Package: autotab 1.0.1

autotab: Variational Autoencoders for Heterogeneous Tabular Data

Build and train a variational autoencoder (VAE) for mixed-type tabular data (continuous, binary, categorical). Models are implemented using 'TensorFlow' and 'Keras' via the 'reticulate' interface, enabling reproducible VAE training for heterogeneous tabular datasets.

Authors:Sarah Milligan [aut, cre]

autotab_1.0.1.tar.gz
autotab_1.0.1.zip(r-4.7)autotab_1.0.1.zip(r-4.6)autotab_1.0.1.zip(r-4.5)
autotab_1.0.1.tgz(r-4.6-any)autotab_1.0.1.tgz(r-4.5-any)
autotab_1.0.1.tar.gz(r-4.7-any)autotab_1.0.1.tar.gz(r-4.6-any)
autotab_1.0.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
autotab/json (API)

# Install 'autotab' in R:

install.packages('autotab', repos = c('https://sarahmilligan-hub.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/sarahmilligan-hub/autotab/issues

Datasets:

data_example - Health and Demographics Dataset

On CRAN:

3.48 score 3 scripts 530 downloads 12 exports 33 dependencies

Last updated from:79b903e622. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	132
source / vignettes	OK	231
linux-release-x86_64	OK	151
macos-release-arm64	OK	136
macos-oldrel-arm64	OK	152
windows-devel	OK	82
windows-release	OK	78
windows-oldrel	OK	85
wasm-release	OK	118

Exports:decoder_model Decoder_weights encoder_latent Encoder_weights extracting_distribution feat_reorder get_feat_dist Latent_sample min_max_scale reset_seeds set_feat_dist VAE_train

Dependencies:backports base64enc cli config generics glue here jsonlite keras lattice lifecycle magrittr Matrix png processx ps R6 rappdirs Rcpp RcppTOML reticulate rlang rprojroot rstudioapi tensorflow tfautograph tfruns tidyselect vctrs whisker withr yaml zeallot

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Health and Demographics Dataset	data_example
Builds the decoder graph for an AutoTab VAE	decoder_model
Extract decoder-only weights from a trained Keras model	Decoder_weights
Specifying Encoder and Decoder Architectures for 'VAE_train()'	encoder_decoder_information
Rebuild the encoder graph to export z_mean and z_log_var	encoder_latent
Extract encoder-only weights from a trained Keras model	Encoder_weights
Build the 'feat_dist' data frame for AutoTab	extracting_distribution
Reorder 'feat_dist' rows to match preprocessed data	feat_reorder
Get the stored feature distribution	get_feat_dist
Sample from the latent space	Latent_sample
Min–max scale continuous variables	min_max_scale
Mixture-of-Gaussians (MoG) prior in AutoTab	mog_prior
Reset all random seeds across R, TensorFlow, and Python	reset_seeds
Set the feature distribution for AutoTab	set_feat_dist
Train an AutoTab VAE on mixed-type tabular data	VAE_train