How to plot a big dataset

How_to_plot_a_big_dataset_using_ggplot.r

# How to plot a BIG data set (600 million rows/values with 8555 keys)
# Use the follow example!!

library(dplyr)
library(ggplot2)

data(diamonds)

# plot density of different keys
ggplot(diamonds, aes(x=depth)) + geom_line(aes(color= cut), stat="density", size=0.4, alpha=0.4)

# extract different keys individually
Fair <- filter(diamonds, cut == "Fair")                              
Good <- filter(diamonds, cut == "Good")
VeryGood <- filter(diamonds, cut == "Very Good")   
Premium <- filter(diamonds, cut == "Premium")
Ideal <- filter(diamonds, cut == "Ideal")                                                     

# plot each key one by one 
ggplot() +
 geom_line(data=Fair, aes(x=depth), stat="density", size=0.4, alpha=0.4, color = "red") +
 geom_line(data=Good, aes(x=depth), stat="density", size=0.4, alpha=0.4, color = "green") +
 geom_line(data=VeryGood, aes(x=depth), stat="density", size=0.4, alpha=0.4, color = "blue") +
 geom_line(data=Premium, aes(x=depth), stat="density", size=0.4, alpha=0.4, color = "black") + 
 geom_line(data=Ideal, aes(x=depth), stat="density", size=0.4, alpha=0.4, color = "purple")