We don't have any data in hdi-cpi.csv about population. So how did we get a density function - stat_density2d() - in the graph? What am I missing? This is the code: sp <- ggplot(hdi, aes(CPI.2015, HDI.2015)) sp + geom_point(aes(color = Region), shape = 21, fill = "white", size = 3, stroke = 2) + theme_light() + labs(x = "Corruption Perception Index, 2015", y = "Human Development Index, 2015", title = "Corruption And Human Development") + stat_density2d() Thank you

Hi T.Serghides, thanks for reaching out and sorry for the inconvenience! You should be able to download the data set in question from this lecture:https://learn.365datascience.com/courses/introduction-to-r-programming/intro-to-ggplot2/ Let me know if you have any further issues. Best, 365 Eli

Elitsa, Thank you for the reply. > You should be able to download the data set in question from this lecture... I did download the data and I can replicate the scatter plot with the countour lines (the density plot) with the density function stat_density2d() as follows: library(ggplot2) hdi <- read.csv("hdi-cpi.csv") sp <- ggplot(hdi, aes(CPI.2015, HDI.2015)) sp + geom_point(aes(color = Region), shape = 21, fill = "white", size = 3, stroke = 2) + theme_light() + labs(x = "Corruption Perception Index, 2015", y = "Human Development Index, 2015", title = "Corruption And Human Development") + stat_density2d() My question is this: Where is the data, in the csv file (hdi-cpi.csv), for the countour lines? What is the name of the variable (the column) for the contour lines? This, I don't understand. Thank you again for the reply.

Hi T. Serghides, sorry for the confusion. stat_density2d() is an R function. So, you can use it for every scatterplot you create in R and it will plot the density of the data. As mentioned in the video, that's a good option if you have too many data points and the scatter will look overcrowded. In that case you can plot the density of the data distribution for a nicer overview. Hope this helps! Best, 365 Eli