1
0
ml_measurement_error_public/simulations/plot_irr_dv_example.R

74 lines
2.3 KiB
R

source("RemembR/R/RemembeR.R")
library(arrow)
library(data.table)
library(ggplot2)
library(filelock)
library(argparser)
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, "--name", default="", help="The name to safe the data to in the remember file.")
args <- parse_args(parser)
source("summarize_estimator.R")
build_plot_dataset <- function(df){
x.true <- summarize.estimator(df, 'true','x')
z.true <- summarize.estimator(df, 'true','z')
x.naive <- summarize.estimator(df, 'naive','x')
z.naive <- summarize.estimator(df, 'naive','z')
x.loa0.feasible <- summarize.estimator(df, 'loa0.feasible','x')
z.loa0.feasible <- summarize.estimator(df,'loa0.feasible','z')
x.loa0.mle <- summarize.estimator(df, 'loa0.mle', 'x')
z.loa0.mle <- summarize.estimator(df, 'loa0.mle', 'z')
x.loco.feasible <- summarize.estimator(df, 'loco.feasible', 'x')
z.loco.feasible <- summarize.estimator(df, 'loco.feasible', 'z')
x.loco.mle <- summarize.estimator(df, 'loco.mle', 'x')
z.loco.mle <- summarize.estimator(df, 'loco.mle', 'z')
z.loco.amelia <- summarize.estimator(df, 'amelia.full', 'z')
x.loco.amelia <- summarize.estimator(df, 'amelia.full', 'x')
z.loco.zhang <- summarize.estimator(df, 'zhang', 'z')
x.loco.zhang <- summarize.estimator(df, 'zhang', 'x')
accuracy <- df[,mean(accuracy)]
plot.df <- rbindlist(list(x.true,z.true,x.loa0.feasible,z.loa0.feasible,x.naive,z.naive,x.loa0.mle,z.loa0.mle,x.loco.feasible, z.loco.feasible, z.loco.mle, x.loco.mle, x.loco.amelia, z.loco.amelia, z.loco.zhang, x.loco.zhang),use.names=T)
plot.df[,accuracy := accuracy]
plot.df <- plot.df[,":="(sd.est=sqrt(var.est)/N.sims)]
return(plot.df)
}
plot.df <- read_feather(args$infile)
print(unique(plot.df$N))
# df <- df[apply(df,1,function(x) !any(is.na(x)))]
if(!('Bzx' %in% names(plot.df)))
plot.df[,Bzx:=NA]
if(!('accuracy_imbalance_difference' %in% names(plot.df)))
plot.df[,accuracy_imbalance_difference:=NA]
unique(plot.df[,'accuracy_imbalance_difference'])
#plot.df <- build_plot_dataset(df[accuracy_imbalance_difference==0.1][N==700])
plot.df <- build_plot_dataset(plot.df)
change.remember.file("remember_irr.RDS",clear=TRUE)
remember(plot.df,args$name)