X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/003733f22f42b435315803fd5f47d483c712d72d..588bdd7ed74cf8fe8fd0f15df58a6a40c26ebae5:/simulations/02_indep_differential.R

diff --git a/simulations/02_indep_differential.R b/simulations/02_indep_differential.R
index 5a7784b..d4e0916 100644
--- a/simulations/02_indep_differential.R
+++ b/simulations/02_indep_differential.R
@@ -31,68 +31,70 @@ source("simulation_base.R")
 
 ## 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, Bgy, Bkx, Bgx, seed, xy.explained.variance=0.01, u.explained.variance=0.1){
+simulate_data <- function(N, m, B0, Bxy, Bgy, seed, y_explained_variance=0.025, prediction_accuracy=0.73, accuracy_imbalance_difference=0.3){
     set.seed(seed)
-
-    ## the true value of x
-
-    g <- rbinom(N, 1, 0.5)
-
     # make w and y dependent
-    u <- rnorm(N,0,)
-
-    xprime <- Bgx * g + rnorm(N,0,1) 
-
-    k <- Bkx*xprime + rnorm(N,0,1.5) + 1.1*Bkx*u
-
-    x <- as.integer(logistic(scale(xprime)) > 0.5)
-
-    y <-  Bxy * x  + Bgy * g + B0 + u + rnorm(N, 0, 1)
+    g <- rbinom(N, 1, 0.5)
+    x <- rbinom(N, 1, 0.5)
 
-    df <- data.table(x=x,k=k,y=y,g=g)
+    y.var.epsilon <- (var(Bgy * g) + var(Bxy *x) + 2*cov(Bgy*g,Bxy*x)) * ((1-y_explained_variance)/y_explained_variance)
+    y.epsilon <- rnorm(N, sd = sqrt(y.var.epsilon))
+    y <- Bgy * g + Bxy * x + y.epsilon
 
-    w.model <- glm(x ~ k,df, family=binomial(link='logit')) 
+    df <- data.table(x=x,y=y,g=g)
 
-    if( m < N){
+    if(m < N){
         df <- df[sample(nrow(df), m), x.obs := x]
     } else {
         df <- df[, x.obs := x]
     }
 
-    df[, x.obs := x.obs]
+    df <- df[,w_pred:=x]
 
-    w <- predict(w.model, df) + rnorm(N, 0, 1)
-    ## y = B0 + B1x + e
+    pg <- mean(g)
+    px <- mean(x)
+    accuracy_imbalance_ratio <- (prediction_accuracy + accuracy_imbalance_difference/2) / (prediction_accuracy - accuracy_imbalance_difference/2)
 
-    df[,':='(w=w, w_pred = as.integer(w>0.5),u=u)]
-    return(df)
-}
+    # this works because of conditional probability
+    accuracy_g0 <- prediction_accuracy / (pg*(accuracy_imbalance_ratio) + (1-pg))
+    accuracy_g1 <- accuracy_imbalance_ratio * accuracy_g0
 
-schennach <- function(df){
+    dfg0 <- df[g==0]
+    ng0 <- nrow(dfg0)
+    dfg1 <- df[g==1]
+    ng1 <- nrow(dfg1)
 
-    fwx <- glm(x.obs~w, df, family=binomial(link='logit'))
-    df[,xstar_pred := predict(fwx, df)]
-    gxt <- lm(y ~ xstar_pred+g, df)
+    dfg0 <- dfg0[sample(ng0, (1-accuracy_g0)*ng0), w_pred := (w_pred-1)**2]
+    dfg1 <- dfg1[sample(ng1, (1-accuracy_g1)*ng1), w_pred := (w_pred-1)**2]
 
-}
+    df <- rbind(dfg0,dfg1)
 
+    w <- predict(glm(x ~ w_pred,data=df,family=binomial(link='logit')),type='response')
+    df <- df[,':='(w=w, w_pred = w_pred)]
+    return(df)
+}
 
 parser <- arg_parser("Simulate data and fit corrected models")
 parser <- add_argument(parser, "--N", default=5000, help="number of observations of w")
 parser <- add_argument(parser, "--m", default=200, help="m the number of ground truth observations")
 parser <- add_argument(parser, "--seed", default=432, 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=0.01)
+parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.73)
+parser <- add_argument(parser, "--accuracy_imbalance_difference", help='how much more accurate is the predictive model for one class than the other?', default=0.3)
+
 args <- parse_args(parser)
 
 B0 <- 0
 Bxy <- 0.2
-Bgy <- 0
-Bkx <- 2
-Bgx <- 0
+Bgy <- -0.2
+
+df <- simulate_data(args$N, args$m, B0, Bxy, Bgy, args$seed, args$y_explained_variance, args$prediction_accuracy, args$accuracy_imbalance_difference)
+
+result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bgy'=Bgy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference)
 
+outline <- run_simulation_depvar(df=df, result)
 
-outline <- run_simulation(simulate_data(args$N, args$m, B0, Bxy, Bgy, Bkx, Bgx, args$seed)
-                         ,list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bgy'=Bgy, 'Bkx'=Bkx, 'Bgx'=Bgx, 'seed'=args$seed))
 
 outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
 if(file.exists(args$outfile)){