Data Science and Model Tracking in Fabric

Modern data science requires a unified workspace where data preparation, model training, and experiment tracking happen seamlessly. This text-based course guides you through the foundational concepts of data science within the Fabric ecosystem, preparing you to handle real-world analytical tasks. You will transition from understanding basic workspace setups to confidently training machine learning models in interactive notebooks. By leveraging built-in tools, you will learn how to organize your datasets, run experiments, and systematically track model performance metrics. What you'll learn: Understand the foundational architecture of Fabric workspaces for data science; Prepare and explore datasets using notebooks and integrated data structures; Train machine learning models using popular Python libraries within a managed notebook environment; Track model parameters, metrics, and artifacts using MLflow integrations; Manage and compare different machine learning experiments to identify the best-performing models; Apply modern MLOps best practices for organizing and versioning your analytical assets. The course begins with core terminology and workspace configuration before moving into hands-on data exploration and model training. You will progress through structured text explanations and practical code examples that demonstrate how to manage the entire machine learning lifecycle. This course is designed for aspiring data scientists, analysts, and developers who want to learn Fabric without prior experience in the platform. Start reading today to build your foundation in modern cloud-based data science.