Introduction
This book is a very early draft - ideas are being sketched out and played with. The direction and focus may change. Most of the content is high level and work in progress. It is online so that we can get early feedback. Check back regularly to see updates and feel free to make suggestions.
The world of data science is changing at an astonishing pace. Significant advances in both the theory and practical implementation of machine learning and AI are happening almost daily.
It can be hard to build an understanding of the essential concepts that relate to data science in the modern world because there is simply so much information out there - and the landscape is changing so quickly.
The goal of Excel to AI is to rapidly go through the development of the applications of data science, starting with the basics of analysis in Excel, to the implementation of generative AI platforms like ChatGPT, covering the core concepts along the way. This book is aimed at a broad set of readers. The idea is that you can stay high-level and conceptual, and understand the practical applications of data science, or go deep and learn the how to actually implement these techniques.
This means the book will be valuable for both technical and non-technical readers.
This allows you to quickly understand how the technology and techniques have evolved, find the point at which you want to learn more, and then go as deep as you need.
Each chapter aims to introduce fundamental concepts clearly and with practical applications. You can stick to these core concepts or go deeper by actually learning how to use these techniques in practice using Python, one of the most popular languages used by Data Scientists. These Python demonstrations are interactive and can be used as a high-paced way to learn the language or expand your existing skills.
Through each chapter we work on a dataset that gets larger, more varied, more complex and a lot more messy - just like real world data sets. The essential concepts of data science are taught by asking how we can get more sophisticated insights from an ever more complex set of data - essentially by following the pattern that has driven research and development.
Let's get started.
Part 1 - Introduction to Data Science
The first part of this book teaches the fundamentals of Data Science. It also introduces the tools we'll use to perform analysis - such as Python and Juypter. This will provide a strong conceptual and practical foundation that we will build upon with more advanced topics in the following chapters.
Chapter 1 - Structured Data & Visualisation
In Chapter 1 we define the meaning of Data Science. We'll then introduce the concept of structured data using a simple dataset. We'll perform simple analysis in Excel - and then jump right into Python and Jupyter Notebooks.
Step by step we'll see how to perform the same analysis interactively using Python - a programming language that is highly popular with data scientists.
In each chapter that follows, our dataset will grow in size and complexity. We'll also be introducing increasingly sophisticated applications of data science. This will allow us to demonstrate and learn more advanced Python and data engineering skills.
Chapter 2 - Predictions
Chapter 3 - Sizes
- Challenge group orders in such a way to determine whether overall profits are driven by a small number of large ticket items or a large number of small ticket items.
🧠 Ananconda