mjbommar · May 21, 2012 12:59 · May 21, 2012
diff --git a/plotHashtag2.R b/plotHashtag2.R
@@ -0,0 +1,45 @@
+
+# @author: Bommarito Consulting, LLC; http://michaelbommarito.com/
+# @date: May 21, 2012
+# @email: michael@bommaritollc.com
+# @packages: ggplot2, plyr
+
+# Clear and import.
+rm(list=ls())
+library(ggplot2)
+library(plyr)
+
+# Controlling parameters.
+hashtag <- "#nonato"	# Hashtag for label purposes
+cutoff <- as.POSIXct("2012-01-11 00:00:00", tz="EDT")	# First timestamp we will consider	
+dt <- 30	# \Delta t, minutes
+
+# Load and pre-process tweets
+tweets <- unique(read.table('data/tweets.csv', sep="\t", quote="", comment.char="", 
+		stringsAsFactors=FALSE, header=FALSE, nrows=300000))
+names(tweets) <- c("id", "date", "user", "text")
+tweets$date <- as.POSIXct(strptime(tweets$date, "%a, %d %b %Y %H:%M:%S %z", tz = "GMT"))
+tweets <- tweets[which(tweets$date > cutoff), ]
+
+# Build date breaks
+minDate <- min(tweets$date)
+maxDate <- max(tweets$date) + 60 * dt
+dateBreaks <- seq(minDate, maxDate, by=60 * dt)
+
+# Use hist to count the number of tweets per bin; don't plot.
+tweetCount <- hist(tweets$date, breaks=dateBreaks, plot=FALSE)
+
+# Strip out the left endpoint of each bin.
+binBreaks <- tweetCount$breaks[1:length(tweetCount$breaks)-1]
+
+# Count number of unique tweeters per bin.
+userCount <- sapply(binBreaks, function(d) length(unique(tweets$user[which((tweets$date >= d) & (tweets$date <= d + 60*dt))]))) 
+
+# Plot data
+plotData <- data.frame(dates=dateBreaks[1:length(dateBreaks)-1], tweets=as.numeric(tweetCount$count), users=as.numeric(userCount))
+ggplot(plotData) + 
+	geom_bar(aes(x=dates, y=tweets, color=users), stat="identity") +
+	scale_x_datetime("Date") +
+	scale_y_continuous("Number of tweets") +
+	opts(title="Number of tweets and unique users : #nonato")
+ggsave("fig/ts_tweet_user.jpg", width=12, height=8)
No results found