# Load the MNIST digit recognition dataset into R
# http://yann.lecun.com/exdb/mnist/
# assume you have all 4 files and gunzip'd them
# creates train$n, train$x, train$y  and test$n, test$x, test$y
# e.g. train$x is a 60000 x 784 matrix, each row is one digit (28x28)
# call:  show_digit(train$x[5,])   to see a digit.
# brendan o'connor - gist.github.com/39760 - anyall.org

load_mnist <- function() {
  load_image_file <- function(filename) {
    ret = list()
    f = file(filename,'rb')
    readBin(f,'integer',n=1,size=4,endian='big')
    ret$n = readBin(f,'integer',n=1,size=4,endian='big')
    nrow = readBin(f,'integer',n=1,size=4,endian='big')
    ncol = readBin(f,'integer',n=1,size=4,endian='big')
    x = readBin(f,'integer',n=ret$n*nrow*ncol,size=1,signed=F)
    ret$x = matrix(x, ncol=nrow*ncol, byrow=T)
    close(f)
    ret
  }
  
  load_label_file <- function(filename) {
    f = file(filename,'rb')
    readBin(f,'integer',n=1,size=4,endian='big')
    n = readBin(f,'integer',n=1,size=4,endian='big')
    y = readBin(f,'integer',n=n,size=1,signed=F)
    close(f)
    y
  }
  train <<- load_image_file('train-images-idx3-ubyte')
  test <<- load_image_file('t10k-images-idx3-ubyte')
  
  train$y <<- load_label_file('train-labels-idx1-ubyte')
  test$y <<- load_label_file('t10k-labels-idx1-ubyte')  
}


show_digit <- function(x, col=gray(12:1/12), title='image') {
  image(matrix(x, nrow=28)[,28:1], col=col, main=title)
}

#Basado en script de J.Jacques, univ. Lyon II

#Los archivos deben estar en la misma carpeta que este archivo y la sesión 
#debe ser la de la carpeta
# session -> set working directory -> to source file location 
load_mnist()

# cada fila de train$x contiene una imagen vectorializada,
# el número que aparece en esta imagen está en train$y

# ver la imagen
 numero=10
 show_digit(train$x[numero,],title=train$y[numero])

 par(mfrow=c(3,4))
 for (i in 0:9){
   show_digit(colMeans(train$x[train$y==i,]),title=i)
 }

show_digit(test$x[1,])