Project4

Load libraries

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.3     v purrr   0.3.4
## v tibble  3.0.6     v dplyr   1.0.4
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(tm)

## Warning: package 'tm' was built under R version 4.0.5

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

require(RTextTools)

## Loading required package: RTextTools

## Warning: package 'RTextTools' was built under R version 4.0.5

## Loading required package: SparseM

## Warning: package 'SparseM' was built under R version 4.0.4

## 
## Attaching package: 'SparseM'

## The following object is masked from 'package:base':
## 
##     backsolve

## Registered S3 method overwritten by 'tree':
##   method     from
##   print.tree cli

Load all files from folders into R

Each classification has TWO (2) sub-folders, e.g. “easy_ham” and “easy_ham_2”. This makes it easier as the first set is used for training data, and the second set (with “_2”) is used for testing data.

spam_files = list.files(path = "C:/CUNY/DATA607/Project4/spam", full.names = TRUE)
spam2_files = list.files(path = "C:/CUNY/DATA607/Project4/spam_2", full.names = TRUE)
easy_ham_files = list.files(path = "C:/CUNY/DATA607/Project4/easy_ham", full.names = TRUE)
easy_ham2_files = list.files(path = "C:/CUNY/DATA607/Project4/easy_ham_2", full.names = TRUE)
spam_text = ''
spam2_text = ''
easy_ham_text = ''
easy_ham2_text = ''
for(f in spam_files) {
  spam_text = paste(spam_text, (readChar(f, file.info(f)$size)))
}
for(f in spam2_files) {
  spam2_text = paste(spam2_text, (readChar(f, file.info(f)$size)))
}
for(f in easy_ham_files) {
  easy_ham_text = paste(easy_ham_text, (readChar(f, file.info(f)$size)))
}
for(f in easy_ham2_files) {
  easy_ham2_text = paste(easy_ham2_text, (readChar(f, file.info(f)$size)))
}

Split the data into train/test sets

easy_ham.dfr    <- as.data.frame(easy_ham_text)
easy_ham_2.dfr  <- as.data.frame(easy_ham2_text)
spam.dfr        <- as.data.frame(spam_text)
spam_2.dfr      <- as.data.frame(spam2_text)

rownames(easy_ham.dfr)    <- NULL
rownames(easy_ham_2.dfr)  <- NULL
rownames(spam.dfr)        <- NULL
rownames(spam_2.dfr)      <- NULL

easy_ham.dfr$outcome    <- 2
easy_ham_2.dfr$outcome  <- 2
spam.dfr$outcome        <- 4
spam_2.dfr$outcome      <- 4

names(easy_ham.dfr)   <- c("text", "outcome")
names(easy_ham_2.dfr) <- c("text", "outcome")
names(spam.dfr)       <- c("text", "outcome")
names(spam_2.dfr)     <- c("text", "outcome")

train.data  <- rbind(easy_ham.dfr, spam.dfr)
train.num   <- nrow(train.data)
train.data  <- rbind(train.data, easy_ham_2.dfr, spam_2.dfr)
names(train.data) <- c("text", "outcome")

Build the model

set.seed(2012)
train_out.data <- train.data$outcome
train_txt.data <- train.data$text
matrix <- create_matrix(train_txt.data, language="english", minWordLength=3, removeNumbers=TRUE, stemWords=FALSE, removePunctuation=TRUE, weighting=weightTfIdf)

## Warning in TermDocumentMatrix.SimpleCorpus(x, control): custom functions are
## ignored

## Warning in TermDocumentMatrix.SimpleCorpus(x, control): custom tokenizer is
## ignored

container <- create_container(matrix,t(train_out.data), trainSize=1:train.num, testSize=(train.num+1):nrow(train.data), virgin=FALSE)
#maxent.model    <- train_model(container, "SLDA") Error: cannot allocate vector of size 76.4 Gb
svm.model       <- train_model(container, "SVM")

Comparing the model to the Benchmark

svm.result    <- classify_model(container, svm.model)
svm.analytic  <- create_analytics(container, svm.result)
svm.doc       <- svm.analytic@document_summary
svm_spam.doc  <- svm.doc[svm.doc$MANUAL_CODE==4, ]
svm_ham.doc   <- svm.doc[svm.doc$MANUAL_CODE==2, ]
svm.true.pos  <- nrow(svm_spam.doc[svm_spam.doc$CONSENSUS_CODE==4,]) / nrow(svm_spam.doc)
svm.false.neg <- nrow(svm_spam.doc[svm_spam.doc$CONSENSUS_CODE==2,]) / nrow(svm_spam.doc)
svm.true.neg  <- nrow(svm_ham.doc[svm_ham.doc$CONSENSUS_CODE==2,]) / nrow(svm_ham.doc)
svm.false.pos <- nrow(svm_ham.doc[svm_ham.doc$CONSENSUS_CODE==4,]) / nrow(svm_ham.doc)
print(svm.true.pos)

## [1] 0

print(svm.false.neg)

## [1] 1

print(svm.true.neg)

## [1] 0

print(svm.false.pos)

## [1] 1