knitr::opts_chunk$set(eval = FALSE)
pkgs <- list("rmsutilityr", "glmnet", "doParallel", "foreach", "pROC", "stepwiser") lapply(pkgs, library, character.only = TRUE) registerDoParallel(cores = 4) file <- get_dated_filename("dk_sim.csv") file
Number of simulations
sims <- 10 sims
Stepwise algorithm
## Can be any subset of c("backward", "forward", "both") directions <- "forward" directions
Coefficients
betas <- c(1, 2, 3, -1, -2, -3) #betas <- 2 betas
Sample sizes
#n_values <- c(30, 60, 90, 300, 600, 900, 3000, 6000, 9000) n_values <- c(30, 60, 90) n_values
from $\rho_{X_{i}X_{j}}$
rho_values <- c(0, sqrt(0.4), sqrt(0.8)) #rho_values <- c(0, sqrt(0.1), sqrt(0.2), sqrt(0.4)) rho_values
Candidate predictor variables
predictors <- c(12, 18, 24, 50, 100) predictors <- c(12, 18, 24) predictors
$\alpha$
MFWER <- 0.15 alpha_values <- c(0.5, 0.15, 1 - (1 - MFWER)^(1 / predictors), 0.05) alpha_values
#sim_object <- dk_sim(file = file, directions = directions, betas, n_values, alpha_values, rho_values, predictors, sims = sims, rnorm, 0, 0.2) weight <- 1 nlambda = 100 sim_object <- dk_and_net_sim(file = file, directions = directions, betas, n_values, alpha_values, rho_values, predictors, weight = weight, nlambda = nlambda, sims = sims, rnorm, 0, 0.2)
library("reshape2") library("ggplot2") #backward_sim_object <- sim_object #save(backward_sim_object, file = "../data/backward_sim_object.RData") sim_wide_df <- sim_object_to_df(sim_object) sim_wide_median_df <- sim_wide_df[ , !names(sim_wide_df) %in% c("family", "link", "sims", "noise_min_step", "noise_1st_step", "noise_3rd_step", "noise_max_step", "authentic_min_step", "authentic_1st_step", "authentic_3rd_step", "authentic_max_step", "noise_min_lasso", "noise_1st_lasso", "noise_3rd_lasso", "noise_max_lasso", "authentic_min_lasso", "authentic_1st_lasso", "authentic_3rd_lasso", "authentic_max_lasso", "noise_min_ridge", "noise_1st_ridge", "noise_3rd_ridge", "noise_max_ridge", "authentic_min_ridge", "authentic_1st_ridge", "authentic_3rd_ridge", "authentic_max_ridge", "noise_min_net", "noise_1st_net", "noise_3rd_net", "noise_max_net", "authentic_min_net", "authentic_1st_net", "authentic_3rd_net", "authentic_max_net")] # sim_long_median_df <- melt(sim_wide_df, id.vars = c("alpha", "n", "rho", "p"), # measure.vars = c("authentic_median", "noise_median"), # variable.name = "predictor_type", # value.name = "count", factorsAsStrings = FALSE) # sim_long_df_a5_rho0 <- sim_long_median_df[sim_long_median_df$alpha == 0.5 & # sim_long_median_df$rho == 0, ] # sim_long_df_a5_rho0_noise <- # sim_long_df_a5_rho0[sim_long_df_a5_rho0$predictor_type == "noise_median", ] # sim_long_df_a5_rho0_authentic <- # sim_long_df_a5_rho0[sim_long_df_a5_rho0$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a5_rho0_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a5_rho0_authentic, # aes(x=p, y=count, colour=n)) + # geom_line() # # sim_long_df_a15_rho0 <- sim_long_median_df[sim_long_median_df$alpha == 0.15 & # sim_long_median_df$rho == 0, ] # sim_long_df_a15_rho0_noise <- # sim_long_df_a15_rho0[sim_long_df_a15_rho0$predictor_type == "noise_median", ] # sim_long_df_a15_rho0_authentic <- # sim_long_df_a15_rho0[sim_long_df_a15_rho0$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a15_rho0_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a15_rho0_authentic, # aes(x=p, y=count, colour=n)) + # geom_line() # table(sim_long_median_df$alpha) # table(sim_long_median_df$rho) # # sim_long_df_a0016_rho0 <- sim_long_median_df[sim_long_median_df$alpha < 0.0017 & # sim_long_median_df$rho == 0, ] # sim_long_df_a0016_rho0_noise <- # sim_long_df_a0016_rho0[sim_long_df_a0016_rho0$predictor_type == "noise_median", ] # sim_long_df_a0016_rho0_authentic <- # sim_long_df_a0016_rho0[sim_long_df_a0016_rho0$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a0016_rho0_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a0016_rho0_authentic, # aes(x=p, y=count, colour=n)) + # geom_line() # ####### rho = 0.316 # sim_long_df_a5_rho3 <- sim_long_median_df[sim_long_median_df$alpha == 0.5 & # sim_long_median_df$rho > 0.3 & # sim_long_median_df$rho < 0.4, ] # sim_long_df_a5_rho3_noise <- # sim_long_df_a5_rho3[sim_long_df_a5_rho3$predictor_type == "noise_median", ] # sim_long_df_a5_rho3_authentic <- # sim_long_df_a5_rho3[sim_long_df_a5_rho3$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a5_rho3_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a5_rho3_authentic, # aes(x=p, y=count, colour=n)) + # geom_line() # # sim_long_df_a15_rho3 <- sim_long_median_df[sim_long_median_df$alpha == 0.15 & # sim_long_median_df$rho == 0, ] # sim_long_df_a15_rho3_noise <- # sim_long_df_a15_rho3[sim_long_df_a15_rho3$predictor_type == "noise_median", ] # sim_long_df_a15_rho3_authentic <- # sim_long_df_a15_rho3[sim_long_df_a15_rho3$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a15_rho3_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a15_rho3_authentic, # aes(x=p, y=count, colour=n)) + # geom_line() # table(sim_long_median_df$alpha) # table(sim_long_median_df$rho) # # sim_long_df_a0016_rho3 <- sim_long_median_df[sim_long_median_df$alpha < 0.0017 & # sim_long_median_df$rho == 0, ] # sim_long_df_a0016_rho3_noise <- # sim_long_df_a0016_rho3[sim_long_df_a0016_rho3$predictor_type == "noise_median", ] # sim_long_df_a0016_rho3_authentic <- # sim_long_df_a0016_rho3[sim_long_df_a0016_rho3$predictor_type == "authentic_median", ] # # ggplot(data=sim_long_df_a0016_rho3_noise, # aes(x=p, y=count, colour=n)) + # geom_line() # ggplot(data=sim_long_df_a0016_rho3_authentic, # aes(x=p, y=count, colour=n)) + # geom_line()
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.