## print(mean(df[z==1]$x == df[z==1]$w_pred))
## print(mean(df$w_pred == df$x))
- odds.x1 <- qlogis(prediction_accuracy) + y_bias*qlogis(pnorm(scale(df[x==1]$y)))
- odds.x0 <- qlogis(prediction_accuracy,lower.tail=F) + y_bias*qlogis(pnorm(scale(df[x==0]$y)))
+ resids <- resid(lm(y~x + z))
+ odds.x1 <- qlogis(prediction_accuracy) + y_bias*qlogis(pnorm(resids[x==1]))
+ odds.x0 <- qlogis(prediction_accuracy,lower.tail=F) + y_bias*qlogis(pnorm(resids[x==0]))
## acc.x0 <- p.correct[df[,x==0]]
## acc.x1 <- p.correct[df[,x==1]]
df[,w_pred := as.integer(w > 0.5)]
- print(mean(df[z==0]$x == df[z==0]$w_pred))
- print(mean(df[z==1]$x == df[z==1]$w_pred))
+
print(mean(df$w_pred == df$x))
print(mean(df[y>=0]$w_pred == df[y>=0]$x))
print(mean(df[y<=0]$w_pred == df[y<=0]$x))
}
parser <- arg_parser("Simulate data and fit corrected models")
-parser <- add_argument(parser, "--N", default=1000, help="number of observations of w")
+parser <- add_argument(parser, "--N", default=5000, help="number of observations of w")
parser <- add_argument(parser, "--m", default=500, help="m the number of ground truth observations")
parser <- add_argument(parser, "--seed", default=51, help='seed for the rng')
parser <- add_argument(parser, "--outfile", help='output file', default='example_2.feather')
parser <- add_argument(parser, "--Bxy", help='Effect of z on y', default=0.3)
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*x")
-parser <- add_argument(parser, "--y_bias", help='coefficient of y on the probability a classification is correct', default=-0.75)
+parser <- add_argument(parser, "--y_bias", help='coefficient of y on the probability a classification is correct', default=-1)
parser <- add_argument(parser, "--truth_formula", help='formula for the true variable', default="x~z")
args <- parse_args(parser)
## 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){
+simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, log.likelihood.gain = 0.1){
+ set.seed(seed)
set.seed(seed)
# make w and y dependent
ystar <- Bzy * z + Bxy * x + B0
y <- rbinom(N,1,plogis(ystar))
- # glm(y ~ x + z, family="binomial")
-
df <- data.table(x=x,y=y,ystar=ystar,z=z)
if(m < N){
}
parser <- arg_parser("Simulate data and fit corrected models")
-parser <- add_argument(parser, "--N", default=1000, help="number of observations of w")
+parser <- add_argument(parser, "--N", default=10000, help="number of observations of w")
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_2.feather')
parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.72)
## parser <- add_argument(parser, "--x_bias_y1", help='how is the classifier biased when y = 1?', default=-0.75)
## parser <- add_argument(parser, "--x_bias_y0", help='how is the classifier biased when y = 0 ?', default=0.75)
-parser <- add_argument(parser, "--Bxy", help='coefficient of x on y', default=0.3)
-parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.3)
+parser <- add_argument(parser, "--Bxy", help='coefficient of x on y', default=0.01)
+parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.01)
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")
SHELL=bash
Ns=[1000, 2000, 4000]
-ms=[200, 400, 800]
+ms=[100, 200, 400, 800]
seeds=[$(shell seq -s, 1 250)]
explained_variances=[0.1]
all:remembr.RDS remember_irr.RDS
+supplement: remember_robustness_misspec.RDS
-srun=srun -A comdata -p compute-bigmem --time=6:00:00 --mem 4G -c 1
+srun=sbatch --wait --verbose run_job.sbatch
joblists:example_1_jobs example_2_jobs example_3_jobs
# test_true_z_jobs: test_true_z.R simulation_base.R
-# grid_sweep.py --command "Rscript test_true_z.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["test_true_z.feather"], "y_explained_variancevari":${explained_variances}, "Bzx":${Bzx}}' --outfile test_true_z_jobsb
+# sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript test_true_z.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["test_true_z.feather"], "y_explained_variancevari":${explained_variances}, "Bzx":${Bzx}}' --outfile test_true_z_jobsb
# test_true_z.feather: test_true_z_jobs
# rm -f test_true_z.feather
# sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 test_true_z_jobs
-example_1_jobs: 01_two_covariates.R simulation_base.R
- grid_sweep.py --command "Rscript 01_two_covariates.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"], "y_explained_variance":${explained_variances}, "Bzx":[0.1]}' --outfile example_1_jobs
+example_1_jobs: 01_two_covariates.R simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 01_two_covariates.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_1.feather"], "y_explained_variance":${explained_variances}, "Bzx":[0.3]}' --outfile example_1_jobs
example_1.feather: example_1_jobs
rm -f example_1.feather
sbatch --wait --verbose --array=1-$(shell cat example_1_jobs | wc -l) run_simulation.sbatch 0 example_1_jobs
# sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_1_jobs
-example_2_jobs: 02_indep_differential.R simulation_base.R
- grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y*z*x"]}' --outfile example_2_jobs
+example_2_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":${seeds}, "outfile":["example_2.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y*z*x"]}' --outfile example_2_jobs
example_2.feather: example_2_jobs
rm -f example_2.feather
- sbatch --wait --verbose --array=1-$(shell cat example_2_jobs | wc -l) run_simulation.sbatch 0 example_2_jobs
+ sbatch --wait --verbose --array=1-$(shell cat example_1_jobs | wc -l) run_simulation.sbatch 0 example_2_jobs
# sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_jobs
# example_2_B_jobs: example_2_B.R
-# grid_sweep.py --command "Rscript example_2_B.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B.feather"]}' --outfile example_2_B_jobs
+# sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript example_2_B.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B.feather"]}' --outfile example_2_B_jobs
# example_2_B.feather: example_2_B_jobs
# rm -f example_2_B.feather
# sbatch --wait --verbose --array=1-3000 run_simulation.sbatch 0 example_2_B_jobs
-example_3_jobs: 03_depvar.R simulation_base.R
- grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_3.feather"], "y_explained_variance":${explained_variances}}' --outfile example_3_jobs
+example_3_jobs: 03_depvar.R simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 03_depvar.R" --arg_dict '{"N":${Ns},"m":${ms}, "Bxy":[0.01],"Bzy":[-0.01],"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-$(shell cat example_3_jobs | wc -l) run_simulation.sbatch 0 example_3_jobs
-example_4_jobs: 04_depvar_differential.R simulation_base.R
- grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "y_explained_variance":${explained_variances}}' --outfile example_4_jobs
+example_4_jobs: 04_depvar_differential.R simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 04_depvar_differential.R" --arg_dict '{"N":${Ns},"Bxy":[0.01],"Bzy":[-0.01],"m":${ms}, "seed":${seeds}, "outfile":["example_4.feather"], "y_explained_variance":${explained_variances}}' --outfile example_4_jobs
example_4.feather: example_4_jobs
rm -f example_4.feather
sbatch --wait --verbose --array=1-$(shell cat example_4_jobs | wc -l) run_simulation.sbatch 0 example_4_jobs
-remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feather plot_example.R plot_dv_example.R
+remembr.RDS:example_1.feather example_2.feather example_3.feather example_4.feather plot_example.R plot_dv_example.R summarize_estimator.R
rm -f remembr.RDS
${srun} Rscript plot_example.R --infile example_1.feather --name "plot.df.example.1"
${srun} Rscript plot_example.R --infile example_2.feather --name "plot.df.example.2"
irr_seeds=${seeds}
irr_explained_variances=${explained_variances}
-example_5_jobs: 05_irr_indep.R irr_simulation_base.R
- grid_sweep.py --command "Rscript 05_irr_indep.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_5.feather"], "y_explained_variance":${irr_explained_variances}}' --outfile example_5_jobs
+example_5_jobs: 05_irr_indep.R irr_simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 05_irr_indep.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_5.feather"], "y_explained_variance":${irr_explained_variances}}' --outfile example_5_jobs
example_5.feather:example_5_jobs
rm -f example_5.feather
sbatch --wait --verbose --array=1-$(shell cat example_5_jobs | wc -l) run_simulation.sbatch 0 example_5_jobs
-example_6_jobs: 06_irr_dv.R irr_dv_simulation_base.R
- grid_sweep.py --command "Rscript 06_irr_dv.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_6.feather"], "y_explained_variance":${irr_explained_variances}}' --outfile example_6_jobs
+example_6_jobs: 06_irr_dv.R irr_dv_simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 06_irr_dv.R" --arg_dict '{"N":${irr_Ns},"m":${irr_ms}, "seed":${irr_seeds}, "outfile":["example_6.feather"], "y_explained_variance":${irr_explained_variances}}' --outfile example_6_jobs
example_6.feather:example_6_jobs
rm -f example_6.feather
sbatch --wait --verbose --array=1-$(shell cat example_6_jobs | wc -l) run_simulation.sbatch 0 example_6_jobs
-remember_irr.RDS: example_5.feather example_6.feather plot_irr_example.R plot_irr_dv_example.R
+remember_irr.RDS: example_5.feather example_6.feather plot_irr_example.R plot_irr_dv_example.R summarize_estimator.R
rm -f remember_irr.RDS
- ${srun} Rscript plot_irr_example.R --infile example_5.feather --name "plot.df.example.5"
- ${srun} Rscript plot_irr_dv_example.R --infile example_6.feather --name "plot.df.example.6"
+ sbatch --wait --verbose run_job.sbatch Rscript plot_irr_example.R --infile example_5.feather --name "plot.df.example.5"
+ sbatch --wait --verbose run_job.sbatch Rscript plot_irr_dv_example.R --infile example_6.feather --name "plot.df.example.6"
+
+
+
+robustness_1_jobs: 02_indep_differential.R simulation_base.R grid_sweep.py
+ sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript 02_indep_differential.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["robustness_1.feather"],"y_explained_variance":${explained_variances}, "Bzy":[-0.3],"Bxy":[0.3],"Bzx":[0.3], "outcome_formula":["y~x+z"], "proxy_formula":["w_pred~y+x"], "truth_formula":["x~1"]}' --outfile robustness_1_jobs
+
+
+
+robustness_1.feather: robustness_1_jobs
+ rm -f robustness_1.feather
+ sbatch --wait --verbose --array=1-$(shell cat robustness_1_jobs | wc -l) run_simulation.sbatch 0 robustness_1_jobs
+
+robustness_1_dv_jobs: simulation_base.R 04_depvar_differential.R grid_sweep.py
+ ${srun} bash -c "source ~/.bashrc && grid_sweep.py --command 'Rscript 04_depvar_differential.R' --arg_dict \"{'N':${Ns},'m':${ms}, 'seed':${seeds}, 'outfile':['robustness_1_dv.feather'], 'y_explained_variance':${explained_variances}, 'proxy_formula':['w_pred~y']}\" --outfile robustness_1_dv_jobs"
+
+
+robustness_1_dv.feather: robustness_1_dv_jobs
+ rm -f robustness_1_dv.feather
+ sbatch --wait --verbose --array=1-$(shell cat example_3_jobs | wc -l) run_simulation.sbatch 0 robustness_1_dv_jobs
+
+
+remember_robustness_misspec.RDS: robustness_1.feather robustness_1_dv.feather
+ rm -f remember_robustness_misspec.RDS
+ sbatch --wait --verbose run_job.sbatch Rscript plot_example.R --infile robustness_1.feather --name "plot.df.robustness.1" --remember-file "remember_robustness_misspec.RDS"
+ sbatch --wait --verbose run_job.sbatch Rscript plot_dv_example.R --infile robustness_1_dv.feather --name "plot.df.robustness.1.dv" --remember-file "remember_robustness_mispec.RDS"
+
clean:
rm *.feather
# sbatch --wait --verbose --array=3001-6001 run_simulation.sbatch 0 example_2_B_jobs
# example_2_B_mecor_jobs:
-# grid_sweep.py --command "Rscript example_2_B_mecor.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B_mecor.feather"]}' --outfile example_2_B_mecor_jobs
+# sbatch --wait --verbose run_job.sbatch grid_sweep.py --command "Rscript example_2_B_mecor.R" --arg_dict '{"N":${Ns},"m":${ms}, "seed":${seeds}, "outfile":["example_2_B_mecor.feather"]}' --outfile example_2_B_mecor_jobs
# example_2_B_mecor.feather:example_2_B_mecor.R example_2_B_mecor_jobs
# rm -f example_2_B_mecor.feather
+.PHONY: supplement
import fire
from itertools import product
+import pyRemembeR
-def main(command, arg_dict, outfile):
+def main(command, arg_dict, outfile, remember_file='remember_grid_sweep.RDS'):
+ remember = pyRemembeR.remember.Remember()
+ remember.set_file(remember_file)
+ remember[outfile] = arg_dict
+ remember.save_to_r()
keys = []
values = []
Bxy.ci.upper.loco.mle = ci.upper['x'],
Bxy.ci.lower.loco.mle = ci.lower['x'],
Bzy.ci.upper.loco.mle = ci.upper['z'],
- Bzy.ci.lower.loco.mle = ci.upper['z']))
+ Bzy.ci.lower.loco.mle = ci.lower['z']))
print(rater_formula)
print(proxy_formula)
Bxy.ci.upper.loco.mle = ci.upper['x'],
Bxy.ci.lower.loco.mle = ci.lower['x'],
Bzy.ci.upper.loco.mle = ci.upper['z'],
- Bzy.ci.lower.loco.mle = ci.upper['z']))
+ Bzy.ci.lower.loco.mle = ci.lower['z']))
## print(rater_formula)
## print(proxy_formula)
library(formula.tools)
library(matrixStats)
-
+library(bbmle)
## df: dataframe to model
## outcome_formula: formula for y | x, z
## outcome_family: family for y | x, z
## outcome_formula <- y ~ x + z; proxy_formula <- w_pred ~ y + x + z + x:z + x:y + z:y
-measerr_mle_dv <- function(df, outcome_formula, outcome_family=binomial(link='logit'), proxy_formula, proxy_family=binomial(link='logit')){
+measerr_mle_dv <- function(df, outcome_formula, outcome_family=binomial(link='logit'), proxy_formula, proxy_family=binomial(link='logit'),method='optim'){
nll <- function(params){
df.obs <- model.frame(outcome_formula, df)
start <- rep(0.1,length(params))
names(start) <- params
- fit <- optim(start, fn = nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+ if(method=='optim'){
+ fit <- optim(start, fn = nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+ } else {
+ quoted.names <- gsub("[\\(\\)]",'',names(start))
+ print(quoted.names)
+ text <- paste("function(", paste0(quoted.names,'=',start,collapse=','),"){params<-c(",paste0(quoted.names,collapse=','),");return(nll(params))}")
+
+ measerr_mle_nll <- eval(parse(text=text))
+ names(start) <- quoted.names
+ names(lower) <- quoted.names
+ fit <- mle2(minuslogl=measerr_mle_nll, start=start, lower=lower, parnames=params,control=list(maxit=1e6),method='L-BFGS-B')
+ }
return(fit)
}
## Experimental, and not necessary if errors are independent.
-measerr_irr_mle <- function(df, outcome_formula, outcome_family=gaussian(), rater_formula, proxy_formula, proxy_family=binomial(link='logit'), truth_formula, truth_family=binomial(link='logit')){
+measerr_irr_mle <- function(df, outcome_formula, outcome_family=gaussian(), rater_formula, proxy_formula, proxy_family=binomial(link='logit'), truth_formula, truth_family=binomial(link='logit'),method='optim'){
### in this scenario, the ground truth also has measurement error, but we have repeated measures for it.
start <- rep(0.1,length(params))
names(start) <- params
- fit <- optim(start, fn = nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+
+ if(method=='optim'){
+ fit <- optim(start, fn = nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+ } else {
+
+ quoted.names <- gsub("[\\(\\)]",'',names(start))
+ print(quoted.names)
+ text <- paste("function(", paste0(quoted.names,'=',start,collapse=','),"){params<-c(",paste0(quoted.names,collapse=','),");return(nll(params))}")
+
+ measerr_mle_nll <- eval(parse(text=text))
+ names(start) <- quoted.names
+ names(lower) <- quoted.names
+ fit <- mle2(minuslogl=measerr_mle_nll, start=start, lower=lower, parnames=params,control=list(maxit=1e6),method='L-BFGS-B')
+ }
+
return(fit)
}
-measerr_mle <- function(df, outcome_formula, outcome_family=gaussian(), proxy_formula, proxy_family=binomial(link='logit'), truth_formula, truth_family=binomial(link='logit')){
+measerr_mle <- function(df, outcome_formula, outcome_family=gaussian(), proxy_formula, proxy_family=binomial(link='logit'), truth_formula, truth_family=binomial(link='logit'),method='optim'){
- measrr_mle_nll <- function(params){
+ measerr_mle_nll <- function(params){
df.obs <- model.frame(outcome_formula, df)
proxy.variable <- all.vars(proxy_formula)[1]
proxy.model.matrix <- model.matrix(proxy_formula, df)
lower <- c(lower, rep(-Inf, length(truth.params)))
start <- rep(0.1,length(params))
names(start) <- params
-
- fit <- optim(start, fn = measrr_mle_nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+
+ if(method=='optim'){
+ fit <- optim(start, fn = measerr_mle_nll, lower=lower, method='L-BFGS-B', hessian=TRUE, control=list(maxit=1e6))
+ } else { # method='mle2'
+
+ quoted.names <- gsub("[\\(\\)]",'',names(start))
+
+ text <- paste("function(", paste0(quoted.names,'=',start,collapse=','),"){params<-c(",paste0(quoted.names,collapse=','),");return(measerr_mle_nll(params))}")
+
+ measerr_mle_nll_mle <- eval(parse(text=text))
+ names(start) <- quoted.names
+ names(lower) <- quoted.names
+ fit <- mle2(minuslogl=measerr_mle_nll_mle, start=start, lower=lower, parnames=params,control=list(maxit=1e6),method='L-BFGS-B')
+ }
return(fit)
}
+
parser <- arg_parser("Simulate data and fit corrected models.")
parser <- add_argument(parser, "--infile", default="", help="name of the file to read.")
+parser <- add_argument(parser, "--remember-file", default="remembr.RDS", help="name of the remember file.")
parser <- add_argument(parser, "--name", default="", help="The name to safe the data to in the remember file.")
args <- parse_args(parser)
-summarize.estimator <- function(df, suffix='naive', coefname='x'){
-
- part <- df[,c('N',
- 'm',
- 'Bxy',
- paste0('B',coefname,'y.est.',suffix),
- paste0('B',coefname,'y.ci.lower.',suffix),
- paste0('B',coefname,'y.ci.upper.',suffix),
- 'y_explained_variance',
- 'Bzy'
- ),
- with=FALSE]
+## summarize.estimator <- function(df, suffix='naive', coefname='x'){
+
+## part <- df[,c('N',
+## 'm',
+## 'Bxy',
+## paste0('B',coefname,'y.est.',suffix),
+## paste0('B',coefname,'y.ci.lower.',suffix),
+## paste0('B',coefname,'y.ci.upper.',suffix),
+## 'y_explained_variance',
+## 'Bzy'
+## ),
+## with=FALSE]
- true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
- zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
- bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
- sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
-
- part <- part[,':='(true.in.ci = true.in.ci,
- zero.in.ci = zero.in.ci,
- bias=bias,
- sign.correct =sign.correct)]
-
- part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
- mean.bias = mean(bias),
- mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
- var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
- est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95),
- est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05),
- N.sims = .N,
- p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
- variable=coefname,
- method=suffix
- ),
- by=c("N","m",'Bzy','y_explained_variance')
- ]
+## true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
+## zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
+## bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
+## sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
+
+## part <- part[,':='(true.in.ci = true.in.ci,
+## zero.in.ci = zero.in.ci,
+## bias=bias,
+## sign.correct =sign.correct)]
+
+## part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
+## mean.bias = mean(bias),
+## mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+## var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+## est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95),
+## est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05),
+## N.sims = .N,
+## p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
+## variable=coefname,
+## method=suffix
+## ),
+## by=c("N","m",'Bzy','y_explained_variance')
+## ]
- return(part.plot)
-}
+## return(part.plot)
+## }
+source("summarize_estimator.R")
build_plot_dataset <- function(df){
return(plot.df)
}
-
-df <- read_feather(args$infile)
-plot.df <- build_plot_dataset(df)
+change.remember.file(args$remember_file, clear=TRUE)
+sims.df <- read_feather(args$infile)
+sims.df[,Bzx:=NA]
+sims.df[,accuracy_imbalance_difference:=NA]
+plot.df <- build_plot_dataset(sims.df)
remember(plot.df,args$name)
+set.remember.prefix(gsub("plot.df.","",args$name))
+
+remember(median(sims.df$cor.xz),'med.cor.xz')
+remember(median(sims.df$accuracy),'med.accuracy')
+remember(median(sims.df$error.cor.x),'med.error.cor.x')
+remember(median(sims.df$lik.ratio),'med.lik.ratio')
+
+
+
## df[gmm.ER_pval<0.05]
## plot.df.test <- plot.df[,':='(method=factor(method,levels=c("Naive","Multiple imputation", "Multiple imputation (Classifier features unobserved)","Regression Calibration","2SLS+gmm","Bespoke MLE", "Feasible"),ordered=T),
library(filelock)
library(argparser)
+source("summarize_estimator.R")
+
+
parser <- arg_parser("Simulate data and fit corrected models.")
parser <- add_argument(parser, "--infile", default="", help="name of the file to read.")
+parser <- add_argument(parser, "--remember-file", default="remembr.RDS", help="name of the remember file.")
parser <- add_argument(parser, "--name", default="", help="The name to safe the data to in the remember file.")
args <- parse_args(parser)
-summarize.estimator <- function(df, suffix='naive', coefname='x'){
-
- part <- df[,c('N',
- 'm',
- 'Bxy',
- paste0('B',coefname,'y.est.',suffix),
- paste0('B',coefname,'y.ci.lower.',suffix),
- paste0('B',coefname,'y.ci.upper.',suffix),
- 'y_explained_variance',
- 'Bzx',
- 'Bzy',
- 'accuracy_imbalance_difference'
- ),
- with=FALSE]
+
+
+## summarize.estimator <- function(df, suffix='naive', coefname='x'){
+
+## part <- df[,c('N',
+## 'm',
+## 'Bxy',
+## paste0('B',coefname,'y.est.',suffix),
+## paste0('B',coefname,'y.ci.lower.',suffix),
+## paste0('B',coefname,'y.ci.upper.',suffix),
+## 'y_explained_variance',
+## 'Bzx',
+## 'Bzy',
+## 'accuracy_imbalance_difference'
+## ),
+## with=FALSE]
- true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
- zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
- bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
- sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
-
- part <- part[,':='(true.in.ci = true.in.ci,
- zero.in.ci = zero.in.ci,
- bias=bias,
- sign.correct =sign.correct)]
-
- part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
- mean.bias = mean(bias),
- mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
- var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
- est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95,na.rm=T),
- est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05,na.rm=T),
- N.sims = .N,
- p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
- variable=coefname,
- method=suffix
- ),
- by=c("N","m",'y_explained_variance','Bzx', 'Bzy', 'accuracy_imbalance_difference')
- ]
+## true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
+## zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
+## bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
+## sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
+
+## part <- part[,':='(true.in.ci = true.in.ci,
+## zero.in.ci = zero.in.ci,
+## bias=bias,
+## sign.correct =sign.correct)]
+
+## part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
+## mean.bias = mean(bias),
+## mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+## var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+## est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95,na.rm=T),
+## est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05,na.rm=T),
+## N.sims = .N,
+## p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
+## variable=coefname,
+## method=suffix
+## ),
+## by=c("N","m",'y_explained_variance','Bzx', 'Bzy', 'accuracy_imbalance_difference')
+## ]
- return(part.plot)
-}
+## return(part.plot)
+## }
build_plot_dataset <- function(df){
}
-plot.df <- read_feather(args$infile)
-print(unique(plot.df$N))
+sims.df <- read_feather(args$infile)
+print(unique(sims.df$N))
# df <- df[apply(df,1,function(x) !any(is.na(x)))]
-if(!('Bzx' %in% names(plot.df)))
- plot.df[,Bzx:=NA]
+if(!('Bzx' %in% names(sims.df)))
+ sims.df[,Bzx:=NA]
-if(!('accuracy_imbalance_difference' %in% names(plot.df)))
- plot.df[,accuracy_imbalance_difference:=NA]
+if(!('accuracy_imbalance_difference' %in% names(sims.df)))
+ sims.df[,accuracy_imbalance_difference:=NA]
-unique(plot.df[,'accuracy_imbalance_difference'])
+unique(sims.df[,'accuracy_imbalance_difference'])
+change.remember.file(args$remember_file, clear=TRUE)
#plot.df <- build_plot_dataset(df[accuracy_imbalance_difference==0.1][N==700])
-plot.df <- build_plot_dataset(plot.df)
+plot.df <- build_plot_dataset(sims.df)
remember(plot.df,args$name)
+set.remember.prefix(gsub("plot.df.","",args$name))
+
+remember(median(sims.df$cor.xz),'med.cor.xz')
+remember(median(sims.df$accuracy),'med.accuracy')
+remember(median(sims.df$accuracy.y0),'med.accuracy.y0')
+remember(median(sims.df$accuracy.y1),'med.accuracy.y1')
+remember(median(sims.df$fpr),'med.fpr')
+remember(median(sims.df$fpr.y0),'med.fpr.y0')
+remember(median(sims.df$fpr.y1),'med.fpr.y1')
+remember(median(sims.df$fnr),'med.fnr')
+remember(median(sims.df$fnr.y0),'med.fnr.y0')
+remember(median(sims.df$fnr.y1),'med.fnr.y1')
+
+remember(median(sims.df$cor.resid.w_pred),'cor.resid.w_pred')
+
#ggplot(df,aes(x=Bxy.est.mle)) + geom_histogram() + facet_grid(accuracy_imbalance_difference ~ Bzy)
## ## ## df[gmm.ER_pval<0.05]
#SBATCH --partition=compute-bigmem
## Resources
#SBATCH --nodes=1
-## Walltime (12 hours)
-#SBATCH --time=1:00:00
+## Walltime (4 hours)
+#SBATCH --time=4:00:00
## Memory per node
-#SBATCH --mem=8G
+#SBATCH --mem=4G
#SBATCH --cpus-per-task=1
#SBATCH --ntasks-per-node=1
#SBATCH --chdir /gscratch/comdata/users/nathante/ml_measurement_error_public/simulations
#SBATCH --output=simulation_jobs/%A_%a.out
#SBATCH --error=simulation_jobs/%A_%a.err
+source ~/.bashrc
TASK_NUM=$(($SLURM_ARRAY_TASK_ID + $1))
TASK_CALL=$(sed -n ${TASK_NUM}p $2)
accuracy <- df[,mean(w_pred==y)]
result <- append(result, list(accuracy=accuracy))
+ error.cor.x <- cor(df$x, df$w - df$x)
+ result <- append(result, list(error.cor.x = error.cor.x))
+ model.null <- glm(y~1, data=df,family=binomial(link='logit'))
(model.true <- glm(y ~ x + z, data=df,family=binomial(link='logit')))
+ (lik.ratio <- exp(logLik(model.true) - logLik(model.null)))
+
true.ci.Bxy <- confint(model.true)['x',]
true.ci.Bzy <- confint(model.true)['z',]
+
+ result <- append(result, list(lik.ratio=lik.ratio))
+
result <- append(result, list(Bxy.est.true=coef(model.true)['x'],
Bzy.est.true=coef(model.true)['z'],
Bxy.ci.upper.true = true.ci.Bxy[2],
run_simulation <- function(df, result, outcome_formula=y~x+z, proxy_formula=NULL, truth_formula=NULL){
accuracy <- df[,mean(w_pred==x)]
- result <- append(result, list(accuracy=accuracy))
-
+ accuracy.y0 <- df[y<=0,mean(w_pred==x)]
+ accuracy.y1 <- df[y>=0,mean(w_pred==x)]
+ cor.y.xi <- cor(df$x - df$w_pred, df$y)
+
+ fnr <- df[w_pred==0,mean(w_pred!=x)]
+ fnr.y0 <- df[(w_pred==0) & (y<=0),mean(w_pred!=x)]
+ fnr.y1 <- df[(w_pred==0) & (y>=0),mean(w_pred!=x)]
+
+ fpr <- df[w_pred==1,mean(w_pred!=x)]
+ fpr.y0 <- df[(w_pred==1) & (y<=0),mean(w_pred!=x)]
+ fpr.y1 <- df[(w_pred==1) & (y>=0),mean(w_pred!=x)]
+ cor.resid.w_pred <- cor(resid(lm(y~x+z,df)),df$w_pred)
+
+ result <- append(result, list(accuracy=accuracy,
+ accuracy.y0=accuracy.y0,
+ accuracy.y1=accuracy.y1,
+ cor.y.xi=cor.y.xi,
+ fnr=fnr,
+ fnr.y0=fnr.y0,
+ fnr.y1=fnr.y1,
+ fpr=fpr,
+ fpr.y0=fpr.y0,
+ fpr.y1=fpr.y1,
+ cor.resid.w_pred=cor.resid.w_pred
+ ))
+
+ result <- append(result, list(cor.xz=cor(df$x,df$z)))
(model.true <- lm(y ~ x + z, data=df))
true.ci.Bxy <- confint(model.true)['x',]
true.ci.Bzy <- confint(model.true)['z',]
'accuracy_imbalance_difference'
),
with=FALSE]
-
+
+
true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
- bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
+ bias <- part[[paste0('B',coefname,'y')]] - part[[paste0('B',coefname,'y.est.',suffix)]]
sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
part <- part[,':='(true.in.ci = true.in.ci,
mean.bias = mean(bias),
mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
- est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95,na.rm=T),
- est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05,na.rm=T),
+ est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.975,na.rm=T),
+ est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.025,na.rm=T),
+ mean.ci.upper = mean(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]]),
+ mean.ci.lower = mean(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]]),
+ ci.upper.975 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.975,na.rm=T),
+ ci.upper.025 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.025,na.rm=T),
+ ci.lower.975 = quantile(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],0.975,na.rm=T),
+ ci.lower.025 = quantile(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],0.025,na.rm=T),
+ N.ci.is.NA = sum(is.na(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]])),
N.sims = .N,
p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
variable=coefname,
projects / ml_measurement_error_public.git / commitdiff