update simulations code
This commit is contained in:
parent
b8d2048cc5
commit
acb119418a
@ -79,6 +79,7 @@ parser <- add_argument(parser, "--Bzx", help='Effect of z on x', default=0.3)
|
||||
parser <- add_argument(parser, "--Bzy", help='Effect of z on y', default=-0.3)
|
||||
parser <- add_argument(parser, "--Bxy", help='Effect of x on y', default=0.3)
|
||||
parser <- add_argument(parser, "--Px", help='Base rate of x', default=0.5)
|
||||
parser <- add_argument(parser, "--confint_method", help='method for approximating confidence intervals', default='quad')
|
||||
|
||||
args <- parse_args(parser)
|
||||
B0 <- 0
|
||||
@ -89,9 +90,9 @@ Bzx <- args$Bzx
|
||||
|
||||
df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, Bzx, Px, seed=args$seed + 500, y_explained_variance = args$y_explained_variance, prediction_accuracy=args$prediction_accuracy)
|
||||
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, Bzx=Bzx, 'Bzy'=Bzy, 'Px'=Px, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, error='')
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, 'Bzx'=Bzx, 'Bzy'=Bzy, 'Px'=Px, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, confint_method=args$confint_method,error='')
|
||||
|
||||
outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula))
|
||||
outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula),confint_method=args$confint_method)
|
||||
|
||||
outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
|
||||
if(file.exists(args$outfile)){
|
||||
|
||||
@ -141,7 +141,7 @@ parser <- add_argument(parser, "--y_bias", help='coefficient of y on the probabi
|
||||
parser <- add_argument(parser, "--z_bias", help='coefficient of z on the probability a classification is correct', default=0)
|
||||
parser <- add_argument(parser, "--truth_formula", help='formula for the true variable', default="x~z")
|
||||
parser <- add_argument(parser, "--Px", help='base rate of x', default=0.5)
|
||||
|
||||
parser <- add_argument(parser, "--confint_method", help='method for approximating confidence intervals', default='quad')
|
||||
args <- parse_args(parser)
|
||||
|
||||
B0 <- 0
|
||||
@ -159,9 +159,9 @@ if(args$m < args$N){
|
||||
## pc.df <- pc(suffStat=list(C=cor(df.pc),n=nrow(df.pc)),indepTest=gaussCItest,labels=names(df.pc),alpha=0.05)
|
||||
## plot(pc.df)
|
||||
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, 'Bzx'=args$Bzx, 'Bzy'=Bzy, 'Px'=Px, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'y_bias'=args$y_bias,'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, error='')
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, 'Bzx'=args$Bzx, 'Bzy'=Bzy, 'Px'=Px, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'y_bias'=args$y_bias,'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, confint_method=args$confint_method, error='')
|
||||
|
||||
outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula))
|
||||
outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula),confint_method=args$confint_method)
|
||||
|
||||
|
||||
outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
|
||||
|
||||
@ -79,6 +79,7 @@ parser <- add_argument(parser, "--Bzx", help='coeffficient of z on x', default=-
|
||||
parser <- add_argument(parser, "--B0", help='Base rate of y', default=0.5)
|
||||
parser <- add_argument(parser, "--outcome_formula", help='formula for the outcome variable', default="y~x+z")
|
||||
parser <- add_argument(parser, "--proxy_formula", help='formula for the proxy variable', default="w_pred~y")
|
||||
parser <- add_argument(parser, "--confint_method", help='method for getting confidence intervals', default="quad")
|
||||
|
||||
args <- parse_args(parser)
|
||||
|
||||
@ -91,9 +92,9 @@ if(args$m < args$N){
|
||||
df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, Bzx, args$seed, args$prediction_accuracy)
|
||||
|
||||
# result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'x_bias_y0'=args$x_bias_y0,'x_bias_y1'=args$x_bias_y1,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'Bzx'=Bzx,'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'Bzx'=Bzx,'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula, 'confint_method'=args$confint_method)
|
||||
|
||||
outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula))
|
||||
outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula), confint_method=args$confint_method)
|
||||
|
||||
outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
|
||||
|
||||
|
||||
@ -31,12 +31,12 @@ source("simulation_base.R")
|
||||
|
||||
## one way to do it is by adding correlation to x.obs and y that isn't in w.
|
||||
## in other words, the model is missing an important feature of x.obs that's related to y.
|
||||
simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, z_bias=-0.75){
|
||||
simulate_data <- function(N, m, B0, Bxy, Bzy, Bxz=0, seed=0, prediction_accuracy=0.73, z_bias=-0.75){
|
||||
set.seed(seed)
|
||||
|
||||
# make w and y dependent
|
||||
z <- rnorm(N,sd=0.5)
|
||||
x <- rbinom(N,1,0.5)
|
||||
x <- rbinom(N,1,plogis(Bxz*z))
|
||||
|
||||
ystar <- Bzy * z + Bxy * x + B0
|
||||
y <- rbinom(N,1,plogis(ystar))
|
||||
@ -70,30 +70,32 @@ parser <- add_argument(parser, "--N", default=1000, help="number of observations
|
||||
parser <- add_argument(parser, "--m", default=500, help="m the number of ground truth observations")
|
||||
parser <- add_argument(parser, "--seed", default=17, help='seed for the rng')
|
||||
parser <- add_argument(parser, "--outfile", help='output file', default='example_4.feather')
|
||||
parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.79)
|
||||
parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.75)
|
||||
## parser <- add_argument(parser, "--z_bias_y1", help='how is the classifier biased when y = 1?', default=-0.75)
|
||||
## parser <- add_argument(parser, "--z_bias_y0", help='how is the classifier biased when y = 0 ?', default=0.75)
|
||||
parser <- add_argument(parser, "--z_bias", help='how is the classifier biased?', default=1.5)
|
||||
parser <- add_argument(parser, "--Bxy", help='coefficient of x on y', default=0.1)
|
||||
parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.1)
|
||||
parser <- add_argument(parser, "--B0", help='coeffficient of z on y', default=-0.1)
|
||||
parser <- add_argument(parser, "--z_bias", help='how is the classifier biased?', default=-0.5)
|
||||
parser <- add_argument(parser, "--Bxy", help='coefficient of x on y', default=0.7)
|
||||
parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.7)
|
||||
parser <- add_argument(parser, "--Bzx", help='coeffficient of z on y', default=1)
|
||||
parser <- add_argument(parser, "--B0", help='coeffficient of z on y', default=0)
|
||||
parser <- add_argument(parser, "--outcome_formula", help='formula for the outcome variable', default="y~x+z")
|
||||
parser <- add_argument(parser, "--proxy_formula", help='formula for the proxy variable', default="w_pred~y+z")
|
||||
|
||||
parser <- add_argument(parser, "--confint_method", help='method for approximating confidence intervals', default='quad')
|
||||
args <- parse_args(parser)
|
||||
|
||||
B0 <- args$B0
|
||||
Bxy <- args$Bxy
|
||||
Bzy <- args$Bzy
|
||||
|
||||
Bzx <- args$Bzx
|
||||
|
||||
if(args$m < args$N){
|
||||
df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, args$seed, args$prediction_accuracy, args$z_bias)
|
||||
df <- simulate_data(args$N, args$m, B0, Bxy, Bzx, Bzy, args$seed, args$prediction_accuracy, args$z_bias)
|
||||
|
||||
# result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'z_bias_y0'=args$z_bias_y0,'z_bias_y1'=args$z_bias_y1,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'z_bias'=args$z_bias,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
|
||||
# result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy,'Bzx'=Bzx, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'z_bias_y0'=args$z_bias_y0,'z_bias_y1'=args$z_bias_y1,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
|
||||
result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy,'Bzx'=Bzx, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'z_bias'=args$z_bias,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula, confint_method=args$confint_method)
|
||||
|
||||
outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula))
|
||||
outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula),confint_method=args$confint_method)
|
||||
print(outline$error.cor.z)
|
||||
|
||||
outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
|
||||
|
||||
|
||||
@ -8,7 +8,7 @@ explained_variances=[0.1]
|
||||
|
||||
all:main supplement
|
||||
main:remembr.RDS
|
||||
supplement:robustness_1.RDS robustness_1_dv.RDS robustness_2.RDS robustness_2_dv.RDS robustness_3.RDS robustness_3_dv.RDS robustness_4.RDS robustness_4_dv.RDS
|
||||
supplement:robustness_1.RDS robustness_1_dv.RDS robustness_2.RDS robustness_2_dv.RDS robustness_3.RDS robustness_3_dv.RDS robustness_3_proflik.RDS robustness_3_dv_proflik.RDS robustness_4.RDS robustness_4_dv.RDS
|
||||
|
||||
srun=sbatch --wait --verbose run_job.sbatch
|
||||
|
||||
@ -44,7 +44,7 @@ example_2.feather: example_2_jobs
|
||||
sbatch --wait --verbose --array=1001-2000 run_simulation.sbatch 0 example_2_jobs
|
||||
sbatch --wait --verbose --array=2001-3000 run_simulation.sbatch 0 example_2_jobs
|
||||
sbatch --wait --verbose --array=3001-4000 run_simulation.sbatch 0 example_2_jobs
|
||||
sbatch --wait --verbose --array=4001-$(shell cat example_2_jobs | wc -l) run_simulation.sbatch 0 example_2_jobs
|
||||
sbatch --wait --verbose --array=4001-$(shell cat example_2_jobs | wc -l)
|
||||
|
||||
|
||||
# example_2_B_jobs: example_2_B.R
|
||||
@ -55,7 +55,7 @@ example_2.feather: example_2_jobs
|
||||
# sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_2_B_jobs
|
||||
|
||||
example_3_jobs: 03_depvar.R simulation_base.R grid_sweep.py pl_methods.R
|
||||
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${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":${explained_variances}}' --outfile example_3_jobs
|
||||
|
||||
example_3.feather: example_3_jobs
|
||||
rm -f example_3.feather
|
||||
@ -66,12 +66,13 @@ example_3.feather: example_3_jobs
|
||||
sbatch --wait --verbose --array=4001-$(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":${seeds}, "outfile":["example_4.feather"], "z_bias":[0.3], "prediction_accuracy":[0.73]}' --outfile example_4_jobs
|
||||
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${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]
|
||||
|
||||
$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_jobs;)
|
||||
#in robustness 1 / example 2 misclassification is correlated with Y.
|
||||
robustness_1_jobs_p1: 02_indep_differential.R simulation_base.R grid_sweep.py
|
||||
sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":[1000],"m":${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
|
||||
|
||||
robustness_1.RDS: robustness_1.feather
|
||||
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.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)
|
||||
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))
|
||||
$(foreach item,$(ITEMS_1),sbatch --wait --verbose --array=$(shell expr $(item) + $(ONE))-$(shell expr $(item) + $(STEP)) run_simulation.sbatch 0 robustness_1_dv_jobs;)
|
||||
$(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_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} 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} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${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} $< --command 'Rscript 03_depvar.R' --arg_dict '{"N":${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 $@
|
||||
|
||||
|
||||
|
||||
clean_main:
|
||||
rm -f remembr.RDS
|
||||
rm -f example_1_jobs
|
||||
@ -359,5 +405,4 @@ clean_all:
|
||||
# sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_B_mecor_jobs
|
||||
|
||||
|
||||
|
||||
.PHONY: supplement
|
||||
|
||||
@ -1,8 +1,8 @@
|
||||
#!/bin/bash
|
||||
#SBATCH --job-name="simulate measurement error models"
|
||||
## Allocation Definition
|
||||
#SBATCH --account=comdata
|
||||
#SBATCH --partition=compute-bigmem
|
||||
#SBATCH --account=comdata-ckpt
|
||||
#SBATCH --partition=ckpt
|
||||
## Resources
|
||||
#SBATCH --nodes=1
|
||||
## Walltime (4 hours)
|
||||
@ -14,4 +14,5 @@
|
||||
#SBATCH --chdir /gscratch/comdata/users/nathante/ml_measurement_error_public/simulations
|
||||
#SBATCH --output=simulation_jobs/%A_%a.out
|
||||
#SBATCH --error=simulation_jobs/%A_%a.err
|
||||
echo "$@"
|
||||
"$@"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user