szilard

library(data.table)

n <- 2e9
m <- 1e9
system.time( d <- data.table(x = sample(m, n, replace=TRUE), y = runif(n)) )
#   user  system elapsed
# 103.843   8.255 112.242
system.time( dm <- data.table(x = sample(m)) )
#   user  system elapsed
# 47.298   1.860  49.288

szilard

#### h2o

library(h2o)
h2o.init(max_mem_size = "50g", nthreads = -1)

dx_train <- h2o.importFile("train-1m.csv")
dx_test <- h2o.importFile("test.csv")

Xnames <- names(dx_train)[which(names(dx_train)!="dep_delayed_15min")]

szilard

library(caret)
library(readr)
library(ROCR)

set.seed(123)

d <- read_csv("https://raw.githubusercontent.com/szilard/teach-data-science-UCLA-master-appl-stats/master/wk-06-ML/data/airline100K.csv")

szilard

## training a model

library(h2o)
h2o.init(nthreads = -1)

dx_train <- h2o.importFile("https://s3.amazonaws.com/benchm-ml--main/train-0.1m.csv")

md_rf <- h2o.randomForest(x = 1:(ncol(dx_train)-1), y = ncol(dx_train), training_frame = dx_train, 
                    model_id = "h2o_RF",
                    ntrees = 100, max_depth = 10, nbins = 100)

szilard

#include <stdio.h>
#include <stdlib.h>

#define N 100
#define B0 100
#define R 1000000

int main() {
  int b[N], rec[N];
  for (int i=0; i<N; i++) b[i] = B0;

szilard

#include <stdio.h>
#include <stdlib.h>

#define N 128
#define B0 100
#define R 1000000
#define M 1000

int cmpfunc (const void * a, const void * b)
{

szilard

## https://github.com/EpistasisLab/penn-ml-benchmarks

## pip install pmlb

import numpy as np
from pmlb import fetch_data
from pmlb import dataset_names

x = np.zeros(len(dataset_names))
for i, dn in enumerate(dataset_names):

szilard

# OpenML Benchmarking Suites and the OpenML100
# https://arxiv.org/abs/1708.03731
# https://www.openml.org/s/14/data

library(OpenML)
ids <- getOMLStudy('OpenML100')$data$data.id
dsall <- listOMLDataSets()
sum(dsall$data.id %in% ids)   ## 96???
ds <- dsall[dsall$data.id %in% ids,]

szilard

## partial credit :) to @earino for the idea

library(lightgbm)
library(data.table)
library(ROCR)

d0_train <- fread("/var/data/bm-ml/train-10m.csv") 
d0_test <- fread("/var/data/bm-ml/test.csv") 
d0 <- rbind(d0_train, d0_test)

szilard

library(data.table)
library(ROCR)
library(lightgbm)

set.seed(123)

d_train <- fread("/var/data/bm-ml/train-0.1m.csv")
d_test <- fread("/var/data/bm-ml/test.csv")