1. ## Re: [R Graphics] Beautiful graphics thread

Tr, Vinux's plot was an intraday graphic. I'm saying take a composite over multiple days so that an hour slice represents some function of the aggregate at that hour on all days. Then any people that have clustering should align closely and all be in one graph. Your multi-day plot appears to have different time scales on the x-axis. The only way to see how people tend to cluster over days would be if the plots were stacked on top of each other with the same scale. Then you can essentially take a slice down the plots to see how people cluster at that time. Trying to evaluate something like that for a month or a year would basically be incomprehensible. Instead, I was proposing an aggregation of the multi-day information into one plot. Each person's outcome is a function of the distribution of the phenomena over multiple days.

2. ## Re: [R Graphics] Beautiful graphics thread

Plot1: Clustering based on the time. Clustering based 24 variables ( 0-1, 1-2, ...).
Plot2: I have seen the season package in the latest R journal. We could achieve the same by stars.
Plot3. Further drill down of plot2.

Code:
``````ts <- read.csv(insert_url_for_dropbox_csv_here, stringsAsFactors=FALSE)

ts\$dt <- strptime(ts\$Date, "%m/%d %H:%M")
ts\$dttime <- as.POSIXlt(ts\$dt, "IST")

ts\$hourgroup <- cut(ts\$dttime\$hour, breaks=c(-1, 6, 12, 18, 24), labels=c("0-6", "6-12", "12-18", "18-24"))
ts\$wdays <- factor( weekdays(ts\$dttime, abbreviate=TRUE), levels=c("Sun", "Mon", "Tue", "Wed", "Thu","Fri","Sat"))
chat.wtable <- table(ts\$wdays)

## PLOT 1
par(mfrow=c(1, 2))
plot(hclust(dist(as.data.frame.matrix(table( ts\$User.Name, ts\$dttime\$hour))), "ave"), main="Cluster Based on Time", xlab="Users", frame.plot=T,  yaxt="n")
## PLOT 2
library(season)
plotCircular(chat.wtable, labels=names(chat.wtable), lines=T, pieces.col="brown", main="Weekly data")

## PLOT 3
stars(as.data.frame.matrix(table(ts\$wdays, ts\$hourgroup)), key.loc= c(6, 4.5), key.labels="Clock",  draw.segments=TRUE, col.segments=gray(c(0.1, .9, .8, .2)), nrow=4, ncol=3, main="Chats by Time and Weekday", frame.plot=TRUE)``````
The clustering brings timezone matches. Even I change the methods the clusters look similar. In the second graph. It is showing the seasonality. It seems chatbox is very active in the last three working days.

I am thinking of exploring grid graphics. It would be fun adding "SVG + Javascript" to make it interactive.

If anyone can suggest some interesting data, we could all analyze on that.

3. ## The Following 2 Users Say Thank You to vinux For This Useful Post:

TheEcologist (06-07-2013), trinker (10-25-2012)

4. ## Re: [R Graphics] Beautiful graphics thread

@BG still not sure if I know what you mean. Is this what you're thinking? Plus should the scaling be done by person or just overall? I did it by person.

Code:
``````library(ggplot2); library(talkstats); library(plyr); library(reshape2)
dat <- ts_chatbox()
dat\$hour <- sapply(strsplit(as.character(dat\$time), ":"),
function(x) x[c(T, F, F)])

dat3 <- data.frame(with(dat, table(person, date, hour)))
x3 <- melt(dat3)
x3 <- ddply(x3, .(person), transform, rescale = rescale(value))

ggplot(x3, aes(hour, date, group=person)) + geom_tile(aes(fill = rescale),
colour = "white") + scale_fill_gradient(low = "gold",
high = "darkviolet") + theme_grey() + labs(x = "",
y = "") + scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) + theme(legend.position = "none",
axis.ticks = element_blank(), axis.text.x = element_text(angle = -90,
hjust = 0, colour = "grey50")) + facet_wrap(~person, ncol=3)``````

Code:
``````ggplot(x3, aes(hour, person, group=person)) + geom_tile(aes(fill = rescale),
colour = "white") + scale_fill_gradient(low = "gold",
high = "darkviolet") + theme_grey() + labs(x = "",
y = "") + scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) + theme(legend.position = "none",
axis.ticks = element_blank(), axis.text.x = element_text(angle = -90,
hjust = 0, colour = "grey50")) + facet_wrap(~date, ncol=3)``````

5. ## Re: [R Graphics] Beautiful graphics thread

Vinux, that star graph is nice! It clearly shows that people talk the most Wednesday through Friday and aren't that active on the weekends, which I know, but I would always think people would be more active! Mainly because that's when I'm more active since I work all day and can't use TS lol

Trinker, that heat map looks good. The scales are all the same now so when I look at a certain point on one graph then I know it's the same time point on the other graph, but a nice transformation of the data now would be to look at a time point (say Dason at 8 PM) across all the days. Maybe just take the median value. Do that for all time points. Then we'd have a composite single graph representing what hour people are the busiest. With Vinux's star graph, this composite can also be done by day, so we can see which hour people are most active on a given day given all the days data we have.

6. ## Re: [R Graphics] Beautiful graphics thread

@BG I tried median and it wasn't informative except for three people so I used mean instead.

Code:
``````ggplot(x3, aes(hour, person, group=person)) + geom_tile(aes(fill = rescale),
colour = "white") + scale_fill_gradient(low = "white",
high = "darkblue") + theme_grey() + labs(x = "",
y = "") + scale_x_discrete(expand = c(0, 0)) +
scale_y_discrete(expand = c(0, 0)) + theme(legend.position = "none",
axis.ticks = element_blank(), axis.text.x = element_text(angle = -90,
vjust = .1, colour = "grey50"))``````

7. ## The Following 2 Users Say Thank You to trinker For This Useful Post:

bryangoodrich (10-25-2012), vinux (10-25-2012)

8. ## Re: [R Graphics] Beautiful graphics thread

@Vinux who's zorro?

9. ## Re: [R Graphics] Beautiful graphics thread

lol @ trinker & Dason being close together... the eternal battle of the bots VS the raptors will continue forever...

ps- so... why am i associated with jimmy brooks?

10. ## Re: [R Graphics] Beautiful graphics thread

If you're talking about Vinux's it's because you both speak during the same time intervals. However we don't know if it's on the same day. Also Jimmy Brooks has almost no words spoken (see below):

This gives some basic word statistics (ignore sentence because I didn't break it up by sentence; that's more our turns of talk or chat inputs).
Code:
``````library(qdap); library(talkstats)
dat <- ts_chatbox()
with(dat, word_stats(dialogue, person))``````
Here's a link to a txt data frame of the stats as it's pretty long: LINK

11. ## Re: [R Graphics] Beautiful graphics thread

Originally Posted by trinker
If you're talking about Vinux's it's because you both speak during the same time intervals. However we don't know if it's on the same day. Also Jimmy Brooks has almost no words spoken (see below):

This gives some basic word statistics (ignore sentence because I didn't break it up by sentence; that's more our turns of talk or chat inputs).
Code:
``````library(qdap); library(talkstats)
dat <- ts_chatbox()
with(dat, word_stats(dialogue, person))``````
Here's a link to a txt data frame of the stats as it's pretty long: LINK
Trinker, I used the old data for my last graphs, where jimmy was one other top ten. For clustering my idea was to identify the timezone (Just because we have the reference so it can easily comparable). I mean the variable I have created in that way.

12. ## The Following User Says Thank You to vinux For This Useful Post:

trinker (10-25-2012)

13. ## Re: [R Graphics] Beautiful graphics thread

Oh I didn't realize it had changed that much.

14. ## Re: [R Graphics] Beautiful graphics thread

I like the graph trinker! I wonder what other aggregation we can do, maybe something that accounts for timezone (since every hour is locally different), and include a scale on the right to show what the continuous variable represents (graphs need to be completely informative, at least in the final analysis).

15. ## Re: [R Graphics] Beautiful graphics thread

I decided to showcase the use of images in R graphics.

Lets take a look at the forum's from a spammer perspective. Generally speaking its a dangerous place, with ravenous moderators around each corner waiting to devour their posts and ban them for all eternity. Thus lets see how the TS mods compare in evil (from a spammers perspective) to famous cinema villains.

Using data from the net, on villain body counts and comparing these to the mod ban statistics we can get a mle estimate of how the mods compare to famous villains. This finally give us an opportunity to scientifically prove who is a raptor and who is a (Skynet) bot. [I would want to compare mods to super heroes but there is no way to rank super heroes objectively that I can think of]. In the analysis I assume that ban stats are a Poisson distributed random variable.

So here are the results;

And here is the script (make sure to download the images zip file and set your working directory);

Code:
``````
#have you set your image working directory yet?

setwd("/home/marco/images")

killcount=sort(structure(c(9L, 6L, 89L, 33L, 8L, 34L), .Dim = 6L, .Dimnames = structure(list(
dat = c("bugman", "CowboyBear", "Dason", "Dragan", "quark",
"TheEcologist")), .Names = "dat"), class = "table"))

# Movie Villains kill stats taken from the net
villains=structure(list(Kills = c(6, 10, 18, 22, 32, 35, 42, 57, 64),
name = structure(c(8L, 1L, 5L, 2L, 3L, 4L, 6L, 9L, 7L), .Label = c("Alien",
"Predator", "Raptors", "Terminator"), class = "factor")), .Names = c("Kills",
"name"), row.names = c(4L, 3L, 5L, 7L, 8L, 6L, 9L, 2L, 1L), class = "data.frame")

#blood palette
tibetanmonk.colors=colorRampPalette(c("#FC580C","#FC6B0A","#F8872E","#FFA927","#FDCA49"))

# Blood splash background
require(biOps)

text(1,1,"A")

layoutmat=
structure(c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 77L, 1L, 17L, 26L, 35L,
44L, 53L, 62L, 8L, 1L, 18L, 27L, 36L, 45L, 54L, 63L, 9L, 1L,
19L, 28L, 37L, 46L, 55L, 64L, 10L, 1L, 20L, 29L, 38L, 47L, 56L,
65L, 11L, 1L, 21L, 30L, 39L, 48L, 57L, 66L, 12L, 1L, 22L, 31L,
40L, 49L, 58L, 67L, 13L, 1L, 23L, 32L, 41L, 50L, 59L, 68L, 14L,
1L, 24L, 33L, 42L, 51L, 60L, 69L, 15L, 1L, 25L, 34L, 43L, 52L,
61L, 70L, 16L, 1L, 71L, 72L, 73L, 74L, 75L, 76L, 1L), .Dim = c(8L,
11L), .Dimnames = list(NULL, c("V1", "V2", "V3", "V4", "V5",
"V6", "V7", "V8", "V9", "V10", "V11")))

Avatars=vector("list",5)

par(mar=c(0,0,0,0),xaxt="n",yaxt="n")
layout(layoutmat)

plot(bloodbackground)

lims=dim(bloodbackground)[1:2]

#Title
text(lims[2]/2,lims[1]-40,expression(bold("How Moderators Compare to Movie Villains")),cex=3,col="blue")

# MLE
text(lims[2]-40,lims[1]-60,expression(bold("MLE")),cex=2,col="blue")

#mod
text(0+40,lims[1]-60.5,expression(bold("MOD")),cex=2,col="blue")

for(i in 1:6){
plot(Avatars[[i]])
}

for(i in 1:9){
plot(vilpic)
}

for(i in 1:6){

for (j in 1:dim(villains)[1]){
barplot(dpois(villains[j,1],killcount[i]),
col=tibetanmonk.colors(dim(villains)[1])[j],
ylim=c(0,max(dpois(villains[,1],killcount[i]))))
}
}

for(i in 1:6){
l=dpois(villains[,1],killcount[i])
mle=which(l==max(l))
[mle],".jpg",sep=""))
plot(vilpic)
}

plot(-100,ylim=c(0,1),xlim=c(0,1))``````
As we can see there are certainly Raptors on the forum, Dragan is as deadly as Chucky, Dason is likely the Predator but cant be significantly distinguished from the T101 (a bot). Quark, like his DS9 Ferengi bar-tender counterpart, is likely an Alien (but still most likely a Raptor)... bugman will incubate his spawn in your abdomen... and funny enough I'm Darth Vader.

So come on over to the Darkside and join me in the power of (wrapper free) R graphics

Note; the mod stats may not reflect actual clean-up contributions of the moderators, as we have an automatic spammer "remove all posts and ban" button.. which does not get recorded in the stats. Some mods may therefore be more deadly than the image suggests

16. ## The Following 3 Users Say Thank You to TheEcologist For This Useful Post:

bugman (10-27-2012), trinker (10-27-2012), vinux (10-28-2012)

17. ## Re: [R Graphics] Beautiful graphics thread

Does this mean quark is a raptor?

18. ## Re: [R Graphics] Beautiful graphics thread

Originally Posted by trinker
Does this mean quark is a raptor?
Indeed a Raptor. But it really all boils down towards whether you are a Frequentest or a Bayesian. You see the mode of the likelihood distribution is a Raptor, but Bayesians would be more interested in the mean which is an Alien , I w

Also, as I am Darth Vader, I would like to urge bugman to finish that death star in his avatar. I want it fully operational!

19. ## Re: [R Graphics] Beautiful graphics thread

Happy birthday to Velociraptor. I made this one using raptor's favourite package

Code:
``````rapt = read.csv("http://dl.dropbox.com/u/32095775/raptor.csv")
library(ggplot2)
ggplot(data=rapt) + geom_polygon(aes(x=V1, y=V2, group=group), colour=I("gray") )+ theme_bw() + scale_x_continuous(limits = c(0, 400)) +   scale_y_continuous(limits = c(0, 250)) +
geom_text(aes(100,230, label="Happy Birthday Raptor"))+
theme(axis.line=element_blank(), axis.text.x=element_blank(),  axis.text.y=element_blank(),axis.ticks=element_blank(), axis.title.x=element_blank(),    axis.title.y=element_blank(),legend.position="none", panel.background=element_blank(),panel.border=element_blank(), panel.grid.major=element_blank(), panel.grid.minor=element_blank(), plot.background=element_blank())``````

20. ## The Following User Says Thank You to vinux For This Useful Post:

trinker (11-15-2012)

Page 3 of 9 First 1 2 3 4 5 6 7 8 9 Last

 Tweet