Practical Machine Learning with LightGBM and Python

Get to the grips with the fast, distributed, and high-performing gradient boosting framework to perform, analyze, and optimize data science and machine learning tasks Key Features * Become well-versed with the LightGBM framework and how it fits into decision tree algorithms * Understand how to use LightGBM to solve various data science problems * Explore advanced topics such as optimization, fine-tuning, and building accurate machine learning models Book Description LightGBM by Microsoft uses histogram-based algorithms for decision tree learning. This book will help you compare LightGBM with other gradient boosting frameworks to understand how it works best for large-scale data, providing faster training speed and much better accuracy. The book helps you get acquainted with the different parameters and features in LightGBM and shows you how to use it to solve at least 10 different real-world data science problems. Practical Machine Learning with LightGBM and Python covers examples that will guide you in solving problems in different runtime environments, along with detailed explanations to fine-tune models for efficiency and accuracy. As you advance, you'll be able to speed up machine learning training processes in different environments through parallelization, apply GPU in the mix, and analyze how LightGBM is used in Kaggle competitions to improve existing solutions. Finally, you'll transform the LightGBM model to an ONNX format so that it can be used in a variety of other ML pipelines. By the end of this book, you'll have learned how to use LightGBM to overcome machine learning problems and be able to optimize and fine-tune the entire workflow by building an end-to-end solution from scratch. What you will learn * Get under the hood of the LightGBM machine learning framework * Implement optimization and fine-tuning techniques while working on different data science problems * Improve MLOps pipelines with LightGBM for more speed with GPU and parallel training * Solve over 10 different real-world problems with LightGBM * Build an end-to-end data science solution using LightGBM and various other components * Apply LightGBM with other popular environments running on-premises and in the cloud * Transform the LightGBM model to the ONNX format Who This Book Is For This book is for data scientists, data science professionals, and data analysts looking to use a distributed and high-performance gradient boosting framework for building accurate and scalable machine learning models. If you want to learn how to choose the right algorithm to solve your problem and optimize it for best use, you'll find this book helpful. A basic understanding of data science and working knowledge of Python is required.