Index

A

• = assignment operator / Vectors
• abline() function / ROC curves
• abstraction process
  • about / Abstraction and knowledge representation
• actionable associations / Step 4 – evaluating model performance
• activation function
  • about / From biological to artificial neurons, Activation functions
  • threshold activation function / Activation functions
  • unit step activation function / Activation functions
  • sigmoid activation function / Activation functions
• AdaBoost
  • about / Boosting
• adaptive boosting
  • about / Boosting the accuracy of decision trees
• aggregate() function / Step 5 – improving model performance
• aggregate function / Bagging
• apply() function / Data preparation – creating indicator features for frequent words
• appropriate k
  • selecting / Choosing an appropriate k
• Apriori
  • about / The Apriori algorithm for association rule learning
• apriori() function / Step 3 – training a model on the data
• Apriori algorithm
  • for association rule learning / The Apriori algorithm for association rule learning
  • strengths / The Apriori algorithm for association rule learning
  • weaknesses / The Apriori algorithm for association rule learning
• Apriori principle
  • used, for building set of rules / Building a set of rules with the Apriori principle
• Apriori property
  • about / The Apriori algorithm for association rule learning
• array
  • about / R data structures, Matrixes and arrays
• Artificial Neural Network (ANN)
  • about / Understanding neural networks
  • applications / Understanding neural networks
• association rules
  • about / Understanding association rules
  • potential applications / Understanding association rules
  • rule interest, measuring / Measuring rule interest – support and confidence
  • set of rules, building with Apriori principle / Building a set of rules with the Apriori principle
  • frequently purchased groceries, identifying with / Example – identifying frequently purchased groceries with association rules
• automated parameter tuning
  • caret package used / Using caret for automated parameter tuning
  • requisites / Using caret for automated parameter tuning
• axon
  • about / From biological to artificial neurons

B

• 0.632 bootstrap accounts / Bootstrap sampling
• backpropagation
  • neural networks, training with / Training neural networks with backpropagation
  • about / Training neural networks with backpropagation
• backpropagation algorithm
  • strengths / Training neural networks with backpropagation
  • weaknesses / Training neural networks with backpropagation
• bag() function / Bagging
• bag-of-words / Step 2 – exploring and preparing the data
• bagging
  • about / Bagging
• bagging() function
  • about / Bagging
• bank loans example, with C5.0 decision trees
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data
  • random training, creating / Data preparation – creating random training and test datasets
  • test datasets, creating / Data preparation – creating random training and test datasets
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• basics concepts, Bayesian methods
  • about / Basic concepts of Bayesian methods
  • probability / Probability
  • joint probability / Joint probability
  • conditional probability / Conditional probability with Bayes' theorem
• Bayesian classifiers
  • uses / Understanding naive Bayes
• Bayesian methods
  • about / Understanding naive Bayes
  • basic concepts / Basic concepts of Bayesian methods
• benefits, machine learning / Uses and abuses of machine learning
• bias
  • about / Generalization
• bias-variance tradeoff
  • about / Choosing an appropriate k
• biganalytics package / Using massive matrices with bigmemory
• bigkmeans() function / Using massive matrices with bigmemory
• biglm() function
  • about / Building bigger regression models with biglm
• biglm package
  • about / Building bigger regression models with biglm
  • regression model, building / Building bigger regression models with biglm
• bigmemory package
  • about / Using massive matrices with bigmemory
  • URL, for documentation / Using massive matrices with bigmemory
  • massive matrices, using with / Using massive matrices with bigmemory
• bigrf package
  • about / Growing bigger and faster random forests with bigrf
  • random forests, building / Growing bigger and faster random forests with bigrf
• bimodal / Measuring the central tendency – the mode
• binning
  • about / Using numeric features with naive Bayes
• bins
  • about / Visualizing numeric variables – histograms
• Bioconductor project
  • about / Working with bioinformatics data
  • URL / Working with bioinformatics data
• bioinformatics data
  • working with / Working with bioinformatics data
• bivariate relationships
  • about / Exploring relationships between variables
• blind tasting experience example / The kNN algorithm
• body mass index (BMI) / Step 1 – collecting data
• boosting
  • about / Boosting
• bootstrap aggregating
  • about / Bagging
• bootstrap sampling / Bootstrap sampling
• box-and-whiskers plot
  • about / Visualizing numeric variables – boxplots
• boxplot
  • about / Visualizing numeric variables – boxplots
• boxplot() function / Visualizing numeric variables – boxplots
• branches
  • about / Understanding decision trees
• breast cancer
  • diagnosing, with kNN algorithm / Diagnosing breast cancer with the kNN algorithm
• breast cancer example
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance, Transformation – z-score standardization

C

• c() function / Vectors
• C5.0 algorithm
  • about / The C5.0 decision tree algorithm
  • strengths / The C5.0 decision tree algorithm
  • weaknesses / The C5.0 decision tree algorithm
  • split, selecting / Choosing the best split
  • decision tree, pruning / Pruning the decision tree
• caret character / Ordinary least squares estimation
• caret package
  • using, for automated parameter tuning / Using caret for automated parameter tuning
  • about / Using caret for automated parameter tuning, Training and evaluating models in parallel with caret
• categorical variables
  • about / Exploring categorical variables
  • exploring / Exploring categorical variables
  • central tendency, measuring / Measuring the central tendency – the mode
• cbind() function / Multiple linear regression
• central tendency
  • measuring / Measuring the central tendency – mean and median
• centroid / Using distance to assign and update clusters
• characteristics, neural networks
  • activation function / From biological to artificial neurons, Activation functions
  • network topology / From biological to artificial neurons, Network topology, The number of layers, The direction of information travel, The number of nodes in each layer
  • training algorithm / From biological to artificial neurons, Training neural networks with backpropagation
• character vectors
  • about / Factors
• Chi-Squared statistic
  • about / Choosing the best split
• classification
  • about / Thinking about types of machine learning algorithms
  • nearest neighbors used / Understanding classification using nearest neighbors
• classification performance
  • measuring / Measuring performance for classification
• classification prediction data
  • working with / Working with classification prediction data in R
• classification rules
  • about / Understanding classification rules
  • separate-and-conquer / Separate and conquer
  • One Rule algorithm / The One Rule algorithm
  • RIPPER algorithm / The RIPPER algorithm
  • obtaining, from decision trees / Rules from decision trees
• cluster
  • about / Understanding clustering
• clustering
  • about / Thinking about types of machine learning algorithms, Understanding clustering
  • applications / Understanding clustering
  • as machine learning task / Clustering as a machine learning task
• clustering, k-means algorithm
  • about / The k-means algorithm for clustering
  • distance, used for assigning cluster / Using distance to assign and update clusters
  • distance, used for updating cluster / Using distance to assign and update clusters
  • appropriate number of clusters, selecting / Choosing the appropriate number of clusters
• clusters / Learning faster with parallel computing
• column-major order
  • about / Matrixes and arrays
• combine function / Vectors
• components, machine learning
  • generalization / Generalization
  • success of learning, assessing / Assessing the success of learning
• components, machine learnng
  • data input / How do machines learn?
  • abstraction / How do machines learn?, Abstraction and knowledge representation
  • generalization / How do machines learn?
  • knowledge representation / Abstraction and knowledge representation
• Comprehensive R Archive Network (CRAN)
  • about / Using R for machine learning
  / Step 3 – training a model on the data
• concrete strength, modeling with ANNs
  • about / Modeling the strength of concrete with ANNs
  • data, collecting / Step 1 – collecting data
  • data, preparing / Step 2 – exploring and preparing the data
  • data, exploring / Step 2 – exploring and preparing the data
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• conditional probability
  • about / Conditional probability with Bayes' theorem
• confusion matrix
  • about / A closer look at confusion matrices
  • used, for measuring performance / Using confusion matrices to measure performance
• contingency table
  • about / Examining relationships – two-way cross-tabulations
• convex hull / The case of linearly separable data
• cor() command / Exploring relationships among features – the correlation matrix
• cor() function / Correlations
• corpus
  • about / Data preparation – processing text data for analysis
• Corpus() function / Data preparation – processing text data for analysis
• correlation / Visualizing relationships – scatterplots
  • about / Correlations
• correlation ellipse / Visualizing relationships among features – the scatterplot matrix
• correlation matrix / Exploring relationships among features – the correlation matrix
• cov() function / Ordinary least squares estimation, Correlations
• covariance
  • about / Ordinary least squares estimation
• createDataPartition() function / The holdout method
• cross-validation / Cross-validation
• crosstab
  • about / Examining relationships – two-way cross-tabulations
• CrossTable() function / Examining relationships – two-way cross-tabulations, Using confusion matrices to measure performance
• CSV files
  • data, importing from / Importing and saving data from CSV files
  • about / Importing and saving data from CSV files
  • loading, into R / Importing and saving data from CSV files
• CUDA
  • about / GPU computing
• curve() function / Choosing the best split
• cut points
  • about / Using numeric features with naive Bayes

D

• data
  • machine learning algorithm, applying to / Steps to apply machine learning to your data
  • managing, with R / Managing data with R
  • importing, from CSV files / Importing and saving data from CSV files
  • importing, from SQL databases / Importing data from SQL databases
  • about / Working with specialized data
  • obtaining, from web / Getting data from the Web with the RCurl package
• data.frame() function / Data frames
• data.table package
  • about / Making data frames faster with data.table
• data dictionary
  • about / Exploring the structure of data
• data exploration
  • about / Exploring and understanding data
• data frame
  • about / R data structures, Data frames
  • making faster, with data.table package / Making data frames faster with data.table
• data mining
  • about / The origins of machine learning
• data munging
  • about / Working with specialized data
• data preparation, breast cancer example
  • training, creating / Data preparation – creating training and test datasets
  • test datasets, creating / Data preparation – creating training and test datasets
• data structures, R
  • about / R data structures
  • vector / Vectors
  • factor / Factors, Lists
  • data frame / Data frames
  • matrix / Matrixes and arrays
  • array / Matrixes and arrays
  • saving / Saving and loading R data structures
  • loading / Saving and loading R data structures
  • exploring / Exploring the structure of data
• DBMS
  • about / Importing data from SQL databases
• decision nodes
  • about / Understanding decision trees
• decision tree
  • about / Understanding decision trees, Example – identifying risky bank loans using C5.0 decision trees
  • potential uses / Understanding decision trees
  • divide-and-conquer / Divide and conquer
  • pruning / Pruning the decision tree
  • used, for identifying risky bank loans / Example – identifying risky bank loans using C5.0 decision trees, Step 1 – collecting data
  • accuracy, boosting / Boosting the accuracy of decision trees
• decision tree forests
  • about / Random forests
• decision trees
  • classification rules, obtaining from / Rules from decision trees
• deep learning / The direction of information travel
• delimiter
  • about / Importing and saving data from CSV files
• dendrites
  • about / From biological to artificial neurons
• dependent events
  • about / Joint probability
• dependent variable / Visualizing relationships – scatterplots
  • about / Understanding regression
• descriptive model
  • about / Thinking about types of machine learning algorithms
• diff() function / Measuring spread – quartiles and the five-number summary
• disk-based data frames
  • creating, with ff package / Creating disk-based data frames with ff
• distance function
  • about / Calculating distance
• divide-and-conquer
  • about / Divide and conquer
• DSN
  • about / Importing data from SQL databases
• dummy coding
  • about / Preparing data for use with kNN
  / Step 3 – training a model on the data

E

• e1071 package
  • naive Bayes classification, with naiveBayes() function / Step 3 – training a model on the data
• elbow method / Choosing the appropriate number of clusters
• elbow point / Choosing the appropriate number of clusters
• elements
  • about / Vectors
• ensemble methods
  • bagging / Bagging
  • boosting / Boosting
  • random forests / Random forests
• ensembles
  • about / Understanding ensembles
  • advantages / Understanding ensembles
• entropy
  • about / Choosing the best split
• epoch / Training neural networks with backpropagation
• ethical considerations, machine learning / Ethical considerations
• Euclidean distance
  • about / Calculating distance
• Euclidean norm / The case of linearly separable data
• events
  • about / Basic concepts of Bayesian methods
• example
  • about / Thinking about the input data

F

• 10-fold cross-validation
  • about / Cross-validation
• F-measure
  • about / The F-measure
• Facebook / Finding teen market segments using k-means clustering
• factor
  • about / R data structures, Factors, Lists
  • creating, from character vector / Factors
• factor() function / Factors
• feature
  • about / Thinking about the input data
• feedforward networks
  • about / The direction of information travel
• ff package
  • about / Creating disk-based data frames with ff
  • used, for creating disk-based data frames / Creating disk-based data frames with ff
• five-number summary
  • about / Measuring spread – quartiles and the five-number summary
• foreach package
  • about / Working in parallel with foreach, Training and evaluating models in parallel with caret
• frequently purchased groceries
  • identifying, with association rules / Example – identifying frequently purchased groceries with association rules
• future performance
  • estimating / Estimating future performance
• future performance estimation
  • holdout method / The holdout method
  • cross-validation / Cross-validation
  • bootstrap sampling / Bootstrap sampling

G

• gain ratio
  • about / Choosing the best split
• Gaussian Radial Basis Function (RBF) kernel / Using kernels for non-linear spaces
• generalization
  • about / Generalization
• generalized linear models (GLM)
  • about / Understanding regression
• Gini index
  • about / Choosing the best split
• GPU computing
  • about / GPU computing
• gputools package
  • about / GPU computing
• gradient descent
  • about / Training neural networks with backpropagation
• graph data
  • working with / Working with social network data and graph data
• greedy learners
  • about / Separate and conquer
• grid
  • about / Using caret for automated parameter tuning

H

• Hadoop
  • parallel computing / Parallel cloud computing with MapReduce and Hadoop
• header line
  • about / Importing and saving data from CSV files
• heuristics
  • about / Generalization
• hidden layers
  • about / The number of layers
• hist() function / Visualizing numeric variables – histograms
• histogram
  • about / Visualizing numeric variables – histograms
• holdout method / The holdout method
• human brain / Understanding neural networks
• hyperplane / Understanding Support Vector Machines

I

• imputation / Data preparation – imputing missing values
• Incremental Reduced Error Pruning algorithm (IREP) / The RIPPER algorithm
• independent events
  • about / Joint probability
• independent variables
  • about / Understanding regression
• information gain / Choosing the best split
• Input Nodes / The number of layers
• installation, R package / Installing an R package
• instance-based learning
  • about / Why is the kNN algorithm lazy?
• interaction
  • about / Model specification – adding interaction effects
• intercept
  • about / Understanding regression
• interquartile range (IQR) / Measuring spread – quartiles and the five-number summary
• ipred package
  • about / Bagging
• IQR() function / Measuring spread – quartiles and the five-number summary
• itemFrequencyPlot() function / Visualizing item support – item frequency plots
• itemset
  • about / Understanding association rules

J

• joint probability
  • about / Joint probability
• JRip() classifier / Step 5 – improving model performance
• JSON
  • about / Reading and writing JSON with the rjson package
  • reading, rjson package used / Reading and writing JSON with the rjson package
  • writing, rjson package used / Reading and writing JSON with the rjson package
  • converting, to R / Reading and writing JSON with the rjson package
• JSON format
  • URL / Reading and writing JSON with the rjson package

K

• k-means algorithm
  • about / The k-means algorithm for clustering
  • strengths / The k-means algorithm for clustering
  • weaknesses / The k-means algorithm for clustering
• kappa statistic
  • about / The kappa statistic
• kernels
  • using, for non-linear spaces / Using kernels for non-linear spaces
• kernel trick / Using kernels for non-linear spaces
• kernlab package / Bagging
• kmeans() function / Step 3 – training a model on the data
• knn() function / Step 3 – training a model on the data
• kNN algorithm
  • about / The kNN algorithm, Step 3 – training a model on the data
  • strengths / The kNN algorithm
  • weaknesses / The kNN algorithm
  • distance, calculating / Calculating distance
  • appropriate k, selecting / Choosing an appropriate k
  • data, preparing / Preparing data for use with kNN
  • used, for diagnosing breast cancer / Diagnosing breast cancer with the kNN algorithm
• knowledge representation
  • about / Abstraction and knowledge representation
• ksvm() function / Bagging

L

• Laplace estimator
  • about / The Laplace estimator
• lapply() function / Transformation – normalizing numeric data, Transformation – z-score standardization
• large datasets
  • managing / Managing very large datasets
• large datasets management
  • about / Managing very large datasets
  • data frames, making faster with data.table package / Making data frames faster with data.table
  • disk-based data frames, creating with ff package / Creating disk-based data frames with ff
  • massive matrices, using with bigmemory package / Using massive matrices with bigmemory
• layers
  • about / The number of layers
• lazy learning algorithms / Why is the kNN algorithm lazy?
• leaf nodes
  • about / Understanding decision trees
• learning, with parallel computing
  • about / Learning faster with parallel computing
  • execution time, measuring / Measuring execution time
  • working, in paralle with foreach / Working in parallel with foreach
  • multitasking operating system, using with multicore package / Using a multitasking operating system with multicore
  • multiple workstations, networking / Networking multiple workstations with snow and snowfall
  • parallel cloud computing, with MapReduce / Parallel cloud computing with MapReduce and Hadoop
  • parallel cloud computing, with Hadoop / Parallel cloud computing with MapReduce and Hadoop
• learning rate / Training neural networks with backpropagation
• left hand side (LHS) / Step 4 – evaluating model performance
• levels
  • about / Thinking about types of machine learning algorithms
• likelihood
  • about / Conditional probability with Bayes' theorem
• likelihood table
  • about / Conditional probability with Bayes' theorem
• linear kernel / Using kernels for non-linear spaces
• linearly separable / Classification with hyperplanes
• linear regression
  • about / Understanding regression
• link function
  • about / Understanding regression
• list() function / Lists
• lists
  • about / R data structures
• lm() function
  • about / Building bigger regression models with biglm
• load() command / Saving and loading R data structures
• loess smooth / Visualizing relationships among features – the scatterplot matrix
• logistic regression
  • about / Understanding regression

M

• M5' algorithm (M5-prime) / Step 5 – improving model performance
• machine learning
  • origins / The origins of machine learning
  • benefits / Uses and abuses of machine learning
  • ethical considerations / Ethical considerations
  • about / How do machines learn?
  • applying, to data / Steps to apply machine learning to your data
  • R, using / Using R for machine learning
• machine learning algorithm
  • about / The origins of machine learning, Uses and abuses of machine learning
  • selecting / Choosing a machine learning algorithm
  • data, matching / Matching your data to an appropriate algorithm
• machine learning algorithms
  • input training data / Thinking about the input data
  • types / Thinking about types of machine learning algorithms
• Manhattan distance
  • about / Calculating distance
• MapReduce programming model
  • about / Parallel cloud computing with MapReduce and Hadoop
  • parallel computing / Parallel cloud computing with MapReduce and Hadoop
• marginal likelihood
  • about / Conditional probability with Bayes' theorem
• market basket analysis example
  • data, collecting / Step 1 – collecting data
  • data, preparing / Step 2 – exploring and preparing the data
  • data, exploring / Step 2 – exploring and preparing the data
  • sparse matrix, creating for transaction data / Data preparation – creating a sparse matrix for transaction data
  • item support, visualizing / Visualizing item support – item frequency plots
  • transaction data, visualizing / Visualizing transaction data – plotting the sparse matrix
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
  • set of association rules, sorting / Sorting the set of association rules, Taking subsets of association rules
  • association rules, saving to file / Saving association rules to a file or data frame
• massive matrices
  • using, with bigmemory package / Using massive matrices with bigmemory
• matrix
  • about / Matrixes and arrays
• matrix() function / Matrixes and arrays
• Maximum Margin Hyperplane (MMH)
  • about / Finding the maximum margin
  • case, of linearly separable data / The case of linearly separable data
  • case, of non-linearly separable data / The case of non-linearly separable data
• mcapply() function / Using a multitasking operating system with multicore
• mean
  • about / Measuring the central tendency – mean and median
• mean() function / Measuring the central tendency – mean and median, Ordinary least squares estimation
• mean absolute error (MAE) / Measuring performance with mean absolute error
• median
  • about / Measuring the central tendency – mean and median
• median() function / Measuring the central tendency – mean and median
• medical expenses, predicting with linear regression
  • about / Example – predicting medical expenses using linear regression
  • data, collecting / Step 1 – collecting data
  • data, preparing / Step 2 – exploring and preparing the data
  • data, exploring / Step 2 – exploring and preparing the data
  • correlation matrix / Exploring relationships among features – the correlation matrix
  • relationships, exploring among features / Exploring relationships among features – the correlation matrix
  • relationships, visualizing among features / Visualizing relationships among features – the scatterplot matrix
  • scatterplot matrix / Visualizing relationships among features – the scatterplot matrix
  • model, training on data / Step 3 – training a model on the data
  • model performance, training / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance, Transformation – converting a numeric variable to a binary indicator, Putting it all together – an improved regression model
• meta-learning methods
  • about / Improving model performance with meta-learning
  • used, for improving model performance / Improving model performance with meta-learning
• Microsoft Excel / Importing and saving data from CSV files
• Microsoft Excel spreadsheets
  • reading, xlsx package used / Reading and writing Microsoft Excel spreadsheets using xlsx
  • writing, xlsx package used / Reading and writing Microsoft Excel spreadsheets using xlsx
• Microsoft SQL
  • about / Importing data from SQL databases
• min-max normalization
  • about / Preparing data for use with kNN
• Mobile Phone Spam
  • filtering, with naive Bayes algorithm / Example – filtering mobile phone spam with the naive Bayes algorithm
• Mobile Phone Spam example
  • data, collecting / Step 1 – collecting data
  • data, preparing / Step 2 – exploring and preparing the data
  • data, exploring / Step 2 – exploring and preparing the data
  • text data, processing for analysis / Data preparation – processing text data for analysis
  • training, creating / Data preparation – creating training and test datasets
  • test datasets, creating / Data preparation – creating training and test datasets
  • text data, visualizing / Visualizing text data – word clouds
  • indicator features, creating for frequent words / Data preparation – creating indicator features for frequent words
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• mode
  • about / Measuring the central tendency – the mode
• mode() function / Measuring the central tendency – the mode
• model
  • about / Abstraction and knowledge representation
• model performance
  • improving, with meta-learning / Improving model performance with meta-learning
• model performance, breast cancer example
  • z-score standardization / Transformation – z-score standardization
  • alternatives values, testing of k / Testing alternative values of k
• model trees
  • about / Understanding regression trees and model trees
• multicore package
  • about / Using a multitasking operating system with multicore
• multidimensional feature space / The kNN algorithm
• multilayer network
  • about / The number of layers
• Multilayer Perceptron (MLP)
  • about / The direction of information travel
• multimodal / Measuring the central tendency – the mode
• multiple linear regression
  • about / Multiple linear regression
  • strengths / Multiple linear regression
  • weaknesses / Multiple linear regression
• multiple workstations
  • networking, with snow package / Networking multiple workstations with snow and snowfall
  • networking, with snowfall package / Networking multiple workstations with snow and snowfall
• multitasking operating system
  • using, with multicore package / Using a multitasking operating system with multicore
• multivariate relationships
  • about / Exploring relationships between variables
• MySpace / Finding teen market segments using k-means clustering
• MySQL
  • about / Importing data from SQL databases

N

• naive Bayes
  • numeric features, using with / Using numeric features with naive Bayes
• naive Bayes algorithm
  • about / Understanding naive Bayes, The naive Bayes algorithm
  • strengths / The naive Bayes algorithm
  • weaknesses / The naive Bayes algorithm
  • naive Bayes classification / The naive Bayes classification
  • Laplace estimator / The Laplace estimator
  • used, for filtering Mobile Phone Spam / Example – filtering mobile phone spam with the naive Bayes algorithm
• naive Bayes classification
  • about / The naive Bayes classification
  • naiveBayes() function, using in e1071 package / Step 3 – training a model on the data
• nearest neighbor classifiers
  • about / Understanding classification using nearest neighbors
• network package
  • about / Working with social network data and graph data
  • URL, for info / Working with social network data and graph data
• network topology
  • about / Network topology
  • number of layers / The number of layers
  • direction, of information travel / The direction of information travel
  • number of nodes, in each layer / The number of nodes in each layer
• neural networks
  • about / Understanding neural networks
  • biological, to artificial neurons / From biological to artificial neurons
  • characteristics / From biological to artificial neurons
  • training, with backpropagation / Training neural networks with backpropagation
• neurons
  • about / Understanding neural networks
• No Free Lunch theorem
  • about / Choosing a machine learning algorithm
• nominal variables
  • about / Factors
• non-linearly separable data / The case of non-linearly separable data
• non-linear spaces
  • kernels, using for / Using kernels for non-linear spaces
• normal distributions / Understanding numeric data – uniform and normal distributions
• normalize() function / Transformation – normalizing numeric data
• numeric data
  • about / Understanding numeric data – uniform and normal distributions
  • normalizing / Transformation – normalizing numeric data
• numeric features
  • using, with naive Bayes / Using numeric features with naive Bayes
• numeric prediction
  • about / Thinking about types of machine learning algorithms
• numeric variables
  • about / Exploring numeric variables
  • exploring / Exploring numeric variables
  • central tendency, measuring / Measuring the central tendency – mean and median
  • spread, measuring / Measuring spread – quartiles and the five-number summary
  • visualizing / Visualizing numeric variables – boxplots, Visualizing numeric variables – histograms

O

• <- operator / Vectors
• OCR, performing with SVMs
  • about / Performing OCR with SVMs
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• ODBC
  • about / Importing data from SQL databases
• odbcConnect() function / Importing data from SQL databases
• one-way table / Exploring categorical variables
• One Rule algorithm
  • about / The One Rule algorithm
  • strengths / The One Rule algorithm
  • weaknesses / The One Rule algorithm
• optimized learning algorithms
  • deploying / Deploying optimized learning algorithms
• optimized learning algorithms deployment
  • regression models, building with biglm package / Building bigger regression models with biglm
  • random forests, building with bigrf package / Growing bigger and faster random forests with bigrf
  • caret package, used for evaluating models in parallel / Training and evaluating models in parallel with caret
• Oracle
  • about / Importing data from SQL databases
• order() function / Data preparation – creating random training and test datasets
• ordinary least squares (OLS) / Ordinary least squares estimation
• ordinary least squares estimation
  • about / Ordinary least squares estimation
• out-of-bag error rate
  • about / Training random forests
• Output Node / The number of layers
• overfitting
  • about / Assessing the success of learning

P

• pairs() function / Visualizing relationships among features – the scatterplot matrix
• parallel computing methods
  • about / Learning faster with parallel computing
• parameter estimates
  • about / Simple linear regression
• parameter tuning
  • about / Tuning stock models for better performance
• pattern discovery
  • about / Thinking about types of machine learning algorithms
• Pearson's Chi-squared test / Examining relationships – two-way cross-tabulations
• Pearson's correlation
  • about / Correlations
• performance
  • measuring, confusion matrices used / Using confusion matrices to measure performance
  • improving, of R / Improving the performance of R
• performance() function / ROC curves
• performance measures
  • about / Beyond accuracy – other measures of performance
  • kappa statistic / The kappa statistic
  • sensitivity / Sensitivity and specificity
  • specificity / Sensitivity and specificity
  • precision / Precision and recall
  • recall / Precision and recall
  • F-measure / The F-measure
• performance tradeoffs
  • visualizing / Visualizing performance tradeoffs
• plot() command / ROC curves
• plot() function / Visualizing relationships – scatterplots
• point-and-click interface
  • used, for installing R package / Installing a package using the point-and-click interface
• poisonous mushrooms
  • identifying, with rule learners / Example – identifying poisonous mushrooms with rule learners
• poisonous mushrooms example, with rule learners
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• Poisson regression
  • about / Understanding regression
• polynomial kernel / Using kernels for non-linear spaces
• posPredValue() function / Precision and recall
• posterior probability
  • about / Conditional probability with Bayes' theorem
• PostgreSQL
  • about / Importing data from SQL databases
• postpruning
  • about / Pruning the decision tree
• precision
  • about / Precision and recall
• pred function / Bagging
• predict() function / Working with classification prediction data in R, Creating a simple tuned model
  • about / Bagging
• predictive model
  • about / Thinking about types of machine learning algorithms
• prepruning
  • about / Pruning the decision tree
• prior probability
  • about / Conditional probability with Bayes' theorem
• probability
  • about / Probability

Q

• quadratic optimization / The case of linearly separable data
• quantile() function / Measuring spread – quartiles and the five-number summary
• quartiles
  • about / Measuring spread – quartiles and the five-number summary

R

• 68-95-99.7 rule / Measuring spread – variance and standard deviation
• R
  • using, for machine learning / Using R for machine learning
  • data structures / R data structures
  • used, for managing data / Managing data with R
  • CSV file, loading into / Importing and saving data from CSV files
  • working with classification prediction data / Working with classification prediction data in R
  • JSON, converting to / Reading and writing JSON with the rjson package
  • performance, improving / Improving the performance of R
• Radial Basis Function (RBF) network
  • about / Activation functions
• randomForest() function
  • about / Training random forests
  / Evaluating random forest performance
• randomForest package / Training random forests
• random forests
  • about / Random forests
  • strengths / Random forests
  • weaknesses / Random forests
  • training / Training random forests
  • performance, evaluating / Evaluating random forest performance
• range
  • about / Measuring spread – quartiles and the five-number summary
• range() function / Measuring spread – quartiles and the five-number summary
• RCurl package
  • about / Getting data from the Web with the RCurl package
  • used, for obtaining data from web / Getting data from the Web with the RCurl package
  • URL, for documentation / Getting data from the Web with the RCurl package
• real-world data
  • about / Working with specialized data
• recall / Precision and recall
• recurrent network
  • about / The direction of information travel
• recursive partitioning
  • about / Divide and conquer
• reg() function / Multiple linear regression
• regression
  • about / Understanding regression
  • simple linear regression / Simple linear regression
  • ordinary least squares estimation / Ordinary least squares estimation
  • correlation / Correlations
  • multiple linear regression / Multiple linear regression
  • adding, to trees / Adding regression to trees
• regression analysis
  • use cases / Understanding regression
• regression equations
  • about / Understanding regression
• regression models
  • building, with biglm package / Building bigger regression models with biglm
• regression trees
  • about / Understanding regression trees and model trees
  • strengths / Adding regression to trees
  • weaknesses / Adding regression to trees
• relationships
  • exploring, between variables / Exploring relationships between variables
  • visualizing / Visualizing relationships – scatterplots
  • examining / Examining relationships – two-way cross-tabulations
• residuals
  • about / Ordinary least squares estimation
• resubstitution error / Estimating future performance
• RHIPE package / Parallel cloud computing with MapReduce and Hadoop
• right hand side (RHS) / Step 4 – evaluating model performance
• RIPPER algorithm
  • about / The RIPPER algorithm
  • strengths / The RIPPER algorithm
  • weaknesses / The RIPPER algorithm
• risky bank loans
  • identifying, C5.0 decision trees used / Example – identifying risky bank loans using C5.0 decision trees, Step 1 – collecting data
• rjson package
  • about / Reading and writing JSON with the rjson package
  • used, for reading JSON / Reading and writing JSON with the rjson package
  • used, for writing JSON / Reading and writing JSON with the rjson package
• rmr package
  • about / Parallel cloud computing with MapReduce and Hadoop
• ROC curve
  • about / ROC curves
  • creating / ROC curves
• ROCR package
  • about / Visualizing performance tradeoffs
• RODBC package
  • about / Importing data from SQL databases
• rote learning
  • about / Why is the kNN algorithm lazy?
• round() function / Exploring categorical variables
• R package
  • installing / Installing an R package
  • installing, point-and-click interface used / Installing a package using the point-and-click interface
  • loading / Loading an R package
• R performance
  • large datasets, managing / Managing very large datasets
  • learning, with parallel computing / Learning faster with parallel computing
  • GPU computing / GPU computing
  • optimized learning algorithms, deploying / Deploying optimized learning algorithms
• rudimentary ANNs / Understanding neural networks
• runif() function / Data preparation – creating random training and test datasets
• RWeka package
  • using / Installing and loading R packages
  • loading / Loading an R package
  / The C5.0 decision tree algorithm

S

• save() function / Saving and loading R data structures
• scale() function / Transformation – z-score standardization
• scatterplot
  • about / Visualizing relationships – scatterplots
• Scoville scale
  • about / Preparing data for use with kNN
• sd() function / Measuring spread – variance and standard deviation, Correlations
• semi-supervised learning
  • about / Clustering as a machine learning task
• sensitivity() function / Precision and recall
• sensor / The origins of machine learning
• separate-and-conquer
  • about / Separate and conquer
• seq() function / Measuring spread – quartiles and the five-number summary
• Short Message Service (SMS) / Example – filtering mobile phone spam with the naive Bayes algorithm
• sigmoid activation function
  • about / Activation functions
• sigmoid kernel / Using kernels for non-linear spaces
• simple linear regression
  • about / Simple linear regression
• simple tuned model
  • creating / Creating a simple tuned model
• single-layer network
  • about / The number of layers
• skew / Visualizing numeric variables – histograms
• slack variable / The case of non-linearly separable data
• slope
  • about / Understanding regression
• sna package
  • URL, for info / Working with social network data and graph data
• snowfall package
  • multiple workstations, networking / Networking multiple workstations with snow and snowfall
• snow package
  • about / Networking multiple workstations with snow and snowfall
  • multiple workstations, networking / Networking multiple workstations with snow and snowfall
• social network data
  • working with / Working with social network data and graph data
• Social Networking Service (SNS) / Finding teen market segments using k-means clustering
• sparse matrix
  • about / Data preparation – processing text data for analysis, Data preparation – creating a sparse matrix for transaction data
  • creating, for transaction data / Data preparation – creating a sparse matrix for transaction data
• specialized data
  • working with / Working with specialized data
• SQL databases
  • data, importing from / Importing data from SQL databases
• SQLite
  • about / Importing data from SQL databases
• sqlQuery() function / Importing data from SQL databases
• stacking
  • about / Understanding ensembles
• standard deviation
  • about / Measuring spread – variance and standard deviation
• standard deviation reduction (SDR) / Adding regression to trees
• stock models
  • tuning, for better performance / Tuning stock models for better performance
• stop words
  • about / Data preparation – processing text data for analysis
• str() function
  • about / Exploring the structure of data
  / Step 2 – exploring and preparing the data
• stringsAsFactors option / Data frames
• subset() function / Working with classification prediction data in R
• summary() function / Exploring numeric variables
• summary statistics
  • about / Exploring numeric variables
• Sum of Squared Errors (SSE) / Step 3 – training a model on the data
• supervised learning
  • about / Thinking about types of machine learning algorithms
• support vector machine (SVM)
  • about / Bagging
• Support Vector Machine (SVM)
  • about / Understanding Support Vector Machines
  • applications / Understanding Support Vector Machines
  • classifications, with hyperplanes / Classification with hyperplanes
  • maximum margin, finding / Finding the maximum margin
  • OCR, performing with / Performing OCR with SVMs
• support vectors / Finding the maximum margin
• synapse
  • about / From biological to artificial neurons

T

• Tab-Separated Value (TSV)
  • about / Importing and saving data from CSV files
• table() function / Exploring categorical variables, Using confusion matrices to measure performance
• target feature
  • about / Thinking about types of machine learning algorithms
• teen market segments serach, with k-means clustering
  • about / Finding teen market segments using k-means clustering
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data, Data preparation – dummy coding missing values, Data preparation – imputing missing values
  • model, training on data / Step 3 – training a model on the data
  • model performance, evaluating / Step 4 – evaluating model performance
  • model performance, improving / Step 5 – improving model performance
• threshold activation function
  • about / Activation functions
• tm package / Data preparation – processing text data for analysis
• token
  • about / Data preparation – processing text data for analysis
• tokenization
  • about / Data preparation – processing text data for analysis
• topology
  • about / Network topology
• train() function / Using caret for automated parameter tuning, Creating a simple tuned model
• trainControl() function / Customizing the tuning process
• training
  • about / Abstraction and knowledge representation
• transaction data
  • sparse matrix, creating for / Data preparation – creating a sparse matrix for transaction data
• transpose
  • about / Multiple linear regression
• trees
  • regression, adding to / Adding regression to trees
• tree structure
  • about / Understanding decision trees
• trial
  • about / Basic concepts of Bayesian methods
• trivial rules / Step 4 – evaluating model performance
• tuning process
  • customizing / Customizing the tuning process
• Turing test
  • about / Understanding neural networks
• two-way cross-tabulation
  • about / Examining relationships – two-way cross-tabulations

U

• UCI Machine Learning Data Repository
  • URL / Step 1 – collecting data, Step 1 – collecting data
  • about / Step 1 – collecting data
• uniform distribution / Understanding numeric data – uniform and normal distributions
• unimodal / Measuring the central tendency – the mode
• unit of observation phrase / Thinking about the input data
• unit step activation function
  • about / Activation functions
• univariate statistics
  • about / Exploring relationships between variables
• universal function approximator
  • about / The number of nodes in each layer
• unsupervised classification
  • about / Clustering as a machine learning task
• unsupervised learning
  • about / Thinking about types of machine learning algorithms
• usedcars.csv dataset
  • about / Exploring and understanding data

V

• var() function / Measuring spread – variance and standard deviation, Ordinary least squares estimation
• variables
  • relationships, exploring between / Exploring relationships between variables
• variance
  • about / Measuring spread – variance and standard deviation
• vector
  • about / R data structures, Vectors
• vector types
  • integer / Vectors
  • numeric / Vectors
  • character / Vectors
  • logical / Vectors
• Venn diagram
  • about / Joint probability
• Voronoi diagram / Using distance to assign and update clusters

W

• web
  • data, obtaining from / Getting data from the Web with the RCurl package
• weighted voting process
  • about / Choosing an appropriate k
• wine quality estimation, with regression trees
  • about / Example – estimating the quality of wines with regression trees and model trees
  • data, collecting / Step 1 – collecting data
  • data, exploring / Step 2 – exploring and preparing the data
  • data, preparing / Step 2 – exploring and preparing the data
  • model, training on data / Step 3 – training a model on the data
  • decision trees, visualizing / Visualizing decision trees
  • model performance, evaluating / Step 4 – evaluating model performance
  • performance, measuring with mean absolute error / Measuring performance with mean absolute error
  • model performance, improving / Step 5 – improving model performance
• word cloud
  • about / Visualizing text data – word clouds

X

• xlsx package
  • about / Reading and writing Microsoft Excel spreadsheets using xlsx
  • used, for reading Microsoft Excel spreadsheets / Reading and writing Microsoft Excel spreadsheets using xlsx
  • used, for writing Microsoft Excel spreadsheets / Reading and writing Microsoft Excel spreadsheets using xlsx
  • URL / Reading and writing Microsoft Excel spreadsheets using xlsx
• XML
  • about / Reading and writing XML with the XML package
  • reading, XML package used / Reading and writing XML with the XML package
  • writing, XML package used / Reading and writing XML with the XML package
• XML package
  • about / Reading and writing XML with the XML package
  • used, for reading XML / Reading and writing XML with the XML package
  • used, for writing XML / Reading and writing XML with the XML package
  • URL, for info / Reading and writing XML with the XML package

Z

• z-score standardization
  • about / Preparing data for use with kNN
• ZeroR
  • about / The One Rule algorithm