add stuff to get perspective scores from civil comments

[ml_measurement_error_public.git] / simulations / 03_depvar.R

diff --git a/simulations/03_depvar.R b/simulations/03_depvar.R
index 69b4485947e9b2c2a89b0484dc38e2b467d72376..79a516fd6d3edf9cba19e2270fb007e404c181a6 100644 (file)
--- a/simulations/03_depvar.R
+++ b/simulations/03_depvar.R
@@ -31,7 +31,8 @@ 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.
 
 ## 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, Bzy, seed, prediction_accuracy=0.73){
+simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73, log.likelihood.gain = 0.1){
+    set.seed(seed)

     set.seed(seed)
 
     # make w and y dependent
     set.seed(seed)
 
     # make w and y dependent


@@ -41,8 +42,6 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73){
     ystar <- Bzy * z + Bxy * x + B0
     y <- rbinom(N,1,plogis(ystar))
 
     ystar <- Bzy * z + Bxy * x + B0
     y <- rbinom(N,1,plogis(ystar))
 

-    # glm(y ~ x + z, family="binomial")
-

     df <- data.table(x=x,y=y,ystar=ystar,z=z)
 
     if(m < N){
     df <- data.table(x=x,y=y,ystar=ystar,z=z)
 
     if(m < N){


@@ -66,16 +65,16 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73){
 }
 
 parser <- arg_parser("Simulate data and fit corrected models")
 }
 
 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=10000, 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, "--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, "--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=0.72)
 ## 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, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.72)
 ## 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, "--Bxy", help='coefficient of x on y', default=0.01)
+parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.01)

 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, "--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")