deephit | R Documentation |
DeepHit fits a neural network based on the PMF of a discrete Cox model. This is the single (non-competing) event implementation.
deephit( formula = NULL, data = NULL, reverse = FALSE, time_variable = "time", status_variable = "status", x = NULL, y = NULL, frac = 0, cuts = 10, cutpoints = NULL, scheme = c("equidistant", "quantiles"), cut_min = 0, activation = "relu", custom_net = NULL, num_nodes = c(32L, 32L), batch_norm = TRUE, dropout = NULL, device = NULL, mod_alpha = 0.2, sigma = 0.1, early_stopping = FALSE, best_weights = FALSE, min_delta = 0, patience = 10L, batch_size = 256L, epochs = 1L, verbose = FALSE, num_workers = 0L, shuffle = TRUE, ... )
formula |
|
data |
|
reverse |
|
time_variable |
|
status_variable |
|
x |
|
y |
|
frac |
|
cuts |
|
cutpoints |
|
scheme |
|
cut_min |
|
activation |
|
custom_net |
|
num_nodes, batch_norm, dropout |
|
device |
|
mod_alpha |
|
sigma |
|
early_stopping, best_weights, min_delta, patience |
|
batch_size |
|
epochs |
|
verbose |
|
num_workers |
|
shuffle |
|
... |
|
Implemented from the pycox
Python package via reticulate.
Calls pycox.models.DeepHitSingle
.
An object inheriting from class deephit
.
An object of class survivalmodel
.
Changhee Lee, William R Zame, Jinsung Yoon, and Mihaela van der Schaar. Deephit: A deep learning approach to survival analysis with competing risks. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018. http://medianetlab.ee.ucla.edu/papers/AAAI_2018_DeepHit
if (requireNamespaces("reticulate")) { # all defaults deephit(data = simsurvdata(50)) # common parameters deephit(data = simsurvdata(50), frac = 0.3, activation = "relu", num_nodes = c(4L, 8L, 4L, 2L), dropout = 0.1, early_stopping = TRUE, epochs = 100L, batch_size = 32L) }
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.