Book Image

Machine Learning with R - Third Edition

By : Brett Lantz
Book Image

Machine Learning with R - Third Edition

By: Brett Lantz

Overview of this book

Machine learning, at its core, is concerned with transforming data into actionable knowledge. R offers a powerful set of machine learning methods to quickly and easily gain insight from your data. Machine Learning with R, Third Edition provides a hands-on, readable guide to applying machine learning to real-world problems. Whether you are an experienced R user or new to the language, Brett Lantz teaches you everything you need to uncover key insights, make new predictions, and visualize your findings. This new 3rd edition updates the classic R data science book to R 3.6 with newer and better libraries, advice on ethical and bias issues in machine learning, and an introduction to deep learning. Find powerful new insights in your data; discover machine learning with R.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning with R - Third Edition
Brett Lantz
Apr, 2019 | 458 pages
Small book image
Mastering Predictive Analytics with R
Rui Miguel Forte | James D Miller
Aug, 2017 | 448 pages
Small book image
Mastering Machine Learning with R
Cory Lesmeister
Apr, 2017 | 420 pages
Small book image
Mastering Machine Learning with R.
Cory Lesmeister
Jan, 2019 | 354 pages
Table of Contents (18 chapters)
Machine Learning with R - Third Edition
Machine Learning with R - Third Edition
Contributors
Contributors
Preface
Preface
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Leave a review - let other readers know what you think
Free Chapter
1
Introducing Machine Learning
Introducing Machine Learning
The origins of machine learning
Uses and abuses of machine learning
How machines learn
Machine learning in practice
Machine learning with R
Summary
2
Managing and Understanding Data
Managing and Understanding Data
R data structures
Managing data with R
Exploring and understanding data
Summary
3
Lazy Learning – Classification Using Nearest Neighbors
Lazy Learning – Classification Using Nearest Neighbors
Understanding nearest neighbor classification
Example – diagnosing breast cancer with the k-NN algorithm
Summary
4
Probabilistic Learning – Classification Using Naive Bayes
Probabilistic Learning – Classification Using Naive Bayes
Understanding Naive Bayes
Example – filtering mobile phone spam with the Naive Bayes algorithm
Summary
5
Divide and Conquer – Classification Using Decision Trees and Rules
Divide and Conquer – Classification Using Decision Trees and Rules
Understanding decision trees
Example – identifying risky bank loans using C5.0 decision trees
Understanding classification rules
Example – identifying poisonous mushrooms with rule learners
Summary
6
Forecasting Numeric Data – Regression Methods
Forecasting Numeric Data – Regression Methods
Understanding regression
Example – predicting medical expenses using linear regression
Understanding regression trees and model trees
Example – estimating the quality of wines with regression trees and model trees
Summary
7
Black Box Methods – Neural Networks and Support Vector Machines
Black Box Methods – Neural Networks and Support Vector Machines
Understanding neural networks
Example – modeling the strength of concrete with ANNs
Understanding support vector machines
Example – performing OCR with SVMs
Summary
8
Finding Patterns – Market Basket Analysis Using Association Rules
Finding Patterns – Market Basket Analysis Using Association Rules
Understanding association rules
Example – identifying frequently purchased groceries with association rules
Summary
9
Finding Groups of Data – Clustering with k-means
Finding Groups of Data – Clustering with k-means
Understanding clustering
Finding teen market segments using k-means clustering
Summary
10
Evaluating Model Performance
Evaluating Model Performance
Measuring performance for classification
Estimating future performance
Summary
11
Improving Model Performance
Improving Model Performance
Tuning stock models for better performance
Improving model performance with meta-learning
Summary
12
Specialized Machine Learning Topics
Specialized Machine Learning Topics
Managing and preparing real-world data
Working with online data and services
Working with domain-specific data
Improving the performance of R
Summary
Index
Index

Estimating future performance

Some R machine learning packages present confusion matrices and performance measures during the model-building process. The purpose of these statistics is to provide insight about the model's resubstitution error, which occurs when the training data is incorrectly predicted in spite of the model being built directly from this data. This information can be used as a rough diagnostic to identify obviously poor performers.

The resubstitution error is not a very useful marker of future performance, however. For example, a model that used rote memorization to perfectly classify every training instance with zero resubstitution error would be unable to generalize its predictions to data it has never seen before. For this reason, the error rate on the training data can be extremely optimistic about a model's future performance.

Instead of relying on resubstitution error, a better practice is to evaluate a model's performance on data it has not yet seen. We used such a...

Previous Section
End of Section 3
Next Section