https://github.com/colemonnahan/hmc_tests

Testing HMC/NUTS for ADMB and TMB

https://github.com/colemonnahan/hmc_tests

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 2 DOI reference(s) in README
  • Academic publication links
  • Committers with academic emails
    1 of 1 committers (100.0%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Testing HMC/NUTS for ADMB and TMB

Basic Info
  • Host: GitHub
  • Owner: colemonnahan
  • Language: R
  • Default Branch: master
  • Size: 763 MB
Statistics
  • Stars: 2
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created almost 10 years ago · Last pushed over 6 years ago
Metadata Files
Readme

README.md

Performance tests for no-U-turn sampling for TMB and ADMB vs. Stan

This repository contains code, data, and models to recreate the analysis in the paper:

Monnahan CC, Kristensen K (2018) No-U-turn sampling for fast Bayesian inference in ADMB and TMB: Introducing the adnuts and tmbstan R packages. PLoS ONE 13(5): e0197954. https://doi.org/10.1371/journal.pone.0197954

The repository evolved from some previous testing code which is left for now and should be ignored. The plots folder contains extra performance plots, the models folder the models and data, and the results folder saved output from running the R scripts.

The paper has three components with scripts to recreate them:

Demonstration of features

This can recreated by executing the file run_demo.R and shows basic functionality of the two packages using two real models.

Laplace approximation checks

The paper includes a component where a TMB model is run with and without the Laplace approximation turned on, in order to test the accuracy of this on the fixed effects. The file run_laplace.R recreates this analysis. Note that this takes a long time to run.

Performance testing

The supplementary material has a more thorough exploration of peformance between the three software platforms: Stan, TMB, and ADMB, using their respective R packages (rstan, tmbstan, adnuts). This is run on two simulated models with increasing dimensionality (zdiag and growth) as well as three "real" models. The file run_analysis.R recreates this part. It takes a long time and is not setup to run in parallel.

Owner

  • Name: Cole Monnahan
  • Login: colemonnahan
  • Kind: user
  • Location: Seattle, WA

Personal account. See @Cole-Monnahan-NOAA for professional account.

GitHub Events

Total
Last Year

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 421
  • Total Committers: 1
  • Avg Commits per committer: 421.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
colemonnahan m****c@u****u 421
Committer Domains (Top 20 + Academic)
uw.edu: 1

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 3
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
  • colemonnahan (2)
Top Labels
Issue Labels
Pull Request Labels