]> code.communitydata.science - ml_measurement_error_public.git/blobdiff - simulations/Makefile
projects / ml_measurement_error_public.git / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
Add exploratory data analysis to come up with a real-data example.
[ml_measurement_error_public.git] / simulations / Makefile
diff --git a/simulations/Makefile b/simulations/Makefile
index d278c8c2aeb8f0bfc2e7482bdb9b538491a1fd16..b3ab77a3c62d773b5b577940c8e1e373bac955d5 100644 (file)
--- a/simulations/Makefile
+++ b/simulations/Makefile
@@ -1,20 +1,21 @@
 
 SHELL=bash
 
 
 SHELL=bash
 
-Ns=[1000, 2000, 4000, 8000]
-ms=[100, 200, 400, 800]
-seeds=[$(shell seq -s, 1 100)]
+Ns=[1000, 5000, 10000]
+ms=[100, 200, 400]
+seeds=[$(shell seq -s, 1 500)]
 explained_variances=[0.1]
 
 explained_variances=[0.1]
 
-all:remembr.RDS
+all:remembr.RDS remember_irr.RDS
+supplement: remember_robustness_misspec.RDS
 
 
-srun=srun -A comdata -p compute-bigmem --time=6:00:00 --mem 4G -c 1
+srun=sbatch --wait --verbose run_job.sbatch
 
 
 joblists:example_1_jobs example_2_jobs example_3_jobs
 
 # test_true_z_jobs: test_true_z.R simulation_base.R
 
 
 joblists:example_1_jobs example_2_jobs example_3_jobs
 
 # test_true_z_jobs: test_true_z.R simulation_base.R
-#      grid_sweep.py --command "Rscript test_true_z.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["test_true_z.feather"], "y_explained_variancevari":${explained_variances}, "Bzx":${Bzx}}' --outfile test_true_z_jobsb
+#      sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript test_true_z.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["test_true_z.feather"], "y_explained_variancevari":${explained_variances}, "Bzx":${Bzx}}' --outfile test_true_z_jobsb
 
 # test_true_z.feather: test_true_z_jobs 
 #      rm -f test_true_z.feather
 
 # test_true_z.feather: test_true_z_jobs 
 #      rm -f test_true_z.feather
@@ -22,50 +23,128 @@ joblists:example_1_jobs example_2_jobs example_3_jobs
 #      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 test_true_z_jobs
 
 
 #      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 test_true_z_jobs
 
 
-example_1_jobs: 01_two_covariates.R simulation_base.R
-       grid_sweep.py --command "Rscript 01_two_covariates.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"], "y_explained_variance":${explained_variances}, "Bzx":[0.1]}' --outfile example_1_jobs
+example_1_jobs: 01_two_covariates.R simulation_base.R grid_sweep.py pl_methods.R
+       sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 01_two_covariates.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"], "y_explained_variance":${explained_variances}, "Bzx":[1]}' --outfile example_1_jobs
 
 example_1.feather: example_1_jobs 
        rm -f example_1.feather
 
 example_1.feather: example_1_jobs 
        rm -f example_1.feather
-       sbatch --wait --verbose --array=1-$(shell cat example_1_jobs | wc -l) run_simulation.sbatch 0 example_1_jobs
-#      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_1_jobs
+       sbatch --wait --verbose --array=1-1000  run_simulation.sbatch 0 example_1_jobs
+       sbatch --wait --verbose --array=1001-2000  run_simulation.sbatch 0 example_1_jobs
+       sbatch --wait --verbose --array=2001-3000  run_simulation.sbatch 0 example_1_jobs
+       sbatch --wait --verbose --array=3001-4000  run_simulation.sbatch 0 example_1_jobs
+       sbatch --wait --verbose --array=4001-$(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 --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":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y*z*x"], "truth_formula":["x~z"]}' --outfile example_2_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
 
 example_2.feather: example_2_jobs 
        rm -f example_2.feather
 
 example_2.feather: example_2_jobs 
        rm -f example_2.feather
-       sbatch --wait --verbose --array=1-$(shell cat example_2_jobs | wc -l) run_simulation.sbatch 0 example_2_jobs
-#      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_jobs
+       sbatch --wait --verbose --array=1-1000  run_simulation.sbatch 0 example_2_jobs
+       sbatch --wait --verbose --array=1001-2000  run_simulation.sbatch 0 example_2_jobs
+       sbatch --wait --verbose --array=2001-3000  run_simulation.sbatch 0 example_2_jobs
+       sbatch --wait --verbose --array=3001-4000  run_simulation.sbatch 0 example_2_jobs
+       sbatch --wait --verbose --array=4001-$(shell cat example_2_jobs | wc -l)  run_simulation.sbatch 0 example_2_jobs
+
 
 # example_2_B_jobs: example_2_B.R
 
 # example_2_B_jobs: example_2_B.R
-#      grid_sweep.py --command "Rscript example_2_B.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B.feather"]}' --outfile example_2_B_jobs
+#      sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript example_2_B.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B.feather"]}' --outfile example_2_B_jobs
 
 # example_2_B.feather: example_2_B_jobs
 #      rm -f example_2_B.feather
 #      sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_2_B_jobs
 
 
 # example_2_B.feather: example_2_B_jobs
 #      rm -f example_2_B.feather
 #      sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_2_B_jobs
 
-example_3_jobs: 03_depvar.R simulation_base.R
-       grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_3.feather"], "y_explained_variance":${explained_variances}}' --outfile example_3_jobs
+example_3_jobs: 03_depvar.R simulation_base.R grid_sweep.py pl_methods.R
+       sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "Bxy":[0.7],"Bzy":[-0.7],"seed":${seeds}, "outfile":["example_3.feather"], "y_explained_variance":${explained_variances}}' --outfile example_3_jobs
 
 example_3.feather: example_3_jobs
        rm -f example_3.feather 
 
 example_3.feather: example_3_jobs
        rm -f example_3.feather 
-       sbatch --wait --verbose --array=1-$(shell cat example_3_jobs | wc -l)  run_simulation.sbatch 0 example_3_jobs
+       sbatch --wait --verbose --array=1-1000  run_simulation.sbatch 0 example_3_jobs
+       sbatch --wait --verbose --array=1001-2000  run_simulation.sbatch 0 example_3_jobs
+       sbatch --wait --verbose --array=2001-3000  run_simulation.sbatch 0 example_3_jobs
+       sbatch --wait --verbose --array=3001-4000  run_simulation.sbatch 0 example_3_jobs
+       sbatch --wait --verbose --array=4001-$(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 --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "y_explained_variance":${explained_variances}}' --outfile example_4_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
 
 example_4.feather: example_4_jobs
        rm -f example_4.feather 
 
 example_4.feather: example_4_jobs
        rm -f example_4.feather 
-       sbatch --wait --verbose --array=1-$(shell cat example_4_jobs | wc -l)  run_simulation.sbatch 0 example_4_jobs
+       sbatch --wait --verbose --array=1-1000  run_simulation.sbatch 0 example_4_jobs
+       sbatch --wait --verbose --array=1001-2000  run_simulation.sbatch 0 example_4_jobs
+       sbatch --wait --verbose --array=2001-3000  run_simulation.sbatch 0 example_4_jobs
+       sbatch --wait --verbose --array=3001-4000  run_simulation.sbatch 0 example_4_jobs
+       sbatch --wait --verbose --array=4001-$(shell cat example_4_jobs | wc -l)  run_simulation.sbatch 0 example_4_jobs
+
 
 
-remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feather plot_example.R plot_dv_example.R
+
+remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feather plot_example.R plot_dv_example.R summarize_estimator.R
        rm -f remembr.RDS
        ${srun} Rscript plot_example.R --infile example_1.feather --name "plot.df.example.1"
        ${srun} Rscript plot_example.R --infile example_2.feather --name "plot.df.example.2"
        ${srun} Rscript plot_dv_example.R --infile example_3.feather --name "plot.df.example.3"
        ${srun} Rscript plot_dv_example.R --infile example_4.feather --name "plot.df.example.4"
 
        rm -f remembr.RDS
        ${srun} Rscript plot_example.R --infile example_1.feather --name "plot.df.example.1"
        ${srun} Rscript plot_example.R --infile example_2.feather --name "plot.df.example.2"
        ${srun} Rscript plot_dv_example.R --infile example_3.feather --name "plot.df.example.3"
        ${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":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~1"]}' --outfile robustness_1_jobs
+
+
+
+robustness_1.feather: robustness_1_jobs
+       rm -f robustness_1.feather
+       sbatch --wait --verbose --array=1-$(shell cat robustness_1_jobs | wc -l)  run_simulation.sbatch 0 robustness_1_jobs
+
+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':${explained_variances}, 'proxy_formula':['w_pred~y']}\" --outfile robustness_1_dv_jobs"
+
+
+robustness_1_dv.feather: robustness_1_dv_jobs
+       rm -f robustness_1_dv.feather
+       sbatch --wait --verbose --array=1-$(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"
+
+
 clean:
        rm *.feather
        rm -f remembr.RDS
 clean:
        rm *.feather
        rm -f remembr.RDS
@@ -73,7 +152,7 @@ clean:
 #      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_B_jobs
 
 # example_2_B_mecor_jobs:
 #      sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_B_jobs
 
 # example_2_B_mecor_jobs:
-#      grid_sweep.py --command "Rscript example_2_B_mecor.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B_mecor.feather"]}' --outfile example_2_B_mecor_jobs
+#      sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript example_2_B_mecor.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B_mecor.feather"]}' --outfile example_2_B_mecor_jobs
 
 # example_2_B_mecor.feather:example_2_B_mecor.R example_2_B_mecor_jobs
 #      rm -f example_2_B_mecor.feather
 
 # example_2_B_mecor.feather:example_2_B_mecor.R example_2_B_mecor_jobs
 #      rm -f example_2_B_mecor.feather
@@ -82,3 +161,4 @@ clean:
 
 
 
 
 
 
+.PHONY: supplement
Project studying methods for accounting for measurement error in variables derived from predictive models.

Community Data Science Collective || Want to submit a patch?