X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/8ac33c14d7e7874bf283aa9c252fa06566dc8b15..d8bc08f18f8c2128369ee959196e0e6080a11689:/simulations/Makefile?ds=inline

diff --git a/simulations/Makefile b/simulations/Makefile
index e6a3bbe..feeeaa5 100644
--- a/simulations/Makefile
+++ b/simulations/Makefile
@@ -148,21 +148,204 @@ robustness_1_dv.feather: robustness_1_dv_jobs
 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
+
+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 $@
+
+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 $@
+
+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 $@
+
+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 $@
+
+START=0
+END_1=$(shell cat robustness_2_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_2_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_2_jobs_p3 | wc -l)
+END_4=$(shell cat robustness_2_jobs_p4 | wc -l)
+STEP=1000
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+ITEMS_4=$(shell seq $(START) $(STEP) $(END_4))
+
+robustness_2.feather: robustness_2_jobs_p1 robustness_2_jobs_p2 robustness_2_jobs_p3 robustness_2_jobs_p4
+	$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_jobs_p1)
+	$(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_jobs_p2;)
+	$(foreach item,$(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_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.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 $@
+
+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.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 $@
+
+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.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 $@
+
+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.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 $@
+
+START=0
+END_1=$(shell cat robustness_2_dv_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_2_dv_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_2_dv_jobs_p3 | wc -l)
+END_4=$(shell cat robustness_2_dv_jobs_p4 | wc -l)
+STEP=1000
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+ITEMS_4=$(shell seq $(START) $(STEP) $(END_4))
+
+robustness_2_dv.feather: robustness_2_dv_jobs_p1 robustness_2_dv_jobs_p2 robustness_2_dv_jobs_p3 robustness_2_dv_jobs_p4
+	$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_dv_jobs_p1)
+	$(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_2_dv_jobs_p2;)
+	$(foreach item,$(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_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 $@
+
+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 $@
+
+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 $@
+
+START=0
+END_1=$(shell cat robustness_3_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_3_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_3_jobs_p3 | wc -l)
+
+STEP=1000
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+
+robustness_3.feather: robustness_3_jobs_p1 robustness_3_jobs_p2 robustness_3_jobs_p3
+	$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_jobs_p1)
+	$(foreach item,$(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_dv_jobs_p1: 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.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 $@
+	${srun} $< --command 'Rscript 03_depvar.R'  --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_3.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"B0":[0.5,0.6], "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.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 $@
 
+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.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 $@
+
+START=0
+END_1=$(shell cat robustness_3_dv_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_3_dv_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_3_dv_jobs_p3 | wc -l)
 
-START=1
-END=$(shell cat robustness_2_jobs | wc -l)
 STEP=1000
-ITEMS=$(shell seq $(START) $(STEP) $(END))
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+
+robustness_3_dv.feather: robustness_3_dv_jobs_p1 robustness_3_dv_jobs_p2 robustness_3_dv_jobs_p3
+	$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_dv_jobs_p1)
+	$(foreach item,$(ITEMS_2),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_dv_jobs_p2;)
+	$(foreach item,$(ITEMS_3),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_3_dv_jobs_p3;)
+
 
-robustness_2.feather: robustness_2_jobs
-	$(foreach item,$(ITEMS),sbatch --wait --verbose --array=$(shell expr $(item))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 $<)
+
+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 $@
+
+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 $@
+
+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 $@
+
+START=0
+END_1=$(shell cat robustness_4_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_4_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_4_jobs_p3 | wc -l)
+END_4=$(shell cat robustness_4_jobs_p3 | wc -l)
+
+STEP=1000
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+ITEMS_4=$(shell seq $(START) $(STEP) $(END_4))
+
+robustness_4.feather: robustness_4_jobs_p1 robustness_4_jobs_p2 robustness_4_jobs_p3
+	$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_4_jobs_p1)
+	$(foreach item,$(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_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_4.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"B0":[0.5] "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],z_bias=[0,0.1]}' --outfile $@
+
+robustness_4_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_4.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3],"B0":[0.5] "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],z_bias=[0.25,0.4]}' --outfile $@
+
+robustness_4_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_4.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "B0":[0.5], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],z_bias=[0.55,0.7]}' --outfile $@
+robustness_4_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_4.feather"],"y_explained_variance":${explained_variances},  "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "B0":[0.5], "outcome_formula":["y~x+z"], "prediction_accuracy":[0.85],z_bias=[0.85,1]}' --outfile $@
+
+
+START=0
+END_1=$(shell cat robustness_4_dv_jobs_p1 | wc -l)
+END_2=$(shell cat robustness_4_dv_jobs_p2 | wc -l)
+END_3=$(shell cat robustness_4_dv_jobs_p3 | wc -l)
+
+STEP=1000
+ONE=1
+ITEMS_1=$(shell seq $(START) $(STEP) $(END_1))
+ITEMS_2=$(shell seq $(START) $(STEP) $(END_2))
+ITEMS_3=$(shell seq $(START) $(STEP) $(END_3))
+
+robustness_4_dv.feather: robustness_4_dv_jobs_p1 robustness_4_dv_jobs_p2 robustness_4_dv_jobs_p3
+	$(foreach item,$(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;)
 
 #	
 clean: