X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/588bdd7ed74cf8fe8fd0f15df58a6a40c26ebae5..fa05dbab6bd2c5db6ed4eccf38cff03bb4fd6683:/simulations/03_depvar_differential.R

diff --git a/simulations/03_depvar_differential.R b/simulations/03_depvar_differential.R
index d52afe7..02944a5 100644
--- a/simulations/03_depvar_differential.R
+++ b/simulations/03_depvar_differential.R
@@ -31,83 +31,81 @@ 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, seed, prediction_accuracy=0.73, accuracy_imbalance_difference=0.3){
+simulate_data <- function(N, m, B0, Bxy, Bzy, Py, seed, prediction_accuracy=0.73, x_bias=-0.75){
     set.seed(seed)
+
     # make w and y dependent
-    g <- rbinom(N, 1, 0.5)
+    z <- rbinom(N, 1, 0.5)
     x <- rbinom(N, 1, 0.5)
 
-    ystar <- Bgy * g + Bxy * x
-    y <- rbinom(N,1,logistic(ystar))
+    ystar <- Bzy * z + Bxy * x + B0 + qlogix(Py)
+    y <- rbinom(N,1,plogis(ystar))
 
-    # glm(y ~ x + g, family="binomial")
+    # glm(y ~ x + z, family="binomial")
 
-    df <- data.table(x=x,y=y,ystar=ystar,g=g)
+    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]
     }
+    
+    odds.y1 <- qlogis(prediction_accuracy) + x_bias*df[y==1]$x
+    odds.y0 <- qlogis(prediction_accuracy,lower.tail=F) + x_bias*df[y==0]$x
 
-    df <- df[,w_pred:=y]
-
-    pg <- mean(g)
-
-    accuracy_imbalance_ratio <- (prediction_accuracy + accuracy_imbalance_difference/2) / (prediction_accuracy - accuracy_imbalance_difference/2)
-
-    # this works because of conditional probability
-    accuracy_g0 <- prediction_accuracy / (pg*(accuracy_imbalance_ratio) + (1-pg))
-    accuracy_g1 <- accuracy_imbalance_ratio * accuracy_g0
-
-    dfg0 <- df[g==0]
-    ng0 <- nrow(dfg0)
-    dfg1 <- df[g==1]
-    ng1 <- nrow(dfg1)
-
-    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)
+    df[y==0,w:=plogis(rlogis(.N,odds.y0))]
+    df[y==1,w:=plogis(rlogis(.N,odds.y1))]
 
-    wmod <- glm(y.obs ~ w_pred,data=df[!is.null(y.obs)],family=binomial(link='logit'))
-    w <- predict(wmod,df,type='response')
-
-    df <- df[,':='(w=w)]
+    df[,w_pred := as.integer(w > 0.5)]
 
+    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))
     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=4321, help='seed for the rng')
+parser <- add_argument(parser, "--N", default=1000, 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, "--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=0.73)
-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)
+parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.8)
+## 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, "--x_bias", help='how is the classifier biased?', 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, "--Py", help='Base rate of y', default=0.5)
+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*x")
 
 args <- parse_args(parser)
 
 B0 <- 0
-Bxy <- 0.2
-Bgy <- -0.2
+Bxy <- args$Bxy
+Bzy <- args$Bzy
 
-df <- simulate_data(args$N, args$m, B0, Bxy, Bgy, args$seed, args$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)
+if(args$m < args$N){
+    df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, args$seed, args$prediction_accuracy, args$x_bias_y0, args$x_bias_y1)
 
-outline <- run_simulation_depvar(df=df, result)
+#    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, 'x_bias'=args$x_bias,'x_bias'=args$x_bias,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
 
+    outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula))
 
-outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
-if(file.exists(args$outfile)){
-    logdata <- read_feather(args$outfile)
-    logdata <- rbind(logdata,as.data.table(outline))
-} else {
-    logdata <- as.data.table(outline)
-}
+    outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
+
+    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$outfile)
-unlock(outfile_lock)
+    print(outline)
+    write_feather(logdata, args$outfile)
+    unlock(outfile_lock)
+}