som-multimodal-datareduction 0.2.0__tar.gz

som_multimodal_datareduction-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "{}"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright {yyyy} {name of copyright owner}
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

som_multimodal_datareduction-0.2.0/NOTICE

@@ -0,0 +1,46 @@
+som-multimodal-datareduction
+Copyright 2026 Cameron B. Renteria
+
+This product includes software developed by third parties, redistributed here in
+original or MODIFIED form under their respective licenses. The overall pipeline,
+the HDF5 codebook schema, the de-widgetized command-line interface, the enamel
+feature set, and the dataset are original to this project; the SOM core and its
+visualization layer are not (see below).
+
+--------------------------------------------------------------------------------
+1. SOMPY  (vendored verbatim, except 3 imports - som_multimodal/_vendor/sompy/)
+--------------------------------------------------------------------------------
+   "SOMPY: A Python Library for Self Organizing Map (SOM)"
+   Copyright (c) Vahid Moosavi (@sevamoo) and contributors.
+   Licensed under the Apache License, Version 2.0.
+   https://github.com/sevamoo/SOMPY
+   Original license retained at som_multimodal/_vendor/sompy/LICENSE.
+
+--------------------------------------------------------------------------------
+2. tfprop_sompy  (MODIFIED - som_multimodal/engine/tfprop_vis.py, strings.py)
+--------------------------------------------------------------------------------
+   "tfprop_sompy: Self-Organizing Map Data-Mining for Thermo-Fluid Properties"
+   Developed by Gota Kikugawa and Yuta Nishimura (Tohoku University, Japan),
+   built on SOMPY. The files in som_multimodal/engine/ are MODIFIED versions of
+   that work; modifications Copyright 2026 Cameron B. Renteria, Apache-2.0.
+   Each modified file documents its changes in a header; see also
+   som_multimodal/engine/ACKNOWLEDGMENTS.md.
+
+--------------------------------------------------------------------------------
+3. Notebook / template lineage
+--------------------------------------------------------------------------------
+   The original Jupyter notebooks descend from SOM-lab teaching templates by
+   Tim Letz (University of Washington,
+   https://github.com/timletz/materials_datascience_uw_somlab) and the MSESOM
+   consolidation in the Huang group at the University of Washington.
+
+--------------------------------------------------------------------------------
+Dataset
+--------------------------------------------------------------------------------
+   data/general_main.csv accompanies, and should be cited as:
+   C. Renteria, W. Yan, Y. L. Huang, D. D. Arola, "Contributions to enamel
+   durability with aging: An application of data science tools," Journal of the
+   Mechanical Behavior of Biomedical Materials, vol. 129, 105147, 2022.
+   doi:10.1016/j.jmbbm.2022.105147
+
+This NOTICE file is provided for attribution and does not modify the License.

som_multimodal_datareduction-0.2.0/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: som-multimodal-datareduction
+Version: 0.2.0
+Summary: Self-Organizing-Map data reduction for multimodal materials data (nanomechanics + Raman + fracture), applied to tooth enamel.
+Author-email: "Cameron B. Renteria" <crentb@uw.edu>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/crentb/som-multimodal-datareduction
+Project-URL: Issues, https://github.com/crentb/som-multimodal-datareduction/issues
+Keywords: self-organizing map,SOM,unsupervised learning,multimodal,data reduction,clustering,materials science,tooth enamel,Raman,nanoindentation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy>=1.24
+Requires-Dist: scipy>=1.10
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: scikit-image>=0.20
+Requires-Dist: joblib>=1.2
+Requires-Dist: pandas>=1.5
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: tables>=3.8
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: ruff==0.14.10; extra == "dev"
+Requires-Dist: black==26.3.1; extra == "dev"
+Requires-Dist: mypy==1.17.1; extra == "dev"
+Requires-Dist: pre-commit>=3.7; extra == "dev"
+Dynamic: license-file
+
+# som-multimodal-datareduction
+
+> **Dataset & method paper - please cite:**
+> C. Renteria, W. Yan, Y. L. Huang, D. D. Arola, *"Contributions to enamel durability
+> with aging: An application of data science tools,"* **Journal of the Mechanical
+> Behavior of Biomedical Materials** 129, 105147 (2022).
+> doi:[10.1016/j.jmbbm.2022.105147](https://doi.org/10.1016/j.jmbbm.2022.105147)
+
+A reproducible, command-line pipeline that applies **Self-Organizing Maps (SOMs)** plus
+**k-means** to *multimodal* materials data - reducing high-dimensional, mixed-source
+measurements to interpretable maps. It is the de-widgetized, packaged version of the
+analysis behind the paper above, in which nanomechanical, Raman, and fracture
+measurements of tooth enamel are fused to map structure-property relationships with
+aging across species.
+
+The shipped dataset (`data/general_main.csv`, 138 measurements) carries eight features -
+modulus, hardness, carbonate, crystallinity, fluorescence, depth, fracture toughness
+(`kc`), and a crack-resistance parameter (`b`) - plus tooth/mammal/position metadata.
+
+## What it produces
+
+| Figure | Description |
+|--------|-------------|
+| `component_planes.png` | One heat map per feature over the trained SOM grid, k-means cluster borders overlaid - shows how each property varies and which co-vary. |
+| `cluster_map_by_<label>.png` | SOM nodes colored by k-means cluster, data points colored by a metadata column (e.g. `mammal`) - shows how groups distribute across the map. |
+| `umatrix.png` | Unified distance matrix (inter-node distances) with projected samples - reveals cluster boundaries. |
+| `cluster_diagnostics.png` | Elbow + silhouette vs. *k* to choose the cluster count. |
+
+## Install
+
+```bash
+git clone https://github.com/crentb/som-multimodal-datareduction.git
+cd som-multimodal-datareduction
+pip install -e ".[dev]"      # core + test/lint tools; or drop [dev] for runtime only
+```
+
+No GPU or deep-learning stack is required - only the standard scientific-Python
+libraries. The SOM core (SOMPY) is **vendored**, so nothing extra is fetched at install.
+
+## Quickstart
+
+End-to-end (train -> figures) on the bundled data:
+
+```bash
+som-pipeline --data-csv data/general_main.csv --n-clusters 6 --output-dir outputs
+```
+
+Or step by step:
+
+```bash
+som-train     --data-csv data/general_main.csv --mapsize 25 25 --output-dir outputs
+som-analysis  --output-dir outputs --k-min 2 --k-max 12      # pick k (elbow/silhouette)
+som-visualize --output-dir outputs --n-clusters 6 --label-column mammal
+```
+
+Every entry point shares the same flags (`--features`, `--mapsize`, `--normalization`,
+`--n-clusters`, `--label-column`, ...); run any with `-h` for the full list. Use
+`--features` to point the same pipeline at a different column set or dataset.
+
+## How it works
+
+```
+CSV --> train --> som_codebook.h5 --> visualize --> PNG figures
+        (SOMPY build+train,           (rebuild SOM, k-means
+         topographic/quantization      over codebook, render)
+         error, save codebook)
+```
+
+- **`config.RunConfig`** - one dataclass holding every parameter; shared by all CLIs.
+- **`train.py`** - builds a SOMPY map (`var` normalization, PCA init), trains it,
+  reports topographic + quantization error, and writes the codebook + data to HDF5.
+- **`io.py`** - the HDF5 schema (codebook / data / mapsize / feature names / specimen
+  ids), interchangeable with the original notebooks.
+- **`visualize.py`** - reloads the codebook, clusters it with k-means, and renders the
+  figures via the engine.
+- **`analysis.py`** - elbow + silhouette diagnostics for choosing *k*.
+
+## Repository layout
+
+```
+som_multimodal/
+  config.py  train.py  visualize.py  analysis.py  pipeline.py  io.py
+  engine/      MODIFIED tfprop_sompy visualization layer (credited)
+  _vendor/sompy/   vendored SOMPY core (Apache-2.0, verbatim)
+data/          general_main.csv + data dictionary
+tests/         fast, synthetic, CPU tests
+```
+
+## Attribution
+
+This project **builds on, and contains modified copies of, prior open-source work**;
+only the overall pipeline, the HDF5 schema, the CLI, the enamel feature set, and the
+dataset are original here.
+
+- **SOMPY** - Vahid Moosavi (@sevamoo) et al., Apache-2.0 - the SOM core, vendored.
+- **tfprop_sompy** - Gota Kikugawa & Yuta Nishimura (Tohoku University) - the
+  visualization layer, used here in **modified** form.
+- Notebook/template lineage: Tim Letz (UW SOM lab) and the Huang group (UW) MSESOM.
+
+Full details and per-file modification notes: [`NOTICE`](NOTICE) and
+[`som_multimodal/engine/ACKNOWLEDGMENTS.md`](som_multimodal/engine/ACKNOWLEDGMENTS.md).
+
+## Citing
+
+Please cite the **JMBBM 2022 paper** above (the dataset and method) and, optionally, this
+software via [`CITATION.cff`](CITATION.cff).
+
+## License
+
+[Apache-2.0](LICENSE). Vendored/modified upstream code is redistributed under its
+original Apache-2.0 terms with attribution preserved.

som_multimodal_datareduction-0.2.0/README.md

@@ -0,0 +1,111 @@
+# som-multimodal-datareduction
+
+> **Dataset & method paper - please cite:**
+> C. Renteria, W. Yan, Y. L. Huang, D. D. Arola, *"Contributions to enamel durability
+> with aging: An application of data science tools,"* **Journal of the Mechanical
+> Behavior of Biomedical Materials** 129, 105147 (2022).
+> doi:[10.1016/j.jmbbm.2022.105147](https://doi.org/10.1016/j.jmbbm.2022.105147)
+
+A reproducible, command-line pipeline that applies **Self-Organizing Maps (SOMs)** plus
+**k-means** to *multimodal* materials data - reducing high-dimensional, mixed-source
+measurements to interpretable maps. It is the de-widgetized, packaged version of the
+analysis behind the paper above, in which nanomechanical, Raman, and fracture
+measurements of tooth enamel are fused to map structure-property relationships with
+aging across species.
+
+The shipped dataset (`data/general_main.csv`, 138 measurements) carries eight features -
+modulus, hardness, carbonate, crystallinity, fluorescence, depth, fracture toughness
+(`kc`), and a crack-resistance parameter (`b`) - plus tooth/mammal/position metadata.
+
+## What it produces
+
+| Figure | Description |
+|--------|-------------|
+| `component_planes.png` | One heat map per feature over the trained SOM grid, k-means cluster borders overlaid - shows how each property varies and which co-vary. |
+| `cluster_map_by_<label>.png` | SOM nodes colored by k-means cluster, data points colored by a metadata column (e.g. `mammal`) - shows how groups distribute across the map. |
+| `umatrix.png` | Unified distance matrix (inter-node distances) with projected samples - reveals cluster boundaries. |
+| `cluster_diagnostics.png` | Elbow + silhouette vs. *k* to choose the cluster count. |
+
+## Install
+
+```bash
+git clone https://github.com/crentb/som-multimodal-datareduction.git
+cd som-multimodal-datareduction
+pip install -e ".[dev]"      # core + test/lint tools; or drop [dev] for runtime only
+```
+
+No GPU or deep-learning stack is required - only the standard scientific-Python
+libraries. The SOM core (SOMPY) is **vendored**, so nothing extra is fetched at install.
+
+## Quickstart
+
+End-to-end (train -> figures) on the bundled data:
+
+```bash
+som-pipeline --data-csv data/general_main.csv --n-clusters 6 --output-dir outputs
+```
+
+Or step by step:
+
+```bash
+som-train     --data-csv data/general_main.csv --mapsize 25 25 --output-dir outputs
+som-analysis  --output-dir outputs --k-min 2 --k-max 12      # pick k (elbow/silhouette)
+som-visualize --output-dir outputs --n-clusters 6 --label-column mammal
+```
+
+Every entry point shares the same flags (`--features`, `--mapsize`, `--normalization`,
+`--n-clusters`, `--label-column`, ...); run any with `-h` for the full list. Use
+`--features` to point the same pipeline at a different column set or dataset.
+
+## How it works
+
+```
+CSV --> train --> som_codebook.h5 --> visualize --> PNG figures
+        (SOMPY build+train,           (rebuild SOM, k-means
+         topographic/quantization      over codebook, render)
+         error, save codebook)
+```
+
+- **`config.RunConfig`** - one dataclass holding every parameter; shared by all CLIs.
+- **`train.py`** - builds a SOMPY map (`var` normalization, PCA init), trains it,
+  reports topographic + quantization error, and writes the codebook + data to HDF5.
+- **`io.py`** - the HDF5 schema (codebook / data / mapsize / feature names / specimen
+  ids), interchangeable with the original notebooks.
+- **`visualize.py`** - reloads the codebook, clusters it with k-means, and renders the
+  figures via the engine.
+- **`analysis.py`** - elbow + silhouette diagnostics for choosing *k*.
+
+## Repository layout
+
+```
+som_multimodal/
+  config.py  train.py  visualize.py  analysis.py  pipeline.py  io.py
+  engine/      MODIFIED tfprop_sompy visualization layer (credited)
+  _vendor/sompy/   vendored SOMPY core (Apache-2.0, verbatim)
+data/          general_main.csv + data dictionary
+tests/         fast, synthetic, CPU tests
+```
+
+## Attribution
+
+This project **builds on, and contains modified copies of, prior open-source work**;
+only the overall pipeline, the HDF5 schema, the CLI, the enamel feature set, and the
+dataset are original here.
+
+- **SOMPY** - Vahid Moosavi (@sevamoo) et al., Apache-2.0 - the SOM core, vendored.
+- **tfprop_sompy** - Gota Kikugawa & Yuta Nishimura (Tohoku University) - the
+  visualization layer, used here in **modified** form.
+- Notebook/template lineage: Tim Letz (UW SOM lab) and the Huang group (UW) MSESOM.
+
+Full details and per-file modification notes: [`NOTICE`](NOTICE) and
+[`som_multimodal/engine/ACKNOWLEDGMENTS.md`](som_multimodal/engine/ACKNOWLEDGMENTS.md).
+
+## Citing
+
+Please cite the **JMBBM 2022 paper** above (the dataset and method) and, optionally, this
+software via [`CITATION.cff`](CITATION.cff).
+
+## License
+
+[Apache-2.0](LICENSE). Vendored/modified upstream code is redistributed under its
+original Apache-2.0 terms with attribution preserved.

som_multimodal_datareduction-0.2.0/pyproject.toml

@@ -0,0 +1,112 @@
+# Packaging + tooling for som-multimodal-datareduction (PEP 621).
+# Editable-installable ("pip install -e .[dev]"); deps, lint/format/type config,
+# and test markers all live here so one config drives local dev and CI.
+#
+# The vendored SOM core (som_multimodal/_vendor) and the modified visualization
+# engine (som_multimodal/engine) are EXCLUDED from ruff/black/mypy: they are
+# upstream / upstream-derived code carried for fidelity, not held to this
+# project's style. The original-authored pipeline + tests ARE gated.
+[build-system]
+requires      = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name            = "som-multimodal-datareduction"
+version         = "0.2.0"
+description     = "Self-Organizing-Map data reduction for multimodal materials data (nanomechanics + Raman + fracture), applied to tooth enamel."
+readme          = "README.md"
+requires-python = ">=3.10"
+license         = { text = "Apache-2.0" }
+authors         = [{ name = "Cameron B. Renteria", email = "crentb@uw.edu" }]
+keywords = [
+    "self-organizing map", "SOM", "unsupervised learning", "multimodal",
+    "data reduction", "clustering", "materials science", "tooth enamel",
+    "Raman", "nanoindentation",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Visualization",
+]
+
+# Core runtime deps. No GPU / deep-learning stack: SOMPY needs only the standard
+# scientific Python libraries; `tables` (PyTables) backs the HDF5 codebook I/O.
+dependencies = [
+    "numpy>=1.24",
+    "scipy>=1.10",
+    "scikit-learn>=1.3",
+    "scikit-image>=0.20",   # vendored SOMPY's umatrix view uses skimage.feature.blob_log
+    "joblib>=1.2",          # vendored SOMPY imports joblib directly (also a sklearn dep)
+    "pandas>=1.5",
+    "matplotlib>=3.7",
+    "tables>=3.8",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0", "pytest-cov>=4.1", "ruff==0.14.10", "black==26.3.1", "mypy==1.17.1", "pre-commit>=3.7"]
+
+[project.scripts]
+som-train     = "som_multimodal.train:main"
+som-visualize = "som_multimodal.visualize:main"
+som-analysis  = "som_multimodal.analysis:main"
+som-pipeline  = "som_multimodal.pipeline:main"
+
+[project.urls]
+Homepage = "https://github.com/crentb/som-multimodal-datareduction"
+Issues   = "https://github.com/crentb/som-multimodal-datareduction/issues"
+
+[tool.setuptools.packages.find]
+where   = ["."]
+include = ["som_multimodal*"]
+
+[tool.setuptools.package-data]
+# Ship the vendored SOMPY license alongside the vendored code.
+"som_multimodal._vendor.sompy" = ["LICENSE"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+markers = [
+    "slow: full-size SOM training on the real dataset; skipped in default CI",
+]
+
+[tool.ruff]
+line-length    = 100
+target-version = "py310"
+# Vendored SOMPY + modified engine are not held to this project's lint rules.
+extend-exclude = ["som_multimodal/_vendor", "som_multimodal/engine"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]            # pycodestyle errors, pyflakes, isort
+ignore = ["E501", "E402", "F841"]   # long lines (black), import-after-stmt (CLIs), unused locals
+
+[tool.black]
+line-length    = 100
+target-version = ["py310", "py311", "py312"]
+extend-exclude = '''
+/(
+    som_multimodal/_vendor
+  | som_multimodal/engine
+)/
+'''
+
+[tool.mypy]
+python_version         = "3.10"
+ignore_missing_imports = true        # third-party libs (sompy, tables, ...) ship no stubs
+exclude                = ['som_multimodal/_vendor/', 'som_multimodal/engine/']
+
+# Treat the vendored SOMPY + modified engine as opaque: don't type-check them even
+# when the original-authored code imports them (they are upstream-derived).
+[[tool.mypy.overrides]]
+module          = ["som_multimodal._vendor.*", "som_multimodal.engine.*"]
+follow_imports  = "skip"
+ignore_errors   = true
+
+[tool.coverage.run]
+source = ["som_multimodal"]
+omit   = ["som_multimodal/_vendor/*", "som_multimodal/engine/*"]

som_multimodal_datareduction-0.2.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

som_multimodal_datareduction-0.2.0/som_multimodal/__init__.py

@@ -0,0 +1,30 @@
+"""
+som-multimodal-datareduction
+============================
+
+A reproducible, command-line pipeline that applies Self-Organizing Maps (SOMs)
+plus k-means to *multimodal* materials data -- reducing high-dimensional,
+mixed-source measurements (here: nanomechanics + Raman + fracture metrics on tooth
+enamel) to interpretable cluster maps and component planes.
+
+The SOM core (SOMPY) and its visualization layer (tfprop_sompy) are vendored and
+*modified* from prior open-source work; see ``som_multimodal/engine/ACKNOWLEDGMENTS.md``
+and ``NOTICE``. The pipeline, HDF5 schema, feature set, and dataset are original to
+this project.
+
+Public API:
+    RunConfig        -- one config object for the whole pipeline
+    DEFAULT_FEATURES -- the eight enamel feature columns
+
+Command-line entry points:
+    python -m som_multimodal.train       (or: som-train)
+    python -m som_multimodal.visualize   (or: som-visualize)
+    python -m som_multimodal.analysis    (or: som-analysis)
+    python -m som_multimodal.pipeline    (or: som-pipeline)
+"""
+
+from som_multimodal.config import DEFAULT_FEATURES, RunConfig
+
+__version__ = "0.1.0"
+
+__all__ = ["RunConfig", "DEFAULT_FEATURES", "__version__"]