X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/d0c5766bdf867a81a2477d2cac1d40812110af90..69948cae1e691191fc86e6abdaa485bc98f38f1f:/simulations/06_irr_dv.R?ds=inline

diff --git a/simulations/06_irr_dv.R b/simulations/06_irr_dv.R
index 0dd13b6..dd8fa72 100644
--- a/simulations/06_irr_dv.R
+++ b/simulations/06_irr_dv.R
@@ -31,14 +31,13 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, co
 
     df <- data.table(x=x,y=y,ystar=ystar,z=z)
 
-    if(m < N){
-        df <- df[sample(nrow(df), m), y.obs := y]
-    } else {
-        df <- df[, y.obs := y]
-    }
+    df <- df[sample(nrow(df), m), y.obs := y]
     
-    df[ (!is.na(y.obs)) ,y.obs.0 := abs(y.obs - rbinom(.N, 1, 1-coder_accuracy))]
-    df[ (!is.na(y.obs)) ,y.obs.1 := abs(y.obs - rbinom(.N, 1, 1-coder_accuracy))]
+    coder.0.correct <- rbinom(m, 1, coder_accuracy)
+    coder.1.correct <- rbinom(m, 1, coder_accuracy)
+    
+    df[!is.na(y.obs),y.obs.0 := as.numeric((.SD$y.obs & coder.0.correct) | (!.SD$y.obs & !coder.0.correct))]
+    df[!is.na(y.obs),y.obs.1 := as.numeric((.SD$y.obs & coder.1.correct) | (!.SD$y.obs & !coder.1.correct))]
 
     odds.y1 <- qlogis(prediction_accuracy)
     odds.y0 <- qlogis(prediction_accuracy,lower.tail=F)
@@ -48,6 +47,9 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, co
 
     df[,w_pred := as.integer(w > 0.5)]
 
+    print(mean(df$y == df$y.obs.0,na.rm=T))
+    print(mean(df$y == df$y.obs.1,na.rm=T))
+
     print(mean(df[x==0]$y == df[x==0]$w_pred))
     print(mean(df[x==1]$y == df[x==1]$w_pred))
     print(mean(df$w_pred == df$y))
@@ -55,18 +57,18 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, co
 }
 
 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=17, help='seed for the rng')
+parser <- add_argument(parser, "--seed", default=16, help='seed for the rng')
 parser <- add_argument(parser, "--outfile", help='output file', default='example_2.feather')
-parser <- add_argument(parser, "--y_explained_variance", help='what proportion of the variance of y can be explained?', default=0.005)
-parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.72)
+parser <- add_argument(parser, "--y_explained_variance", help='what proportion of the variance of y can be explained?', default=0.1)
+parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.73)
 ## 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, "--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, "--proxy_formula", help='formula for the proxy variable', default="w_pred~y+y.obs.1+y.obs.0")
 parser <- add_argument(parser, "--coder_accuracy", help='How accurate are the coders?', default=0.8)
 
 args <- parse_args(parser)
@@ -76,24 +78,24 @@ Bxy <- args$Bxy
 Bzy <- args$Bzy
 
 
-if(args$m < args$N){
-    df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, args$seed, args$prediction_accuracy, args$coder_accuracy)
-
-#    result <- list('N'=args$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, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
+df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, args$seed, args$prediction_accuracy, args$coder_accuracy)
 
-    outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$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$prediction_accuracy, 'x_bias_y0'=args$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$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
 
-    outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
+outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula))
 
-    if(file.exists(args$outfile)){
-        logdata <- read_feather(args$outfile)
-        logdata <- rbind(logdata,as.data.table(outline),fill=TRUE)
-    } else {
-        logdata <- as.data.table(outline)
-    }
+outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
 
-    print(outline)
-    write_feather(logdata, args$outfile)
-    unlock(outfile_lock)
+if(file.exists(args$outfile)){
+    logdata <- read_feather(args$outfile)
+    logdata <- rbind(logdata,as.data.table(outline),fill=TRUE)
+} else {
+    logdata <- as.data.table(outline)
 }
+
+print(outline)
+write_feather(logdata, args$outfile)
+unlock(outfile_lock)
+
+warnings()