Machine Learning with R: Learn techniques for building and improving machine learning models, from data preparation to model tuning, evaluation, and working with big data, 4th Edition

Cover
Copyright
Contributors
Table of Contents
Preface
Chapter 1: Introducing Machine Learning
	The origins of machine learning
	Uses and abuses of machine learning
		Machine learning successes
		The limits of machine learning
		Machine learning ethics
	How machines learn
		Data storage
		Abstraction
		Generalization
		Evaluation
	Machine learning in practice
		Types of input data
		Types of machine learning algorithms
		Matching input data to algorithms
	Machine learning with R
		Installing R packages
		Loading and unloading R packages
		Installing RStudio
		Why R and why R now?
	Summary
Chapter 2: Managing and Understanding Data
	R data structures
		Vectors
		Factors
		Lists
		Data frames
		Matrices and arrays
	Managing data with R
		Saving, loading, and removing R data structures
		Importing and saving datasets from CSV files
		Importing common dataset formats using RStudio
	Exploring and understanding data
		Exploring the structure of data
		Exploring numeric features
			Measuring the central tendency – mean and median
			Measuring spread – quartiles and the five-number summary
			Visualizing numeric features – boxplots
			Visualizing numeric features – histograms
			Understanding numeric data – uniform and normal distributions
			Measuring spread – variance and standard deviation
		Exploring categorical features
			Measuring the central tendency – the mode
		Exploring relationships between features
			Visualizing relationships – scatterplots
			Examining relationships – two-way cross-tabulations
	Summary
Chapter 3: Lazy Learning – Classification Using Nearest Neighbors
	Understanding nearest neighbor classification
		The k-NN algorithm
			Measuring similarity with distance
			Choosing an appropriate k
			Preparing data for use with k-NN
		Why is the k-NN algorithm lazy?
	Example – diagnosing breast cancer with the k-NN algorithm
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Transformation – normalizing numeric data
			Data preparation – creating training and test datasets
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
			Transformation – z-score standardization
			Testing alternative values of k
	Summary
Chapter 4: Probabilistic Learning – Classification Using Naive Bayes
	Understanding Naive Bayes
		Basic concepts of Bayesian methods
			Understanding probability
			Understanding joint probability
			Computing conditional probability with Bayes’ theorem
		The Naive Bayes algorithm
			Classification with Naive Bayes
			The Laplace estimator
			Using numeric features with Naive Bayes
	Example – filtering mobile phone spam with the Naive Bayes algorithm
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Data preparation – cleaning and standardizing text data
			Data preparation – splitting text documents into words
			Data preparation – creating training and test datasets
			Visualizing text data – word clouds
			Data preparation – creating indicator features for frequent words
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
	Summary
Chapter 5: Divide and Conquer – Classification Using Decision Trees and Rules
	Understanding decision trees
		Divide and conquer
		The C5.0 decision tree algorithm
			Choosing the best split
			Pruning the decision tree
	Example – identifying risky bank loans using C5.0 decision trees
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Data preparation – creating random training and test datasets
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
			Boosting the accuracy of decision trees
			Making some mistakes cost more than others
	Understanding classification rules
		Separate and conquer
		The 1R algorithm
		The RIPPER algorithm
		Rules from decision trees
		What makes trees and rules greedy?
	Example – identifying poisonous mushrooms with rule learners
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
	Summary
Chapter 6: Forecasting Numeric Data – Regression Methods
	Understanding regression
		Simple linear regression
		Ordinary least squares estimation
		Correlations
		Multiple linear regression
		Generalized linear models and logistic regression
	Example – predicting auto insurance claims costs using linear regression
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Exploring relationships between features – the correlation matrix
			Visualizing relationships between features – the scatterplot matrix
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
			Model specification – adding nonlinear relationships
			Model specification – adding interaction effects
			Putting it all together – an improved regression model
			Making predictions with a regression model
		Going further – predicting insurance policyholder churn with logistic regression
	Understanding regression trees and model trees
		Adding regression to trees
	Example – estimating the quality of wines with regression trees and model trees
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
		Step 3 – training a model on the data
			Visualizing decision trees
		Step 4 – evaluating model performance
			Measuring performance with the mean absolute error
		Step 5 – improving model performance
	Summary
Chapter 7: Black-Box Methods – Neural Networks and Support Vector Machines
	Understanding neural networks
		From biological to artificial neurons
		Activation functions
		Network topology
			The number of layers
			The direction of information travel
			The number of nodes in each layer
		Training neural networks with backpropagation
	Example – modeling the strength of concrete with ANNs
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
	Understanding support vector machines
		Classification with hyperplanes
			The case of linearly separable data
			The case of nonlinearly separable data
		Using kernels for nonlinear spaces
	Example – performing OCR with SVMs
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
			Changing the SVM kernel function
			Identifying the best SVM cost parameter
	Summary
Chapter 8: Finding Patterns – Market Basket Analysis Using Association Rules
	Understanding association rules
		The Apriori algorithm for association rule learning
		Measuring rule interest – support and confidence
		Building a set of rules with the Apriori principle
	Example – identifying frequently purchased groceries with association rules
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Data preparation – creating a sparse matrix for transaction data
			Visualizing item support – item frequency plots
			Visualizing the transaction data – plotting the sparse matrix
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
			Sorting the set of association rules
			Taking subsets of association rules
			Saving association rules to a file or data frame
			Using the Eclat algorithm for greater efficiency
	Summary
Chapter 9: Finding Groups of Data – Clustering with k-means
	Understanding clustering
		Clustering as a machine learning task
		Clusters of clustering algorithms
		The k-means clustering algorithm
			Using distance to assign and update clusters
			Choosing the appropriate number of clusters
	Finding teen market segments using k-means clustering
		Step 1 – collecting data
		Step 2 – exploring and preparing the data
			Data preparation – dummy coding missing values
			Data preparation – imputing the missing values
		Step 3 – training a model on the data
		Step 4 – evaluating model performance
		Step 5 – improving model performance
	Summary
Chapter 10: Evaluating Model Performance
	Measuring performance for classification
		Understanding a classifier’s predictions
		A closer look at confusion matrices
		Using confusion matrices to measure performance
		Beyond accuracy – other measures of performance
			The kappa statistic
			The Matthews correlation coefficient
			Sensitivity and specificity
			Precision and recall
			The F-measure
		Visualizing performance tradeoffs with ROC curves
			Comparing ROC curves
			The area under the ROC curve
			Creating ROC curves and computing AUC in R
	Estimating future performance
		The holdout method
		Cross-validation
		Bootstrap sampling
	Summary
Chapter 11: Being Successful with Machine Learning
	What makes a successful machine learning practitioner?
	What makes a successful machine learning model?
		Avoiding obvious predictions
		Conducting fair evaluations
		Considering real-world impacts
		Building trust in the model
	Putting the “science” in data science
		Using R Notebooks and R Markdown
		Performing advanced data exploration
			Constructing a data exploration roadmap
			Encountering outliers: a real-world pitfall
			Example – using ggplot2 for visual data exploration
	Summary
Chapter 12: Advanced Data Preparation
	Performing feature engineering
		The role of human and machine
		The impact of big data and deep learning
	Feature engineering in practice
		Hint 1: Brainstorm new features
		Hint 2: Find insights hidden in text
		Hint 3: Transform numeric ranges
		Hint 4: Observe neighbors’ behavior
		Hint 5: Utilize related rows
		Hint 6: Decompose time series
		Hint 7: Append external data
	Exploring R’s tidyverse
		Making tidy table structures with tibbles
		Reading rectangular files faster with readr and readxl
		Preparing and piping data with dplyr
		Transforming text with stringr
		Cleaning dates with lubridate
	Summary
Chapter 13: Challenging Data – Too Much, Too Little, Too Complex
	The challenge of high-dimension data
		Applying feature selection
			Filter methods
			Wrapper methods and embedded methods
			Example – Using stepwise regression for feature selection
			Example – Using Boruta for feature selection
		Performing feature extraction
			Understanding principal component analysis
			Example – Using PCA to reduce highly dimensional social media data
	Making use of sparse data
		Identifying sparse data
		Example – Remapping sparse categorical data
		Example – Binning sparse numeric data
	Handling missing data
		Understanding types of missing data
		Performing missing value imputation
			Simple imputation with missing value indicators
			Missing value patterns
	The problem of imbalanced data
		Simple strategies for rebalancing data
		Generating a synthetic balanced dataset with SMOTE
			Example – Applying the SMOTE algorithm in R
		Considering whether balanced is always better
	Summary
Chapter 14: Building Better Learners
	Tuning stock models for better performance
		Determining the scope of hyperparameter tuning
		Example – using caret for automated tuning
			Creating a simple tuned model
			Customizing the tuning process
	Improving model performance with ensembles
		Understanding ensemble learning
		Popular ensemble-based algorithms
			Bagging
			Boosting
			Random forests
			Gradient boosting
			Extreme gradient boosting with XGBoost
			Why are tree-based ensembles so popular?
	Stacking models for meta-learning
		Understanding model stacking and blending
		Practical methods for blending and stacking in R
	Summary
Chapter 15: Making Use of Big Data
	Practical applications of deep learning
		Beginning with deep learning
			Choosing appropriate tasks for deep learning
			The TensorFlow and Keras deep learning frameworks
		Understanding convolutional neural networks
			Transfer learning and fine tuning
			Example – classifying images using a pre-trained CNN in R
	Unsupervised learning and big data
		Representing highly dimensional concepts as embeddings
			Understanding word embeddings
			Example – using word2vec for understanding text in R
		Visualizing highly dimensional data
			The limitations of using PCA for big data visualization
			Understanding the t-SNE algorithm
			Example – visualizing data’s natural clusters with t-SNE
	Adapting R to handle large datasets
		Querying data in SQL databases
			The tidy approach to managing database connections
			Using a database backend for dplyr with dbplyr
		Doing work faster with parallel processing
			Measuring R’s execution time
			Enabling parallel processing in R
			Taking advantage of parallel with foreach and doParallel
			Training and evaluating models in parallel with caret
		Utilizing specialized hardware and algorithms
			Parallel computing with MapReduce concepts via Apache Spark
			Learning via distributed and scalable algorithms with H2O
			GPU computing
	Summary
Other Books You May Enjoy
Index