Previous Chapter

About the Authors

Index

A note on the digital index

A link in an index entry is displayed as the section title in which that entry appears. Because some sections have multiple index markers, it is not unusual for an entry to have several links to the same section. Clicking on any link will take you directly to the place in the text in which the marker appears.

Symbols

%*% (percent, asterisk, percent), for matrix multiplication, A Brief Introduction to Distance Metrics and Multidirectional Scaling
? (question mark) syntax, for R help, Loading libraries and the data
?? (question mark, double) syntax, for R help, Loading libraries and the data

A

additivity assumption, Linear Regression in a Nutshell–Linear Regression in a Nutshell

aggregating data, Aggregating and organizing the data (see data, aggregating)

analyzing data, Analyzing the data (see data analysis)

apply functions, Organizing location data, Aggregating and organizing the data, Writing Our First Bayesian Spam Classifier, Writing Our First Bayesian Spam Classifier, Functions for Extracting the Feature Set, Introduction to Optimization, Analyzing US Senator Roll Call Data (101st–111th Congresses), Exploring senator MDS clustering by Congress

lapply function, Organizing location data, Aggregating and organizing the data, Functions for Extracting the Feature Set, Analyzing US Senator Roll Call Data (101st–111th Congresses), Exploring senator MDS clustering by Congress
sapply function, Writing Our First Bayesian Spam Classifier, Writing Our First Bayesian Spam Classifier, Introduction to Optimization

as.Date function, Loading libraries and the data

as.factor function, Loading libraries and the data

as.matrix function, Writing Our First Bayesian Spam Classifier

B

baseline model, for linear regression, The Baseline Model–The Baseline Model

Bayesian classifier, Writing Our First Bayesian Spam Classifier (see Naive Bayes classifier)

bell curve, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization

modes in, Exploratory Data Visualization–Exploratory Data Visualization
types of, Exploratory Data Visualization–Exploratory Data Visualization
verifying with density plots, Exploratory Data Visualization–Exploratory Data Visualization
verifying with different binwidths, Exploratory Data Visualization–Exploratory Data Visualization

bimodal, Exploratory Data Visualization

binary classification, This or That: Binary Classification–This or That: Binary Classification, Logistic Regression to the Rescue–Logistic Regression to the Rescue

(see also spam detection case study)

book popularity prediction case study, Text Regression–Logistic Regression to the Rescue

books and publications, How This Book Is Organized, Further Reading on R, Social Network Analysis, Works Cited–Works Cited

bibliography of, Works Cited–Works Cited
machine learning, How This Book Is Organized
R language, Further Reading on R
social network analysis, Social Network Analysis

boot package, Logistic Regression to the Rescue

C

Caesar cipher, Code Breaking as Optimization

case studies, How This Book Is Organized–How This Book Is Organized, R Basics for Machine Learning–Analyzing the data, Loading libraries and the data–Loading libraries and the data, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data, Organizing location data–Dealing with data outside our scope, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data, This or That: Binary Classification–Improving the Results, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types, Improving the Results–Improving the Results, How Do You Sort Something When You Don’t Know the Order?–Training and Testing the Ranker, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker, Predicting Web Traffic–Predicting Web Traffic, Text Regression–Logistic Regression to the Rescue, Code Breaking as Optimization–Code Breaking as Optimization, Unsupervised Learning–Unsupervised Learning, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress, R Package Installation Data–R Package Installation Data, Social Network Analysis–Visualizing the Clustered Twitter Network with Gephi, Hacking Twitter Social Graph Data–Working with the Google SocialGraph API, Analyzing Twitter Networks–Analyzing Twitter Networks, Local Community Structure–Local Community Structure, Local Community Structure–Local Community Structure, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi, Building Your Own “Who to Follow” Engine–Building Your Own “Who to Follow” Engine

book popularity prediction, Text Regression–Logistic Regression to the Rescue

code breaking, Code Breaking as Optimization–Code Breaking as Optimization

list of, How This Book Is Organized–How This Book Is Organized

priority inbox, How Do You Sort Something When You Don’t Know the Order?–Training and Testing the Ranker, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker

feature generation, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set
testing, Training and Testing the Ranker–Training and Testing the Ranker
training, Training and Testing the Ranker–Training and Testing the Ranker
weighting scheme for, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity

R package installation, R Package Installation Data–R Package Installation Data

spam detection, This or That: Binary Classification–Improving the Results, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types, Improving the Results–Improving the Results

improving results of classifier, Improving the Results–Improving the Results
testing classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types
training classifier, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier
writing classifier, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham

stock market index, Unsupervised Learning–Unsupervised Learning

Twitter follower recommendations, Building Your Own “Who to Follow” Engine–Building Your Own “Who to Follow” Engine

Twitter network analysis, Social Network Analysis–Visualizing the Clustered Twitter Network with Gephi, Hacking Twitter Social Graph Data–Working with the Google SocialGraph API, Analyzing Twitter Networks–Analyzing Twitter Networks, Local Community Structure–Local Community Structure, Local Community Structure–Local Community Structure, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

building networks, Analyzing Twitter Networks–Analyzing Twitter Networks
data for, obtaining, Hacking Twitter Social Graph Data–Working with the Google SocialGraph API
ego-network analysis, Local Community Structure–Local Community Structure
k-core analysis, Local Community Structure–Local Community Structure
visualizations for, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

UFO sightings, R Basics for Machine Learning–Analyzing the data, Loading libraries and the data–Loading libraries and the data, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data, Organizing location data–Dealing with data outside our scope, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data

aggregating data, Aggregating and organizing the data–Aggregating and organizing the data
analyzing data, Analyzing the data–Analyzing the data
cleaning data, Organizing location data–Dealing with data outside our scope
loading data, Loading libraries and the data–Loading libraries and the data
malformed data, handling, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data

US Senate clustering, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress

web traffic predictions, Predicting Web Traffic–Predicting Web Traffic

cast function, Unsupervised Learning, Unsupervised Learning, R Package Installation Data, R Package Installation Data

categorical variables, Loading libraries and the data

Cauchy distribution, Exploratory Data Visualization–Exploratory Data Visualization

class function, The k-Nearest Neighbors Algorithm

classification, This or That: Binary Classification–This or That: Binary Classification, This or That: Binary Classification–Moving Gently into Conditional Probability, How Do You Sort Something When You Don’t Know the Order?–Ordering Email Messages by Priority, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker, Logistic Regression to the Rescue–Logistic Regression to the Rescue, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

binary classification, This or That: Binary Classification–This or That: Binary Classification, Logistic Regression to the Rescue–Logistic Regression to the Rescue

ranking classes, How Do You Sort Something When You Don’t Know the Order?–Ordering Email Messages by Priority, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker

(see also priority inbox case study)
feature generation, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set
testing, Training and Testing the Ranker–Training and Testing the Ranker
training, Training and Testing the Ranker–Training and Testing the Ranker
weighting scheme for, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity

SVM (support vector machine) for, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

text classification, This or That: Binary Classification–Moving Gently into Conditional Probability

(see also spam detection case study)

classification picture, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns

cleaning data, Organizing location data (see data, cleaning)

clustering, Clustering Based on Similarity–Clustering Based on Similarity, Clustering Based on Similarity–A Brief Introduction to Distance Metrics and Multidirectional Scaling, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress, Local Community Structure–Visualizing the Clustered Twitter Network with Gephi

hierarchical clustering of node distances, Local Community Structure–Visualizing the Clustered Twitter Network with Gephi
MDS (multidimensional scaling) for, Clustering Based on Similarity–A Brief Introduction to Distance Metrics and Multidirectional Scaling
of US Senate, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress

cmdscale function, A Brief Introduction to Distance Metrics and Multidirectional Scaling, Exploring senator MDS clustering by Congress

code breaking case study, Code Breaking as Optimization–Code Breaking as Optimization

code examples, using, Using Code Examples

coef function, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Preventing Overfitting with Regularization

columns, Loading libraries and the data, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data, Inferring Meaning, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns

meaning of, Inferring Meaning
names for, assigning, Loading libraries and the data
relationships between, visualizations for, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns
types of data in, determining, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data

Comprehensive R Archive Network (CRAN), How This Book Is Organized

computer hacker, Machine Learning for Hackers (see hacker)

conditional probability, Moving Gently into Conditional Probability–Moving Gently into Conditional Probability

confirmatory data analysis, Exploration versus Confirmation–Exploration versus Confirmation

Congress, US, Clustering Based on Similarity (see US Senate clustering case study)

contact information for this book, How to Contact Us

content features, of email, Priority Features of Email

control list, Writing Our First Bayesian Spam Classifier

conventions used in this book, Conventions Used in This Book

convergence, Introduction to Optimization

cor function, Defining Correlation, R Package Installation Data

Corpus function, Writing Our First Bayesian Spam Classifier

correlation, What Is Data?, Defining Correlation–Defining Correlation

Cowgill, Bo (Google, Inc.), R for Machine Learning, R for Machine Learning

regarding R language, R for Machine Learning, R for Machine Learning

CRAN (Comprehensive R Archive Network), How This Book Is Organized

Criswell, Joan (anthropologist), Social Network Analysis

sociometry used by, Social Network Analysis

cross-validation, Methods for Preventing Overfitting–Methods for Preventing Overfitting

curve function, Introduction to Optimization, Ridge Regression–Ridge Regression

curve, in scatterplot, Linear Regression in a Nutshell

cutree function, Local Community Structure

D

data, Loading libraries and the data–Loading libraries and the data, Loading libraries and the data, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data, Organizing location data–Dealing with data outside our scope, Aggregating and organizing the data–Aggregating and organizing the data, What Is Data?–What Is Data?, What Is Data?, What Is Data?, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data, Inferring Meaning, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns

aggregating, Aggregating and organizing the data–Aggregating and organizing the data

cleaning, Organizing location data–Dealing with data outside our scope

columns in, Loading libraries and the data, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data, Inferring Meaning, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns

meaning of, Inferring Meaning
names for, assigning, Loading libraries and the data
relationships between, visualizations for, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns
types of data in, determining, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data

loading, Loading libraries and the data–Loading libraries and the data

malformed, handling, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data

“as rectangles” model of, What Is Data?

source of, What Is Data?

data analysis, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data, Exploration versus Confirmation–Exploration versus Confirmation, Exploration versus Confirmation–Exploration versus Confirmation, What Is Data?, What Is Data?–What Is Data?, What Is Data?, What Is Data?, Numeric Summaries–Numeric Summaries, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization, Exploratory Data Visualization, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns, Defining Correlation–Defining Correlation, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

confirmatory, Exploration versus Confirmation–Exploration versus Confirmation

correlation, What Is Data?, Defining Correlation–Defining Correlation

dimensionality reduction, What Is Data?

exploratory, Exploration versus Confirmation–Exploration versus Confirmation

numeric summary, What Is Data?, Numeric Summaries–Numeric Summaries

visualizations, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data, What Is Data?–What Is Data?, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization, Exploratory Data Visualization, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

density plot, Exploratory Data Visualization (see density plot)
histogram, Aggregating and organizing the data–Aggregating and organizing the data, Exploratory Data Visualization–Exploratory Data Visualization
line plot, Analyzing the data–Analyzing the data
network graphs, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi
relationships between columns, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns
scatterplot, Exploratory Data Visualization (see scatterplot)

data dictionary, Inferring the Types of Columns in Your Data

data frame structure, R for Machine Learning, Loading libraries and the data

data types and structures, R for Machine Learning, R for Machine Learning, Loading libraries and the data, Loading libraries and the data, Loading libraries and the data–Converting date strings and dealing with malformed data, Organizing location data, Aggregating and organizing the data, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data

data frame structure, R for Machine Learning, Loading libraries and the data

dates, Loading libraries and the data–Converting date strings and dealing with malformed data, Aggregating and organizing the data

conversions to, Loading libraries and the data–Converting date strings and dealing with malformed data
sequence of, creating, Aggregating and organizing the data

determining for data columns, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data

factor data type, Loading libraries and the data

list structure, Organizing location data

vector data type, R for Machine Learning

data.frame function, Writing Our First Bayesian Spam Classifier

database, data set compared to, What Is Data?

(see also matrices)

dates, Loading libraries and the data–Converting date strings and dealing with malformed data, Aggregating and organizing the data

conversions to, Loading libraries and the data–Converting date strings and dealing with malformed data
sequence of, creating, Aggregating and organizing the data

ddply function, Aggregating and organizing the data, Creating a Weighting Scheme for Ranking

decision boundary, This or That: Binary Classification–This or That: Binary Classification, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

linear, This or That: Binary Classification–This or That: Binary Classification
nonlinear, handling, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

dendrogram, Local Community Structure

density plot, Exploratory Data Visualization–Exploratory Data Visualization, The Baseline Model–The Baseline Model, Predicting Web Traffic–Predicting Web Traffic, Unsupervised Learning–Unsupervised Learning

dimensionality reduction, What Is Data?

dir function, Writing Our First Bayesian Spam Classifier

directed graph, Thinking Graphically

dist function, A Brief Introduction to Distance Metrics and Multidirectional Scaling, Local Community Structure

distance matrix, A Brief Introduction to Distance Metrics and Multidirectional Scaling

distance metrics, A Brief Introduction to Distance Metrics and Multidirectional Scaling–A Brief Introduction to Distance Metrics and Multidirectional Scaling, The k-Nearest Neighbors Algorithm–The k-Nearest Neighbors Algorithm

distributions, Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization

bell curve (normal distribution), Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization

modes in, Exploratory Data Visualization–Exploratory Data Visualization
verifying with density plots, Exploratory Data Visualization–Exploratory Data Visualization
verifying with different binwidths, Exploratory Data Visualization–Exploratory Data Visualization

Cauchy distribution, Exploratory Data Visualization–Exploratory Data Visualization

exponential distribution, Exploratory Data Visualization–Exploratory Data Visualization

gamma distribution, Exploratory Data Visualization–Exploratory Data Visualization

heavy-tailed distribution, Exploratory Data Visualization–Exploratory Data Visualization

skewed distribution, Exploratory Data Visualization–Exploratory Data Visualization

symmetric distribution, Exploratory Data Visualization–Exploratory Data Visualization

thin-tailed distribution, Exploratory Data Visualization–Exploratory Data Visualization

do.call function, Organizing location data, Aggregating and organizing the data, Functions for Extracting the Feature Set

.dta file extension, Analyzing US Senator Roll Call Data (101st–111th Congresses)

dummy coding, Inferring the Types of Columns in Your Data

dummy variables, regression using, Regression Using Dummy Variables–Regression Using Dummy Variables

E

e1071 package, SVMs: The Support Vector Machine

ego-network, Social Network Analysis, Local Community Structure–Local Community Structure

email, Writing Our First Bayesian Spam Classifier, How Do You Sort Something When You Don’t Know the Order?

detecting spam in, Writing Our First Bayesian Spam Classifier (see spam detection case study)
prioritizing messages in, How Do You Sort Something When You Don’t Know the Order? (see priority inbox case study)

encoding schemes, Inferring the Types of Columns in Your Data–Inferring the Types of Columns in Your Data

enumerations, compared to factors, Inferring the Types of Columns in Your Data

Erdős number, Social Network Analysis

error handling, Organizing location data

Euclidean distance, A Brief Introduction to Distance Metrics and Multidirectional Scaling, The k-Nearest Neighbors Algorithm

Euler, Leonhard (mathematician), Social Network Analysis

regarding Königsberg Bridge problem, Social Network Analysis

exploratory data analysis, Exploration versus Confirmation–Exploration versus Confirmation

exponential distribution, Exploratory Data Visualization–Exploratory Data Visualization

F

F-statistic, Predicting Web Traffic
facet_wrap function, Analyzing the data, Exploring senator MDS clustering by Congress
factor data type, Loading libraries and the data, Inferring the Types of Columns in Your Data
feature generation, This or That: Binary Classification, Priority Features of Email–Priority Features of Email
first quartile, Numeric Summaries, Means, Medians, and Modes
fonts used in this book, Conventions Used in This Book
force-directed algorithms, Visualizing the Clustered Twitter Network with Gephi
foreign package, Analyzing US Senator Roll Call Data (101st–111th Congresses), Analyzing US Senator Roll Call Data (101st–111th Congresses)
fromJSON function, Working with the Google SocialGraph API

G

Galston, William A. (Senior Fellow, Brookings Institute), How Do US Senators Cluster?

regarding polarization in US Congress, How Do US Senators Cluster?

gamma distribution, Exploratory Data Visualization–Exploratory Data Visualization

Gaussian distribution, Exploratory Data Visualization (see bell curve)

geom_density function, Exploratory Data Visualization

(see also density plot)

geom_histogram function, Aggregating and organizing the data, Exploratory Data Visualization

(see also histogram)

geom_line function, Analyzing the data

geom_point function, Visualizing the Relationships Between Columns

(see also scatterplot)

geom_smooth function, Visualizing the Relationships Between Columns, Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation, Nonlinear Relationships Between Columns: Beyond Straight Lines, Introducing Polynomial Regression

geom_text function, Exploring senator MDS clustering by Congress

Gephi software, Analyzing Twitter Networks, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

get.edgelist function, Building Your Own “Who to Follow” Engine

getURL function, Working with the Google SocialGraph API

ggplot object, Aggregating and organizing the data

ggplot2 package, Loading and Installing R Packages, Loading libraries and the data, Aggregating and organizing the data, Analyzing the data, Analyzing the data, Further Reading on R, Analyzing US Senator Roll Call Data (101st–111th Congresses), Exploring senator MDS clustering by Congress

(see also specific functions)
MDS results using, Analyzing US Senator Roll Call Data (101st–111th Congresses)
plotting themes of, Analyzing the data
resources for, Further Reading on R
two plots using, Exploring senator MDS clustering by Congress

ggsave function, Aggregating and organizing the data, Analyzing the data

glm function, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

glmnet function, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization, Text Regression, Logistic Regression to the Rescue, Comparing Algorithms

glmnet package, Loading and Installing R Packages, Preventing Overfitting with Regularization

global optimum, Introduction to Optimization

Goffman, Erving (social scientist), Social Network Analysis

regarding nature of human interaction, Social Network Analysis

Google, Priority Features of Email–Priority Features of Email, Hacking Twitter Social Graph Data

priority inbox by, Priority Features of Email–Priority Features of Email
SocialGraph API, Hacking Twitter Social Graph Data (see SGA)

gradient, Introduction to Optimization

graph.coreness function, Local Community Structure

GraphML files, Local Community Structure

grepl function, Functions for Extracting the Feature Set, Functions for Extracting the Feature Set, Functions for Extracting the Feature Set, Working with the Google SocialGraph API

grid search, Introduction to Optimization–Introduction to Optimization

gsub function, Organizing location data, Functions for Extracting the Feature Set

H

hacker, Machine Learning for Hackers

hclust function, Local Community Structure

head function, Loading libraries and the data

heavy-tailed distribution, Exploratory Data Visualization–Exploratory Data Visualization

Heider, Fritz (psychologist), Building Your Own “Who to Follow” Engine

social balance theory by, Building Your Own “Who to Follow” Engine

help, for R language, Loading libraries and the data

help.search function, Loading libraries and the data

hierarchical clustering of node distances, Local Community Structure–Visualizing the Clustered Twitter Network with Gephi

histogram, Aggregating and organizing the data–Aggregating and organizing the data, Exploratory Data Visualization–Exploratory Data Visualization

I

IDEs, for R, IDEs and Text Editors
ifelse function, Converting date strings and dealing with malformed data
igraph library, Analyzing Twitter Networks
igraph package, Loading and Installing R Packages, Working with the Google SocialGraph API, Local Community Structure
install.packages function, Loading and Installing R Packages
inv.logit function, Logistic Regression to the Rescue
is.character function, Inferring the Types of Columns in Your Data
is.factor function, Inferring the Types of Columns in Your Data
is.na function, Dealing with data outside our scope, Aggregating and organizing the data
is.numeric function, Inferring the Types of Columns in Your Data

J

jittering, This or That: Binary Classification

K

k-core analysis, Local Community Structure–Local Community Structure

k-nearest neighbors algorithm, The k-Nearest Neighbors Algorithm (see kNN algorithm)

KDE (kernel density estimate), Exploratory Data Visualization (see density plot)

kernel trick, SVMs: The Support Vector Machine (see SVM (support vector machine))

kNN (k-nearest neighbors) algorithm, The k-Nearest Neighbors Algorithm–R Package Installation Data, R Package Installation Data–R Package Installation Data, Comparing Algorithms

comparing to other algorithms, Comparing Algorithms
R package installation case study using, R Package Installation Data–R Package Installation Data

knn function, The k-Nearest Neighbors Algorithm

Königsberg Bridge problem, Social Network Analysis

L

L1 norm, Preventing Overfitting with Regularization

L2 norm, Preventing Overfitting with Regularization

label features, of email, Priority Features of Email

labels, compared to factors, Inferring the Types of Columns in Your Data

Lambda, for regularization, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization, Text Regression, Ridge Regression

lapply function, Organizing location data, Aggregating and organizing the data, Functions for Extracting the Feature Set, Analyzing US Senator Roll Call Data (101st–111th Congresses), Exploring senator MDS clustering by Congress

length function, Converting date strings and dealing with malformed data

library function, Loading and Installing R Packages

line plot, Analyzing the data

line, in scatterplot, Linear Regression in a Nutshell

linear kernel SVM, SVMs: The Support Vector Machine, Comparing Algorithms

linear regression, R for Machine Learning, Introducing Regression–Linear Regression in a Nutshell, The Baseline Model–The Baseline Model, Regression Using Dummy Variables–Regression Using Dummy Variables, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Predicting Web Traffic–Predicting Web Traffic, Predicting Web Traffic, Defining Correlation–Defining Correlation, Defining Correlation, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines, Introduction to Optimization, Introduction to Optimization

adapting for nonlinear relationships, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines
assumptions in, Linear Regression in a Nutshell–Linear Regression in a Nutshell
baseline model for, The Baseline Model–The Baseline Model
correlation as indicator of, Defining Correlation–Defining Correlation
dummy variables for, Regression Using Dummy Variables–Regression Using Dummy Variables
lm function for, R for Machine Learning, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation, Introduction to Optimization
optimizing, Introduction to Optimization
web traffic predictions case study using, Predicting Web Traffic–Predicting Web Traffic

linearity assumption, Linear Regression in a Nutshell–Linear Regression in a Nutshell

Linux, installing R language on, Linux

list structure, Organizing location data

list.files function, Analyzing US Senator Roll Call Data (101st–111th Congresses)

lm function, R for Machine Learning, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation, Introduction to Optimization

load function, Comparing Algorithms

loading data, Loading libraries and the data (see data, loading)

log base-10 transformation, A log-weighting scheme

log function, A log-weighting scheme

log-transformations, A log-weighting scheme

log-weighting scheme, A log-weighting scheme–A log-weighting scheme

log1p function, A log-weighting scheme

logarithms, A log-weighting scheme

logistic regression, Logistic Regression to the Rescue–Logistic Regression to the Rescue, The k-Nearest Neighbors Algorithm, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, Comparing Algorithms

comparing to other algorithms, Comparing Algorithms
glm function for, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine
when not to use, The k-Nearest Neighbors Algorithm, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

lubridate package, Unsupervised Learning

M

Mac OS X, installing R language on, Mac OS X

machine learning, Machine Learning for Hackers, How This Book Is Organized, How This Book Is Organized, Using R, Using R, Works Cited–Works Cited

compared to statistics, Using R
as pattern recognition algorithms, Using R
resources for, How This Book Is Organized, Works Cited–Works Cited

malformed data, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data

match function, Dealing with data outside our scope

matrices, What Is Data?, Writing Our First Bayesian Spam Classifier, A Brief Introduction to Distance Metrics and Multidirectional Scaling, A Brief Introduction to Distance Metrics and Multidirectional Scaling–A Brief Introduction to Distance Metrics and Multidirectional Scaling

conversions to, Writing Our First Bayesian Spam Classifier
data as, What Is Data?
multiplication of, A Brief Introduction to Distance Metrics and Multidirectional Scaling–A Brief Introduction to Distance Metrics and Multidirectional Scaling
transposition of, A Brief Introduction to Distance Metrics and Multidirectional Scaling

max function, Quantiles

maximum value, Numeric Summaries, Quantiles

MDS (multidimensional scaling), Clustering Based on Similarity–A Brief Introduction to Distance Metrics and Multidirectional Scaling, A Brief Introduction to Distance Metrics and Multidirectional Scaling, A Brief Introduction to Distance Metrics and Multidirectional Scaling, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress

cmdscale function for, A Brief Introduction to Distance Metrics and Multidirectional Scaling
dimensions of, A Brief Introduction to Distance Metrics and Multidirectional Scaling
for US Senate clustering, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress

mean, Means, Medians, and Modes–Means, Medians, and Modes

mean function, Means, Medians, and Modes

mean squared error (MSE), The Baseline Model–The Baseline Model, Linear Regression in a Nutshell

median, Means, Medians, and Modes–Means, Medians, and Modes

median function, Means, Medians, and Modes

melt function, Unsupervised Learning, SVMs: The Support Vector Machine

merge function, Aggregating and organizing the data

Metropolis method, Code Breaking as Optimization–Code Breaking as Optimization

min function, Quantiles

minimum value, Numeric Summaries, Quantiles

mode, Means, Medians, and Modes, Exploratory Data Visualization–Exploratory Data Visualization

monotonicity, Linear Regression in a Nutshell

Moreno, Jacob L. (psychologist), Social Network Analysis

sociometry developed by, Social Network Analysis

MSE (mean squared error), The Baseline Model–The Baseline Model, Linear Regression in a Nutshell

multidimensional scaling, Clustering Based on Similarity (see MDS)

multimodal, Exploratory Data Visualization

N

Naive Bayes classifier, Moving Gently into Conditional Probability–Moving Gently into Conditional Probability, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types, Improving the Results–Improving the Results

improving results of, Improving the Results–Improving the Results
testing, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types
training, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier
writing, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham

names function, Loading libraries and the data

natural log, A log-weighting scheme

nchar function, Converting date strings and dealing with malformed data

neighbors function, Local Community Structure, Building Your Own “Who to Follow” Engine

Netflix, How Do You Sort Something When You Don’t Know the Order?

recommendation system used by, How Do You Sort Something When You Don’t Know the Order?

network graphs, Thinking Graphically–Thinking Graphically, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

network hairball, Visualizing the Clustered Twitter Network with Gephi

noise, This or That: Binary Classification (see jittering)

normal distribution, Exploratory Data Visualization (see bell curve)

nrow function, Aggregating and organizing the data

numbers, determining whether column contains, Inferring the Types of Columns in Your Data

numeric summary, What Is Data?, Numeric Summaries–Numeric Summaries

O

objective function, Introduction to Optimization

online resources, R for Machine Learning (see website resources)

optim function, Introduction to Optimization–Introduction to Optimization, Ridge Regression–Ridge Regression

optimization, Introduction to Optimization–Introduction to Optimization, Introduction to Optimization–Introduction to Optimization, Introduction to Optimization–Introduction to Optimization, Ridge Regression–Ridge Regression, Code Breaking as Optimization–Code Breaking as Optimization, Code Breaking as Optimization, Code Breaking as Optimization–Code Breaking as Optimization

code breaking case study using, Code Breaking as Optimization–Code Breaking as Optimization
grid search for, Introduction to Optimization–Introduction to Optimization
Metropolis method for, Code Breaking as Optimization–Code Breaking as Optimization
optim function for, Introduction to Optimization–Introduction to Optimization
ridge regression for, Ridge Regression–Ridge Regression
stochastic optimization, Code Breaking as Optimization

optimum, Introduction to Optimization, Introduction to Optimization

opts function, Analyzing the data

orthogonal polynomials, Introducing Polynomial Regression

overfitting, Introducing Polynomial Regression–Preventing Overfitting with Regularization, Methods for Preventing Overfitting–Methods for Preventing Overfitting, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization

cross-validation preventing, Methods for Preventing Overfitting–Methods for Preventing Overfitting
regularization preventing, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization

P

p-value, Predicting Web Traffic, Predicting Web Traffic, Predicting Web Traffic

packages for R, Loading and Installing R Packages–Loading and Installing R Packages, Loading and Installing R Packages, Loading and Installing R Packages–Loading and Installing R Packages, Loading and Installing R Packages–Loading and Installing R Packages, R Package Installation Data–R Package Installation Data

(see also specific packages)
case study involving, R Package Installation Data–R Package Installation Data
installing, Loading and Installing R Packages–Loading and Installing R Packages
list of, Loading and Installing R Packages–Loading and Installing R Packages
loading, Loading and Installing R Packages

paste function, Writing Our First Bayesian Spam Classifier

pattern matching, in expressions, Using R (see regular expressions)

patterns in data, Using R, Using R, Exploration versus Confirmation–Exploration versus Confirmation

(see also classification; distributions; regression)
confirming, Exploration versus Confirmation–Exploration versus Confirmation
pattern recognition algorithms for, Using R

PCA (principal components analysis), Unsupervised Learning–Unsupervised Learning

percent, asterisk, percent (%*%), for matrix multiplication, A Brief Introduction to Distance Metrics and Multidirectional Scaling

plot function, R for Machine Learning, Local Community Structure

plotting results, R for Machine Learning (see visualizations of data)

plyr package, Loading libraries and the data, Aggregating and organizing the data, Creating a Weighting Scheme for Ranking

poly function, Introducing Polynomial Regression–Introducing Polynomial Regression

polynomial kernel SVM, SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

polynomial regression, Introducing Polynomial Regression–Introducing Polynomial Regression, Introducing Polynomial Regression–Preventing Overfitting with Regularization, Methods for Preventing Overfitting

overfitting with, preventing, Introducing Polynomial Regression–Preventing Overfitting with Regularization
underfitting with, Methods for Preventing Overfitting

Poole, Keith (political scientist), How Do US Senators Cluster?

roll call data repository by, How Do US Senators Cluster?

predict function, Linear Regression in a Nutshell, Logistic Regression to the Rescue, Unsupervised Learning

predictions, improving, Introduction to Optimization (see optimization)

principle components analysis (PCA), Unsupervised Learning–Unsupervised Learning

princomp function, Unsupervised Learning

print function, Loading and Installing R Packages

priority inbox case study, How Do You Sort Something When You Don’t Know the Order?–Training and Testing the Ranker, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker

feature generation, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set
testing, Training and Testing the Ranker–Training and Testing the Ranker
training, Training and Testing the Ranker–Training and Testing the Ranker
weighting scheme for, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity

Q

quantile function, Quantiles, Standard Deviations and Variances, Predicting Web Traffic
quantiles, Numeric Summaries, Quantiles–Quantiles
question mark (?) syntax, for R help, Loading libraries and the data
question mark, double (??) syntax, for R help, Loading libraries and the data

R

R console, Windows, Mac OS X, Linux

Linux, Linux
Mac OS X, Mac OS X
Windows, Windows

R programming language, How This Book Is Organized, Using R–Using R, R for Machine Learning–R for Machine Learning, R for Machine Learning, R for Machine Learning, R for Machine Learning–R for Machine Learning, Downloading and Installing R, Downloading and Installing R–Linux, IDEs and Text Editors, IDEs and Text Editors, Loading and Installing R Packages, Loading and Installing R Packages–Loading and Installing R Packages, Loading and Installing R Packages, Loading and Installing R Packages, Loading libraries and the data, Loading libraries and the data, Loading libraries and the data, Loading libraries and the data–Converting date strings and dealing with malformed data, Organizing location data, Aggregating and organizing the data, Further Reading on R, R Package Installation Data–R Package Installation Data, Works Cited–Works Cited

data types and structures, R for Machine Learning, R for Machine Learning, Loading libraries and the data, Loading libraries and the data, Loading libraries and the data–Converting date strings and dealing with malformed data, Organizing location data, Aggregating and organizing the data

data frame structure, R for Machine Learning, Loading libraries and the data
dates, Loading libraries and the data–Converting date strings and dealing with malformed data, Aggregating and organizing the data
factor data type, Loading libraries and the data
list structure, Organizing location data
vector data type, R for Machine Learning

disadvantages of, R for Machine Learning–R for Machine Learning

downloading, Downloading and Installing R

help for, Loading libraries and the data

IDEs for, IDEs and Text Editors

installing, Downloading and Installing R–Linux

packages for, Loading and Installing R Packages, Loading and Installing R Packages–Loading and Installing R Packages, Loading and Installing R Packages, Loading and Installing R Packages, R Package Installation Data–R Package Installation Data

case study involving, R Package Installation Data–R Package Installation Data
checking for, Loading and Installing R Packages
installing, Loading and Installing R Packages–Loading and Installing R Packages
list of, Loading and Installing R Packages
loading, Loading and Installing R Packages

resources for, Further Reading on R, Works Cited–Works Cited

text editors for, IDEs and Text Editors

R Project for Statistical Computing, R for Machine Learning

R-Bloggers website, R for Machine Learning

R2 (R squared), Linear Regression in a Nutshell–Linear Regression in a Nutshell, Predicting Web Traffic, Predicting Web Traffic, Nonlinear Relationships Between Columns: Beyond Straight Lines

radial kernel SVM, SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, Comparing Algorithms

random number generation, Code Breaking as Optimization, A Brief Introduction to Distance Metrics and Multidirectional Scaling

range function, Quantiles, Standard Deviations and Variances

ranking classes, How Do You Sort Something When You Don’t Know the Order?–Ordering Email Messages by Priority, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity, Training and Testing the Ranker–Training and Testing the Ranker, Training and Testing the Ranker–Training and Testing the Ranker

feature generation, Priority Features of Email–Priority Features of Email, Functions for Extracting the Feature Set–Functions for Extracting the Feature Set
testing, Training and Testing the Ranker–Training and Testing the Ranker
training, Training and Testing the Ranker–Training and Testing the Ranker
weighting scheme for, Creating a Weighting Scheme for Ranking–Weighting from Email Thread Activity

rbind function, Organizing location data, Functions for Extracting the Feature Set, Methods for Preventing Overfitting

RCurl package, Loading and Installing R Packages, Working with the Google SocialGraph API

read.* functions, Loading libraries and the data

read.delim function, Loading libraries and the data, Loading libraries and the data

read.dta function, Analyzing US Senator Roll Call Data (101st–111th Congresses)

readKH function, Analyzing US Senator Roll Call Data (101st–111th Congresses)

readLines function, Writing Our First Bayesian Spam Classifier, Functions for Extracting the Feature Set

recommendation system, How Do You Sort Something When You Don’t Know the Order?, The k-Nearest Neighbors Algorithm–R Package Installation Data, R Package Installation Data–R Package Installation Data, Building Your Own “Who to Follow” Engine–Building Your Own “Who to Follow” Engine

(see also ranking classes)
k-nearest neighbors algorithm for, The k-Nearest Neighbors Algorithm–R Package Installation Data
R package installation case study using, R Package Installation Data–R Package Installation Data
of Twitter followers, Building Your Own “Who to Follow” Engine–Building Your Own “Who to Follow” Engine

rectangles, data as, What Is Data?

(see also matrices)

regression, R for Machine Learning, Introducing Regression, Introducing Regression–Linear Regression in a Nutshell, The Baseline Model–The Baseline Model, Regression Using Dummy Variables–Regression Using Dummy Variables, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation–Defining Correlation, Defining Correlation, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines, Introducing Polynomial Regression–Introducing Polynomial Regression, Introducing Polynomial Regression–Preventing Overfitting with Regularization, Methods for Preventing Overfitting, Text Regression–Logistic Regression to the Rescue, Logistic Regression to the Rescue–Logistic Regression to the Rescue, Introduction to Optimization, Introduction to Optimization, Ridge Regression–Ridge Regression, The k-Nearest Neighbors Algorithm, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, Comparing Algorithms

linear regression, R for Machine Learning, Introducing Regression–Linear Regression in a Nutshell, The Baseline Model–The Baseline Model, Regression Using Dummy Variables–Regression Using Dummy Variables, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation–Defining Correlation, Defining Correlation, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines, Introduction to Optimization, Introduction to Optimization

adapting for nonlinear relationships, Nonlinear Relationships Between Columns: Beyond Straight Lines–Nonlinear Relationships Between Columns: Beyond Straight Lines
assumptions in, Linear Regression in a Nutshell–Linear Regression in a Nutshell
baseline model for, The Baseline Model–The Baseline Model
correlation as indicator of, Defining Correlation–Defining Correlation
dummy variables for, Regression Using Dummy Variables–Regression Using Dummy Variables
lm function for, R for Machine Learning, Linear Regression in a Nutshell, Predicting Web Traffic, Defining Correlation, Introduction to Optimization
optimizing, Introduction to Optimization

logistic regression, Logistic Regression to the Rescue–Logistic Regression to the Rescue, The k-Nearest Neighbors Algorithm, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine, Comparing Algorithms

comparing to other algorithms, Comparing Algorithms
glm function for, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine
when not to use, The k-Nearest Neighbors Algorithm, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

polynomial regression, Introducing Polynomial Regression–Introducing Polynomial Regression, Introducing Polynomial Regression–Preventing Overfitting with Regularization, Methods for Preventing Overfitting

overfitting with, preventing, Introducing Polynomial Regression–Preventing Overfitting with Regularization
underfitting with, Methods for Preventing Overfitting

ridge regression, Ridge Regression–Ridge Regression

text regression, Text Regression–Logistic Regression to the Rescue

regression picture, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns

regular expressions, Organizing location data, Functions for Extracting the Feature Set, Functions for Extracting the Feature Set

grepl function for, Functions for Extracting the Feature Set, Functions for Extracting the Feature Set
gsub function for, Organizing location data

regularization, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization, Text Regression–Text Regression, Logistic Regression to the Rescue–Logistic Regression to the Rescue, Ridge Regression, SVMs: The Support Vector Machine, Comparing Algorithms, Comparing Algorithms

logistic regression using, Logistic Regression to the Rescue–Logistic Regression to the Rescue, Comparing Algorithms, Comparing Algorithms
preventing overfitting using, Preventing Overfitting with Regularization–Preventing Overfitting with Regularization
ridge regression using, Ridge Regression
SVM using, SVMs: The Support Vector Machine
text regression using, Text Regression–Text Regression

rep function, Aggregating and organizing the data

require function, Loading and Installing R Packages

reshape package, Loading and Installing R Packages, Loading libraries and the data, Unsupervised Learning, R Package Installation Data

residuals function, Linear Regression in a Nutshell–Linear Regression in a Nutshell

resources, Works Cited (see books and publications; website resources)

RGui and R Console, Windows

ridge regression, Ridge Regression–Ridge Regression

RJSONIO package, Loading and Installing R Packages, Working with the Google SocialGraph API

rm function, Comparing Algorithms

RMSE (root mean squared error), Regression Using Dummy Variables–Regression Using Dummy Variables, Linear Regression in a Nutshell, Predicting Web Traffic, Methods for Preventing Overfitting

root mean squared error (RMSE), Regression Using Dummy Variables–Regression Using Dummy Variables, Linear Regression in a Nutshell, Predicting Web Traffic, Methods for Preventing Overfitting

Rosenthal, Howard (political scientist), How Do US Senators Cluster?

roll call data repository by, How Do US Senators Cluster?

ROT13 cipher, Code Breaking as Optimization

rowSums function, Writing Our First Bayesian Spam Classifier

Rscript utility, Analyzing Twitter Networks

RSeek website, R for Machine Learning

RSiteSearch function, Loading libraries and the data

#rstats Twitter community, R for Machine Learning

S

sample function, Methods for Preventing Overfitting, A Brief Introduction to Distance Metrics and Multidirectional Scaling

sapply function, Writing Our First Bayesian Spam Classifier, Writing Our First Bayesian Spam Classifier, Introduction to Optimization

scale function, Unsupervised Learning

scale_color_manual function, Analyzing the data

scale_x_date function, Aggregating and organizing the data, Analyzing the data

scale_x_log function, Predicting Web Traffic

scale_y_log function, Predicting Web Traffic

scatterplot, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns, Testing the Classifier Against All Email Types, Linear Regression in a Nutshell–Linear Regression in a Nutshell, Predicting Web Traffic–Predicting Web Traffic, Predicting Web Traffic, Nonlinear Relationships Between Columns: Beyond Straight Lines

second quartile, Numeric Summaries, Means, Medians, and Modes

seed, Code Breaking as Optimization (see ego-network; random number generation)

Senators, US, Clustering Based on Similarity (see US Senate clustering case study)

separability, Linear Regression in a Nutshell

separating hyperplane, Visualizing the Relationships Between Columns, This or That: Binary Classification

(see also decision boundary)

seq function, Quantiles

seq.Date function, Aggregating and organizing the data

set.seed function, A Brief Introduction to Distance Metrics and Multidirectional Scaling

set.vertex.attributes function, Local Community Structure

setwd function, Loading and Installing R Packages

SGA (SocialGraph API), Hacking Twitter Social Graph Data–Working with the Google SocialGraph API

sgeom_point function, Exploring senator MDS clustering by Congress

shortest.paths function, Local Community Structure

sigmoid kernel SVM, SVMs: The Support Vector Machine, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

simulated annealing, Code Breaking as Optimization

singularity, Introducing Polynomial Regression

skewed distribution, Exploratory Data Visualization–Exploratory Data Visualization

social balance theory, Building Your Own “Who to Follow” Engine

social features, of email, Priority Features of Email

social network analysis, Social Network Analysis–Thinking Graphically

(see also Twitter network analysis case study)

SocialGraph API, Hacking Twitter Social Graph Data (see SGA)

sociometry, Social Network Analysis

source function, Loading and Installing R Packages, Analyzing Twitter Networks

spam detection case study, This or That: Binary Classification–Improving the Results, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types, Improving the Results–Improving the Results

improving results of classifier, Improving the Results–Improving the Results
testing classifier, Defining the Classifier and Testing It with Hard Ham–Testing the Classifier Against All Email Types
training classifier, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier
writing classifier, Writing Our First Bayesian Spam Classifier–Defining the Classifier and Testing It with Hard Ham

SpamAssassin public corpus, This or That: Binary Classification, Priority Features of Email

spread, Standard Deviations and Variances–Standard Deviations and Variances

squared error, The Baseline Model–The Baseline Model, Linear Regression in a Nutshell, Introduction to Optimization–Introduction to Optimization

StackOverflow website, R for Machine Learning

standard deviation, Standard Deviations and Variances–Standard Deviations and Variances

statistics, How This Book Is Organized, Using R, R for Machine Learning, Works Cited–Works Cited

compared to machine learning, Using R
R language for, R for Machine Learning (see R programming language)
resources for, How This Book Is Organized, Works Cited–Works Cited

stochastic optimization, Code Breaking as Optimization

stock market index case study, Unsupervised Learning–Unsupervised Learning

strftime function, Aggregating and organizing the data

strings, determining whether column contains, Inferring the Types of Columns in Your Data

strptime function, Functions for Extracting the Feature Set

strsplit function, Organizing location data, Functions for Extracting the Feature Set

subgraph function, Local Community Structure

subset function, Dealing with data outside our scope, Aggregating and organizing the data

substitution cipher, Code Breaking as Optimization

summary function, Aggregating and organizing the data, Numeric Summaries–Numeric Summaries, Predicting Web Traffic–Predicting Web Traffic

summary, numeric, What Is Data? (see numeric summary)

supervised learning, How Do You Sort Something When You Don’t Know the Order?

SVM (support vector machine), SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

svm function, SVMs: The Support Vector Machine–SVMs: The Support Vector Machine

symmetric distribution, Exploratory Data Visualization–Exploratory Data Visualization

T

t function, A Brief Introduction to Distance Metrics and Multidirectional Scaling

t value, Predicting Web Traffic, Predicting Web Traffic

tab-delimited files, Loading libraries and the data

table function, Building Your Own “Who to Follow” Engine

tables, What Is Data? (see matrices)

tail function, Loading libraries and the data

TDM (term document matrix), Writing Our First Bayesian Spam Classifier

Temple, Duncan (developer), Working with the Google SocialGraph API

packages developed by, Working with the Google SocialGraph API

term document matrix (TDM), Writing Our First Bayesian Spam Classifier

text classification, This or That: Binary Classification–Moving Gently into Conditional Probability

(see also spam detection case study)

text editors, for R, IDEs and Text Editors

text mining package, Writing Our First Bayesian Spam Classifier (see tm package)

text regression, Text Regression–Logistic Regression to the Rescue

thin-tailed distribution, Exploratory Data Visualization–Exploratory Data Visualization

third quartile, Numeric Summaries

thread features, for email, Priority Features of Email

tm package, Loading and Installing R Packages, Loading and Installing R Packages, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Text Regression

tolower function, Organizing location data

traffic order, Social Network Analysis

(see also social network analysis)

training set, Using R, Writing Our First Bayesian Spam Classifier–Writing Our First Bayesian Spam Classifier, Methods for Preventing Overfitting

transform function, Organizing location data, Writing Our First Bayesian Spam Classifier, Exploring senator MDS clustering by Congress

Traveling Salesman problem, Social Network Analysis

tryCatch function, Organizing location data

.tsv file extension, Loading libraries and the data

(see also tab-delimited files)

Tukey, John (statistician), Exploration versus Confirmation, Text Regression

regarding data not always having an answer, Text Regression
regarding exploratory data analysis, Exploration versus Confirmation

Twitter follower recommendations case study, Building Your Own “Who to Follow” Engine–Building Your Own “Who to Follow” Engine

Twitter network analysis case study, Social Network Analysis–Visualizing the Clustered Twitter Network with Gephi, Hacking Twitter Social Graph Data–Working with the Google SocialGraph API, Analyzing Twitter Networks–Analyzing Twitter Networks, Local Community Structure–Local Community Structure, Local Community Structure–Local Community Structure, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

building networks, Analyzing Twitter Networks–Analyzing Twitter Networks
data for, obtaining, Hacking Twitter Social Graph Data–Working with the Google SocialGraph API
ego-network analysis, Local Community Structure–Local Community Structure
k-core analysis, Local Community Structure–Local Community Structure
visualizations for, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

U

UFO sightings, case study of, R Basics for Machine Learning–Analyzing the data, Loading libraries and the data–Loading libraries and the data, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data, Organizing location data–Dealing with data outside our scope, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data

aggregating data, Aggregating and organizing the data–Aggregating and organizing the data
analyzing data, Analyzing the data–Analyzing the data
cleaning data, Organizing location data–Dealing with data outside our scope
loading data, Loading libraries and the data–Loading libraries and the data
malformed data, handling, Converting date strings and dealing with malformed data–Converting date strings and dealing with malformed data

underfitting, Methods for Preventing Overfitting

undirected graph, Thinking Graphically

unimodal, Exploratory Data Visualization

unsupervised learning, How Do You Sort Something When You Don’t Know the Order?, Unsupervised Learning–Unsupervised Learning

US Senate clustering case study, How Do US Senators Cluster?–Exploring senator MDS clustering by Congress

V

var function, Standard Deviations and Variances

variables, Loading libraries and the data, Regression Using Dummy Variables–Regression Using Dummy Variables

categorical, Loading libraries and the data
dummy, for linear regression, Regression Using Dummy Variables–Regression Using Dummy Variables

variance, Standard Deviations and Variances–Standard Deviations and Variances

vector data type, R for Machine Learning

VectorSource function, Writing Our First Bayesian Spam Classifier

Video Rchive website, R for Machine Learning

visualizations of data, Aggregating and organizing the data–Aggregating and organizing the data, Analyzing the data–Analyzing the data, What Is Data?–What Is Data?, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization–Exploratory Data Visualization, Exploratory Data Visualization, Exploratory Data Visualization, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi

density plot, Exploratory Data Visualization (see density plot)
histogram, Aggregating and organizing the data–Aggregating and organizing the data, Exploratory Data Visualization–Exploratory Data Visualization
line plot, Analyzing the data–Analyzing the data
network graphs, Visualizing the Clustered Twitter Network with Gephi–Visualizing the Clustered Twitter Network with Gephi
relationships between columns, Visualizing the Relationships Between Columns–Visualizing the Relationships Between Columns
scatterplot, Exploratory Data Visualization (see scatterplot)

W

wave, in scatterplot, Linear Regression in a Nutshell

web traffic predictions case study, Predicting Web Traffic–Predicting Web Traffic

website resources, How This Book Is Organized, How to Contact Us, R for Machine Learning, R for Machine Learning–R for Machine Learning, Downloading and Installing R, Loading and Installing R Packages, Further Reading on R, This or That: Binary Classification, Priority Features of Email, Priority Features of Email, How Do US Senators Cluster?, Analyzing US Senator Roll Call Data (101st–111th Congresses), Hacking Twitter Social Graph Data

codebook for US Congress data, Analyzing US Senator Roll Call Data (101st–111th Congresses)
for this book, How to Contact Us
Google Priority Inbox paper, Priority Features of Email
R language, How This Book Is Organized, Further Reading on R
R language communities, R for Machine Learning–R for Machine Learning
R language downloads, Downloading and Installing R
R language packages, Loading and Installing R Packages
R Project for Statistical Computing, R for Machine Learning
roll call data repository for US Congress, How Do US Senators Cluster?
SpamAssassin public corpus, This or That: Binary Classification, Priority Features of Email
Twitter API, Hacking Twitter Social Graph Data

which function, Converting date strings and dealing with malformed data

Windows, installing R language on, Windows

write.graph function, Local Community Structure

X

xlab function, Analyzing the data
XML package, for R, Loading and Installing R Packages
XML-based file formats, Local Community Structure (see GraphML files)

Y

ylab function, Analyzing the data
ymd function, Unsupervised Learning

Previous Chapter

About the Authors