r - ggplot2 geom_line() and smoothing -

i trying create ggplot2 smoothed line graph looks more this

source: http://www.esrl.noaa.gov/psd/enso/mei/

and less this:

source: https://dl.dropboxusercontent.com/u/16400709/stackoverflow/rplot02.png

my data available on dropbox.

having looked @ previous posts used code below:

#mei line graph  d4 <- read.csv("https://dl.dropboxusercontent.com/u/16400709/stackoverflow/data_mei.csv") head(d4,n=20)  mei<-ggplot(d4,aes(x=d4$date, y=d4$mei,group=1))+geom_line()  mei+stat_smooth(method ="auto",level=0.95) 

what think need reduce amount of smoothing taking place, have yet figure out how achieve this.

d4s<-sma(d4$mei,n=8) plot.ts(d4s) 

sma() works cant work ggplot hints appreciated!

be aware mei index 2-month period, it's got smoothing built in. assuming using mei data noaa esrl publishes, should able create same plot.

first of need system set up, you'll working timezeones:

# set things  ---- working.dir = file.path('/code/r/stackoverflow/') setwd(working.dir) sys.setenv(tz='gmt') 

now, download data , read in

d.in <- read.csv("mei.txt") 

the next step dates formatted properly.

d.in$date <- as.posixct(d.in$date,                         format = "%d/%m/%y",                          tz = "gmt") 

and because need figure out things cross x-axis, we'll have work in decimal dates. use epoch value:

d <- data.frame(x = as.numeric(format(d.in$date,                                       '%s')),                 y = d.in$mei) 

now can figure out zero-crossings. we'll use beroe's example that.

rx <- do.call("rbind",               sapply(1:(nrow(d)-1), function(i){                 f <- lm(x~y, d[i:(i+1),])                 if (f$qr$rank < 2) return(null)                 r <- predict(f, newdata=data.frame(y=0))                 if(d[i,]$x < r & r < d[i+1,]$x)                   return(data.frame(x=r,y=0))                 else return(null)               })) 

and tack on end of initial data:

d2 <- rbind(d,rx) 

now convert dates:

d2$date <- as.posixct(d2$x,                       origin = "1960-01-01",                       format = "%s",                       tz = "gmt") 

now can plot:

require(ggplot2) ggplot(d2,aes(x = date,               y = y)) +    geom_area(data=subset(d2, y<=0), fill="blue") +    geom_area(data=subset(d2, y>=0), fill="red") +    scale_y_continuous(name = "mei") 

and gives this:

now, need smooth this?