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

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

## Loading required package: NLP

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

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

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

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 3.4.4

## 
## Attaching package: 'ggplot2'

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

## 
## Attaching package: 'plotly'

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

## The following objects are masked from 'package:plyr':
## 
##     arrange, mutate, rename, summarise

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

corpus = Corpus(VectorSource(zyngatweets))
# 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, tolower = FALSE) )

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

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

#remove the top words which don’t generate insights such as "the", "a", "and", etc.
word_freqs = word_freqs[-(1:9)]  #Here “1” is 1st word in the list we want to remove 

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

#Plot corpus in a clored graph; need RColorBrewer package

wordcloud(head(dm$word, 50), head(dm$freq, 50), random.order=FALSE, colors=brewer.pal(8, "Dark2"))

head(word_freqs, 60)

##        looking         Prized            now            can          Petra 
##            258            219            208            192            187 
##          adult         Jeneva          found          trees        rewards 
##            186            174            166            160            152 
##            How            bit          video    sponsorship        needing 
##            143            140            139            139            138 
##          shook     RTHerescar          gotas         Points          Betty 
##            138            137            137            129            125 
##            The FarmVilleOnWeb          Fruit        Kathryn           Play 
##            114            114            113            112            111 
##         Career         Spring            get           Game            You 
##            105            104            102             98             95 
##            use            Hat          Black         Corner           King 
##             92             92             92             88             88 
##         County          Check            win           game        Nesting 
##             88             86             85             83             83 
##          Horse      FarmVille          Dolls         Mobile         Ribbon 
##             82             82             82             82             81 
##            yet        Roselyn        helping       crafting            Red 
##             80             80             79             79             79 
##          today          Needs        awarded         Online         Market 
##             78             78             78             78             78 
##        Players     Technology          World         Demand           High 
##             78             78             78             77             77

pos.words = scan('positive-words.txt', what='character', comment.char=';')
neg.words = scan('negative-words.txt', what='character', comment.char=';')

neg.words = c(neg.words, 'wtf', 'fail')

#Implementing our sentiment scoring algorithm
require(plyr)
require(stringr)

## Loading required package: stringr

require(stringi)

## Loading required package: stringi

score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
  scores = laply(sentences, function(sentence, pos.words, neg.words) {
    
    # clean up sentences with R's regex-driven global substitute, gsub():
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    # and convert to lower case:
    #sentence = tolower(sentence)
    
    # split into words. str_split is in the stringr package
    word.list = str_split(sentence, '\\s+')
    # sometimes a list() is one level of hierarchy too much
    words = unlist(word.list)
    
    # compare our words to the dictionaries of positive & negative terms
    pos.matches = match(words, pos.words)
    neg.matches = match(words, neg.words)
    
    # match() returns the position of the matched term or NA
    # we just want a TRUE/FALSE:
    pos.matches = !is.na(pos.matches)
    neg.matches = !is.na(neg.matches)
    
    # and conveniently enough, TRUE/FALSE will be treated as 1/0 by sum():
    score = sum(pos.matches) - sum(neg.matches)
    
    return(score)
  }, pos.words, neg.words, .progress=.progress )
  
  scores.df = data.frame(score=scores, text=sentences)
  return(scores.df)
}

sentiment.scores= score.sentiment(zyngatweets, pos.words, neg.words, .progress='none')

score <- sentiment.scores$score

library(plotly)
p <- plot_ly(x = ~score, type = "histogram")
p

zynga$days <- weekdays(as.POSIXlt(zynga$created))
zynga$Msg_Location <- clean.text(zynga$location)
subdf <- subset(zynga, Msg_Location =='Calne' | Msg_Location =='Singapore' | Msg_Location =='Gotham' | Msg_Location =='Sweden' | Msg_Location =='Ireland')
dfrm <-data.frame(table(subdf[,c("Msg_Location","days")]))
genderDays = reshape(dfrm,direction="wide",timevar="days",idvar="Msg_Location")


p <- plot_ly(genderDays, x = ~Msg_Location, y = ~Freq.Monday, type = 'bar', name = 'Monday') %>%
  add_trace(y = ~Freq.Tuesday, name = 'Tuesday') %>%
   add_trace(y = ~Freq.Wednesday, name = 'Wednesday') %>%
   add_trace(y = ~Freq.Thursday, name = 'Thursday') %>%
   add_trace(y = ~Freq.Friday, name = 'Friday') %>%
   add_trace(y = ~Freq.Saturday, name = 'Saturday') %>%
   add_trace(y = ~Freq.Sunday, name = 'Sunday') %>%
  layout(yaxis = list(title = 'Count'), barmode = 'group')

p