##Install Packages
# install.packages("tm")  # for text mining
# install.packages("wordcloud") # word-cloud generator 
# install.packages("RColorBrewer") # color palettes
##Load Require Library
library(tm)

## Warning: package 'tm' was built under R version 3.4.4

## Loading required package: NLP

library(RColorBrewer)
library(wordcloud)

## Warning: package 'wordcloud' was built under R version 3.4.4

##Read the Data
tweetsDS <- readRDS("C:\\Users\\206429159\\Documents\\Rstudio\\Midterm\\zynga.rds")  
##this should be - M:/S18/CS695/Midterm/Zynga.RDS the forward slashes not backward  
tweets <- tweetsDS$text ###the text here is first column on which we should ideally work.. double click on your zynga dataset you will see the coulmn

# Function to clean tweets
clean.text = function(x)
{
  # remove unicode 
  x = gsub("[^\x20-\x7E]", "",x)
  # remove rt
  x = gsub("rt", "", x)
  # remove at
  x = gsub("@\\w+", "", x)
  # remove punctuation
  x = gsub("[[:punct:]]", "", x)
  # remove numbers
  x = gsub("[[:digit:]]", "", x)
  # remove links http
  x = gsub("http\\w+", "", x)
  # remove tabs
  x = gsub("[ |\t]{2,}", "", x)
  # remove blank spaces at the beginning
  x = gsub("^ ", "", x)
  # remove blank spaces at the end
  x = gsub(" $", "", x)
  # tolower
  x = tolower(x)
  return(x)
}
# clean tweets
tweets = clean.text(tweets)

##Create word cloud of tweets of Zynga

corpus = Corpus(VectorSource(tweets))
# corpus = Corpus(VectorSource(cmail))
# create term-document matrix
tdm = TermDocumentMatrix(
  corpus,
  control = list(
    wordLengths=c(3,20),
    removePunctuation = TRUE,
    stopwords = c("the", "a", stopwords("english")),
    removeNumbers = TRUE) )

# convert as matrix
tdm = as.matrix(tdm)

# get word counts in decreasing order
word_freqs = sort(rowSums(tdm), decreasing=TRUE) 

# create a data frame with words and their frequencies
dm = data.frame(word=names(word_freqs), freq=word_freqs)

#remove the top words which donâ????t generate insights such as "the", "a", "and", etc.
word_freqs = word_freqs[-(1:9)]  #Here â????1â?? is 1st word in the list we want to remove

#Plot corpus in a clored graph; need RColorBrewer package

wordcloud(head(dm$word, 200), head(dm$freq, 200), random.order=FALSE, colors=brewer.pal(8, "Dark2"))

#check top 50 most mentioned words
head(word_freqs, 20)

##     looking         can         now      prized       adult       petra 
##         259         233         222         219         187         187 
##        play        game       trees      jeneva       found     rewards 
##         182         181         180         174         167         164 
##      points         bit       video sponsorship     needing       shook 
##         144         140         139         139         138         138 
##       gotas  rtherescar 
##         137         137