MLWithR:

##### Chapter 4: Classification using Naive Bayes --------------------

## Example: Filtering spam SMS messages ----
## Step 2: Exploring and preparing the data ----

# read the sms data into the sms data frame
sms_raw <- read.csv("data/sms_spam.csv", stringsAsFactors = FALSE, encoding = "unknown")

# examine the structure of the sms data
str(sms_raw)

# convert spam/ham to factor.
sms_raw$type <- factor(sms_raw$type)

# examine the type variable more carefully
str(sms_raw$type)
table(sms_raw$type)

# build a corpus using the text mining (tm) package
library(tm)
sms_corpus <- VCorpus(VectorSource(sms_raw$text))

# examine the sms corpus
print(sms_corpus)
inspect(sms_corpus[1:2])

as.character(sms_corpus[[1]])
lapply(sms_corpus[1:2], as.character)

# clean up the corpus using tm_map()
sms_corpus_clean <- tm_map(sms_corpus, content_transformer(tolower))

# show the difference between sms_corpus and corpus_clean
as.character(sms_corpus[[1]])
as.character(sms_corpus_clean[[1]])

sms_corpus_clean <- tm_map(sms_corpus_clean, removeNumbers) # remove numbers
sms_corpus_clean <- tm_map(sms_corpus_clean, removeWords, stopwords()) # remove stop words
sms_corpus_clean <- tm_map(sms_corpus_clean, removePunctuation) # remove punctuation

# tip: create a custom function to replace (rather than remove) punctuation
removePunctuation("hello...world")
replacePunctuation <- function(x) { gsub("[[:punct:]]+", " ", x) }
replacePunctuation("hello...world")

# illustration of word stemming
library(SnowballC)
wordStem(c("learn", "learned", "learning", "learns"))

sms_corpus_clean <- tm_map(sms_corpus_clean, stemDocument)

sms_corpus_clean <- tm_map(sms_corpus_clean, stripWhitespace) # eliminate unneeded whitespace

# examine the final clean corpus
lapply(sms_corpus[1:3], as.character)
lapply(sms_corpus_clean[1:3], as.character)

# create a document-term sparse matrix
# sms_dtm <- DocumentTermMatrix(sms_corpus_clean)

# alternative solution: create a document-term sparse matrix directly from the SMS corpus
sms_dtm2 <- DocumentTermMatrix(sms_corpus, control = list(
  tolower = TRUE,
  removeNumbers = TRUE,
  stopwords = TRUE,
  removePunctuation = TRUE,
  stemming = TRUE
))

sms_dtm2_tidy <- tidytext::tidy(sms_dtm2)
sms_dtm2_inspect <- tm::inspect(sms_dtm2[1:5,1:5])
View(sms_dtm2_inspect)

# alternative solution: using custom stop words function ensures identical result
sms_dtm3 <- DocumentTermMatrix(sms_corpus, control = list(
  tolower = TRUE,
  removeNumbers = TRUE,
  stopwords = function(x) { removeWords(x, stopwords()) },
  removePunctuation = TRUE,
  stemming = TRUE
))

# compare the result
sms_dtm
sms_dtm2
sms_dtm3

# creating training and test datasets
sms_dtm_train <- sms_dtm2[1:4169, ]
sms_dtm_test  <- sms_dtm2[4170:5559, ]

# also save the labels
sms_train_labels <- sms_raw[1:4169, ]$type
sms_test_labels  <- sms_raw[4170:5559, ]$type

# check that the proportion of spam is similar
prop.table(table(sms_train_labels))
prop.table(table(sms_test_labels))

# word cloud visualization
library(wordcloud)
wordcloud(sms_corpus_clean, min.freq = 50, random.order = FALSE)

# subset the training data into spam and ham groups
spam <- subset(sms_raw, type == "spam")
ham  <- subset(sms_raw, type == "ham")

wordcloud(spam$text, max.words = 100, scale = c(3, 0.5))
wordcloud(ham$text, max.words = 100, scale = c(3, 0.5))

sms_dtm_freq_train <- removeSparseTerms(sms_dtm_train, 0.999)
sms_dtm_freq_train

# indicator features for frequent words
findFreqTerms(sms_dtm_train, 5)

# save frequently-appearing terms to a character vector
sms_freq_words <- findFreqTerms(sms_dtm_train, 5)
str(sms_freq_words)

# create DTMs with only the frequent terms
sms_dtm_freq_train <- sms_dtm_train[ , sms_freq_words]
sms_dtm_freq_test <- sms_dtm_test[ , sms_freq_words]

# convert counts to a factor
convert_counts <- function(x) {
  x <- ifelse(x > 0, "Yes", "No")
}

# apply() convert_counts() to columns of train/test data
sms_train <- apply(sms_dtm_freq_train, MARGIN = 2, convert_counts)
sms_test  <- apply(sms_dtm_freq_test, MARGIN = 2, convert_counts)

## Step 3: Training a model on the data ----
library(e1071)
sms_classifier <- naiveBayes(sms_train, sms_train_labels)

## Step 4: Evaluating model performance ----
sms_test_pred <- predict(sms_classifier, sms_test)

library(gmodels)
CrossTable(sms_test_pred, sms_test_labels,
           prop.chisq = FALSE, prop.t = FALSE, prop.r = FALSE,
           dnn = c('predicted', 'actual'))

## Step 5: Improving model performance ----
sms_classifier2 <- naiveBayes(sms_train, sms_train_labels, laplace = 1)
sms_test_pred2 <- predict(sms_classifier2, sms_test)
CrossTable(sms_test_pred2, sms_test_labels,
           prop.chisq = FALSE, prop.t = FALSE, prop.r = FALSE,
           dnn = c('predicted', 'actual'))