From: Nathan TeBlunthuis <nathante@uw.edu>
Date: Wed, 29 Jun 2022 01:40:29 +0000 (-0700)
Subject: update sbatch for new directory and default output filename.
X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/commitdiff_plain/003733f22f42b435315803fd5f47d483c712d72d

update sbatch for new directory and default output filename.
---

diff --git a/simulations/01_two_covariates.R b/simulations/01_two_covariates.R
index c52a3dc..419403d 100644
--- a/simulations/01_two_covariates.R
+++ b/simulations/01_two_covariates.R
@@ -60,7 +60,7 @@ parser <- arg_parser("Simulate data and fit corrected models")
 parser <- add_argument(parser, "--N", default=500, help="number of observations of w")
 parser <- add_argument(parser, "--m", default=100, help="m the number of ground truth observations")
 parser <- add_argument(parser, "--seed", default=4321, help='seed for the rng')
-parser <- add_argument(parser, "--outfile", help='output file', default='example_2_B.feather')
+parser <- add_argument(parser, "--outfile", help='output file', default='example_1.feather')
 args <- parse_args(parser)
 
 B0 <- 0
diff --git a/simulations/Makefile b/simulations/Makefile
index 264b408..97b5894 100644
--- a/simulations/Makefile
+++ b/simulations/Makefile
@@ -1,20 +1,20 @@
 
 SHELL=bash
 
-Ns=[1000,10000,25000]
+Ns=[500,1000,10000,25000]
 ms=[50, 100, 250, 500]
 seeds=[$(shell seq -s, 1 250)]
 all:remembr.RDS
 
 srun=srun -A comdata -p compute-bigmem --time=10:00:00 --mem 4G -c 1
 
-example_1_jobs: example_1.R
-	grid_sweep.py --command "Rscript example_1.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"]}' --outfile example_1_jobs
+example_1_jobs: 01_two_covariates.R simulation_base.R grid_sweep.py
+	grid_sweep.py --command "Rscript 01_two_covariates.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"]}' --outfile example_1_jobs
 
 example_1.feather: example_1_jobs
 	rm -f example_1.feather
 	sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_1_jobs
-#	sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_1_jobs
+	sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_1_jobs
 
 example_2_jobs: example_2.R
 	grid_sweep.py --command "Rscript example_2.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2.feather"]}' --outfile example_2_jobs
diff --git a/simulations/example_1.feather b/simulations/example_1.feather
deleted file mode 100644
index b8efa3f..0000000
Binary files a/simulations/example_1.feather and /dev/null differ
diff --git a/simulations/grid_sweep.py b/simulations/grid_sweep.py
new file mode 100755
index 0000000..86312ea
--- /dev/null
+++ b/simulations/grid_sweep.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+
+import fire
+from itertools import product
+
+def main(command, arg_dict, outfile):
+    keys = []
+    values = []
+        
+    for i,p in enumerate(arg_dict.items()):
+        k,v = p
+        keys.append(k)
+        values.append(v)
+        command = command + f" --{k} {{{i}}} "
+
+    args_list = product(*values)
+
+    with open(outfile,'w') as of:
+        for args in args_list:
+            of.write(command.format(*args) + '\n')
+
+if __name__ == '__main__':
+    fire.Fire(main)
diff --git a/simulations/run_simulation.sbatch b/simulations/run_simulation.sbatch
index 20953ae..835f39b 100644
--- a/simulations/run_simulation.sbatch
+++ b/simulations/run_simulation.sbatch
@@ -11,7 +11,7 @@
 #SBATCH --mem=8G
 #SBATCH --cpus-per-task=1
 #SBATCH --ntasks-per-node=1
-#SBATCH --chdir /gscratch/comdata/users/nathante/ml_measurement_error/mi_simulations
+#SBATCH --chdir /gscratch/comdata/users/nathante/ml_measurement_error_public/simulations
 #SBATCH --output=simulation_jobs/%A_%a.out
 #SBATCH --error=simulation_jobs/%A_%a.out