Week 3 R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.

Install necessary packages

# install.packages('tm')
# install.packages('RColorBrewer')
# install.packages('wordcloud')
library('tm')

## Loading required package: NLP

library('RColorBrewer')
library('wordcloud')

Process data

# Import data from a csv file to data frame 
Trump <- read.csv("Trump.csv", comment.char="#")
maleTw <- subset(Trump, USER_GENDER == "male")
femaleTw <- subset(Trump, USER_GENDER == "female")

# Save and read data to/from a R data object
saveRDS(maleTw, "maleTw.RDS")
maleTw <- readRDS("maleTw.RDS")

Mtweets <- maleTw$MESSAGE_BODY
Ftweets <- femaleTw$MESSAGE_BODY

# Function to clean tweets
clean.text = function(x)
{
  # tolower
  x = tolower(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)
  return(x)
}

# clean tweets
Mtweets = clean.text(Mtweets)
Ftweets = clean.text(Ftweets)


city<- subset(Trump,USER_CITY=="WASHINGTON")
cityn<- subset(Trump,USER_CITY=="NEW YORK CITY")

cityn <- cityn$MESSAGE_BODY
city <- city$MESSAGE_BODY

cityn<- clean.text(cityn)
city<- clean.text(city)

Create word cloud of tweets of WASHINGTON

##          amp        point   republican       answer          can 
##            3            3            3            2            2 
##          new       theyre     michigan          win         beat 
##            2            2            2            2            2 
##     amiright        tough    nhprimary       trumps         good 
##            2            2            2            2            2 
##  donaldtrump planelection          tax     campaign    thousands 
##            2            2            2            2            2

Create word cloud of tweets of New York City

##    donaldtrump    forelection        retweet         voting      wondering 
##              2              2              2              2              2 
## trumpflprimary           will         bratty          child    gopclowncar 
##              2              2              1              1              1 
##          never     noelection           told      interview           next 
##              1              1              1              1              1 
##      president       standing         states         united         witham 
##              1              1              1              1              1