R Fitspline Tutorial

# fitspline.R

# Set the initial seed for the random number generator.
set.seed(sample(1:1000, 1))

# Create n = 100 random data points.
# x is n equally spaced values from 0 to 1.
n <- 100
x <- (1:n)/n

# The model in this simulation (no random error)
mval <- ((exp(x/3) - 2 * exp(-7 * x) + sin(9 * x)) + 1)/3

# Generate n independent normal random variates with mean 0
# and variance derived from the task id
tid <- as.integer(Sys.getenv("SLURM_ARRAY_TASK_ID"))
v <- tid/100
noise <- rnorm(n, 0, v)

# Simulated observed values (model value + noise)
y <- mval + noise

# Alternatively, you can read data from a file:
# dat <- read.table("dataset.dat", header = TRUE)
# attach(dat)

# Fit a cubic smoothing spline to the data
# Use GCV score and all basis functions
fit <- smooth.spline(x, y, cv = FALSE, all.knots = TRUE)

# Create a graph that shows the data, the smoothing spline,
# and the original model
r <- paste("result_", tid, ".ps", sep = "")
postscript(r, height = 8, width = 10, horizo = FALSE)

# Plot data points
plot(x, y, xlab = "x", ylab = "y", cex = 0.5)

# Plot original model values without noise
lines(x, mval, lty = 2)

# Plot smooth spline fit
lines(fit$x, fit$y)

# Save the graph to a PS file
graphics.off()

# To view with Ghostscript, at the
# command line type: gs result_X.ps
# where X is the corresponding task id

#!/bin/bash
#
# [ fitspline.sbatch ]
#
# This script demonstrates how to run an  R  job, specifically,
# how to fit a smooth spline model.  It uses a range of SLURM_ARRAY_TASK_ID's
# as a noise parameter for the model.
# --------------------------------------------------------------------
#
#
# Use environment modules to specify software and version.  Run the
#     "module av" command to get list of installed software versions,
#     then replace the <X.Y.Z> with actual software version as shown below.
#
#     module purge
#     module load R/<X.Y.Z>
#
#     For example:
#
#     rnd> module avail R
#     ---------------- /gridapps/modules -----------------
#     R/4.0.2          R/4.3.2
#
#     rnd>
#     rnd> module  purge
#     rnd> module  load   R/4.3.2
#     rnd>
# --------------------------------------------------------------------


# Submit this job via  'sbatch'  which accepts these command line options:

#SBATCH --job-name=fitsplineJob # Define the name of the current job.

#SBATCH --output=fitsplineJob.Rout # Define the stdout (the terminal output)
                                #    file name.

#SBATCH  --error=fitsplineJob.err  # Define the stderr (the terminal error output)
                                #    file name.  If '--error=' is not specified,
                                #    both stdout and stderr are output to the
                                #    same output file (in this case to file:
                                #    fitspline.out).


#SBATCH --export=ALL            # Export ALL environment variables of the
                                #    submitting process to the submitted job
                                #    including the current working directory.


#SBATCH --mail-type=END,FAIL    # Tell Slurm's  sbatch  to send email when the
                                #    job ENDs or when the job FAILs.  Options
                                #    that may be specified with '--mail=' are
                                #    NONE or any combination of:
                                #    BEGIN,END,FAIL,REQUEUE,STAGE_OUT.  There
                                #    is no default for '--mail-type='.


#SBATCH --mail-user=your-stern-netid@stern.nyu.edu
                                # Specify your Stern email address to notify.


#SBATCH --mem=512m              # Specifies the maximum memory this program will
                                #    be allocated.  The 512M specifies 512
                                #    Megabytes.  Memory units may be:  k|m|g|t
                                #    for kilo/mega/giga/tera-bytes.  The default
                                #    units are Megabytes.


#SBATCH --time=00:10:00         # The wall-clock time limit for this job, here 10 min.


#SBATCH --partition=test        # Specify to which partition to submit the job.
                                #    A partition is group of compute servers
                                #    which may potentially run this job.
                                #    The 'test' partition is the default partition.                                
                                #    The maximum time you
                                #    may request for the 'test' partition is
                                #    100-hours (--time=100:00:00).


# --------------------------------------------------------------------
# How to submit an array job to Stern Slurm cluster. 
# Pass array variable values 5, 10, 15 to the R script.
#
# sbatch  --array=5-15:5 fitspline.sbatch
# --------------------------------------------------------------------


# Select stat package and version to use
  module  purge
  module  load  R/4.3.2

  R CMD BATCH --no-save --no-restore fitspline.R fitspline.$SLURM_ARRAY_TASK_ID.Rout

sbatch --array=5-15:5 fitspline.sbatch