Last active
December 21, 2015 20:39
-
-
Save sureshgorakala/6363104 to your computer and use it in GitHub Desktop.
Shiny App Demo
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tm) | |
library(twitteR) | |
library(stringr) | |
library(plyr) | |
#get the tweets | |
#tweets = local(get(load('D:/SureshPersonal/Coursera/SentiAnalysis/Twitter/CE.RData'))) | |
tweets = local(get(load('C:/shiny/sat.RData'))) | |
tweets_txt = sapply(tweets,function(x) x$getText()) | |
#function to clean data | |
cleanTweets = function(tweets) | |
{ | |
tweets_cl = gsub("(RT|via)((?:\\b\\W*@\\w+)+)","",tweets) | |
tweets_cl = gsub("http[^[:blank:]]+", "", tweets_cl) | |
tweets_cl = gsub("@\\w+", "", tweets_cl) | |
tweets_cl = gsub("[ \t]{2,}", "", tweets_cl) | |
tweets_cl = gsub("^\\s+|\\s+$", "", tweets_cl) | |
tweets_cl = gsub("[[:punct:]]", " ", tweets_cl) | |
tweets_cl = gsub("[^[:alnum:]]", " ", tweets_cl) | |
tweets_cl <- gsub('\\d+', '', tweets_cl) | |
return(tweets_cl) | |
} | |
#function to calculate number of words in each category within a sentence | |
sentimentScore <- function(sentences, vNegTerms, negTerms, posTerms, vPosTerms){ | |
final_scores <- matrix('', 0, 5) | |
scores <- laply(sentences, function(sentence, vNegTerms, negTerms, posTerms, vPosTerms){ | |
initial_sentence <- sentence | |
#remove unnecessary characters and split up by word | |
sentence = cleanTweets(sentence) | |
sentence <- tolower(sentence) | |
wordList <- str_split(sentence, '\\s+') | |
words <- unlist(wordList) | |
#build vector with matches between sentence and each category | |
vPosMatches <- match(words, vPosTerms) | |
posMatches <- match(words, posTerms) | |
vNegMatches <- match(words, vNegTerms) | |
negMatches <- match(words, negTerms) | |
#sum up number of words in each category | |
vPosMatches <- sum(!is.na(vPosMatches)) | |
posMatches <- sum(!is.na(posMatches)) | |
vNegMatches <- sum(!is.na(vNegMatches)) | |
negMatches <- sum(!is.na(negMatches)) | |
score <- c(vNegMatches, negMatches, posMatches, vPosMatches) | |
#add row to scores table | |
newrow <- c(initial_sentence, score) | |
final_scores <- rbind(final_scores, newrow) | |
return(final_scores) | |
}, vNegTerms, negTerms, posTerms, vPosTerms) | |
return(scores) | |
} | |
#load pos,neg statements | |
afinn_list <- read.delim(file='C:/shiny/AFINN/AFINN-111.txt', header=FALSE, stringsAsFactors=FALSE) | |
names(afinn_list) <- c('word', 'score') | |
afinn_list$word <- tolower(afinn_list$word) | |
#categorize words as very negative to very positive and add some movie-specific words | |
vNegTerms <- afinn_list$word[afinn_list$score==-5 | afinn_list$score==-4] | |
negTerms <- c(afinn_list$word[afinn_list$score==-3 | afinn_list$score==-2 | afinn_list$score==-1], "second-rate", "moronic", "third-rate", "flawed", "juvenile", "boring", "distasteful", "ordinary", "disgusting", "senseless", "static", "brutal", "confused", "disappointing", "bloody", "silly", "tired", "predictable", "stupid", "uninteresting", "trite", "uneven", "outdated", "dreadful", "bland") | |
posTerms <- c(afinn_list$word[afinn_list$score==3 | afinn_list$score==2 | afinn_list$score==1], "first-rate", "insightful", "clever", "charming", "comical", "charismatic", "enjoyable", "absorbing", "sensitive", "intriguing", "powerful", "pleasant", "surprising", "thought-provoking", "imaginative", "unpretentious") | |
vPosTerms <- c(afinn_list$word[afinn_list$score==5 | afinn_list$score==4], "uproarious", "riveting", "fascinating", "dazzling", "legendary") | |
#Calculate score on each tweet | |
tweetResult <- as.data.frame(sentimentScore(tweets_txt, vNegTerms, negTerms, posTerms, vPosTerms)) | |
tweetResult$'2' = as.numeric(tweetResult$'2') | |
tweetResult$'3' = as.numeric(tweetResult$'3') | |
tweetResult$'4' = as.numeric(tweetResult$'4') | |
tweetResult$'5' = as.numeric(tweetResult$'5') | |
Score_Neg = sum(tweetResult$'3',tweetResult$'2') | |
Score_Pos = sum(tweetResult$'4',tweetResult$'5') | |
global_score = round( 100 * Score_Pos / (Score_Pos + Score_Neg) ) | |
counts = c(sum(tweetResult$'2'),sum(tweetResult$'3'),sum(tweetResult$'4'),sum(tweetResult$'5')) | |
names = c("Worst","BAD","GOOD","VERY GOOD") | |
mr = list(counts,names) | |
colors = c("red", "yellow", "green", "violet") | |
# Define server logic required to plot various variables against mpg | |
shinyServer(function(input, output) { | |
output$barplot <- renderPlot({ | |
barplot(mr[[1]], main="Movie Review", xlab="Number of votes",legend=mr[[2]],col=colors) | |
}) | |
}) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(shiny) | |
# Define UI for miles per gallon application | |
shinyUI(pageWithSidebar( | |
# Application title | |
headerPanel("Chennai Express"), | |
sidebarPanel(), | |
mainPanel( | |
plotOutput("barplot") | |
) | |
)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment