Discover how TPOT can be used to handle automation in machine learning and explore the different types of tasks that TPOT can automate
Key Features
• Understand parallelism and how to achieve it in Python.
• Learn how to use neurons, layers, and activation functions and structure an artificial neural network.
• Tune TPOT models to ensure optimum performance on previously unseen data.
Book Description
The automation of machine learning tasks allows developers more time to focus on the usability and reactivity of the software powered by machine learning models. TPOT is a Python automated machine learning tool used for optimizing machine learning pipelines using genetic programming. Automating machine learning with TPOT enables individuals and companies to develop production-ready machine learning models cheaper and faster than with traditional methods.
With this practical guide to AutoML, developers working with Python on machine learning tasks will be able to put their knowledge to work and become productive quickly. You'll adopt a hands-on approach to learning the implementation of AutoML and associated methodologies. Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, this book will show you how to build automated classification and regression models and compare their performance to custom-built models. As you advance, you'll also develop state-of-the-art models using only a couple of lines of code and see how those models outperform all of your previous models on the same datasets.
By the end of this book, you'll have gained the confidence to implement AutoML techniques in your organization on a production level.
What you will learn
• Get to grips with building automated machine learning models
• Build classification and regression models with impressive accuracy in a short time
• Develop neural network classifiers with AutoML techniques
• Compare AutoML models with traditional, manually developed models on the same datasets
• Create robust, production-ready models
• Evaluate automated classification models based on metrics such as accuracy, recall, precision, and f1-score
• Get hands-on with deployment using Flask-RESTful on localhost
Who this book is for
Data scientists, data analysts, and software developers who are new to machine learning and want to use it in their applications will find this book useful. This book is also for business users looking to automate business tasks with machine learning. Working knowledge of the Python programming language and beginner-level understanding of machine learning are necessary to get started.
Author(s): Dario Radečić
Edition: 1
Publisher: Packt Publishing
Year: 2021
Language: English
Commentary: Vector PDF
Pages: 270
City: Birmingham, UK
Tags: Machine Learning; Data Analysis; Genetic Algorithms; Neural Networks; Regression; Data Science; Python; Classification; Parallel Programming; Pipelines; Flask; AutoML; Automation; Dask; RESTful API; Model Deployment; Evolutionary Algorithms; TPOT
Cover
Title Page
Copyright and Credits
Contributors
Table of Contents
Preface
Section 1: Introducing Machine Learning and the Idea of Automation
Chapter 1: Machine Learning and the Idea of Automation
Technical requirements
Reviewing the history of machine learning
What is machine learning?
In which sectors are the companies using machine learning?
Supervised learning
Reviewing automation
What is automation?
Why is automation needed?
Are machine learning and automation the same thing?
Applying automation to machine learning
What are we trying to automate?
The problem of too many parameters
What is AutoML?
Automation options
PyCaret
ObviouslyAI
TPOT
Summary
Q&A
Further reading
Section 2: TPOT – Practical Classification and Regression
Chapter 2: Deep Dive into TPOT
Technical requirements
Introducing TPOT
A brief overview of genetic programming
TPOT limitations
Types of problems TPOT can solve
How TPOT handles regression tasks
How TPOT handles classification tasks
Installing TPOT and setting up the environment
Installing and configuring TPOT with standalone Python installation
Installing and configuring TPOT through Anaconda
Summary
Q&A
Further reading
Chapter 3: Exploring Regression with TPOT
Technical requirements
Applying automated regression modeling to the fish market dataset
Applying automated regression modeling to the insurance dataset
Applying automated regression modeling to the vehicle dataset
Summary
Q&A
Chapter 4: Exploring Classification with TPOT
Technical requirements
Applying automated classification models to the iris dataset
Applying automated classification modeling to the titanic dataset
Summary
Q&A
Chapter 5: Parallel Training with TPOT and Dask
Technical requirements
Introduction to parallelism in Python
Introduction to the Dask library
Training machine learning models with TPOT and Dask
Summary
Q&A
Section 3: Advanced Examples and Neural Networks in TPOT
Chapter 6: Getting Started with Deep Learning: Crash Course in Neural Networks
Technical requirements
Overview of deep learning
Introducing artificial neural networks
Theory of a single neuron
Coding a single neuron
Theory of a single layer
Coding a single layer
Activation functions
Using neural networks to classify handwritten digits
Neural networks in regression versus classification
Summary
Q&A
Chapter 7: Neural Network Classifier with TPOT
Technical requirements
Exploring the dataset
Exploring options for training neural network classifiers
Training a neural network classifier
Summary
Questions
Chapter 8: TPOT Model Deployment
Technical requirements
Why do we need model deployment?
Introducing Flask and Flask-RESTful
Best practices for deploying automated models
Deploying machine learning models to localhost
Deploying machine learning models to the cloud
Summary
Question
Chapter 9: Using the Deployed TPOT Model in Production
Technical requirements
Making predictions in a notebook environment
Developing a simple GUI web application
Making predictions in a GUI environment
Summary
Q&A
Why subscribe?
About Packt
Other Books You May Enjoy
Index
