descriptron-core 2.0.1__tar.gz → 2.0.3__tar.gz

{descriptron_core-2.0.1 → descriptron_core-2.0.3}/NOTICE

@@ -14,9 +14,12 @@ Anyone who uses Descriptron, or any software derived from it (including
 descriptron-core, descriptron-vision, descriptron-gui and descriptron-mcp), in
 work that is published, presented or distributed must cite:
 
-  1. The software (Descriptron v2):
-     Van Dam, A. R. Descriptron (version used). GitHub repository.
-     https://github.com/alexrvandam/Descriptron
+  1. The software (Descriptron v2), by the DOI of the version used:
+     Van Dam, A. R. (2026). Descriptron: morphology-driven species descriptions,
+     keys and delimitation for dark taxa (Version 2.0.1). Zenodo.
+     https://doi.org/10.5281/zenodo.22918056
+     (all versions: https://doi.org/10.5281/zenodo.17077224;
+      repository: https://github.com/alexrvandam/Descriptron)
 
   2. The first Descriptron paper:
      Van Dam, A. R. & Štarhová Serbina, L. (2026). Descriptron: Artificial
@@ -29,11 +32,15 @@ work that is published, presented or distributed must cite:
 
 BibTeX:
 
-@misc{vandam_descriptron_software,
-  author       = {Van Dam, Alex R.},
-  title        = {Descriptron},
-  howpublished = {GitHub repository},
-  url          = {https://github.com/alexrvandam/Descriptron}
+@software{vandam_2026_descriptron_v201,
+  author    = {Van Dam, Alex R.},
+  title     = {Descriptron: morphology-driven species descriptions, keys and
+               delimitation for dark taxa},
+  version   = {v2.0.1},
+  year      = {2026},
+  publisher = {Zenodo},
+  doi       = {10.5281/zenodo.22918056},
+  url       = {https://doi.org/10.5281/zenodo.22918056}
 }
 
 @article{vandam2026descriptron,

{descriptron_core-2.0.1 → descriptron_core-2.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: descriptron-core
-Version: 2.0.1
+Version: 2.0.3
 Summary: Evidence-tiered species descriptions, keys and audits from phenomic matrices
 Project-URL: Homepage, https://github.com/alexrvandam/Descriptron
 Project-URL: Repository, https://github.com/alexrvandam/Descriptron

{descriptron_core-2.0.1 → descriptron_core-2.0.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "descriptron-core"
-version = "2.0.1"
+version = "2.0.3"
 description = "Evidence-tiered species descriptions, keys and audits from phenomic matrices"
 readme = "README.md"
 requires-python = ">=3.9"

descriptron_core-2.0.3/pyproject.toml.bak_pre_203_20260924_145320

@@ -0,0 +1,81 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "descriptron-core"
+version = "2.0.2"
+description = "Evidence-tiered species descriptions, keys and audits from phenomic matrices"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Alex R. Van Dam" }]
+keywords = ["taxonomy", "morphometrics", "phenomics", "species description", "COCO"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Topic :: Scientific/Engineering :: Bio-Informatics",
+  "Topic :: Scientific/Engineering :: Image Processing",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Operating System :: OS Independent",
+]
+
+# Derived from the imports of the 62 programs in this package, not from memory:
+# `python -m descriptron_core.cli --list` names them. No torch, no CUDA, no
+# compiler — this installs in about a minute on Linux, macOS and Windows, and
+# with the deposited COCO files it reproduces every analysis in the methods paper.
+dependencies = [
+  "numpy>=1.23",
+  "pandas>=1.5",
+  "scipy>=1.9",
+  "matplotlib>=3.6",
+  "scikit-learn>=1.2",
+  "scikit-image>=0.20",
+  "opencv-python-headless>=4.7",   # headless: the analysis half never opens a window
+  "pillow>=9",
+  "pycocotools>=2.0.6",
+  "seaborn>=0.12",
+  "statsmodels>=0.14",
+  "scikit-posthocs>=0.7",
+  "umap-learn>=0.5",
+  "networkx>=3",
+  "pyefd>=1.6",
+  "biopython>=1.81",
+  "PyYAML>=6",
+  "lxml>=4.9",
+  "openpyxl>=3.1",
+  "python-docx>=1.0",              # treatment and monograph .docx export
+]
+
+[project.optional-dependencies]
+# Only needed to *write* treatments. The audit, key, matrix, novelty scoring and
+# delimitation are all deterministic and need no model at all.
+llm = ["anthropic>=0.40"]
+# literature retrieval (the RAG in BioRAG): BioSysLit treatments from Zenodo and your
+# own PDFs. Keyword retrieval needs only the first two; sentence-embedding retrieval
+# (`index --embeddings`) also needs sentence-transformers + faiss-cpu, which pull in torch.
+rag = ["requests>=2.28", "pdfplumber>=0.10"]
+rag-embeddings = ["requests>=2.28", "pdfplumber>=0.10", "sentence-transformers>=2.2", "faiss-cpu>=1.7"]
+dev = ["pytest>=7", "build>=1", "twine>=5"]
+
+[project.scripts]
+descriptron        = "descriptron_core.cli:main"
+biorag-pipeline    = "descriptron_core.cli:run_pipeline"
+biorag-key         = "descriptron_core.cli:run_key_builder"
+biorag-audit       = "descriptron_core.cli:run_confabulation_checker"
+biorag-novelty     = "descriptron_core.cli:run_novelty_score"
+biorag-calibrate   = "descriptron_core.cli:run_calibrate"
+
+[project.urls]
+Homepage = "https://github.com/alexrvandam/Descriptron"
+Repository = "https://github.com/alexrvandam/Descriptron"
+Issues = "https://github.com/alexrvandam/Descriptron/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/descriptron_core"]
+
+# tools/ and data/ sit inside the package directory, so `packages` already ships
+# them; a force-include here would add every file a second time and the build
+# fails with "a second file is being added to the wheel archive at the same path".
+[tool.hatch.build]
+artifacts = ["src/descriptron_core/tools/**", "src/descriptron_core/data/**"]

{descriptron_core-2.0.1 → descriptron_core-2.0.3}/src/descriptron_core/tools/biorag_key_feature_filter_v2.py

@@ -216,6 +216,7 @@ def drop_flagged(df: pd.DataFrame, flags: pd.DataFrame, report: dict,
     """Remove flagged image x structure rows; remove the whole image when
     >= whole_image_min of its structures are flagged (wrong-scale signature)."""
     if flags is None or not len(flags):
+        report["flagged_rows_removed"] = {"whole_images": [], "rows_removed": 0}
         return df
     per_img = flags.groupby("image_base")["category"].nunique()
     bad_imgs = set(per_img[per_img >= whole_image_min].index)