Question

我感兴趣的是找到MNIST数据集的随机森林分类器在R中错误预测的数字。尤其是每个数字（0-9）的示例。以下是我尝试过的。但是，我不断收到错误Error in y + 1 : non-numeric argument to binary operator，但不确定如何解决该错误。我认为以下是通常只获取最差数字的方法，因此，是否有可能通过更改此方法来获取每个数字的示例？

# The below code is copied directly from https://gist.github.com/daviddalpiaz/ae62ae5ccd0bada4b9acd6dbc9008706
# and https://gist.github.com/brendano/39760

# download data from http://yann.lecun.com/exdb/mnist/
download.file("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz",
              "train-images-idx3-ubyte.gz")
download.file("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz",
              "train-labels-idx1-ubyte.gz")
download.file("http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz",
              "t10k-images-idx3-ubyte.gz")
download.file("http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz",
              "t10k-labels-idx1-ubyte.gz")

# gunzip the files
R.utils::gunzip("train-images-idx3-ubyte.gz")
R.utils::gunzip("train-labels-idx1-ubyte.gz")
R.utils::gunzip("t10k-images-idx3-ubyte.gz")
R.utils::gunzip("t10k-labels-idx1-ubyte.gz")  

# load image files
load_image_file = function(filename) {
  ret = list()
  f = file(filename, 'rb')
  readBin(f, 'integer', n = 1, size = 4, endian = 'big')
  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 = n * nrow * ncol, size = 1, signed = FALSE)
  close(f)
  data.frame(matrix(x, ncol = nrow * ncol, byrow = TRUE))
}

# load label files
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 = FALSE)
  close(f)
  y
}

# load images
train = load_image_file("train-images-idx3-ubyte")
test  = load_image_file("t10k-images-idx3-ubyte")

# load labels
train$y = as.factor(load_label_file("train-labels-idx1-ubyte"))
test$y  = as.factor(load_label_file("t10k-labels-idx1-ubyte"))

library(randomForest)
# testing classification on subset of training data
model.rf<-randomForest(y ~ ., data = train[1:1000, ])
model.rf$confusion

#Using model on test set
predict.rf = predict(model.rf, test)
mean(predict.rf == test$y)
table(predicted = predict.rf, actual = test$y)

iset <- sample(which(predict.rf != ytest),7*7)
par(mar=c(0,0,0,0))
par(mfrow=c(7,7))
for (j in iset) {
  y <- matrix(as.matrix(test[j,-1]),16,16,byrow=TRUE)
  y <- 1 - (y + 1)*0.5
  
  plot(0,0,xlab="",ylab="",axes=FALSE)
  rasterImage(y,-1,-1,1,1)
  box()
  text(-0.8,-0.7, test[j,1], cex=3, col="red")
  text(0.8,-0.7, predict.rf[j], cex=3, col="blue")
}

使用随机森林

0 个答案: