global.R

library(tm)
library(wordcloud)
library(memoise)
library(googleVis)
library(ggplot2)


#Create a list of players

players<-list("Virat Kohli"="kohli",
              "MS Dhoni"= "dhoni",
              "Jasprit Bumrah" ="bumrah",
              "Joe Root"="root",
              "Jos Buttler"="butler",
              "Ben Stokes"="Ben Stokes",
              "Chris Gayle"="gayle",
              "Dwayne Bravo"="bravo",
              "Carlos Brathwaite"="brathwaite",
              "David Warner"="warner",
              "Shane Watson"="watson",
              "Glenn Maxwell"="maxwell",
              "Mushfiqur Rahim"="mushfiqur",
              "Tamim Iqbal"="tamim",
              "Mustafizur Rahman"="mustafizur",
              "Shahid Afridi"="afridi",
              "Mohammad Amir"="amir",
              "Quinton de Kock"="dekock",
              "AB de Villiers"="devillers",
              "Hashim Amla"="amla",
              "Martin Guptill"="guptill",
              "Mitchell Santner"="santner",
              "Ross Taylor"="taylor",
              "Angelo Mathews"="mathews",
              "Tillakaratne Dilshan"="dilshan",
              "Lasith Malinga"="malinga",
              "Mohammad Shahzad"="shahzad"

              )

catch.error = function(x)
{
  # Create a missing value for test purpose
  y = NA

  # Try to catch that error (NA) we just created

  catch_error = tryCatch(tolower(x), error=function(e) e)

  # if not an error, convert y to lowercase
  if (!inherits(catch_error, "error"))

    y = tolower(x)

  # check result if error exists, otherwise the function works fine.
  return(y)
}

cleanTweets<- function(tweet){

  # Clean the tweet for sentiment analysis
  # remove html links, which are not required for sentiment analysis

  tweet = gsub("(f|ht)(tp)(s?)(://)(.*)[.|/](.*)", " ", tweet)

  # First we will remove retweet entities from

  tweet = gsub("(RT|via)((?:\\b\\W*@\\w+)+)", " ", tweet)

  # Then remove all "#Hashtag"

  tweet = gsub("#\\w+", " ", tweet)

  # Then remove all "@people"

  tweet = gsub("@\\w+", " ", tweet)

  # Then remove all the punctuation

  tweet = gsub("[[:punct:]]", " ", tweet)

  # Then remove numbers, we need only text for analytics

  tweet = gsub("[[:digit:]]", " ", tweet)

  # finally, we remove unnecessary spaces (white spaces, tabs etc)

  tweet = gsub("[ \t]{2,}", " ", tweet)
  tweet = gsub("^\\s+|\\s+$", "", tweet)

  tweet = catch.error(tweet)

  tweet
}

cleanTweetsAndRemoveNAs<- function(Tweets) {

  TweetsCleaned = sapply(Tweets, cleanTweets)

  # Remove the "NA" tweets from this tweet list

  TweetsCleaned = TweetsCleaned[!is.na(TweetsCleaned)]

  names(TweetsCleaned) = NULL

  # Remove the repetitive tweets from this tweet list

  TweetsCleaned = unique(TweetsCleaned)

  TweetsCleaned
}

#Get the tweets cleaned

getCleanTweets <- memoise(function(player) {


  if (!(player %in% players))
    stop("Unknown player")

  tweets <-readLines(sprintf("./Data/%s.txt",player)) 

  tweetsCleaned<-cleanTweetsAndRemoveNAs(tweets)

  tweetsCleaned

})

#Generate a term matrix for word cloud

getTermMatrix <- memoise(function(player) {


  if (!(player %in% players))
    stop("Unknown Player")

  text <- readLines(sprintf("./Data/%s.txt", player),
                    encoding="latin1",warn=FALSE)
  #Create a corpus   
  myCorpus = Corpus(VectorSource(text))
  #Convert text to lowercase
  myCorpus = tm_map(myCorpus, content_transformer(tolower))
  #Remove Punctuations
  myCorpus = tm_map(myCorpus, removePunctuation)

  # remove URLs
  removeURL <- function(x) gsub("http[^[:space:]]*", "", x)
  myCorpus <- tm_map(myCorpus, content_transformer(removeURL))

  # remove anything other than English letters or space
  removeNumPunct <- function(x) gsub("[^[:alpha:][:space:]]*", "", x)
  myCorpus <- tm_map(myCorpus, content_transformer(removeNumPunct))

  #remove numbers
  myCorpus = tm_map(myCorpus, removeNumbers)
  #remove stopwords in english
  myCorpus = tm_map(myCorpus, removeWords,stopwords("en"))

  myCorpus = tm_map(myCorpus, removeWords,
                    c(stopwords("SMART"), "thy", "thou", "thee", "the", "and", "but"))
  # remove extra whitespace
  myCorpus <- tm_map(myCorpus, stripWhitespace)


  myDTM = TermDocumentMatrix(myCorpus,
                             control = list(minWordLength = 1))



  m<-as.matrix(myDTM)

  sort(rowSums(m), decreasing = TRUE)
})

#Get the data for emotions

getEmotions <- memoise(function(player) {


  if (!(player %in% players))
    stop("Unknown player")

  data <-read.csv(sprintf("./Emotions/%s.csv",player)) 

  data
})

ui.R

library(shinydashboard)
library(shiny)

dashboardPage(

  dashboardHeader(title = "T20 Cricket Players "),
  dashboardSidebar(
    h3("Choose the Player"),
    selectInput("selection", "",
                choices = players),
    actionButton("update", "Change"),
    hr(),

    sidebarMenu(
      menuItem("Wordcloud",tabName = "wordcloud",icon = icon("cloud")),
      menuItem("Top Words",tabName = "barchart",icon = icon("bar-chart")),
      menuItem("Emotions",tabName = "emotions",icon = icon("smile-o"))


    )
  ),

  dashboardBody(

    tabItems(

      tabItem(tabName ="wordcloud",



              fluidRow(

                tabBox(title = "",width = 12,

                       tabPanel(title = tagList(shiny::icon("comments"),"Tweets"),


                                box(plotOutput("wordcloud1",height=500,width = 300)),

                                box(title = "Controls",
                                    sliderInput("freq","Minimum Frequency:",
                                                min = 1,  max = 50, value = 15),
                                    sliderInput("max","Maximum Number of Words:",
                                                min = 1,  max = 300,  value = 100)
                                )
                       )






                )



              )
      ),

      tabItem(tabName = "barchart",

              fluidRow(

                tabBox(title = "",width = 12,

                       tabPanel(title = tagList(shiny::icon("heart"),"Reviews"),

                                plotOutput("bar1")
                       )



                )


              )


      ),

      tabItem(tabName = "emotions",

              fluidRow(

                tabBox(title = "",width = 12,

                       tabPanel(title = tagList(shiny::icon("smile-o"),"Polarity"),

                                htmlOutput("pie2")
                       ),

                       tabPanel(title = tagList(shiny::icon("pie-chart"),"Emotions"),

                                htmlOutput("pie1")
                       ),


                       tabPanel(title = tagList(shiny::icon("thumbs-o-up"),"Emotion Score"),

                                plotOutput("score1")

                       )


                )


              )


      )








    )


  )
)

server.r

function(input, output, session) {
  # Define a reactive expression for the document term matrix
  terms <- reactive({
    # Change when the "update" button is pressed...
    input$update
    # ...but not for anything else
    isolate({
      withProgress({
        setProgress(message = "Processing corpus...")
        getTermMatrix(input$selection)
      })
    })
  })

  data_emotion<-reactive({

    getEmotions(input$selection)

  })



  # Make the wordcloud drawing predictable during a session
  wordcloud_rep <- repeatable(wordcloud)

  #Create the wordcloud
  output$wordcloud1 <- renderPlot({
    v <- terms()
    wordcloud_rep(names(v), v, scale=c(5,0.5),
                  min.freq = input$freq, max.words=input$max,
                  colors=brewer.pal(8, "Dark2"))
  })

  #Create a barchart for high frequency terms

  output$bar1<-renderPlot({

    plot1<-head(data.frame(Freq=terms()),n=20)
    plot1$word<-row.names(plot1)
    ggplot(plot1,aes(x=reorder(word,Freq),y=Freq))+geom_bar(stat="identity",fill="steelblue")+theme_minimal()+coord_flip()+geom_text(aes(label=Freq),vjust=0.5,color="black",size=4.0)+ylab("Frequency of words")+xlab("Top Words")+ggtitle("Top frequency words")
  }) 

  #Create a pie chart for the emotions
  output$pie1<-renderGvis({

    data<-data_emotion()
    emotion1<-as.data.frame(table(data$emotion))
    Pie1<-gvisPieChart(emotion1,options = list(width=1200,height=600))
    return(Pie1)

  })

  #Create a pie chart for the polarity

  output$pie2<-renderGvis({

    data<-data_emotion()
    emotion2<-as.data.frame(table(data$polarity))
    Pie2<-gvisPieChart(emotion2,options = list(width=1200,height=600))
    return(Pie2)

  })

  #create a histogram for the emotion score
  output$score1<-renderPlot({

    data<-data_emotion()
    ggplot(data,aes(x=score))+geom_histogram(bins=50,color="black",fill="blue")+theme_minimal()+xlab("Sentiment Score")+ylab("count")+ggtitle("Sentiment Scores of reviews")
  })
}