cv_jdify: Cross validation for joint density classification

In tnagler/jdify: Joint density classification

Description

Performs k-fold cross validation for a jdify object.

Usage

cv_jdify(formula, data, jd_method = "cctools", folds = 10, cores = 1, ...)

Arguments

formula	an object of class "formula"; same as stats::lm().
data	matrix, data frame, list or environment (or object coercible by base::as.data.frame()) containing the variables in the model.
jd_method	an object of class "jd_method" defining the method for joint density estimation, see jd_method().
folds	number of folds.
cores	number of cores for parallelized cross validation (based on foreach::foreach()).
...	further arguments passed to fit_fun().

Value

A list with elements

• folds1``, ...,foldsk: for each fold: the fitted model$fit, estimated conditional probabilities ($probs), and indexes for training and test data ($train_index,$test_index').

• cv_probs: aggragated out-of-sample probs in same order as original data.

References

Nagler, T. (2017). A generic approach to nonparametric function estimation with mixed data. arXiv:1704.07457

Examples

# simulate training and test data
dat <- data.frame(
    cl = as.factor(rbinom(100, 1, 0.5)),
    x1 = rnorm(100),
    x2 =  ordered(rbinom(10, 1, 0.3), 0:1)
)

cv <- cv_jdify(cl ~ x1 + x2, dat)
probs <- cv$cv_probs
assess_clsfyr(probs[, 1], dat[, 1] == 0, measure = c("ACC", "F1"))

tnagler/jdify documentation built on May 31, 2019, 4:41 p.m.