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

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

#### 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(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

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

dx_train <- h2o.importFile("https://s3.amazonaws.com/benchm-ml--main/train-1m.csv")


system.time({
  md_10 <- h2o.gbm(x = 1:(ncol(dx_train)-1), y = ncol(dx_train), training_frame = dx_train, 
                   model_id = "airline_depth10",

szilard

library(h2o)
h2o.init(max_mem_size = "20g", nthreads = -1)

# R is connected to the H2O cluster: 
#   H2O cluster uptime:         1 seconds 704 milliseconds 
# H2O cluster version:        3.8.2.8 
# H2O cluster name:           H2O_started_from_R_szilard_lcr105 
# H2O cluster total nodes:    1 
# H2O cluster total memory:   17.78 GB 

szilard

## allocate <1TB first, stuff works
> x <- 1:1.2e11
> gc()
               used     (Mb)  gc trigger      (Mb)     max used     (Mb)
Ncells       214403     11.5 4.60000e+05      24.6       350000     18.7
Vcells 120000397293 915530.4 1.72801e+11 1318366.9 120000398080 915530.4
> system("echo 1")
1

szilard

> system.time(x <- 1:1e11)
   user  system elapsed
221.491 210.466 432.030

> object.size(x)/1e9
800.00000004 bytes

> system.time(sum(x))
   user  system elapsed
145.913  78.183 230.063

szilard

system.time(z <- 1:1e9)

system.time(d <- data.frame(x = 1:1e9))
system.time(d$y <- 1:1e9)
system.time(d$z <- z)

system.time(d$x[1] <- 0L)

szilard

sqlite vs R's data.table

TLDR;   sqlite (:memory:) 250 sec    data.table 7 sec


data: 100 million rows, 1 million groups
generated by: https://github.com/szilard/benchm-databases/blob/master/0-gendata.txt