Created
February 13, 2014 12:10
-
-
Save akhilsbehl/8973994 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(dplyr) | |
library(data.table) | |
library(microbenchmark) | |
########################################################################### | |
# FUNCTIONALITY # | |
########################################################################### | |
set.seed(pi) | |
samp = data.frame(x=runif(1e7, 2, 4), | |
y=rnorm(1e7, mean=runif(1), sd=runif(1, 1, 2)), | |
z=letters[sample.int(26, 1e7, TRUE)], | |
w=LETTERS[sample.int(26, 1e7, TRUE)], | |
stringsAsFactors=FALSE) | |
# The process: | |
# 1. Filter the samp on the first half of `letters' and the second half of | |
# LETTERS and the second half of LETTERS. | |
# 2. Select only columns x, y, and z out of the data.frame. | |
# 3. Create two new columns: | |
# 3.1 xProp = x / sum(x) | |
# 3.2 yScale = (y - mean(y)) / sd(y) | |
# 4. Calculate mean(xProp) and mean(yScale) by z. | |
# 5. Arrange / Order output by letters. | |
############ | |
# Base R # | |
############ | |
baseR = samp[samp[["z"]] %in% letters[1:20] & | |
samp[["w"]] %in% LETTERS[7:26], | |
c("x", "y", "z")] | |
baseR[["xProp"]] = with(baseR, x / sum(x)) | |
baseR[["yScale"]] = with(baseR, (y - mean(y)) / sd(y)) | |
baseR = by(baseR, baseR[["z"]], | |
function (x) | |
c("meanXProp"=mean(x[["xProp"]]), | |
"meanYScale"=mean(x[["yScale"]]))) | |
baseR = do.call("rbind", baseR) | |
########### | |
# dplyr # | |
########### | |
dply = | |
samp %.% | |
filter(z %in% letters[1:20], w %in% LETTERS[7:26]) %.% | |
select(x, y, z) %.% | |
mutate(xProp=x / sum(x), | |
yScale=(y - mean(y)) / sd(y)) %.% | |
group_by(z) %.% | |
summarise(meanXProp=mean(xProp), meanYScale=mean(yScale)) %.% | |
arrange(z) | |
################ | |
# data.table # | |
################ | |
dt = data.table(samp) | |
dt = dt[z %in% letters[1:20] & w %in% LETTERS[7:26], list(x, y, z)] | |
dt = dt[ , list(xProp=(x / sum(x)), yScale=(y - mean(y)) / sd(y), z)] | |
dt = dt[ , list(meanXProp=mean(xProp), meanYScale=mean(yScale)), by=z] | |
dt = dt[order(dt[["z"]]), ] | |
########################################################################### | |
# BENCHMARKING # | |
########################################################################### | |
set.seed(pi) | |
samp = data.frame(x=runif(1e7, 2, 4), | |
y=rnorm(1e7, mean=runif(1), sd=runif(1, 1, 2)), | |
z=letters[sample.int(26, 1e7, TRUE)], | |
w=LETTERS[sample.int(26, 1e7, TRUE)], | |
stringsAsFactors=FALSE) | |
dtSamp = data.table(samp) | |
mbc = microbenchmark({ | |
baseR = samp[samp[["z"]] %in% letters[1:20] & | |
samp[["w"]] %in% LETTERS[7:26], | |
c("x", "y", "z")] | |
baseR[["xProp"]] = with(baseR, x / sum(x)) | |
baseR[["yScale"]] = with(baseR, (y - mean(y)) / sd(y)) | |
baseR = by(baseR, baseR[["z"]], | |
function (x) | |
c("meanXProp"=mean(x[["xProp"]]), | |
"meanYScale"=mean(x[["yScale"]]))) | |
baseR = do.call("rbind", baseR) | |
}, | |
{ | |
dply = | |
samp %.% | |
filter(z %in% letters[1:20], w %in% LETTERS[7:26]) %.% | |
select(x, y, z) %.% | |
mutate(xProp=x / sum(x), | |
yScale=(y - mean(y)) / sd(y)) %.% | |
group_by(z) %.% | |
summarise(meanXProp=mean(xProp), meanYScale=mean(yScale)) %.% | |
arrange(z) | |
}, | |
{ | |
dt = dtSamp[z %in% letters[1:20] & w %in% LETTERS[7:26], list(x, y, z)] | |
dt = dt[ , list(xProp=(x / sum(x)), yScale=(y - mean(y)) / sd(y), z)] | |
dt = dt[ , list(meanXProp=mean(xProp), meanYScale=mean(yScale)), by=z] | |
dt = dt[order(dt[["z"]]), ] | |
}, | |
times=10L) | |
print(mbc) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment