Test manipulating a large, 1.8 gig dataset with SQLite and sqldf

test_sqlite_sqldf

#creating a dataset with 1.8 GIGs
setwd("~/Desktop")
bigdf <- data.frame(dim=sample(letters, replace=T, 4e7), fact1=rnorm(4e7), fact2=rnorm(4e7, 20, 50))
write.csv(bigdf, 'bigdf.csv', quote = F)

#opening the dataset and measuring performance time
setwd("~/Desktop")
library(sqldf)
f <- file("bigdf.csv")
system.time(bigdf <- sqldf("select * from f", dbname = tempfile(), file.format = list(header = T, row.names = F)))
#    user  system elapsed 
# 246.994  16.165 281.253