R used to generate views of ScraperWiki's Twitter Search tool

view-source.R

#!/usr/bin/Rscript
# Script to create r-view 2013-08-14
# Ian Hopkinson

source('scraperwiki_utils.R')

NumberOfTweets<-function(){
  query = 'select count(*) from tweets'
  number = ScraperWikiSQL(query)
  return(number)
}

TweetsHistogram<-function(){
  library("ggplot2")
  library("scales")
  #threshold = 20
  bin = 60 # Size of the time bins in seconds
  query = 'select created_at from tweets order by created_at limit 40000'
  dates_raw = ScraperWikiSQL(query)
  posix = strptime(dates_raw$created_at, "%Y-%m-%d %H:%M:%S+00:00")
  num = as.POSIXct(posix)
  Dates = data.frame(num)
  
  p = qplot(num, data = Dates, binwidth = bin)
  # This gets us out the histogram count values
  counts = ggplot_build(p)$data[[1]]$count
  timeticks = ggplot_build(p)$data[[1]]$x
  # Calculate limits, method 1 - simple min and max of range
  start = min(num)
  finish  = max(num)
  minor = waiver() # Default breaks
  major = waiver()
  p = p+scale_x_datetime(limits = c(start, finish ),
                         breaks = major, minor_breaks = minor)
  p = p + theme_bw() + xlab(NULL) + theme(axis.text.x  = element_text(angle=45,
                                                                    hjust = 1,
                                                                    vjust = 1))
  p = p + xlab('Date') + ylab('Tweets per minute') + ggtitle('Tweets per minute (Limited to 40000 tweets in total)')
  return(p)
}