystem.

Chapter 2, Deep Dive into TPOT, provides an in-depth overview of what TPOT is and isn't, how it is used to handle automation in machine learning, and what types of tasks it can automate. This chapter also sees you set up the programming environment.

Chapter 3, Exploring Regression with TPOT, covers the use of TPOT for regression tasks. You'll learn how to apply automated algorithms to data and how to explore your datasets.

Chapter 4, Exploring Classification with TPOT, covers the use of TPOT for classification tasks. You'll learn how to perform basic exploratory data analysis, preparation, train automated models, and compare these automated models with default models from scikit-learn.

Chapter 5, Parallel Training with TPOT and Dask, covers the basics of parallel programming with Python and the Dask library. You'll learn how to use Dask to train automated models in a parallel fashion.

Chapter 6, Getting Started with Deep Learning: A Crash Course in Neural Networks, covers the fundamental ideas behind deep learning, such as neurons, layers, activation functions, and artificial neural networks.

Chapter 7, Neural Network Classifier with TPOT, provides a step-by-step guide to implementing a fully automated neural network classifier, dataset exploration, model training, and evaluation.

Chapter 8, TPOT Model Deployment, takes you through a step-by-step guide to model deployment. You'll learn how to use Flask and Flask-RESTful to build a REST API that is then deployed both locally and to AWS.

Chapter 9, Using the Deployed TPOT Model in Production, covers the usage of the deployed model in a notebook environment and in a simple web application.