Some lines to get timings for the glmnet fortran implementation via the R interface. This should later be used to compare it against the scikit-learn glmnet implementation.

get_glmnet_timing_from_R.py

import rpy2.robjects as robjects
from rpy2.robjects import *

r_script_path = r"/home/mane/workspace/benchmark"

# Set wd in R
robjects.r.setwd(r_script_path)

# Load the R code
r.source(os.path.join(r_script_path, "time_glmnet_fit.R"))


leukemia_time = robjects.r.timeLogisticRegression("Leukemia",0.8, 100)

#internetAd_time = robjects.r.timeLogisticRegression("InternetAd",0.8, 10)

#NewsGroup_time = robjects.r.timeLogisticRegression("NewsGroup",0.8, 3)

time_glmnet_fit.R

require(glmnet)
require(Matrix)
require(lattice)

timeLogisticRegression<- function(data_name="Leukemia", alpha=0.5, repetitions=1){

	file_name = paste(data_name, "RData", sep=".")
	load(file.path(getwd(),file_name))
	
	print(paste("Logistic Regression",file_name, " alpha=", alpha))
	

	
	X = get(data_name)$x
	y = get(data_name)$y
	all_timings = NA
	
	for (i in 1:repetitions){	
		my_timer = system.time( {fit = glmnet(x=X,y=y, family="binomial")} )
		print(my_timer)
		all_timings = rbind(all_timings, as.numeric(my_timer))
	}
	
	#averageTime = colMedians(all_timings, na.rm = TRUE)
	medianTime = apply(as.array(all_timings), 2, median, na.rm=TRUE)
	print(medianTime)
	return(medianTime)
}


#ergebniss = timeLogisticRegression(data_name="Leukemia", alpha=0.5)