groceryheist/ml_measurement_error_public
1
0
Fork 0
Code

add more simulations.

Browse Source
This commit is contained in:
Nathan TeBlunthuis 2025-06-06 19:45:30 -07:00
parent 4dec710fdc
commit 6af6faeb49
2 changed files with 5 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
multiple_iv_simulations/01_indep_differential.R
View File

@ -1,16 +1,9 @@
#!/usr/bin/env Rscript #!/usr/bin/env Rscript
library(argparser) library(argparser)
library(mecor)
library(ggplot2) library(ggplot2)
library(data.table) library(data.table)
library(filelock) library(filelock)
library(arrow) library(arrow)
library(Amelia)
library(Zelig)
library(predictionError)
options(amelia.parallel="no",
amelia.ncpus=1)
setDTthreads(40)
source("simulation_base.R") source("simulation_base.R")
@ -31,8 +24,9 @@ simulate_data <- function(N,
accuracy_imbalance_difference = 0.3) { accuracy_imbalance_difference = 0.3) {
set.seed(seed) set.seed(seed)
# make w and y dependent # make w and y dependent
z <- rbinom(N, 1, plogis(qlogis(Pz))) l <- rnorm(N)
x <- rbinom(N, 1, plogis(Bzx * z + qlogis(Px))) z <- rbinom(N, 1, plogis(qlogis(Pz)+Bzx*l))
x <- rbinom(N, 1, plogis(-1*Bzx*l + qlogis(Px)))
y.var.epsilon <- (var(Bzy * z) + var(Bxy * x) + 2 * cov(Bzy * z, Bxy * x)) * ((1 - y_explained_variance) / y_explained_variance) y.var.epsilon <- (var(Bzy * z) + var(Bxy * x) + 2 * cov(Bzy * z, Bxy * x)) * ((1 - y_explained_variance) / y_explained_variance)
y.epsilon <- rnorm(N, sd = sqrt(y.var.epsilon)) y.epsilon <- rnorm(N, sd = sqrt(y.var.epsilon))

4
multiple_iv_simulations/Makefile
View File

@ -2,7 +2,7 @@
SHELL=bash SHELL=bash
Ns=[1000,5000,10000] Ns=[1000,5000,10000]
ms=[100,200,400] ms=[100,200,400,1000]
seeds=[$(shell seq -s, 1 500)] seeds=[$(shell seq -s, 1 500)]
explained_variances=[0.1] explained_variances=[0.1]
@ -17,7 +17,7 @@ joblists:example_1_jobs example_2_jobs example_3_jobs
grid_sweep_script=../simulations/grid_sweep.py grid_sweep_script=../simulations/grid_sweep.py
example_1_jobs: 01_indep_differential.R simulation_base.R ${grid_sweep_script} skx_dev.sbatch ../misclassificationmodels example_1_jobs: 01_indep_differential.R simulation_base.R ${grid_sweep_script} skx_dev.sbatch ../misclassificationmodels
${srun} uv run ${grid_sweep_script} --command 01_indep_differential.R --arg_dict '{"N":${Ns},"m":${ms},"seed":${seeds},"outfile":["example_1.feather"],"y_explained_variance":${explained_variances},"Bzx":[1]}' --outfile example_1_jobs --remember_file=remember_grid_sweep.rds ${srun} uv run ${grid_sweep_script} --command 01_indep_differential.R --arg_dict '{"N":${Ns},"m":${ms},"seed":${seeds},"outfile":["example_1.feather"],"y_explained_variance":${explained_variances},"Bzx":[1],"prediction_accuracy":0.825}' --outfile example_1_jobs --remember_file=remember_grid_sweep.rds
example_1.feather: example_1_jobs my_pylauncher.py example_1.feather: example_1_jobs my_pylauncher.py
sbatch -J "multiple iv measerr correction" spr_2.sbatch my_pylauncher.py $< --cores 1 sbatch -J "multiple iv measerr correction" spr_2.sbatch my_pylauncher.py $< --cores 1