damicore-clusterizer 0.1.0__tar.gz

damicore_clusterizer-0.1.0/.gitignore

@@ -0,0 +1,224 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+
+# Local scratch / generated output (never commit)
+.temp/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# LaTeX build artefacts (papers)
+models/**/paper/*.aux
+models/**/paper/*.bbl
+models/**/paper/*.bcf
+models/**/paper/*.blg
+models/**/paper/*.fdb_latexmk
+models/**/paper/*.fls
+models/**/paper/*.log
+models/**/paper/*.out
+models/**/paper/*.run.xml
+models/**/paper/*.synctex.gz
+models/**/paper/*.toc
+models/**/paper/*.pdf

damicore_clusterizer-0.1.0/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 2026 Ennio Politi Lopes
+
+   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.

damicore_clusterizer-0.1.0/PKG-INFO

@@ -0,0 +1,63 @@
+Metadata-Version: 2.5
+Name: damicore-clusterizer
+Version: 0.1.0
+Summary: FastGreedy clustering stage for the DAMICORE pipeline.
+Project-URL: Homepage, https://github.com/Delbem-Research-and-Innovation/damicore
+Project-URL: Repository, https://github.com/Delbem-Research-and-Innovation/damicore
+Project-URL: Issues, https://github.com/Delbem-Research-and-Innovation/damicore/issues
+Project-URL: Documentation, https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md
+Project-URL: Changelog, https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/CHANGELOG.md
+Author-email: Ennio Politi Lopes <enniolopes@users.noreply.github.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: clustering,community-detection,damicore,fastgreedy,modularity
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Typing :: Typed
+Requires-Python: <3.15,>=3.11
+Requires-Dist: igraph<1.1,>=1.0
+Requires-Dist: numpy<3,>=1.26
+Requires-Dist: pydantic<3,>=2.10
+Description-Content-Type: text/markdown
+
+# damicore-clusterizer
+
+damicore-clusterizer clusters every node of a validated DAMICORE tree with
+igraph FastGreedy and projects the resulting communities onto leaves. It is the
+fourth and final stage of the DAMICORE pipeline; most users install the
+aggregate `damicore` distribution, which runs all four stages end to end.
+Install this package alone to cluster trees without the rest of the pipeline.
+
+```bash
+pip install damicore-clusterizer
+```
+
+## Python
+
+```python
+from damicore_clusterizer import ClusterConfig, cluster_tree
+
+result = cluster_tree("tree.json", "run", config=ClusterConfig(num_clusters=None))
+```
+
+`tree.json` is produced by the sibling `damicore-tree-builder` distribution; the
+call writes cluster membership as `membership.csv` and `clusters.json`. Negative
+branch lengths receive one global shift, and output cluster IDs and leaf
+ordering are deterministic.
+
+## Links
+
+- Repository: <https://github.com/Delbem-Research-and-Innovation/damicore>
+- Issues: <https://github.com/Delbem-Research-and-Innovation/damicore/issues>
+- Documentation:
+  <https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md>
+
+Licensed under Apache-2.0.

damicore_clusterizer-0.1.0/README.md

@@ -0,0 +1,33 @@
+# damicore-clusterizer
+
+damicore-clusterizer clusters every node of a validated DAMICORE tree with
+igraph FastGreedy and projects the resulting communities onto leaves. It is the
+fourth and final stage of the DAMICORE pipeline; most users install the
+aggregate `damicore` distribution, which runs all four stages end to end.
+Install this package alone to cluster trees without the rest of the pipeline.
+
+```bash
+pip install damicore-clusterizer
+```
+
+## Python
+
+```python
+from damicore_clusterizer import ClusterConfig, cluster_tree
+
+result = cluster_tree("tree.json", "run", config=ClusterConfig(num_clusters=None))
+```
+
+`tree.json` is produced by the sibling `damicore-tree-builder` distribution; the
+call writes cluster membership as `membership.csv` and `clusters.json`. Negative
+branch lengths receive one global shift, and output cluster IDs and leaf
+ordering are deterministic.
+
+## Links
+
+- Repository: <https://github.com/Delbem-Research-and-Innovation/damicore>
+- Issues: <https://github.com/Delbem-Research-and-Innovation/damicore/issues>
+- Documentation:
+  <https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md>
+
+Licensed under Apache-2.0.

damicore_clusterizer-0.1.0/pyproject.toml

@@ -0,0 +1,60 @@
+[project]
+name = "damicore-clusterizer"
+version = "0.1.0"
+description = "FastGreedy clustering stage for the DAMICORE pipeline."
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Ennio Politi Lopes", email = "enniolopes@users.noreply.github.com" }]
+requires-python = ">=3.11,<3.15"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Typing :: Typed",
+]
+keywords = ["damicore", "clustering", "community-detection", "fastgreedy", "modularity"]
+dependencies = ["igraph>=1.0,<1.1", "numpy>=1.26,<3", "pydantic>=2.10,<3"]
+
+[project.urls]
+Homepage = "https://github.com/Delbem-Research-and-Innovation/damicore"
+Repository = "https://github.com/Delbem-Research-and-Innovation/damicore"
+Issues = "https://github.com/Delbem-Research-and-Innovation/damicore/issues"
+Documentation = "https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/docs/quickstart.md"
+Changelog = "https://github.com/Delbem-Research-and-Innovation/damicore/blob/main/CHANGELOG.md"
+
+[build-system]
+requires = ["hatchling>=1.31.0,<2"]
+build-backend = "hatchling.build"
+
+# Workspace-only files are excluded on purpose: each package's Makefile only includes
+# ../package.mk, pyrightconfig.json extends ../../pyrightconfig.json, and tests/ depends
+# on the workspace conftest and dev tooling, so none of them work in an sdist unpacked
+# outside the monorepo. The repository .gitignore still ships: hatchling force-includes
+# the located VCS ignore file so an sdist-to-wheel build selects files the same way, and
+# `exclude` deliberately cannot override that.
+[tool.hatch.build.targets.sdist]
+exclude = ["Makefile", "pyrightconfig.json", "tests"]
+
+[tool.ruff]
+line-length = 100
+exclude = [".venv", "dist", "__pycache__"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "RUF100", "UP"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+markers = ["unit: fast isolated unit tests"]
+# --cov-branch and the floor mirror the root configuration on purpose: coverage resolves
+# its config from the working directory, so a package-scoped run would otherwise report
+# line coverage with no threshold and read as a stronger result than it is.
+addopts = "--cov=damicore_clusterizer --cov-branch --cov-report=term-missing --cov-fail-under=90"

damicore_clusterizer-0.1.0/src/damicore_clusterizer/__init__.py

@@ -0,0 +1,6 @@
+from damicore_clusterizer.api import cluster_tree
+from damicore_clusterizer.config import ClusterConfig
+from damicore_clusterizer.errors import ClusterizerError
+from damicore_clusterizer.models import ClusterResult
+
+__all__ = ["cluster_tree", "ClusterConfig", "ClusterResult", "ClusterizerError"]

damicore_clusterizer-0.1.0/src/damicore_clusterizer/api.py

@@ -0,0 +1,69 @@
+from __future__ import annotations
+
+import time
+from pathlib import Path
+
+from damicore_clusterizer.artifacts import write_cluster_artifacts
+from damicore_clusterizer.config import ClusterConfig
+from damicore_clusterizer.errors import ClusterizerError
+from damicore_clusterizer.fastgreedy import fastgreedy_membership
+from damicore_clusterizer.models import ClusterResult
+from damicore_clusterizer.tree_graph import load_tree_graph
+
+
+def cluster_tree(
+    tree_path: str | Path,
+    output_dir: str | Path,
+    *,
+    config: ClusterConfig | None = None,
+) -> ClusterResult:
+    """Cluster every node in an unrooted tree and project communities to leaves."""
+    started = time.monotonic()
+    settings = config or ClusterConfig()
+    source = load_tree_graph(Path(tree_path).resolve())
+    if settings.num_clusters is not None and settings.num_clusters > len(source.object_ids):
+        raise ClusterizerError(
+            "num_clusters cannot exceed the leaf count", code="configuration_error"
+        )
+    membership, community_count, modularity = fastgreedy_membership(
+        source.graph,
+        settings.num_clusters,
+    )
+    names = source.vertex_names
+    raw_leaf_groups: dict[int, list[str]] = {}
+    for vertex_index, community in enumerate(membership):
+        name = str(names[vertex_index])
+        if name in source.object_ids:
+            raw_leaf_groups.setdefault(int(community), []).append(name)
+    ordered_groups = sorted(
+        (tuple(sorted(group)) for group in raw_leaf_groups.values() if group),
+        key=lambda group: group,
+    )
+    cluster_for = {
+        object_id: cluster for cluster, group in enumerate(ordered_groups) for object_id in group
+    }
+    if set(cluster_for) != set(source.object_ids):
+        raise ClusterizerError("Cluster membership is incomplete", code="clusterization_error")
+
+    destination = Path(output_dir).resolve()
+    destination.mkdir(parents=True, exist_ok=True)
+    if (destination / "membership.csv").exists() or (destination / "clusters.json").exists():
+        raise ClusterizerError(
+            "Cluster outputs already exist without a reusable receipt",
+            code="output_directory_conflict_error",
+        )
+    membership_path, clusters_path = write_cluster_artifacts(
+        destination,
+        source.object_ids,
+        source.labels,
+        cluster_for,
+        ordered_groups,
+    )
+    return ClusterResult(
+        membership_path=membership_path,
+        clusters_path=clusters_path,
+        community_count=community_count,
+        cluster_count=len(ordered_groups),
+        modularity=modularity,
+        timing=time.monotonic() - started,
+    )

damicore_clusterizer-0.1.0/src/damicore_clusterizer/artifacts.py

@@ -0,0 +1,102 @@
+from __future__ import annotations
+
+import csv
+import io
+import json
+import os
+import tempfile
+from pathlib import Path
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class _ClusterItem(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    cluster: int = Field(ge=0)
+    object_ids: tuple[str, ...]
+    labels: tuple[str, ...]
+
+
+class _ClustersArtifact(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    schema_version: Literal[1]
+    clusters: tuple[_ClusterItem, ...]
+
+
+def _stage(path: Path, payload: str, newline: str) -> str:
+    """Write `payload` beside `path` and return the temporary name, unrenamed."""
+    descriptor, temporary_name = tempfile.mkstemp(dir=path.parent, prefix=f".{path.name}.")
+    try:
+        with os.fdopen(descriptor, "w", encoding="utf-8", newline=newline) as stream:
+            stream.write(payload)
+            stream.flush()
+            os.fsync(stream.fileno())
+    except BaseException:
+        os.unlink(temporary_name)
+        raise
+    return temporary_name
+
+
+def write_cluster_artifacts(
+    destination: Path,
+    object_ids: tuple[str, ...],
+    labels: dict[str, str],
+    cluster_for: dict[str, int],
+    ordered_groups: list[tuple[str, ...]],
+) -> tuple[Path, Path]:
+    """Publish both cluster artifacts, or neither.
+
+    The two files describe one clustering, and the run that follows refuses a directory that
+    already holds either of them. Renaming the first into place before the second exists
+    would therefore let one failed write strand a membership.csv that no later run can clear
+    on its own, so both are staged first and renamed only once both exist.
+    """
+    membership_path = destination / "membership.csv"
+    clusters_path = destination / "clusters.json"
+
+    rows = io.StringIO()
+    writer = csv.writer(rows, lineterminator="\n")
+    writer.writerow(["object_id", "label", "cluster"])
+    for object_id in object_ids:
+        writer.writerow([object_id, labels[object_id], cluster_for[object_id]])
+
+    payload = _ClustersArtifact(
+        schema_version=1,
+        clusters=tuple(
+            _ClusterItem(
+                cluster=cluster,
+                object_ids=group,
+                labels=tuple(labels[object_id] for object_id in group),
+            )
+            for cluster, group in enumerate(ordered_groups)
+        ),
+    )
+    clusters_text = (
+        json.dumps(payload.model_dump(mode="json"), indent=2, sort_keys=True, allow_nan=False)
+        + "\n"
+    )
+
+    membership_temp = _stage(membership_path, rows.getvalue(), newline="")
+    try:
+        clusters_temp = _stage(clusters_path, clusters_text, newline="\n")
+    except BaseException:
+        os.unlink(membership_temp)
+        raise
+
+    try:
+        os.replace(membership_temp, membership_path)
+    except BaseException:
+        os.unlink(membership_temp)
+        os.unlink(clusters_temp)
+        raise
+    try:
+        os.replace(clusters_temp, clusters_path)
+    except BaseException:
+        # membership.csv is already published; withdraw it so the directory is left as found.
+        os.unlink(clusters_temp)
+        membership_path.unlink(missing_ok=True)
+        raise
+    return membership_path, clusters_path

damicore_clusterizer-0.1.0/src/damicore_clusterizer/config.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class ClusterConfig(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    num_clusters: int | None = Field(default=None, ge=1)

damicore_clusterizer-0.1.0/src/damicore_clusterizer/errors.py

@@ -0,0 +1,8 @@
+from __future__ import annotations
+
+
+class ClusterizerError(Exception):
+    def __init__(self, message: str, *, code: str = "clusterizer_error", **context: object) -> None:
+        super().__init__(message)
+        self.code = code
+        self.context = context

damicore_clusterizer-0.1.0/src/damicore_clusterizer/fastgreedy.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from typing import Any
+
+import igraph as ig
+
+
+def fastgreedy_membership(
+    graph: ig.Graph,
+    num_clusters: int | None,
+) -> tuple[list[int], int, float]:
+    dendrogram = graph.community_fastgreedy(weights="weight")
+    # igraph's VertexDendrogram.as_clustering is untyped in the shipped stubs, so the result
+    # arrives as Unknown; Any isolates that one library boundary rather than the module.
+    clustering: Any = (
+        dendrogram.as_clustering()
+        if num_clusters is None
+        else dendrogram.as_clustering(n=num_clusters)
+    )
+    return (
+        [int(value) for value in clustering.membership],
+        len(clustering),
+        float(clustering.modularity),
+    )

damicore_clusterizer-0.1.0/src/damicore_clusterizer/models.py

@@ -0,0 +1,14 @@
+from pathlib import Path
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class ClusterResult(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    membership_path: Path
+    clusters_path: Path
+    community_count: int = Field(ge=0)
+    cluster_count: int = Field(ge=0)
+    modularity: float = Field(allow_inf_nan=False)
+    timing: float = Field(ge=0)

damicore_clusterizer-0.1.0/src/damicore_clusterizer/tree_graph.py

@@ -0,0 +1,170 @@
+from __future__ import annotations
+
+import math
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Literal
+
+import igraph as ig
+from pydantic import BaseModel, ConfigDict, Field, ValidationError
+
+from damicore_clusterizer.errors import ClusterizerError
+
+
+class _TreeNode(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    id: str
+    kind: Literal["leaf", "internal"]
+    label: str | None
+
+
+class _TreeEdge(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    source: str
+    target: str
+    length: float = Field(allow_inf_nan=False)
+
+
+class _TreeArtifact(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    schema_version: Literal[1]
+    root_id: str
+    nodes: tuple[_TreeNode, ...]
+    edges: tuple[_TreeEdge, ...]
+
+
+@dataclass(frozen=True)
+class GraphInput:
+    graph: ig.Graph
+    # Vertex order as igraph holds it. Exposed here so callers never read graph.vs
+    # themselves: this module is the only place that touches igraph's attribute API.
+    vertex_names: tuple[str, ...]
+    object_ids: tuple[str, ...]
+    labels: dict[str, str]
+
+
+def _edge_weights(lengths: list[float]) -> list[float]:
+    """Map branch lengths onto the strictly positive edge weights FastGreedy is given.
+
+    A shorter branch joins a closer pair, so the weight is the reciprocal of the length. The
+    reciprocals are then translated so the smallest is exactly one, and that translation is
+    the point of this function: modularity is a weighted sum, so a single unbounded weight
+    would decide the partition by itself, and a reciprocal is unbounded as the length
+    approaches zero. Translating here rather than on the lengths keeps the ratio between
+    weights bounded by the spread of the data.
+
+    It also settles what a negative branch means. Neighbor Joining emits one where the matrix
+    contradicts the split it is making, and the reciprocal of a negative length sorts below
+    every positive one, so such a branch becomes the weakest edge rather than the strongest.
+
+    The result is at least one everywhere and is unchanged by rescaling every length.
+
+    Raises
+    ------
+    ClusterizerError
+        If a length is zero, which has no reciprocal, or so small that its reciprocal
+        overflows. Neither is repaired here: a repair would be the unbounded weight this
+        function exists to avoid.
+    """
+    reciprocals: list[float] = []
+    for length in lengths:
+        if length == 0.0:
+            raise ClusterizerError(
+                "Branch length is zero and has no reciprocal weight",
+                code="tree_format_error",
+            )
+        value = 1.0 / length
+        if not math.isfinite(value):
+            raise ClusterizerError(
+                "Branch length is too small to carry a finite weight",
+                code="tree_format_error",
+            )
+        reciprocals.append(value)
+
+    mean = sum(reciprocals) / len(reciprocals)
+    deviation = math.sqrt(sum((value - mean) ** 2 for value in reciprocals) / len(reciprocals))
+    if deviation == 0.0:
+        # Every branch has the same length, so the reciprocals carry no ordering to spread.
+        return [1.0] * len(reciprocals)
+    lowest = min(reciprocals)
+    return [1.0 + (value - lowest) / deviation for value in reciprocals]
+
+
+def _load_tree_graph(path: Path) -> GraphInput:
+    try:
+        artifact = _TreeArtifact.model_validate_json(path.read_text(encoding="utf-8"))
+        root_id = artifact.root_id
+        nodes = artifact.nodes
+        edges = artifact.edges
+    except (OSError, ValidationError) as exc:
+        raise ClusterizerError("Invalid tree artifact", code="tree_format_error") from exc
+
+    node_ids = [node.id for node in nodes]
+    if len(node_ids) != len(set(node_ids)):
+        raise ClusterizerError("Tree node ids are not unique", code="tree_format_error")
+    if root_id not in node_ids:
+        raise ClusterizerError("Tree root_id names no node", code="tree_format_error")
+    root_node = next(node for node in nodes if node.id == root_id)
+    if root_node.kind != "internal":
+        raise ClusterizerError("Tree root must be internal", code="tree_format_error")
+    leaves = tuple(node.id for node in nodes if node.kind == "leaf")
+    if len(leaves) < 2:
+        raise ClusterizerError("Tree must contain at least two leaves", code="tree_format_error")
+    # Validate and collect in one pass: a separate `any(...)` guard establishes the invariant
+    # for a reader but not for the comprehension that follows, which then carries `str | None`.
+    labels: dict[str, str] = {}
+    for node in nodes:
+        if node.kind != "leaf":
+            continue
+        if not isinstance(node.label, str):
+            raise ClusterizerError("Every leaf must have a string label", code="tree_format_error")
+        labels[node.id] = node.label
+    root_edges = [edge for edge in edges if edge.source == root_id]
+    if len(root_edges) != 2:
+        raise ClusterizerError("Tree root must have exactly two children", code="tree_format_error")
+
+    retained_nodes = [node_id for node_id in node_ids if node_id != root_id]
+    index = {node_id: position for position, node_id in enumerate(retained_nodes)}
+    graph_edges: list[tuple[int, int]] = []
+    lengths: list[float] = []
+    for edge in edges:
+        source, target = edge.source, edge.target
+        if source == root_id:
+            continue
+        if source not in index or target not in index:
+            raise ClusterizerError("Tree edge references an unknown node", code="tree_format_error")
+        graph_edges.append((index[source], index[target]))
+        lengths.append(edge.length)
+    left, right = root_edges
+    graph_edges.append((index[left.target], index[right.target]))
+    lengths.append(left.length + right.length)
+    if any(not math.isfinite(length) for length in lengths):
+        raise ClusterizerError("Branch lengths must be finite", code="tree_format_error")
+    if len(graph_edges) != len(retained_nodes) - 1:
+        raise ClusterizerError("Unrooted tree must have n-1 edges", code="tree_format_error")
+    graph = ig.Graph(n=len(retained_nodes), edges=graph_edges, directed=False)
+    if not graph.is_connected():
+        raise ClusterizerError("Tree graph is disconnected", code="tree_format_error")
+    graph.vs["name"] = retained_nodes
+    graph.es["weight"] = _edge_weights(lengths)
+    return GraphInput(
+        graph=graph,
+        vertex_names=tuple(retained_nodes),
+        object_ids=leaves,
+        labels=labels,
+    )
+
+
+def load_tree_graph(path: Path) -> GraphInput:
+    try:
+        return _load_tree_graph(path)
+    except ClusterizerError:
+        raise
+    except (KeyError, TypeError, ValueError, OverflowError) as exc:
+        raise ClusterizerError(
+            "Tree artifact does not match schema version 1",
+            code="tree_format_error",
+        ) from exc