added a text file including a series of R instructions to test out parallelism

Rparallel.txt

+install.packages("plyr")
+install.packages("doMC")
+
+
+library(plyr)
+library(doMC)
+doMC::registerDoMC(cores=24) # or however many cores you have access to
+
+system.time(ddply(iris, .(Species), function(x) {
+ Sys.sleep(2)
+ nrow(x)
+}))
+# user system elapsed
+# 0.005 0.001 6.016
+
+system.time(ddply(iris, .(Species), function(x) {
+ Sys.sleep(2)
+ nrow(x)
+}, .parallel = TRUE))
+# user system elapsed
+# 0.018 0.015 2.031
+
+headers <- c("timestamp", "phrase_id", "account_id", "price", "auto")
+df <- read.table("./ydata-ysm-advertiser-bids-v1_0.txt")
+colnames(df) <- headers
+
+system.time(ddply(df, .(phrase_id, account_id), function(x) {
+ data.frame(mean=mean(x$price, na.rm=T), median=median(x$price, na.rm=T))
+ nrow(x)
+}))
+
+#   user  system elapsed 
+#   42.989   0.734  43.726 
+
+system.time(ddply(df, .(phrase_id, account_id), function(x) {
+ data.frame(mean=mean(x$price, na.rm=T), median=median(x$price, na.rm=T))
+ nrow(x)
+}, .parallel = TRUE))