The following is the complete R code used for this project:
# Generate data data <- rnorm(1000, mean=25, sd=5) data.1 <- rnorm(1000, mean=10, sd=2) data <- c(data, data.1) # Plot histogram hist(data) # View the bins hist(data, plot = FALSE) # Histogram with modified bins hist(data, breaks = seq(0,50,2)) # Kernel Density estimation kde = density(data) plot(kde) library(pdfCluster) kde.1 <- kepdf(data) plot(kde.1) kde.1@kernel kde.1@par # Twitter Text library(twitteR, quietly = TRUE) consumer.key <- "" consumer.secret <- "" access.token <- "" token.secret <- "" setup_twitter_oauth(consumer.key, consumer.secret, access.token, token.secret) blade_runner <- searchTwitter("#bladeRunner", n=100,lang = "en") tweet.df <- twListToDF(blade_runner) head(tweet.df) head(tweet.df[tweet.df$isRetweet == FALSE, ]$text) # Data gold set prepration library(sentimentr, quietly = TRUE) sentiment.score <- sentiment(tweet.df$text) head(sentiment...