X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/47e9367ed5c61b721bdc17cddd76bced4f8ed621..979dc14b6861ae31f00d56392fd5b8cf69f17333:/simulations/plot_irr_example.R diff --git a/simulations/plot_irr_example.R b/simulations/plot_irr_example.R new file mode 100644 index 0000000..bf5e661 --- /dev/null +++ b/simulations/plot_irr_example.R @@ -0,0 +1,129 @@ +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.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') + + ## x.mle <- summarize.estimator(df, 'mle', 'x') + + ## z.mle <- summarize.estimator(df, 'mle', 'z') + + accuracy <- df[,mean(accuracy)] + plot.df <- rbindlist(list(x.true,z.true,x.loa0.feasible,z.loa0.feasible,x.loa0.mle,z.loa0.mle,x.loco.feasible, z.loco.feasible, x.loco.mle, z.loco.mle),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) + +#ggplot(df,aes(x=Bxy.est.mle)) + geom_histogram() + facet_grid(accuracy_imbalance_difference ~ Bzy) + +## ## ## 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), +## N=factor(N), +## m=factor(m))] + +## plot.df.test <- plot.df.test[(variable=='x') & (method!="Multiple imputation (Classifier features unobserved)")] +## p <- ggplot(plot.df.test, aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) +## p <- p + geom_hline(data=plot.df.test, mapping=aes(yintercept=0.1),linetype=2) + +## p <- p + geom_pointrange() + facet_grid(N~m,as.table=F,scales='free') + scale_x_discrete(labels=label_wrap_gen(4)) +## print(p) + +## 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), +## N=factor(N), +## m=factor(m))] + +## plot.df.test <- plot.df.test[(variable=='z') & (method!="Multiple imputation (Classifier features unobserved)")] +## p <- ggplot(plot.df.test, aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) +## p <- p + geom_hline(data=plot.df.test, mapping=aes(yintercept=-0.1),linetype=2) + +## p <- p + geom_pointrange() + facet_grid(m~N,as.table=F,scales='free') + scale_x_discrete(labels=label_wrap_gen(4)) +## print(p) + + +## x.mle <- df[,.(N,m,Bxy.est.mle,Bxy.ci.lower.mle, Bxy.ci.upper.mle, y_explained_variance, Bzx, Bzy, accuracy_imbalance_difference)] +## x.mle.plot <- x.mle[,.(mean.est = mean(Bxy.est.mle), +## var.est = var(Bxy.est.mle), +## N.sims = .N, +## variable='z', +## method='Bespoke MLE' +## ), +## by=c("N","m",'y_explained_variance', 'Bzx', 'Bzy','accuracy_imbalance_difference')] + +## z.mle <- df[,.(N,m,Bzy.est.mle,Bzy.ci.lower.mle, Bzy.ci.upper.mle, y_explained_variance, Bzx, Bzy, accuracy_imbalance_difference)] + +## z.mle.plot <- z.mle[,.(mean.est = mean(Bzy.est.mle), +## var.est = var(Bzy.est.mle), +## N.sims = .N, +## variable='z', +## method='Bespoke MLE' +## ), +## by=c("N","m",'y_explained_variance','Bzx')] + +## plot.df <- z.mle.plot +## 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), +## N=factor(N), +## m=factor(m))] + +## plot.df.test <- plot.df.test[(variable=='z') & (m != 1000) & (m!=500) & (method!="Multiple imputation (Classifier features unobserved)")] +## p <- ggplot(plot.df.test, aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) +## p <- p + geom_hline(aes(yintercept=0.2),linetype=2) + +## p <- p + geom_pointrange() + facet_grid(m~Bzx, Bzy,as.table=F) + scale_x_discrete(labels=label_wrap_gen(4)) +## print(p) + + +## ## ggplot(plot.df[variable=='x'], aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) + geom_pointrange() + facet_grid(-m~N) + scale_x_discrete(labels=label_wrap_gen(10)) + +## ## ggplot(plot.df,aes(y=N,x=m,color=p.sign.correct)) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c(option='D') + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size") + +## ## ggplot(plot.df,aes(y=N,x=m,color=abs(mean.bias))) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c(option='D') + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size")