Introduction
The goal of this project is just to display that you’ve gotten used to working with the data and that you are on track to create your prediction algorithm. Please submit a report on R Pubs (http://rpubs.com/) that explains your exploratory analysis and your goals for the eventual app and algorithm. This document should be concise and explain only the major features of the data you have identified and briefly summarize your plans for creating the prediction algorithm and Shiny app in a way that would be understandable to a non-data scientist manager. You should make use of tables and plots to illustrate important summaries of the data set. The motivation for this project is to:
1. Demonstrate that you’ve downloaded the data and have successfully loaded it in.
2. Create a basic report of summary statistics about the data sets
3. Report any interesting findings that you amassed so far.
4. Get feedback on your plans for creating a prediction algorithm and Shiny app.

library(plyr)
library(magrittr)
## Warning: package 'magrittr' was built under R version 3.5.3
library(stringr)
## Warning: package 'stringr' was built under R version 3.5.3
library(stringi)
library(tm)
## Warning: package 'tm' was built under R version 3.5.3
## Loading required package: NLP
library(RWeka)
## Warning: package 'RWeka' was built under R version 3.5.3
library(SnowballC)
## Warning: package 'SnowballC' was built under R version 3.5.3
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.5.3
## 
## Attaching package: 'ggplot2'
## The following object is masked from 'package:NLP':
## 
##     annotate
twitter <- readLines("en_US.twitter.txt",warn=FALSE,encoding="UTF-8")
blogs<-readLines("en_US.blogs.txt",warn=FALSE,encoding="UTF-8")
news<-readLines("en_US.news.txt",warn=FALSE,encoding="UTF-8")

length(twitter)
## [1] 2360148
length(blogs)
## [1] 899288
length(news)
## [1] 77259


General Statistics 

stri_stats_general(twitter)
##       Lines LinesNEmpty       Chars CharsNWhite 
##     2360148     2360148   162096031   134082634
stri_stats_general(blogs)
##       Lines LinesNEmpty       Chars CharsNWhite 
##      899288      899288   206824382   170389539
stri_stats_general(news)
##       Lines LinesNEmpty       Chars CharsNWhite 
##       77259       77259    15639408    13072698


Data Cleaning 

subdataBlogs <- sample(blogs, size = 1000)
subdataNews <- sample(news, size = 1000)
subdataTwitter <- sample(twitter, size = 1000)
sampledData <- c(subdataBlogs, subdataNews, subdataTwitter)
corpus <- VCorpus(VectorSource(sampledData))
toSpace <- content_transformer(function(x, pattern) gsub(pattern, " ", x))
corpus <- tm_map(corpus, toSpace, "/|@|//|$|:|:)|*|&|!|?|_|-|#|")
corpus <- tm_map(corpus, content_transformer(tolower))
corpus <- tm_map(corpus, removeNumbers)
corpus <- tm_map(corpus, removePunctuation)
corpus <- tm_map(corpus, removeWords, stopwords())
corpus <- tm_map(corpus, stemDocument)
corpus <- tm_map(corpus, stripWhitespace)
dtm1 <- TermDocumentMatrix(corpus)
bigram <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
dtm2 <- TermDocumentMatrix(corpus, control = list(tokenize = bigram))
trigram <- function(x) NGramTokenizer(x, Weka_control(min = 3, max = 3))
dtm3 <- TermDocumentMatrix(corpus, control = list(tokenize = trigram))


N-Gram Data Visualisation 

freq1 <- rowSums(as.matrix(dtm1))
freq1 <- sort(freq1, decreasing = TRUE)
dfFreq1 <- data.frame(word = names(freq1), freq=freq1)
ggplot(dfFreq1[1:20, ], aes(word, freq)) +
  geom_bar(stat="identity", fill="red", colour="red") +
  theme(axis.text.x=element_text(angle=45, hjust=1)) + ggtitle("1-Gram Frequency")

freq2 <- rowSums(as.matrix(dtm2))
freq2 <- sort(freq2, decreasing = TRUE)
dfFreq2 <- data.frame(word = names(freq2), freq=freq2)
ggplot(dfFreq2[1:20, ], aes(word, freq)) +
  geom_bar(stat="identity", fill="green", colour="green") +
  theme(axis.text.x=element_text(angle=45, hjust=1)) + ggtitle("2-Gram Frequency")

freq3 <- rowSums(as.matrix(dtm3))
freq3 <- sort(freq3, decreasing = TRUE)
dfFreq3 <- data.frame(word = names(freq3), freq=freq3)
ggplot(dfFreq3[1:20, ], aes(word, freq)) +
  geom_bar(stat="identity", fill="blue", colour="blue") +
  theme(axis.text.x=element_text(angle=45, hjust=1)) + ggtitle("3-Gram Frequency")


Shiny Web App
The goal is to build a Shiny Web App using a prediction algorithm which predicts the next word based on a single word input.