groceryheist/ml_measurement_error_public
1
0
Fork 0
Code Activity

Make summarize estimator group correctly for robustness checks.

Browse Source 
Also fix a possible bug in the MI logic and simplify the error
correction formula in example 2.
This commit is contained in:
Nathan TeBlunthuis
2023-02-11 12:26:48 -08:00
parent c45ea9dfeb
commit b8d2048cc5
5 changed files with 103 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
simulations/Makefile
View File

@@ -36,7 +36,7 @@ example_1.feather: example_1_jobs
sbatch --wait --verbose --array=4001-$(shell cat example_1_jobs | wc -l) run_simulation.sbatch 0 example_1_jobs
example_2_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py pl_methods.R
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y*z*x"]}' --outfile example_2_jobs
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+z+x"]}' --outfile example_2_jobs
example_2.feather: example_2_jobs
rm -f example_2.feather
@@ -66,10 +66,10 @@ example_3.feather: example_3_jobs
sbatch --wait --verbose --array=4001-$(shell cat example_3_jobs | wc -l) run_simulation.sbatch 0 example_3_jobs
example_4_jobs: 04_depvar_differential.R simulation_base.R grid_sweep.py pl_methods.R
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"Bxy":[0.7],"Bzy":[-0.7],"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.5]}' --outfile example_4_jobs
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"Bxy":[0.7],"Bzy":[-0.7],"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.3], "prediction_accuracy":[0.73]}' --outfile example_4_jobs
example_4.feather: example_4_jobs
rm -f example_4.feather
rm -f example_4.feather
sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 example_4_jobs
sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_4_jobs
sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 example_4_jobs
@@ -86,41 +86,6 @@ remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feat
${srun} Rscript plot_dv_example.R --infile example_4.feather --name "plot.df.example.4"
irr_Ns = [1000]
irr_ms = [150,300,600]
irr_seeds=${seeds}
irr_explained_variances=${explained_variances}
irr_coder_accuracy=[0.80]
example_5_jobs: 05_irr_indep.R irr_simulation_base.R grid_sweep.py pl_methods.R measerr_methods.R
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 05_irr_indep.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_5.feather"], "y_explained_variance":${irr_explained_variances}, "coder_accuracy":${irr_coder_accuracy}}' --outfile example_5_jobs
example_5.feather:example_5_jobs
rm -f example_5.feather
sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 example_5_jobs
sbatch --wait --verbose --array=1001-$(shell cat example_5_jobs | wc -l) run_simulation.sbatch 1000 example_5_jobs
# sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 2000 example_5_jobs
# sbatch --wait --verbose --array=3001-4000 run_simulation.sbatch 3000 example_5_jobs
# sbatch --wait --verbose --array=2001-$(shell cat example_5_jobs | wc -l) run_simulation.sbatch 4000 example_5_jobs
# example_6_jobs: 06_irr_dv.R irr_dv_simulation_base.R grid_sweep.py pl_methods.R
# sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 06_irr_dv.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_6.feather"], "y_explained_variance":${irr_explained_variances},"coder_accuracy":${irr_coder_accuracy}}' --outfile example_6_jobs
# example_6.feather:example_6_jobs
# rm -f example_6.feather
# sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 example_6_jobs
# sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 1000 example_6_jobs
# sbatch --wait --verbose --array=2001-$(shell cat example_6_jobs | wc -l) run_simulation.sbatch 2000 example_6_jobs
remember_irr.RDS: example_5.feather plot_irr_example.R plot_irr_dv_example.R summarize_estimator.R
rm -f remember_irr.RDS
sbatch --wait --verbose run_job.sbatch Rscript plot_irr_example.R --infile example_5.feather --name "plot.df.example.5"
# sbatch --wait --verbose run_job.sbatch Rscript plot_irr_dv_example.R --infile example_6.feather --name "plot.df.example.6"
robustness_1_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_1.feather"],"y_explained_variance":${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~1"]}' --outfile robustness_1_jobs
@@ -210,7 +175,7 @@ robustness_2_dv_jobs_p3: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.
robustness_2_dv_jobs_p4: grid_sweep.py 03_depvar.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_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.90,0.95]}' --outfile $@
${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_2_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.90,0.95]}' --outfile $@
robustness_2_dv.feather: robustness_2_dv_jobs_p1 robustness_2_dv_jobs_p2 robustness_2_dv_jobs_p3 robustness_2_dv_jobs_p4
$(eval END_1!=cat robustness_2_dv_jobs_p1 | wc -l)
@@ -361,8 +326,22 @@ robustness_4_dv.RDS: plot_dv_example.R robustness_4_dv.feather
rm -f $@
${srun} Rscript $< --infile $(word 2, $^) --name "robustness_4" --remember-file $@
clean_main:
rm -f remembr.RDS
rm -f example_1_jobs
rm -f example_2_jobs
rm -f example_3_jobs
rm -f example_4_jobs
rm -f example_1.feather
rm -f example_2.feather
rm -f example_3.feather
rm -f example_4.feather
#
clean:
clean_all:
rm *.feather
rm -f remembr.RDS
rm -f remembr*.RDS