bart_machine_get_posterior {bartMachine}

Get Full Posterior Distribution

Description

Generates draws from posterior distribution of \hat{f}(x) for a specified set of observations.

Usage

bart_machine_get_posterior(bart_machine, new_data)

Arguments

bart_machine

An object of class “bartMachine”.

new_data

A data frame containing observations at which draws from posterior distribution of \hat{f}(x) are to be obtained.

Value

Returns a list with the following components:

y_hat

Posterior mean estimates. For regression, the estimates have the same units as the response. For classification, the estimates are probabilities.

new_data

The data frame with rows at which the posterior draws are to be generated. Column names should match that of the training data.

y_hat_posterior_samples

The full set of posterior samples of size num_iterations_after_burn_in for each observation. For regression, the estimates have the same units as the response. For classification, the estimates are probabilities.

Note

This function is parallelized by the number of cores set in set_bart_machine_num_cores.

Author(s)

Adam Kapelner and Justin Bleich

See Also

calc_credible_intervals, calc_prediction_intervals

Examples

## Not run: 
#Regression example

#generate Friedman data
set.seed(11)
n  = 200 
p = 5
X = data.frame(matrix(runif(n * p), ncol = p))
y = 10 * sin(pi* X[ ,1] * X[,2]) +20 * (X[,3] -.5)^2 + 10 * X[ ,4] + 5 * X[,5] + rnorm(n)

##build BART regression model
bart_machine = bartMachine(X, y)

#get posterior distribution
posterior = bart_machine_get_posterior(bart_machine, X)
print(posterior$y_hat)


#Classification example

#get data and only use 2 factors
data(iris)
iris2 = iris[51:150,]
iris2$Species = factor(iris2$Species)

#build BART classification model
bart_machine = bartMachine(iris2[ ,1 : 4], iris2$Species)

#get posterior distribution
posterior = bart_machine_get_posterior(bart_machine, iris2[ ,1 : 4])
print(posterior$y_hat)

## End(Not run)