pca.R

labels <- read.table("batches.meta.txt")
images.rgb <- list()
images.lab <- list()
num.images = 10000 # Set to 10000 to retrieve all images per file to memory

# Cycle through all 5 binary files
for (f in 1:5) {
  to.read <- file(paste("data_batch_", f, ".bin", sep=""), "rb")
  for(i in 1:num.images) {
    l <- readBin(to.read, integer(), size=1, n=1, endian="big")
    r <- as.integer(readBin(to.read, raw(), size=1, n=1024, endian="big"))
    g <- as.integer(readBin(to.read, raw(), size=1, n=1024, endian="big"))
    b <- as.integer(readBin(to.read, raw(), size=1, n=1024, endian="big"))
    index <- num.images * (f-1) + i
    images.rgb[[index]] = data.frame(r, g, b)
    images.lab[[index]] = l+1
  }
  close(to.read)
  remove(l,r,g,b,f,i,index, to.read)
}

# function to run sanity check on photos & labels import
drawImage <- function(index) {
  # Testing the parsing: Convert each color layer into a matrix,
  # combine into an rgb object, and display as a plot
  img <- images.rgb[[index]]
  img.r.mat <- matrix(img$r, ncol=32, byrow = TRUE)
  img.g.mat <- matrix(img$g, ncol=32, byrow = TRUE)
  img.b.mat <- matrix(img$b, ncol=32, byrow = TRUE)
  img.col.mat <- rgb(img.r.mat, img.g.mat, img.b.mat, maxColorValue = 255)
  dim(img.col.mat) <- dim(img.r.mat)

  # Plot and output label
  library(grid)
  grid.raster(img.col.mat, interpolate=FALSE)

  # clean up
  remove(img, img.r.mat, img.g.mat, img.b.mat, img.col.mat)

  labels[[1]][images.lab[[index]]]
}

draw_image_by_rgb <- function(rgb) {
  img <- matrix(rgb, nrow<-1024, ncol<-3)
  img.r.mat <- matrix(img[,1], ncol=32, byrow = TRUE)
  img.g.mat <- matrix(img[,2], ncol=32, byrow = TRUE)
  img.b.mat <- matrix(img[,3], ncol=32, byrow = TRUE)
  img.col.mat <- rgb(img.r.mat, img.g.mat, img.b.mat, maxColorValue = 255)
  dim(img.col.mat) <- dim(img.r.mat)

  # Plot and output label
  library(grid)
  grid.raster(img.col.mat, interpolate=FALSE)

  # clean up
  remove(img, img.r.mat, img.g.mat, img.b.mat, img.col.mat)
}


# drawImage(sample(1:(num.images*5), size=1))
bird_indices = which(images.lab == 3)

birds <- matrix(, nrow=5000, ncol=3072)
for (i in 1:5000) {
	birds[i,] <- as.vector(t(images.rgb[[i]]))
}

birds_df <- data.frame(birds)
pca_result <- princomp(birds_df)
pca_20 <- pca_result$loadings[, 1:20]
pca_20 <- t(pca_20)
p <- data.frame(pca_20)
names(p) <- c(1:3072)