Learning Predictive Analytics with R: Get to grips with key data visualization and predictive analytic skills using R

Cover......Page 1
Copyright......Page 3
Credits......Page 4
About the Author......Page 5
About the Reviewers......Page 6
www.PacktPub.com......Page 9
Table of Contents......Page 10
Preface......Page 16
Chapter 1: Setting GNU R for Predictive Analytics......Page 26
 The R graphic user interface......Page 27
 The menu bar of the R console......Page 28
  A quick look at the File menu......Page 29
  A quick look at the Misc menu......Page 30
 Packages......Page 33
  Installing packages in R......Page 34
  Loading packages in R......Page 36
 Summary......Page 39
Chapter 2: Visualizing and Manipulating Data Using R......Page 40
 The roulette case......Page 41
 Histograms and bar plots......Page 43
 Scatterplots......Page 50
 Boxplots......Page 53
 Line plots......Page 54
 Application – Outlier detection......Page 56
 Formatting plots......Page 57
 Summary......Page 59
Chapter 3: Data Visualization with Lattice......Page 60
 Loading and discovering the lattice package......Page 61
 Discovering multipanel conditioning with xyplot()......Page 62
  Histograms......Page 64
  Stacked bars......Page 66
  Dotplots......Page 68
  Displaying data points as text......Page 70
 Updating graphics......Page 72
  Discovering the dataset......Page 75
  Integrating supplementary external data......Page 80
 Summary......Page 85
Chapter 4: Cluster Analysis......Page 86
 Distance measures......Page 88
 Learning by doing – partition clustering with kmeans()......Page 90
  Setting the centroids......Page 91
  Computing the closest cluster for each case......Page 92
  Tasks performed by the main function......Page 93
   Internal validation......Page 94
  Understanding the data with the all.us.city.crime.1970 dataset......Page 96
  Finding the best number of clusters in the life.expectancy.1971 dataset......Page 102
 Summary......Page 104
Chapter 5: Agglomerative Clustering Using hclust()......Page 106
 The inner working of agglomerative clustering......Page 107
  Exploring the results of votes in Switzerland......Page 111
  The use of hierarchical clustering on binary attributes......Page 117
 Summary......Page 120
Chapter 6: Dimensionality Reduction with Principal Component Analysis......Page 122
 The inner working of Principal Component Analysis......Page 123
 Learning PCA in R......Page 128
  Dealing with missing values......Page 129
  Selecting how many components are relevant......Page 130
  Naming the components using the loadings......Page 132
   Accessing the PCA scores......Page 134
  PCA scores for analysis......Page 135
  PCA diagnostics......Page 137
 Summary......Page 138
Chapter 7: Exploring Association Rules with Apriori......Page 140
  Support......Page 141
 The inner working of apriori......Page 142
  Generating itemsets with support-based pruning......Page 143
  Using apriori for basic analysis......Page 144
  Detailed analysis with apriori......Page 147
   Analyzing the data......Page 148
   Coercing association rules to a data frame......Page 152
   Visualizing association rules......Page 153
 Summary......Page 155
  Introducing probability distributions......Page 156
   Discrete uniform distribution......Page 157
  The normal distribution......Page 158
  The Student\'s t-distribution......Page 161
  The binomial distribution......Page 162
  The importance of distributions......Page 163
 Covariance, correlation, and regression......Page 164
  Correlation......Page 167
  Covariance......Page 166
 Summary......Page 171
Chapter 9: Linear Regression......Page 172
 Understanding simple regression......Page 173
  Computing the intercept and slope coefficient......Page 175
  Obtaining the residuals......Page 176
  Computing the significance of the coefficient......Page 179
 Analyzing data in R: correlation and regression......Page 181
  First steps in the data analysis......Page 182
  Performing the regression......Page 185
  Checking for the normality of residuals......Page 186
  Checking for variance inflation......Page 187
  Examining potential mediations and comparing models......Page 188
  Predicting new data......Page 191
 Robust regression......Page 194
 Bootstrapping......Page 195
 Summary......Page 198
Chapter 10: Classification with k-Nearest Neighbors and Naïve Bayes......Page 200
 Understanding k-NN......Page 201
 Working with k-NN in R......Page 204
  How to select k......Page 206
 Understanding Naïve Bayes......Page 207
 Working with Naïve Bayes in R......Page 211
 Computing the performance of classification......Page 215
 Summary......Page 217
 Understanding decision trees......Page 218
  Entropy......Page 220
  Information gain......Page 222
  The gain ratio......Page 223
 C5.0......Page 224
  CART......Page 225
 Conditional inference trees and forests......Page 226
  Installing random forest......Page 227
  Loading and preparing the data......Page 228
   The unpruned tree......Page 229
   The pruned tree......Page 230
  C50......Page 231
  CART......Page 232
   Pruning......Page 233
   Random forests in R......Page 235
  Examining the predictions on the testing set......Page 236
  Conditional inference trees in R......Page 237
 Summary......Page 238
 Nested data......Page 240
  Random intercepts and fixed slopes......Page 243
  Random intercepts and random slopes......Page 244
  The null model......Page 246
  Random intercepts and fixed slopes......Page 250
  Random intercepts and random slopes......Page 253
  Using the predict() function......Page 258
  Assessing prediction quality......Page 259
 Summary......Page 260
 An introduction to text analytics......Page 262
 Loading the corpus......Page 264
  Preprocessing and inspecting the corpus......Page 266
  Document classification with k-NN......Page 270
  Document classification with Naïve Bayes......Page 272
  Classification using logistic regression......Page 274
  Document classification with support vector machines......Page 277
  A successful document classification......Page 278
  Extracting the topics of the articles......Page 282
  Collecting news articles in R from the New York Times article search API......Page 284
 Summary......Page 287
  Cross-validation......Page 288
  Performing cross-validation in R with caret......Page 289
  Performing bootstrapping in R with caret......Page 292
  What is PMML?......Page 293
  A brief description of the structure of PMML objects......Page 294
   Exporting k-means objects......Page 296
   Hierarchical clustering......Page 297
   Exporting decision trees (rpart objects)......Page 299
   Exporting logistic regression objects......Page 300
 Summary......Page 301
 Exercises......Page 302
 Solutions......Page 307
Appendix B: Further Reading and References......Page 318
Index......Page 324