Overlay decision boundary for random forests and boostings - r

Question

I generate some random data and am trying to overlay a decision boundary based upon fitting using random forests and boosting. I can recreate the problem below. I generate the data, and using regression trees I can easily overlay the decision boundary using the following code:
library(tidyverse)
# set seed and generate some random data
set.seed(123)
Dat <- tibble(
x1 = rnorm(100),
x2 = rnorm(100)
) %>% mutate(y = as_factor(ifelse(x1^2 + x2^2 > 1.39, "A", "B")))
circlepts <- tibble(theta = seq(0, 2*pi, length = 100)) %>%
mutate(x = sqrt(1.39) * sin(theta), y = sqrt(1.39) * cos(theta))
# graph the data and draw the boundary
p <- ggplot(Dat) + geom_point(aes(x1, x2, color = y)) + coord_fixed() +
geom_polygon(data = circlepts, aes(x, y), color = "blue", fill = NA)
# convert character to binary inputs making classification easier
binVec = as.vector(Dat$y)
binVec[which(binVec =="A")] = 1
binVec[which(binVec == "B")] = 0
binVec = as.numeric(binVec)
Dat$y = binVec
# split the data up
datasplit <- initial_split(Dat, prop = 0.7)
training_set <- as_tibble(training(datasplit))
testing_set <- as_tibble(testing(datasplit))
tree_fit <- tree(y~ ., training_set)
grid <- crossing(x1 = modelr::seq_range(testing_set$x1, 50), x2 = modelr::seq_range(testing_set$x1, 50)) %>%
modelr::add_predictions(tree_fit)
# plot the data with the decision overlay of the tree fit
p + geom_contour(data = grid, aes(x2, x1, z = as.numeric(pred)), binwidth = 1)
Now if I try doing so with random forests or gradient boosting, add_predictions doesn't cooperate that well...
rf_fit <- randomForest(y ~ ., data=training_set, mtry = 2, ntree=500)
grid <- crossing(x1 = modelr::seq_range(testing_set$x1, 50), x2 = modelr::seq_range(testing_set$x1, 50)) %>%
modelr::add_predictions(rf_fit)
p + geom_contour(data = grid, aes(x2, x1, z = as.numeric(pred)), binwidth = 1)
##ERROR: Error in if (is.na(out.type)) stop("type must be one of 'response', 'prob', 'vote'") : argument is of length zero
And for gradient boosting:
fitBoost <- gbm(y ~ ., data= Dat, distribution = "gaussian",
n.trees = 1000)
pred <- predict(fitBoost, newdata=training_set, n.trees=1000)
grid <- crossing(x1 = modelr::seq_range(testing_set$x1, 50), x2 = modelr::seq_range(testing_set$x1, 50)) %>%
modelr::add_predictions(fitBoost)
### ERROR: Error in paste("Using", n.trees, "trees...\n") : argument "n.trees" is missing, with no default
It seems to be a very simple problem. Could someone help me out?

Answer 1

The following code works with your random forest:
training_set$y <- factor(training_set$y)
rf_fit <- randomForest(y ~ ., data=training_set, mtry=2, ntree=500)
grid <- crossing(x1 = modelr::seq_range(testing_set$x1, 50),
x2 = modelr::seq_range(testing_set$x1, 50)) %>%
modelr::add_predictions(rf_fit)
p + geom_contour(data = grid, aes(x2, x1, z = as.numeric(pred)), binwidth = 1)
And here is the code for the gradient boosting machine:
fitBoost <- gbm(y ~ ., data=Dat, distribution="gaussian", n.trees=1000)
pred <- predict(fitBoost, newdata=training_set, n.trees=1000)
add_predictions2 <- function (data, model, var = "pred", type = NULL)
{
data[[var]] <- predict2(model, data, type = type)
data
}
predict2 <- function (model, data, type = NULL)
{
if (is.null(type)) {
stats::predict(model, data, n.trees=1000)
} else {
stats::predict(model, data, type = type, n.trees=1000)
}
}
grid <- crossing(x1 = modelr::seq_range(testing_set$x1, 50),
x2 = modelr::seq_range(testing_set$x1, 50)) %>%
add_predictions2(fitBoost)
p + geom_contour(data = grid, aes(x2, x1, z = as.numeric(pred)), binwidth = 1)