from_unstructured_to_deeppam_tensor: Transform unstructured data to an array / tensor that fits to...

In pkopper/deeppam: Machine Learning for Time-to-Event Data with Semi-Structured Deep Piecewise Additive Models

Description

This function transforms the unstrucutred data part. For static covariates (format == "standard") basically nothing happens. All other options are not yet implemented. This current version, however, covers all previous use cases such as Kopper et al. (2020).

Usage

from_unstructured_to_deeppam_tensor(
  data = list(),
  ped_tensor = NULL,
  format = "standard"
)

Arguments

data	a list of tensors. In the current implementeation each tensor must be processible by the respective network supplied to deeppam().
ped_tensor	the associated tensor brought into PED format by from_ped_to_tensor().
format	a character indicating which transformation is used. Currently only "standard has been implemented.

Value

a list of tensors to be supplied to the deep part of the network constructed by deeppam().

Author(s)

Philipp Kopper

pkopper/deeppam documentation built on Jan. 19, 2021, 12:39 a.m.