Package: tensorsem 2.1.0
tensorsem: Estimate structural equation models using computation graphs
Use lavaan code to create structural equation models, use torch to estimate them. This package provides the interface between lavaan and torch.
Authors:
tensorsem_2.1.0.tar.gz
tensorsem_2.1.0.zip(r-4.5)tensorsem_2.1.0.zip(r-4.4)tensorsem_2.1.0.zip(r-4.3)
tensorsem_2.1.0.tgz(r-4.4-any)tensorsem_2.1.0.tgz(r-4.3-any)
tensorsem_2.1.0.tar.gz(r-4.5-noble)tensorsem_2.1.0.tar.gz(r-4.4-noble)
tensorsem_2.1.0.tgz(r-4.4-emscripten)tensorsem_2.1.0.tgz(r-4.3-emscripten)
tensorsem.pdf |tensorsem.html✨
tensorsem/json (API)
| # Install 'tensorsem' in R: |
| install.packages('tensorsem', repos = c('https://vankesteren.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/vankesteren/tensorsem/issues
computation-graphlavaansemtorch
Last updated 1 years agofrom:d0471473c1. Checks:OK: 5 NOTE: 2. Indexed: yes.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | OK | Aug 15 2024 |
| R-4.5-win | NOTE | Aug 15 2024 |
| R-4.5-linux | NOTE | Aug 15 2024 |
| R-4.4-win | OK | Aug 15 2024 |
| R-4.4-mac | OK | Aug 15 2024 |
| R-4.3-win | OK | Aug 15 2024 |
| R-4.3-mac | OK | Aug 15 2024 |
Exports:df_to_tensorlav_mod_to_torch_optsmvn_negloglikpartable_from_torchsyntax_to_torch_optstorch_semtorch_vech
Dependencies:bitbit64callrclicorodescellipsisgluejsonlitelavaanmagrittrMASSmnormtnumDerivpbivnormprocessxpsquadprogR6Rcpprlangsafetensorstorchwithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Prepare data for tensorsem model | df_to_tensor |
| Create a torch options list from a lavaan Model class. | lav_mod_to_torch_opts |
| Multivariate normal negative log-likelihood loss function for tensorsem nn module. | mvn_negloglik |
| Create a lavaan parameter table from torch free_params output | partable_from_torch |
| SEM fitting function | sem_fitfun |
| Create a torch options list from lavaan syntax. | syntax_to_torch_opts |
| Compute jacobian of output wrt input tensor | torch_jacobian |
| Structural equation model with a Torch backend | torch_sem |
| Half-vectorization of square matrices | torch_vech |
| Constructs index vector for transforming a vech vector into a vec vector to create an n*n symmetric matrix from the vech vector. tensor$index_select(0, idx)$view(3,3) | vech_dup_idx |
