Machine Learning and Go (Golang): From Basics to Production

This book is the first practical guide in Russian on building machine learning systems in the Go language. If you are a Go developer looking to integrate ML into your projects, or a data scientist interested in a performant and reliable language for production, this book is for you.

What the book is about

The book covers the complete machine learning workflow in Go: from data collection and preprocessing, building models (linear regression, decision trees, neural networks) to deploying them in a microservice architecture. Special attention is given to:

• Libraries and frameworks: golearn, Gorgonia, gonum, tfgo (TensorFlow for Go);
• Processing large volumes of data using channels and goroutines;
• Integration with external ML services (TensorFlow Serving, ONNX Runtime);
• Creating REST/gRPC APIs for models;
• Testing, monitoring, and A/B testing of ML systems.

Who this book is for

• Go developers who want to add machine learning to their stack;
• Data scientists looking to transition from Python to more performant Go;
• DevOps engineers responsible for deploying ML models;
• Students and instructors of machine learning courses.

What you will learn

• How to choose the right tool for a specific ML task in Go;
• How to build and train regression, classification, and clustering models;
• How to optimize a model for high load and low latency;
• How to integrate a model into an existing Go service (e.g., using the Gin or Echo framework);
• How to use ONNX to transfer models between Python and Go;
• How to write unit tests for ML components and manage model versions (DVC, Git LFS).

Why Go for ML?

Go combines the performance of C/C++ with the simplicity of Python. It is ideal for production: static typing, fast compilation, built-in concurrency support. The book shows how these advantages help build scalable and reliable ML systems.

Example from the book

In Chapter 5, you will implement a recommendation service based on collaborative filtering — from loading data from CSV to deploying in Docker with Kubernetes. The full code and tests are available in the repository.

The book is intended for readers with a basic knowledge of Go (syntax, structures, interfaces) and the fundamentals of machine learning (what features, metrics, and overfitting are).