Package: SEMdeep 0.1.1

SEMdeep: Structural Equation Modeling with Deep Neural Network and Machine Learning

Training and validation of a custom (or data-driven) Structural Equation Models using layer-wise Deep Neural Networks or node-wise Machine Learning algorithms, which extend the fitting procedures of the 'SEMgraph' R package <doi:10.32614/CRAN.package.SEMgraph>.

Authors:Mario Grassi [aut], Barbara Tarantino [aut, cre]

SEMdeep_0.1.1.tar.gz
SEMdeep_0.1.1.zip(r-4.5)SEMdeep_0.1.1.zip(r-4.4)SEMdeep_0.1.1.zip(r-4.3)
SEMdeep_0.1.1.tgz(r-4.4-any)SEMdeep_0.1.1.tgz(r-4.3-any)
SEMdeep_0.1.1.tar.gz(r-4.5-noble)SEMdeep_0.1.1.tar.gz(r-4.4-noble)
SEMdeep_0.1.1.tgz(r-4.4-emscripten)SEMdeep_0.1.1.tgz(r-4.3-emscripten)
SEMdeep.pdf |SEMdeep.html✨
SEMdeep/json (API)
NEWS

# Install 'SEMdeep' in R:

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

Bug tracker:https://github.com/barbaratarantino/semdeep/issues

On CRAN:

3.40 score 1 stars 129 downloads 12 exports 120 dependencies

Last updated 2 months agofrom:5f9e6b81c8. Checks:OK: 1 NOTE: 6. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Nov 03 2024
R-4.5-win	NOTE	Nov 03 2024
R-4.5-linux	NOTE	Nov 03 2024
R-4.4-win	NOTE	Nov 03 2024
R-4.4-mac	NOTE	Nov 03 2024
R-4.3-win	NOTE	Nov 03 2024
R-4.3-mac	NOTE	Nov 03 2024

Exports:benchmark getConnectionWeight getGradientWeight getInputPvalue getShapleyR2 mapGraph nplot predict.DNN predict.ML predict.SEM SEMdnn SEMml

Dependencies:abind aspect backports BH BiocGenerics BiocManager bit bit64 bitops boot callr checkmate cherry cito class cli codetools colorspace condMVNorm coro corpcor cpp11 crayon curl dagitty data.table desc dplyr e1071 ellipsis fansi farver filelock flip foreach fs gdata generics ggm ggplot2 glasso glmnet glue graph gridExtra gtable gtools hms hommel igraph isoband iterators jpeg jsonlite labeling lattice lavaan lifecycle lme4 lpSolve magrittr MASS Matrix mgcv minqa mnormt munsell mvnfast mvtnorm NeuralNetTools nlme nloptr nnet numDeriv parabar pbapply pbivnorm pillar pkgconfig plyr png prettyunits processx progress protoclust proxy ps purrr quadprog R6 ranger rappdirs RBGL RColorBrewer Rcpp RcppArmadillo RcppEigen reshape2 Rgraphviz rlang safetensors scales SEMgraph shape shapr someMTP stringi stringr survival tibble tidyr tidyselect torch torchvision utf8 V8 vctrs viridisLite withr xgboost

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Prediction benchmark evaluation utility	benchmark
Connection Weight Approach for neural network variable importance	getConnectionWeight
Gradient Weight Approach for neural network variable importance	getGradientWeight
Test for the significance of neural network inputs	getInputPvalue
Compute variable importance using Shapley (R2) values	getShapleyR2
Map additional variables (nodes) to a graph object	mapGraph
Create a plot for a neural network model	nplot
SEM-based out-of-sample prediction using layer-wise DNN	predict.DNN
SEM-based out-of-sample prediction using node-wise ML	predict.ML
SEM-based out-of-sample prediction using layer-wise ordering	predict.SEM
Layer-wise SEM train with a Deep Neural Netwok (DNN)	SEMdnn
Nodewise-predictive SEM train using Machine Learning (ML)	SEMml