Project4

Loading Libraries

Function to download the desired files

url.spam <- "http://spamassassin.apache.org/old/publiccorpus/20050311_spam_2.tar.bz2"
file.spam <- "20050311_spam_2.tar.bz2"
file.spam2<-"20050311_spam_2.tar"

url.ham <- "http://spamassassin.apache.org/old/publiccorpus/20030228_easy_ham.tar.bz2"
file.ham <- "20030228_easy_ham.tar.bz2"
file.ham2 <- "20030228_easy_ham.tar"

Downloading Datasets

  download.file(url.spam, destfile= file.spam)
  download.file(url.ham, destfile=file.ham)
  bunzip2(file.spam)
  bunzip2(file.ham)
  untar(file.ham2, exdir="C:\\Rdata\\")
  untar(file.spam2, exdir = "C:\\Rdata\\")

Getting file names

Adding files to list

spam.dir="C:\\Rdata\\spam_2\\"
ham.dir="C:\\Rdata\\easy_ham\\"
spam.docs=list.files(spam.dir)
ham.docs=list.files(ham.dir)

Removing not needed files and writing functions for Corpus Creation, cleaning, and tagging

spam.docs = spam.docs[which(spam.docs!="cmds")]
ham.docs=ham.docs[which(ham.docs!="cmds")]


toVCorpus <- function(file_path) {
  corpus <- file_path %>%                            
    paste(., list.files(.), sep = "/") %>%          # Create a vector of file paths 
    lapply(readLines) %>%                           # Read the text in each file
    VectorSource() %>%                              # Turn into VectorSource
    VCorpus()                                       # Turn into VCorpus
  return(corpus)
}

docClean <- function(corpus) {
    corpus <- corpus %>%
    tm_map(removeNumbers) %>%                       # Remove numbers
    tm_map(removePunctuation) %>%                   # Remove punctuation symbols 
    tm_map(tolower) %>%                             # Transform  to lowercase
    tm_map(PlainTextDocument) %>%                   # Transform back to PlainTextDocument
    tm_map(removeWords, stopwords("en")) %>%        # Remove stopwords
    tm_map(stripWhitespace) %>%                     # Remove white spaces
    tm_map(stemDocument)                            #Reduce to stems
  return(corpus)
}

addTag <- function(corpus, tag, value){
  for (i in 1:length(corpus)){
    meta(corpus[[i]], tag) <- value                    # Add the value to the specified tag
  }
  return(corpus)
}

Create spam and ham corpus

# Create ham corpus
ham_corpus <- ham.dir%>%
   toVCorpus %>% 
   docClean  %>% 
   addTag(tag = "ham_spam", value = "ham")



# Create spam corpus
spam_corpus <- spam.dir %>%
  toVCorpus %>%
  docClean %>%
  addTag(tag = "ham_spam", value = "spam")

Joining the two “Tidy” corpuses together and mixing them

spamassassin_corpus <- c(ham_corpus, spam_corpus)
# Scramble the order
spamassassin_corpus <- spamassassin_corpus[sample(c(1:length(spamassassin_corpus)))]

Check the Corpus

# Check ham/spam proportion
spamassassin_corpus_prop <- spamassassin_corpus %>%
  meta(tag = "ham_spam") %>%
  unlist() %>%
  table() 
spamassassin_corpus_prop

## .
##  ham spam 
## 2501 1397

###Corpus and physical files match

Wordcloud as an output

library(wordcloud)

## Loading required package: RColorBrewer

wordcloud(spamassassin_corpus,max.words = 70, random.order = FALSE, min.freq=1000)#header  wordcloud

## Training create the document term matrix and remove sparse terms. Terms appearing in less than 10 documents will be left out.

spamassassin_dtm <- spamassassin_corpus %>% 
                    DocumentTermMatrix() %>% 
                    removeSparseTerms(1-(10/length(spamassassin_corpus)))

spamassassin_labels <- unlist(meta(spamassassin_corpus, "ham_spam"))

To use the train_model function, I had to create a container, did a 80/20 split in the dataset. About 80% of the data were used for training, and the remaining 20% were used for testing.

N <- length(spamassassin_labels)
split <- round(0.8*N) 
container <- create_container(
  spamassassin_dtm, 
  labels = spamassassin_labels, 
  trainSize = 1:split,
  testSize = (split+1):N,
  virgin = F
)

Begin Training

Using three different algorithms -Suvervisor Vector Machines -Decision Tree

svm_model_spamassassin <- train_model(container, "SVM")
tree_model_spamassassin <- train_model(container, "TREE")

Testing and results

# Classifying using the trained models
svm_out_spamassassin <- classify_model(container, svm_model_spamassassin)
tree_out_spamassassin <- classify_model(container, tree_model_spamassassin)



# Collect the classification results into a table
labels_out_spamassassin <- data.frame(
  correct_label = spamassassin_labels[(split+1):N],
  svm = as.character(svm_out_spamassassin[,1]),
  tree = as.character(tree_out_spamassassin[,1]))


# Print results
for (i in 2:3){
  print(names(labels_out_spamassassin)[i])
  table(labels_out_spamassassin[,1] == labels_out_spamassassin[,i]) %>% 
    print() %>% 
    prop.table() %>% 
    round(2) %>% 
    print()
}

## [1] "svm"
## 
## FALSE  TRUE 
##     3   777 
## 
## FALSE  TRUE 
##     0     1 
## [1] "tree"
## 
## FALSE  TRUE 
##     9   771 
## 
## FALSE  TRUE 
##  0.01  0.99

library(knitr)
final<-summary(labels_out_spamassassin)
kable(final)

	correct_label	svm	tree
	Length:780	Length:780	Length:780
	Class :character	Class :character	Class :character
	Mode :character	Mode :character	Mode :character

Conclusion

The tree classfication algorithm performed less accurate that the other one. The svm classifier were 99% accurate.