2
votes

How can I get ggplot to produce something similar like Example

library(ggplot2)
library(reshape2)
library(ecp)

synthetic_control.data <- read.table("/path/synthetic_control.data.txt", quote="\"", comment.char="")
n <- 2

s <- sample(1:100, n)
idx <- c(s, 100+s, 200+s, 300+s, 400+s, 500+s)
sample2 <- synthetic_control.data[idx,]
df = as.data.frame(t(as.matrix(sample2)))

#calculate the change points
changeP <- e.divisive(as.matrix(df[1]), k=8, R = 400, alpha = 2, min.size = 3)
changeP = changeP$estimates
changeP = changeP[-c(1,length(changeP))]

changePoints = data.frame(changeP,variable=colnames(df)[1])
for(series in 2:ncol(df)){
  changeP <- e.divisive(as.matrix(df[series]), k=8, R = 400, alpha = 2, min.size = 3)
  changeP = changeP$estimates
  changeP = changeP[-c(1,length(changeP))]
  changePoints = rbind(changePoints, data.frame(changeP,variable=colnames(df)[2]))
}

this is the interesting part about the plot:

df$id = 1:nrow(df) dfMelt <- reshape2::melt(df, id.vars = "id") p = ggplot(dfMelt,aes(x=id,y=value))+geom_line(color = "steelblue")+ facet_grid(variable ~ ., scales = 'free_y') p + geom_vline(aes(xintercept=changeP), data=changePoints, linetype='dashed')

So far my result is: https://www.dropbox.com/s/mysadkruo946oox/changePoint.pdf which means that there is something wrong with my array passed to the geom_vlines.

Could you point me in the right direction why I only get vlines in the first 2 plots?

1
I updated the questionGeorg Heiler
if you install the R package ecp it should be possible to just copy / paste the code.Georg Heiler
I updated the question -- the part for ecp is working now and I get some simple vlines BUT only in parts of the plotsGeorg Heiler
As stackoverflow.com/questions/25486994/… show I would have to change the to: xintercept=variable but this results in Discrete value supplied to continuous scaleGeorg Heiler

1 Answers

0
votes

This is the solution:

library(ggplot2)
library(reshape2)
library(ecp)

synthetic_control.data <- read.table("/Users/geoHeil/Dropbox/6.Semester/BachelorThesis/rResearch/data/synthetic_control.data.txt", quote="\"", comment.char="")
n <- 2

s <- sample(1:100, n)
idx <- c(s, 100+s, 200+s, 300+s, 400+s, 500+s)
sample2 <- synthetic_control.data[idx,]
df = as.data.frame(t(as.matrix(sample2)))

#calculate the change points
changeP <- e.divisive(as.matrix(df[1]), k=8, R = 400, alpha = 2, min.size = 3)
changeP = changeP$estimates
changeP = changeP[-c(1,length(changeP))]

changePoints = data.frame(changeP,variable=colnames(df)[1])
for(series in 2:ncol(df)){
  changeP <- e.divisive(as.matrix(df[series]), k=8, R = 400, alpha = 2, min.size = 3)
  changeP = changeP$estimates
  changeP = changeP[-c(1,length(changeP))]
  changePoints = rbind(changePoints, data.frame(changeP,variable=colnames(df)[series]))
}

# plot
df$id = 1:nrow(df)
dfMelt <- reshape2::melt(df, id.vars = "id")
p = ggplot(dfMelt,aes(x=id,y=value))+geom_line(color = "steelblue")+ facet_grid(variable ~ ., scales = 'free_y')
p + geom_vline(aes(xintercept=changeP), data=changePoints, linetype='dashed', colour='darkgreen')