# Chapter 3 R examples:

# load the 'bayesrules' package
# May need to type
# install.packages("bayesrules")
# first.

library(bayesrules)
library(ggplot2)

#####
## Run this multiplot function code ONCE:
# Multiplot function for later: just run this once:
multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {
  library(grid)
  # Make a list from the ... arguments and plotlist
  plots <- c(list(...), plotlist)
  numPlots = length(plots)
  # If layout is NULL, then use 'cols' to determine layout
  if (is.null(layout)) {
    # Make the panel
    # ncol: Number of columns of plots
    # nrow: Number of rows needed, calculated from # of cols
    layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),
                    ncol = cols, nrow = ceiling(numPlots/cols))
  }

 if (numPlots==1) {
    print(plots[[1]])

  } else {
    # Set up the page
    grid.newpage()
    pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))
    # Make each plot, in the correct location
    for (i in 1:numPlots) {
      # Get the i,j matrix positions of the regions that contain this subplot
      matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))
      print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,
                                      layout.pos.col = matchidx$col))
    }
  }
}
## End multiplot function code
#############

# Plots of different beta distributions:

b1.5 <- plot_beta(1,5)+ggtitle("Beta(1,5)")
b1.2 <- plot_beta(1,2)+ggtitle("Beta(1,2)")
b3.7 <- plot_beta(3,7)+ggtitle("Beta(3,7)")
b1.1 <- plot_beta(1,1)+ggtitle("Beta(1,1)")
b5.5 <- plot_beta(5,5)+ggtitle("Beta(5,5)")
b20.20 <- plot_beta(20,20)+ggtitle("Beta(20,20)")
b7.3 <- plot_beta(7,3)+ggtitle("Beta(7,3)")
b2.1 <- plot_beta(2,1)+ggtitle("Beta(2,1)")
b5.1 <- plot_beta(5,1)+ggtitle("Beta(5,1)")

multiplot(b1.5, b1.2, b3.7, b1.1,b5.5,b20.20,b7.3,b2.1,b5.1, cols=3)

## Plots of different beta prior choices:

# Plot the Beta(9,11) prior
plot_beta(9,11,mean=T,mode=T)

# Plot the Beta(18,22) prior
plot_beta(18,22,mean=T,mode=T)

# Plot the Beta(45, 55) prior
plot_beta(45,55,mean=T,mode=T)

# Comparing the prior and the posterior in the political candidate example:

plot_beta_binomial(alpha = 45, beta = 55, y = 30, n = 50)

# prior and the posterior summary statistics in the political candidate example:

summarize_beta_binomial(alpha = 45, beta = 55, y = 30, n = 50)


# Credit Card Debt Example

## Researchers studied whether doctors completing residency take on high credit card debt.

# Let pi= population proportion of all medical residents with over $3000 in credit card debt

#  Prior belief:  20% do??

########### Analysis with beta(2,8) prior:

# Plot the Beta(2, 8) prior
plot_beta(2,8,mean=T,mode=T)

# Sample of 115 residents revealed 22 had credit card debt over $3000.

# Comparing the prior and the posterior in the credit card debt example:

plot_beta_binomial(alpha = 2, beta = 8, y = 22, n = 115)

# prior and the posterior summary statistics in the credit card debt example:

summarize_beta_binomial(alpha = 2, beta = 8, y = 22, n = 115)


########### Analysis with beta(1,1) (i.e., Uniform) prior:


# Sample of 115 residents revealed 22 had credit card debt over $3000.

# Comparing the prior and the posterior in the credit card debt example:

plot_beta_binomial(alpha = 1, beta = 1, y = 22, n = 115)

# prior and the posterior summary statistics in the credit card debt example:

summarize_beta_binomial(alpha = 1, beta = 1, y = 22, n = 115)