Data Science Foundations: Data Preparation and Wrangling in Azure ML

Preparing raw data is the most critical and time-consuming phase of any data science project. This text-based course guides you through the foundational concepts of data preparation, helping you transform messy, real-world datasets into clean, model-ready inputs within Azure Machine Learning. You will start with the core terminology of data science, learning how to distinguish between continuous and categorical variables and understand data distribution. Through clear explanations and practical written examples, you will learn how to handle common data issues such as duplicate values, outliers, and missing information. We also cover modern data science practices, including how to structure your pipelines for reproducibility and manage datasets securely in cloud environments. What you'll learn: - Understand foundational data science concepts and the data preparation lifecycle - Profile and analyze continuous and categorical variables to understand your data's structure - Clean datasets by identifying and removing duplicates, handling missing values, and managing outliers - Register and manage datasets securely within Azure Machine Learning - Prepare data pipelines that ensure consistent preprocessing for training and inference This course starts with the absolute basics of data types and progressively moves into practical cleaning and wrangling techniques in the cloud. You will read through step-by-step workflows and conceptual breakdowns designed to build your confidence from the ground up. This course is designed for beginners, aspiring data scientists, and analysts who want to learn how to prepare data systematically. No prior experience with machine learning or cloud platforms is required. Start reading today to build a solid foundation in data preparation.