From: Nathan TeBlunthuis <nathante@uw.edu>
Date: Sun, 11 Dec 2022 22:42:06 +0000 (-0800)
Subject: Add another robustness check for varying levels of accuracy.
X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/commitdiff_plain/8ac33c14d7e7874bf283aa9c252fa06566dc8b15?ds=sidebyside;hp=82fe7b0f482a71c95e8ae99f7e6d37b79357506a

Add another robustness check for varying levels of accuracy.
---

diff --git a/simulations/Makefile b/simulations/Makefile
index e595811..e6a3bbe 100644
--- a/simulations/Makefile
+++ b/simulations/Makefile
@@ -126,7 +126,15 @@ robustness_1_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py
 
 robustness_1.feather: robustness_1_jobs
 	rm -f robustness_1.feather
-	sbatch --wait --verbose --array=1-$(shell cat robustness_1_jobs | wc -l)  run_simulation.sbatch 0 robustness_1_jobs
+	sbatch --wait --verbose --array=1-1000  run_simulation.sbatch 0 robustness_1_jobs
+	sbatch --wait --verbose --array=1001-2000  run_simulation.sbatch 0 robustness_1_jobs
+	sbatch --wait --verbose --array=2001-3000  run_simulation.sbatch 0 robustness_1_jobs
+	sbatch --wait --verbose --array=3001-4000  run_simulation.sbatch 0 robustness_1_jobs
+	sbatch --wait --verbose --array=4001-$(shell cat robustness_1_jobs | wc -l)  run_simulation.sbatch 0 robustness_1_jobs
+
+robustness_1.RDS: robustness_1.feather
+	rm -f robustness_1.RDS
+	${srun} Rscript plot_example.R --infile $< --name "robustness_1" --remember-file $@
 
 robustness_1_dv_jobs: simulation_base.R 04_depvar_differential.R grid_sweep.py
 	${srun} bash -c "source ~/.bashrc && grid_sweep.py --command 'Rscript 04_depvar_differential.R' --arg_dict \"{'N':${Ns},'m':${ms}, 'seed':${seeds}, 'outfile':['robustness_1_dv.feather'], 'y_explained_variance':${explained_variances}, 'proxy_formula':['w_pred~y']}\" --outfile robustness_1_dv_jobs"
@@ -137,12 +145,26 @@ robustness_1_dv.feather: robustness_1_dv_jobs
 	sbatch --wait --verbose --array=1-$(shell cat example_3_jobs | wc -l)  run_simulation.sbatch 0 robustness_1_dv_jobs
 
 
-remember_robustness_misspec.RDS: robustness_1.feather robustness_1_dv.feather
-	rm -f remember_robustness_misspec.RDS
-	sbatch --wait --verbose run_job.sbatch Rscript plot_example.R --infile robustness_1.feather --name "plot.df.robustness.1" --remember-file "remember_robustness_misspec.RDS"
-	sbatch --wait --verbose run_job.sbatch Rscript plot_dv_example.R --infile robustness_1_dv.feather --name "plot.df.robustness.1.dv" --remember-file "remember_robustness_mispec.RDS"
+robustness_1_dv.RDS: robustness_1_dv.feather
+	rm -f $@
+	${srun} Rscript plot_dv_example.R --infile $< --name "robustness_1_dv" --outfile $@
+ 
+
+robustness_2_jobs: grid_sweep.py 01_two_covariates.R simulation_base.R grid_sweep.py
+	rm -f $@
+	${srun} $< --command 'Rscript 01_two_covariates.R'  --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_2.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.6,0.73,0.8,0.85,0.9,0.95]}' --outfile $@
+
+
+
+START=1
+END=$(shell cat robustness_2_jobs | wc -l)
+STEP=1000
+ITEMS=$(shell seq $(START) $(STEP) $(END))
 
+robustness_2.feather: robustness_2_jobs
+	$(foreach item,$(ITEMS),sbatch --wait --verbose --array=$(shell expr $(item))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 $<)
 
+#	
 clean:
 	rm *.feather
 	rm -f remembr.RDS
diff --git a/simulations/robustness_check_notes.md b/simulations/robustness_check_notes.md
index e6adc8a..0a287a7 100644
--- a/simulations/robustness_check_notes.md
+++ b/simulations/robustness_check_notes.md
@@ -1,5 +1,14 @@
-# robustness_1.RDS
+# robustness\_1.RDS
 
-Tests how robust the MLE method is when the model for $X$ is less precise. In the main result, we include $Z$ on the right-hand-side of the `truth_formula`. 
+Tests how robust the MLE method for independent variables with differential error is when the model for $X$ is less precise. In the main paper, we include $Z$ on the right-hand-side of the `truth_formula`. 
 In this robustness check, the `truth_formula` is an intercept-only model.
+The stats are in the list named `robustness_1` in the `.RDS` file.
+
+# robustness\_1\_dv.RDS
+
+Like `robustness\_1.RDS` but with a less precise model for $w_pred$.  In the main paper, we included $Z$ in the `outcome_formula`. In this robustness check, we do not.
+
+# robustness_2.RDS
+
+This is just example 1 with varying levels of classifier accuracy.