sobig 0.1.0__tar.gz

sobig-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,20 @@
+name: publish
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+      - run: python -m pip install --upgrade build
+      - run: python -m build
+      - uses: pypa/gh-action-pypi-publish@release/v1

sobig-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,21 @@
+name: tests
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: python -m pip install --upgrade pip
+      - run: pip install -e ".[dev]"
+      - run: pytest

sobig-0.1.0/.gitignore

@@ -0,0 +1,24 @@
+TODO.md
+*.png
+*.tif
+*.csv
+*.odp
+*.pptx
+*.pdf
+scratch/*
+__pycache__/
+*.py[cod]
+*.so
+.Python
+.venv/
+venv/
+env/
+build/
+dist/
+*.egg-info/
+.pytest_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+.DS_Store
+.ipynb_checkpoints/

sobig-0.1.0/CHANGELOG.md

@@ -0,0 +1,7 @@
+# Changelog
+
+All changes to the project will be documented here.
+
+## [0.1.0] - Unreleased
+
+- Initial package release. Plan to upgrade to 1.0.0 when methods paper is ready for release.

sobig-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026, Drew Ellison Terasaki Hart, Geonomics Development Team
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sobig-0.1.0/PKG-INFO

@@ -0,0 +1,86 @@
+Metadata-Version: 2.5
+Name: sobig
+Version: 0.1.0
+Summary: Simulation of observations of biodiversity across gradients.
+Project-URL: Homepage, https://github.com/erthward/sobig
+Project-URL: Repository, https://github.com/erthward/sobig
+Project-URL: Issues, https://github.com/erthward/sobig/issues
+Author-email: Drew Terasaki Hart <drew.terasaki.hart@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2026, Drew Ellison Terasaki Hart, Geonomics Development Team
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: dms-variants
+Requires-Dist: matplotlib
+Requires-Dist: nlmpy
+Requires-Dist: numba
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: rasterio
+Requires-Dist: rioxarray
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: xarray
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Requires-Dist: twine>=5; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# SOBiG!
+
+##**S**imulation of **O**bservations of **Bi**odiversity across **G**radients
+
+A Python package for 'reverse-engineering' generalised dissimilarity modelling (GDM)
+to simulate communities distributed across variable landscapes,
+and then using a 'virtual ecologist' to simulate various observation processes on those communities.
+
+## Overview
+
+This package is designed for methods development in community ecology and biodiversity
+modelling. It 'reverse-engineers' generalised dissimilarity modelling (GDM), allowing
+the user to define environmental landscapes, monotonic environmental
+turnover functions (e.g. I-splines) that relate ecological community turnover to those landscapes' variables, the size of the regional species pool (i.e., gamma diversity), and the set of sampling locations. Then it simulates communities at all sampling locations and 
+uses a 'virtual ecologist' approach to simulate various observation processes on those communities
+(ranging from full-communtiy censuses, to abudance-absence, presence-absence, or presence-only (i.e., 'opportunistic') records.
+
+Workflows can be built from the following steps:
+
+1. Define a landscape and environmental turnover functions.
+2. Simulate the latent communities.
+3. Simulate one or more observation/survey processes.
+4. Fit/visualize GDM or other biodiversity models to the simulated data.
+5. Modify environmental layers to represent environmental change.
+6. Re-simulate communities and observations.
+
+See the documentation for the full API and examples.
+
+## Installation
+
+```bash
+pip install sobig
+```
+
+## License
+
+See `LICENSE`.

sobig-0.1.0/README.md

@@ -0,0 +1,37 @@
+# SOBiG!
+
+##**S**imulation of **O**bservations of **Bi**odiversity across **G**radients
+
+A Python package for 'reverse-engineering' generalised dissimilarity modelling (GDM)
+to simulate communities distributed across variable landscapes,
+and then using a 'virtual ecologist' to simulate various observation processes on those communities.
+
+## Overview
+
+This package is designed for methods development in community ecology and biodiversity
+modelling. It 'reverse-engineers' generalised dissimilarity modelling (GDM), allowing
+the user to define environmental landscapes, monotonic environmental
+turnover functions (e.g. I-splines) that relate ecological community turnover to those landscapes' variables, the size of the regional species pool (i.e., gamma diversity), and the set of sampling locations. Then it simulates communities at all sampling locations and 
+uses a 'virtual ecologist' approach to simulate various observation processes on those communities
+(ranging from full-communtiy censuses, to abudance-absence, presence-absence, or presence-only (i.e., 'opportunistic') records.
+
+Workflows can be built from the following steps:
+
+1. Define a landscape and environmental turnover functions.
+2. Simulate the latent communities.
+3. Simulate one or more observation/survey processes.
+4. Fit/visualize GDM or other biodiversity models to the simulated data.
+5. Modify environmental layers to represent environmental change.
+6. Re-simulate communities and observations.
+
+See the documentation for the full API and examples.
+
+## Installation
+
+```bash
+pip install sobig
+```
+
+## License
+
+See `LICENSE`.

sobig-0.1.0/docs/assumptions.md

@@ -0,0 +1,26 @@
+# Assumptions and limitations
+
+The initial simulator makes several deliberate simplifying assumptions.
+
+## Biogeographic assumptions
+
+- Species have an idealized climatic niche represented by a multivariate niche
+  center and niche width.
+- Species' niche centers are realized stochastically within the environmental
+  space represented by the supplied landscape.
+- Areas within a species' climatic niche are assumed to be reachable.
+- There is currently no explicit dispersal limitation or movement model.
+- There are no biotic interactions or competitive effects.
+- There is no explicit truncation of the climatic niche into a realized niche.
+- Spatial autocorrelation in occurrence patterns arises indirectly through
+  spatial structure in the environmental layers rather than through neighboring
+  occurrence states.
+
+## Observation assumptions
+
+Observation processes can be specified separately from the latent community,
+allowing multiple linked or nested datasets to be generated from the same
+underlying community.
+
+Document the precise detection, abundance, and reporting models here as the API
+is finalized.

sobig-0.1.0/docs/index.md

@@ -0,0 +1,19 @@
+# SOBiG documentation
+
+Documentation is under construction.
+
+## Planned sections
+
+- Installation
+- Quick-start example
+- Landscape and environmental layers
+- I-spline / turnover functions
+- Species niche generation
+- Latent community simulation
+- Observation-process simulation
+- Geographic, species-specific detection and reporting bias
+- Environmental change and re-simulation
+- Reproducing GDM relationships
+- API reference
+- Reproducibility and random seeds
+- Assumptions and limitations

sobig-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["hatchling>=1.25"]
+build-backend = "hatchling.build"
+
+[project]
+name = "sobig"
+version = "0.1.0"
+description = "Simulation of observations of biodiversity across gradients."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+authors = [
+  { name = "Drew Terasaki Hart", email = "drew.terasaki.hart@gmail.com" }
+]
+dependencies = [
+  "numpy",
+  "pandas",
+  "numba",
+  "nlmpy",
+  "scikit-learn",
+  "dms-variants",
+  "scipy",
+  "matplotlib",
+  "rasterio",
+  "xarray",
+  "rioxarray",
+]
+
+[project.optional-dependencies]
+dev = [
+  "pytest>=8",
+  "ruff>=0.6",
+  "build>=1.2",
+  "twine>=5",
+]
+
+[project.urls]
+Homepage = "https://github.com/erthward/sobig"
+Repository = "https://github.com/erthward/sobig"
+Issues = "https://github.com/erthward/sobig/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/sobig"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"

sobig-0.1.0/src/sobig/__init__.py

@@ -0,0 +1,7 @@
+"""Simulation of observations of biodiversity across gradients."""
+
+__version__ = "0.1.0"
+
+from .sobig import fEnv, Species, Sim, run_demo
+
+# Public API exports will go here as the package stabilizes.

sobig-0.1.0/src/sobig/_r/run_gdm.R

@@ -0,0 +1,42 @@
+library(gdm)
+library(terra)
+
+# get file paths
+args <- commandArgs(trailingOnly = TRUE)
+site_survey_filename = args[1]
+env_rast_filename = args[2]
+abundance = as.logical(args[3])
+fits_filename = args[4]
+pca_rast_filename = args[5]
+
+# read site-survey table
+site_survey = read.csv(site_survey_filename)
+
+# read environmental raster data
+env_rast = terra::rast(env_rast_filename)
+
+# format data for analysis
+site_pair = gdm::formatsitepair(bioData=site_survey,
+                                bioFormat=1,
+                                abundance=abundance,
+                                siteColumn='site',
+                                XColumn='x',
+                                YColumn='y',
+                                predData=env_rast)
+
+# fit GDM
+mod = gdm::gdm(site_pair, geo=F)
+print(summary(mod))
+
+# save fitted functions
+fits = as.data.frame(isplineExtract(mod))
+write.csv(fits, fits_filename)
+
+# save first <=3 PCs of GDM-transformed env space
+env_rast_trans <- gdm::gdm.transform(model=mod, data=env_rast)
+pca_samp <- terra::prcomp(env_rast_trans, maxcell = 5e5)
+n_pcs = min(3, dim(env_rast)[3])
+pca_rast <- terra::predict(env_rast_trans, pca_samp, index=1:n_pcs)
+pca_rast <- terra::stretch(pca_rast)
+terra::writeRaster(pca_rast, pca_rast_filename, overwrite=T)
+cat("\nGDM OUTPUTS SAVED TO DISK.\n")