X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/b8d2048cc5338fbd872b55029c3e5d01c739a397..acb119418aef75dfa1e882f975ae0638e7736a07:/simulations/Makefile?ds=sidebyside diff --git a/simulations/Makefile b/simulations/Makefile index 3e8fdd5..821280b 100644 --- a/simulations/Makefile +++ b/simulations/Makefile @@ -8,7 +8,7 @@ explained_variances=[0.1] all:main supplement main:remembr.RDS -supplement:robustness_1.RDS robustness_1_dv.RDS robustness_2.RDS robustness_2_dv.RDS robustness_3.RDS robustness_3_dv.RDS robustness_4.RDS robustness_4_dv.RDS +supplement:robustness_1.RDS robustness_1_dv.RDS robustness_2.RDS robustness_2_dv.RDS robustness_3.RDS robustness_3_dv.RDS robustness_3_proflik.RDS robustness_3_dv_proflik.RDS robustness_4.RDS robustness_4_dv.RDS srun=sbatch --wait --verbose run_job.sbatch @@ -30,7 +30,7 @@ example_1_jobs: 01_two_covariates.R simulation_base.R grid_sweep.py pl_methods.R example_1.feather: example_1_jobs rm -f example_1.feather 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=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-$(shell cat example_1_jobs | wc -l) run_simulation.sbatch 0 example_1_jobs @@ -41,10 +41,10 @@ example_2_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py pl_metho example_2.feather: example_2_jobs rm -f example_2.feather sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 example_2_jobs - sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_2_jobs + sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_2_jobs sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 example_2_jobs sbatch --wait --verbose --array=3001-4000 run_simulation.sbatch 0 example_2_jobs - sbatch --wait --verbose --array=4001-$(shell cat example_2_jobs | wc -l) run_simulation.sbatch 0 example_2_jobs + sbatch --wait --verbose --array=4001-$(shell cat example_2_jobs | wc -l) # example_2_B_jobs: example_2_B.R @@ -55,23 +55,24 @@ example_2.feather: example_2_jobs # sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_2_B_jobs example_3_jobs: 03_depvar.R simulation_base.R grid_sweep.py pl_methods.R - sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "Bxy":[0.7],"Bzy":[-0.7],"seed":${seeds}, "outfile":["example_3.feather"], "y_explained_variance":${explained_variances}}' --outfile example_3_jobs + sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "Bxy":[0.7],"Bzy":[-0.7],"Bzx":[1],"seed":${seeds}, "outfile":["example_3.feather"], "y_explained_variance":${explained_variances}}' --outfile example_3_jobs example_3.feather: example_3_jobs rm -f example_3.feather sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 example_3_jobs - sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_3_jobs - sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 example_3_jobs + sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_3_jobs + sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 example_3_jobs sbatch --wait --verbose --array=3001-4000 run_simulation.sbatch 0 example_3_jobs sbatch --wait --verbose --array=4001-$(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 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":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.3], "prediction_accuracy":[0.73]}' --outfile example_4_jobs + sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"Bxy":[0.7],"Bzy":[-0.7],"Bzx":[1], "m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "z_bias":[-0.5], "prediction_accuracy":[0.73]}' --outfile example_4_jobs example_4.feather: example_4_jobs 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=2001-3001 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 @@ -86,63 +87,73 @@ remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feat ${srun} Rscript plot_dv_example.R --infile example_4.feather --name "plot.df.example.4" -robustness_1_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py - sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${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 - - - START=0 STEP=1000 ONE=1 -robustness_1.feather: robustness_1_jobs - $(eval END_1!=cat robustness_1_jobs | wc -l) - $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) - rm -f robustness_1.feather - sbatch --wait --verbose --array=1-1000 run_simulation.sbatch 0 robustness_1_jobs - sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 robustness_1_jobs - sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 robustness_1_jobs - sbatch --wait --verbose --array=3001-4000 run_simulation.sbatch 0 robustness_1_jobs - sbatch --wait --verbose --array=4001-$(shell cat robustness_1_jobs | wc -l) run_simulation.sbatch 0 robustness_1_jobs +robustness_Ns=[1000,5000] +robustness_robustness_ms=[100,200] + +#in robustness 1 / example 2 misclassification is correlated with Y. +robustness_1_jobs_p1: 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":[1000],"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_1.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3,0],"Bxy":[0.3],"Bzx":[1,0], "outcome_formula":["y~x+z"], "z_bias":[0, 0.5], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~1"]}' --outfile robustness_1_jobs_p1 - $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_jobs;) +robustness_1_jobs_p2: 02_indep_differential.R simulation_base.R grid_sweep.py + sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":[5000],"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_1.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3,0],"Bxy":[0.3],"Bzx":[1,0], "outcome_formula":["y~x+z"], "z_bias":[0, 0.5], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~1"]}' --outfile robustness_1_jobs_p2 -robustness_1.RDS: robustness_1.feather +robustness_1.feather: robustness_1_jobs_p1 robustness_1_jobs_p2 + rm -f $@ + $(eval END_1!=cat robustness_1_jobs_p1 | wc -l) + $(eval ITEROBUSTNESS_MS_1!=seq $(START) $(STEP) $(END_1)) + $(eval END_2!=cat robustness_1_jobs_p2 | wc -l) + $(eval ITEROBUSTNESS_MS_2!=seq $(START) $(STEP) $(END_2)) + + $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_jobs_p1;) + $(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_jobs_p2;) + +robustness_1.RDS: robustness_1.feather summarize_estimator.R 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 - ${srun} grid_sweep.py --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${Ns},"Bxy":[0.7],"Bzy":[-0.7],"m":${ms}, "seed":${seeds}, "outfile":["robustness_1_dv.feather"], "proxy_formula":["w_pred~y"],"z_bias":[0.5]}' --outfile robustness_1_dv_jobs +# when Bzy is 0 and zbias is not zero, we have the case where P(W|Y,X,Z) has an omitted variable that is conditionanlly independent from Y. Note that X and Z are independent in this scenario. +robustness_1_dv_jobs_p1: simulation_base.R 04_depvar_differential.R grid_sweep.py + ${srun} grid_sweep.py --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":[1000],"Bzx":[1], "Bxy":[0.7,0],"Bzy":[-0.7,0],"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_1_dv.feather"], "proxy_formula":["w_pred~y"],"z_bias":[-0.5]}' --outfile robustness_1_dv_jobs_p1 -robustness_1_dv.feather: robustness_1_dv_jobs - rm -f robustness_1_dv.feather - $(eval END_1!=cat robustness_1_dv_jobs | wc -l) - $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) - $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_dv_jobs;) +robustness_1_dv_jobs_p2: simulation_base.R 04_depvar_differential.R grid_sweep.py + ${srun} grid_sweep.py --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":[5000],"Bzx":[1], "Bxy":[0.7,0],"Bzy":[-0.7,0],"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_1_dv.feather"], "proxy_formula":["w_pred~y"],"z_bias":[-0.5]}' --outfile robustness_1_dv_jobs_p2 +robustness_1_dv.feather: robustness_1_dv_jobs_p1 robustness_1_dv_jobs_p2 + rm -f $@ + $(eval END_1!=cat robustness_1_dv_jobs_p1 | wc -l) + $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) + $(eval END_2!=cat robustness_1_dv_jobs_p2 | wc -l) + $(eval ITEMS_2!=seq $(START) $(STEP) $(END_1)) + $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_dv_jobs_p1;) + $(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_dv_jobs_p2;) -robustness_1_dv.RDS: robustness_1_dv.feather +robustness_1_dv.RDS: robustness_1_dv.feather summarize_estimator.R rm -f $@ ${srun} Rscript plot_dv_example.R --infile $< --name "robustness_1_dv" --remember-file $@ robustness_2_jobs_p1: 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":[0.60,0.65]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_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+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.60,0.65]}' --outfile $@ robustness_2_jobs_p2: 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":[0.70,0.75]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_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+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.70,0.75]}' --outfile $@ robustness_2_jobs_p3: 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":[0.80,0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_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+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.80,0.85]}' --outfile $@ robustness_2_jobs_p4: 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":[0.90,0.95]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_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+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.90,0.95]}' --outfile $@ robustness_2.feather: robustness_2_jobs_p1 robustness_2_jobs_p2 robustness_2_jobs_p3 robustness_2_jobs_p4 + rm $@ $(eval END_1!=cat robustness_2_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_2_jobs_p2 | wc -l) @@ -157,27 +168,28 @@ robustness_2.feather: robustness_2_jobs_p1 robustness_2_jobs_p2 robustness_2_job $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_jobs_p3;) $(foreach item,$(ITEMS_4),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_jobs_p4;) -robustness_2.RDS: plot_example.R robustness_2.feather +robustness_2.RDS: plot_example.R robustness_2.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_2" --remember-file $@ robustness_2_dv_jobs_p1: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${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":[0.60,0.65]}' --outfile $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_2_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.60,0.65]}' --outfile $@ robustness_2_dv_jobs_p2: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${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":[0.70,0.75]}' --outfile $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_2_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.70,0.75]}' --outfile $@ robustness_2_dv_jobs_p3: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${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":[0.80,0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_2_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.80,0.85]}' --outfile $@ robustness_2_dv_jobs_p4: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${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 $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_2_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "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 + rm -f $@ $(eval END_1!=cat robustness_2_dv_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_2_dv_jobs_p2 | wc -l) @@ -192,24 +204,40 @@ robustness_2_dv.feather: robustness_2_dv_jobs_p1 robustness_2_dv_jobs_p2 robustn $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_dv_jobs_p3;) $(foreach item,$(ITEMS_4),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_dv_jobs_p4;) -robustness_2_dv.RDS: plot_example.R robustness_2_dv.feather +robustness_2_dv.RDS: plot_dv_example.R robustness_2_dv.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_2_dv" --remember-file $@ +robustness_3_proflik_jobs: grid_sweep.py 01_two_covariates.R simulation_base.R grid_sweep.py + rm -f $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":[1000],"m":[100], "seed":${seeds}, "outfile":["robustness_3_proflik.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"Px":[0.5,0.6,0.7,0.8,0.9,0.95], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85], "confint_method":['spline']}' --outfile $@ + +robustness_3_proflik.feather: robustness_3_proflik_jobs + rm -f $@ + $(eval END_1!=cat robustness_3_proflik_jobs | wc -l) + $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) + $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_proflik_jobs;) + +robustness_3_proflik.RDS: plot_example.R robustness_3_proflik.feather summarize_estimator.R + rm -f $@ + ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_3_proflik" --remember-file $@ + + robustness_3_jobs_p1: 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_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"Px":[0.5,0.6], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"Px":[0.5,0.6], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3_jobs_p2: 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_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"Px":[0.7,0.8], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"Px":[0.7,0.8], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3_jobs_p3: 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_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"Px":[0.9,0.95], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 01_two_covariates.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"Px":[0.9,0.95], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3.feather: robustness_3_jobs_p1 robustness_3_jobs_p2 robustness_3_jobs_p3 + rm -f $@ $(eval END_1!=cat robustness_3_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_3_jobs_p2 | wc -l) @@ -221,26 +249,42 @@ robustness_3.feather: robustness_3_jobs_p1 robustness_3_jobs_p2 robustness_3_job $(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_jobs_p2;) $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_jobs_p3;) -robustness_3.RDS: plot_example.R robustness_3.feather +robustness_3.RDS: plot_example.R robustness_3.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_3" --remember-file $@ -robustness_3_dv_jobs_p1: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py +robustness_3_dv_proflik_jobs: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py + rm -f $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":[1000],"m":[100], "seed":${seeds}, "outfile":["robustness_3_dv_proflik.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"B0":[0,0.405,0.846,1.386,2.197,2.944], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"confint_method":['spline']}' --outfile $@ + +robustness_3_dv_proflik.feather: robustness_3_dv_proflik_jobs + rm -f $@ + $(eval END_1!=cat robustness_3_dv_proflik_jobs | wc -l) + $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) + $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_dv_proflik_jobs;) + +robustness_3_dv_proflik.RDS: plot_dv_example.R robustness_3_dv_proflik.feather summarize_estimator.R rm -f $@ - ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"B0":[0.5,0.6], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_3_dv_proflik" --remember-file $@ + + + robustness_3_dv_jobs_p1: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py + rm -f $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"B0":[0,0.405], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3_dv_jobs_p2: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"B0":[0.7,0.8], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1],"B0":[0.847,1.386], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3_dv_jobs_p3: grid_sweep.py 03_depvar.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "B0":[0.9,0.95], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_3_dv.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "B0":[2.197,2.944], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85]}' --outfile $@ robustness_3_dv.feather: robustness_3_dv_jobs_p1 robustness_3_dv_jobs_p2 robustness_3_dv_jobs_p3 + rm -f $@ $(eval END_1!=cat robustness_3_dv_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_3_dv_jobs_p2 | wc -l) @@ -253,28 +297,26 @@ robustness_3_dv.feather: robustness_3_dv_jobs_p1 robustness_3_dv_jobs_p2 robustn $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_dv_jobs_p3;) -robustness_3_dv.RDS: plot_dv_example.R robustness_3_dv.feather +robustness_3_dv.RDS: plot_dv_example.R robustness_3_dv.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_3_dv" --remember-file $@ + robustness_4_jobs_p1: grid_sweep.py 02_indep_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4.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":[0.85],"y_bias":[-1,-0.85]}' --outfile $@ + ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85],"y_bias":[-2.944,-2.197]}' --outfile $@ robustness_4_jobs_p2: grid_sweep.py 02_indep_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4.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":[0.85], "y_bias":[-0.70,-0.55]}' --outfile $@ + ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85], "y_bias":[-1.386,-0.846]}' --outfile $@ robustness_4_jobs_p3: grid_sweep.py 02_indep_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4.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":[0.85],"y_bias":[-0.4,-0.25]}' --outfile $@ - -robustness_4_jobs_p4: grid_sweep.py 02_indep_differential.R simulation_base.R grid_sweep.py - rm -f $@ - ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4.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":[0.85],"y_bias":[-0.1,0]}' --outfile $@ + ${srun} $< --command 'Rscript 02_indep_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[1], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~z"], "prediction_accuracy":[0.85],"y_bias":[-0.405,-0.25]}' --outfile $@ robustness_4.feather: robustness_4_jobs_p1 robustness_4_jobs_p2 robustness_4_jobs_p3 + rm -f $@ $(eval END_1!=cat robustness_4_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_4_jobs_p2 | wc -l) @@ -286,48 +328,52 @@ robustness_4.feather: robustness_4_jobs_p1 robustness_4_jobs_p2 robustness_4_job $(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_jobs_p2;) $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_jobs_p3;) -robustness_4.RDS: plot_example.R robustness_4.feather +robustness_4.RDS: plot_example.R robustness_4.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_4" --remember-file $@ -# '{"N":${Ns},"Bxy":[0.7],"Bzy":[-0.7],"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.5]}' --outfile example_4_jobs +# '{"N":${robustness_Ns},"Bxy":[0.7],"Bzy":[-0.7],"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.5]}' --example_4_jobs robustness_4_dv_jobs_p1: grid_sweep.py 04_depvar_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0,0.1]}' --outfile $@ + ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0,0.1]}' --outfile $@ robustness_4_dv_jobs_p2: grid_sweep.py 04_depvar_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0.25,0.4]}' --outfile $@ + ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0.25,0.405]}' --outfile $@ robustness_4_dv_jobs_p3: grid_sweep.py 04_depvar_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7],"outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0.55,0.7]}' --outfile $@ + ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"], "Bzy":[-0.7],"Bxy":[0.7],"Bzx":[1],"outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0.846,1.386]}' --outfile $@ robustness_4_dv_jobs_p4: grid_sweep.py 04_depvar_differential.R simulation_base.R grid_sweep.py rm -f $@ - ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"],"Bzy":[-0.7],"Bxy":[0.7], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[0.85,1]}' --outfile $@ + ${srun} $< --command 'Rscript 04_depvar_differential.R' --arg_dict '{"N":${robustness_Ns},"m":${robustness_ms}, "seed":${seeds}, "outfile":["robustness_4_dv.feather"],"Bzy":[-0.7],"Bxy":[0.7],"Bzx":[1], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],"z_bias":[2.197,2.944]}' --outfile $@ -robustness_4_dv.feather: robustness_4_dv_jobs_p1 robustness_4_dv_jobs_p2 robustness_4_dv_jobs_p3 +robustness_4_dv.feather: robustness_4_dv_jobs_p1 robustness_4_dv_jobs_p2 robustness_4_dv_jobs_p3 robustness_4_dv_jobs_p4 + rm -f $@ $(eval END_1!=cat robustness_4_dv_jobs_p1 | wc -l) $(eval ITEMS_1!=seq $(START) $(STEP) $(END_1)) $(eval END_2!=cat robustness_4_dv_p2 | wc -l) $(eval ITEMS_2!=seq $(START) $(STEP) $(END_2)) $(eval END_3!=cat robustness_4_dv_p3 | wc -l) $(eval ITEMS_3!=seq $(START) $(STEP) $(END_3)) + $(eval END_3!=cat robustness_4_dv_p4 | wc -l) + $(eval ITEMS_3!=seq $(START) $(STEP) $(END_3)) + $(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_dv_jobs_p1;) $(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_dv_jobs_p2;) $(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_dv_jobs_p3;) + $(foreach item,$(ITEMS_4),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_dv_jobs_p4;) -robustness_4_dv.RDS: plot_dv_example.R robustness_4_dv.feather +robustness_4_dv.RDS: plot_dv_example.R robustness_4_dv.feather summarize_estimator.R rm -f $@ ${srun} Rscript $< --infile $(word 2, $^) --name "robustness_4" --remember-file $@ - clean_main: rm -f remembr.RDS rm -f example_1_jobs @@ -359,5 +405,4 @@ clean_all: # sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_B_mecor_jobs - .PHONY: supplement