week 5

library(readr)
gear <- read.csv("C:\\Users\\Bacchus\\Desktop\\2018 spring\\special topic for CS\\week 4\\Samsung Tweets.csv", row.names=1, sep=";")
geartweets <- gear$tweettext
clean.text = function(x)
{

  x = tolower(x)
  x = gsub("rt", "", x)
  x = gsub("@\\w+", "", x)
  x = gsub("[[:punct:]]", "", x)
  x = gsub("[[:digit:]]", "", x)
  x = gsub("http\\w+", "", x)
  x = gsub("[ |\t]{2,}", "", x)
  x = gsub("^ ", "", x)
  x = gsub(" $", "", x)
  return(x)
}
geartweets = clean.text(geartweets)

sports.words = scan('C:\\Users\\Bacchus\\Desktop\\2018 spring\\special topic for CS\\week 5\\Sports_Word.txt', what='character', comment.char=';')

score.topic = function(sentences, dict, .progress='none')
{
  require(plyr)
  require(stringr)
  require(stringi)
  
  scores = laply(sentences, function(sentence, dict) {
    
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)

    sentence = tolower(sentence)
    

    word.list = str_split(sentence, '\\s+')

    words = unlist(word.list)
    

    topic.matches = match(words, dict)
    

    topic.matches = !is.na(topic.matches)
    

    score = sum(topic.matches)
    
    return(score)
  }, dict, .progress=.progress )
  
  topicscores.df = data.frame(score=scores, text=sentences)
  return(topicscores.df)
}

topic.scores= score.topic(geartweets, sports.words, .progress='none')

## Loading required package: plyr

## Loading required package: stringr

## Loading required package: stringi

sportsTweets = subset(topic.scores, score !=0)$text
pos.words = scan('C:\\Users\\Bacchus\\Desktop\\2018 spring\\special topic for CS\\week 5\\positive-words.txt', what='character', comment.char=';')
neg.words = scan('C:\\Users\\Bacchus\\Desktop\\2018 spring\\special topic for CS\\week 5\\negative-words.txt', what='character', comment.char=';')

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


require(plyr)
require(stringr)
require(stringi)

score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
  

  scores = laply(sentences, function(sentence, pos.words, neg.words) {
    sentence = gsub('[[:punct:]]', '', sentence)
    sentence = gsub('[[:cntrl:]]', '', sentence)
    sentence = gsub('\\d+', '', sentence)
    sentence = tolower(sentence)
    

    word.list = str_split(sentence, '\\s+')

    words = unlist(word.list)
    

    pos.matches = match(words, pos.words)
    neg.matches = match(words, neg.words)
    

    pos.matches = !is.na(pos.matches)
    neg.matches = !is.na(neg.matches)
    

    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(sportsTweets, pos.words, neg.words, .progress='none')

score <- sentiment.scores$score

library(plotly)

## Loading required package: ggplot2

## 
## 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

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

topic.pos = subset(sentiment.scores, score > 0)
topic.neg = subset(sentiment.scores, score < 0)
topic.neu = subset(sentiment.scores, score == 0)
negN = nrow(topic.neg)
posN = nrow(topic.pos)
neuN = nrow(topic.neu)
dftemp=data.frame(topic=c("Postive tweets", "Negative tweets" , "Neutral tweets"), 
                  number=c(posN, negN, neuN))
library(plotly)
p <- plot_ly(data=dftemp, labels = ~topic, values = ~number, type = 'pie') %>%
  layout(title = 'Pie Chart of  the percentage of Positive, Negative and Neutral tweets',
         xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
p