R Data Analysis Projects

Cover......Page 1
Title Page......Page 2
Copyright......Page 3
Credits......Page 4
About the Author......Page 5
About the Reviewer......Page 6
www.PacktPub.com......Page 7
Customer Feedback......Page 8
Table of Contents......Page 9
Preface......Page 13
Chapter 1: Association Rule Mining......Page 18
Understanding the recommender systems......Page 19
Transactions......Page 20
Our web application......Page 21
Retailer use case and data......Page 22
Association rule mining......Page 25
Support and confidence thresholds......Page 37
The cross-selling campaign......Page 42
Leverage ......Page 45
Conviction......Page 46
Weighted association rule mining......Page 47
Hyperlink-induced topic search (HITS)......Page 54
Negative association rules......Page 62
Rules visualization......Page 65
Wrapping up......Page 69
Summary......Page 77
Chapter 2: Fuzzy Logic Induced Content-Based Recommendation......Page 78
Introducing content-based recommendation......Page 80
News aggregator use case and data......Page 84
Designing the content-based recommendation engine......Page 89
Bag-of-words......Page 92
Inverse document frequency (IDF)......Page 93
TFIDF......Page 94
Why cosine similarity?......Page 97
Searching......Page 98
Polarity scores......Page 101
Jaccard's distance......Page 103
Jaccards distance/index......Page 104
Ranking search results......Page 106
 Fuzzification......Page 107
Evaluating the rules......Page 109
Defuzzification......Page 110
Complete R Code......Page 119
Summary......Page 125
Chapter 3: Collaborative Filtering......Page 127
Collaborative filtering......Page 128
Memory-based approach......Page 130
Model-based approach......Page 131
Latent factor approach......Page 132
Recommenderlab package......Page 134
Popular approach......Page 136
Use case and data......Page 138
Designing and implementing collaborative filtering......Page 148
Ratings matrix......Page 149
Normalization......Page 151
Train test split......Page 153
Train model......Page 156
User-based models......Page 161
Item-based models......Page 164
Factor-based models......Page 165
Complete R Code......Page 167
Summary......Page 173
Chapter 4: Taming Time Series Data Using Deep Neural Networks......Page 174
Time series data......Page 176
Non-seasonal time series......Page 177
Seasonal time series......Page 178
Time series as a regression problem......Page 179
Deep neural networks......Page 183
Forward cycle......Page 186
Introduction to the MXNet R package......Page 187
Symbolic programming in MXNet......Page 190
Softmax activation......Page 194
Use case and data......Page 196
Deep networks for time series prediction......Page 198
Training test split......Page 200
Complete R code......Page 214
Summary......Page 221
Chapter 5: Twitter Text Sentiment Classification Using Kernel Density Estimates......Page 222
Kernel density estimation......Page 224
Twitter text......Page 229
Sentiment classification......Page 230
Our approach......Page 231
Dictionary based scoring......Page 232
Text pre-processing......Page 236
Term-frequeny inverse document frequency (TFIDF)......Page 238
Delta TFIDF......Page 239
Building a sentiment classifier......Page 242
Assembling an RShiny application......Page 246
Complete R code......Page 250
Summary......Page 254
Chapter 6: Record Linkage - Stochastic and Machine Learning Approaches......Page 255
Introducing our use case......Page 256
Demonstrating the use of RecordLinkage package......Page 257
Feature generation......Page 259
String features......Page 261
Phonetic features......Page 262
Expectation maximization method......Page 264
Weights-based method......Page 270
Unsupervised learning......Page 273
Supervised learning......Page 275
Building an RShiny application......Page 280
Complete R code......Page 283
Feature generation......Page 284
Expectation maximization method......Page 285
Weights-based method......Page 286
Machine learning method......Page 287
RShiny application......Page 289
Summary......Page 290
Chapter 7: Streaming Data Clustering Analysis in R......Page 291
Streaming data and its challenges......Page 292
Single pass......Page 293
Introducing stream clustering......Page 294
Introducing the stream package......Page 295
Data stream data......Page 296
DSD as a static simulator......Page 297
DSD as a simulator with drift......Page 299
DSD connecting to memory, file, or database......Page 303
Can we connect this DSD to an actual data stream?......Page 304
Data stream task......Page 305
Use case and data......Page 310
Speed layer......Page 311
Batch layer......Page 312
Reservoir sampling......Page 314
Complete R code......Page 317
Summary......Page 320
Chapter 8: Analyze and Understand Networks Using R......Page 321
Graphs in R......Page 323
Degree of a vertex......Page 327
Adjacency Matrix......Page 328
Centrality of a vertex......Page 329
Finding the shortest path between nodes......Page 330
Use case and data......Page 331
Data preparation......Page 333
Product network analysis......Page 338
Building a RShiny application......Page 345
The complete R script......Page 352
Summary......Page 356
Index......Page 357