In stephlocke/Rtraining: Training Materials on R

knitr::opts_chunk$set(echo = TRUE, message = FALSE, dev="svg",
     out.height = "500px",  strip.white=TRUE
     ,collapse = TRUE, dev.args = list(bg="transparent")
)
library(data.table)

data.table

data.table basics

Task | How ------------- | ------------- Read CSV | irisDT <- fread("iris.csv") Return everything | irisDT irisDT[ ] Select columns | irisDT[ , .(Sepal.Length, Sepal.Width) ] Update column | irisDT[,Sepal.Area:=Sepal.Length*Sepal.Width] Restrict rows | irisDT[ Sepal.Length >=5 , ] Aggregate | irisDT[ , mean(Sepal.Length)] Aggregate by group | irisDT[ , mean(Sepal.Length) , Species ] Count | irisDT[ , .N ]

data.table awesomeness - IO

colnames<-paste0("reallyLongColumnNamesSuuuuuck",1:13000)
rows<-13000
sampledt<-data.table(a=1:rows)
sampledt[,c(colnames):=1]
fwrite(sampledt,"sample.csv")

qRead<-fread("sample.csv")
system.time(
fwrite(qRead,"sample.csv"))

data.table awesomeness - groups

irisDT<-data.table(iris)
knitr::kable(
  irisDT[, .SD[which.min(Petal.Length)]
       , Species])

stephlocke/Rtraining documentation built on May 30, 2019, 3:36 p.m.