Book Image

The Data Science Workshop - Second Edition

By : Anthony So, Thomas V. Joseph, Robert Thas John, Andrew Worsley, Dr. Samuel Asare
5 (1)
Book Image

The Data Science Workshop - Second Edition

5 (1)
By: Anthony So, Thomas V. Joseph, Robert Thas John, Andrew Worsley, Dr. Samuel Asare

Overview of this book

Where there’s data, there’s insight. With so much data being generated, there is immense scope to extract meaningful information that’ll boost business productivity and profitability. By learning to convert raw data into game-changing insights, you’ll open new career paths and opportunities. The Data Science Workshop begins by introducing different types of projects and showing you how to incorporate machine learning algorithms in them. You’ll learn to select a relevant metric and even assess the performance of your model. To tune the hyperparameters of an algorithm and improve its accuracy, you’ll get hands-on with approaches such as grid search and random search. Next, you’ll learn dimensionality reduction techniques to easily handle many variables at once, before exploring how to use model ensembling techniques and create new features to enhance model performance. In a bid to help you automatically create new features that improve your model, the book demonstrates how to use the automated feature engineering tool. You’ll also understand how to use the orchestration and scheduling workflow to deploy machine learning models in batch. By the end of this book, you’ll have the skills to start working on data science projects confidently. By the end of this book, you’ll have the skills to start working on data science projects confidently.
Table of Contents (16 chapters)
Preface
12
12. Feature Engineering

Clustering with k-means

k-means is one of the most popular clustering algorithms (if not the most popular) among data scientists due to its simplicity and high performance. Its origins date back as early as 1956, when a famous mathematician named Hugo Steinhaus laid its foundations, but it was a decade later that another researcher called James MacQueen named this approach k-means.

The objective of k-means is to group similar data points (or observations) together that will form a cluster. Think of it as grouping elements close to each other (we will define how to measure closeness later in this chapter). For example, if you were manually analyzing user behavior on a mobile app, you might end up grouping customers who log in quite frequently, or users who make bigger in-app purchases, together. This is the kind of grouping that clustering algorithms such as k-means will automatically find for you from the data.

In this chapter, we will be working with an open source dataset...