How Much Memory Does A Data Scientist Need (base)

datascience_memory_base.R

# Code from blogpost:
# https://fullstackml.com/2015/12/06/how-much-memory-does-a-data-scientist-need/

library(ggplot2)
library(dplyr)

file <- "dataset-sizes.cv"
data <- read.csv(file, sep="\t")

data.slice <- data %>%
        filter(year == 2006 | year == 2009 | year == 2012 | year == 2015)
data.slice.cum_freq <- data.slice %>%
        group_by(year, sizeGB) %>%
        summarise(value = sum(freq)) %>%
        mutate(user_prop = value/sum(value), cum_freq = cumsum(value)/sum(value))
        
ggplot(data.slice.cum_freq, aes(x=log10(sizeGB), y=cum_freq, color=factor(year))) + 
        geom_line(aes(group = factor(year)))