damicore-tree-builder 0.1.0__tar.gz

damicore_tree_builder-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_tree_builder-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_tree_builder-0.1.0/PKG-INFO

@@ -0,0 +1,64 @@
+Metadata-Version: 2.5
+Name: damicore-tree-builder
+Version: 0.1.0
+Summary: Neighbor-Joining tree builder 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: damicore,neighbor-joining,newick,phylogenetics,tree
+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: numpy<3,>=1.26
+Requires-Dist: pydantic<3,>=2.10
+Description-Content-Type: text/markdown
+
+# damicore-tree-builder
+
+damicore-tree-builder builds a deterministic Neighbor Joining tree from a
+distance matrix and its labels. It is the third 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 build trees without the rest of
+the pipeline.
+
+```bash
+pip install damicore-tree-builder
+```
+
+## Python
+
+```python
+from damicore_tree_builder import build_tree
+
+result = build_tree("distance.npy", "labels.json", "run")
+```
+
+`distance.npy` and `labels.json` are produced by the sibling `damicore-distance`
+distribution; the call writes `tree.json` plus Newick, and `tree.json` is the
+input the sibling `damicore-clusterizer` distribution consumes. The path API
+copies into a temporary memory map, reuses slots, evaluates Q pairwise without
+materializing it, and preserves negative branches. `neighbor_joining(matrix,
+labels)` is available for small in-memory matrices.
+
+## 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_tree_builder-0.1.0/README.md

@@ -0,0 +1,35 @@
+# damicore-tree-builder
+
+damicore-tree-builder builds a deterministic Neighbor Joining tree from a
+distance matrix and its labels. It is the third 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 build trees without the rest of
+the pipeline.
+
+```bash
+pip install damicore-tree-builder
+```
+
+## Python
+
+```python
+from damicore_tree_builder import build_tree
+
+result = build_tree("distance.npy", "labels.json", "run")
+```
+
+`distance.npy` and `labels.json` are produced by the sibling `damicore-distance`
+distribution; the call writes `tree.json` plus Newick, and `tree.json` is the
+input the sibling `damicore-clusterizer` distribution consumes. The path API
+copies into a temporary memory map, reuses slots, evaluates Q pairwise without
+materializing it, and preserves negative branches. `neighbor_joining(matrix,
+labels)` is available for small in-memory matrices.
+
+## 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_tree_builder-0.1.0/pyproject.toml

@@ -0,0 +1,60 @@
+[project]
+name = "damicore-tree-builder"
+version = "0.1.0"
+description = "Neighbor-Joining tree builder 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", "neighbor-joining", "phylogenetics", "tree", "newick"]
+dependencies = ["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_tree_builder --cov-branch --cov-report=term-missing --cov-fail-under=90"

damicore_tree_builder-0.1.0/src/damicore_tree_builder/__init__.py

@@ -0,0 +1,16 @@
+from damicore_tree_builder.api import build_tree
+from damicore_tree_builder.config import TreeBuildConfig
+from damicore_tree_builder.errors import TreeBuilderError
+from damicore_tree_builder.models import Tree, TreeBuildResult, TreeEdge, TreeNode
+from damicore_tree_builder.neighbor_joining import neighbor_joining
+
+__all__ = [
+    "build_tree",
+    "neighbor_joining",
+    "TreeBuildConfig",
+    "TreeBuildResult",
+    "Tree",
+    "TreeNode",
+    "TreeEdge",
+    "TreeBuilderError",
+]

damicore_tree_builder-0.1.0/src/damicore_tree_builder/api.py

@@ -0,0 +1,116 @@
+from __future__ import annotations
+
+import time
+from pathlib import Path
+from typing import Literal
+
+import numpy as np
+from pydantic import BaseModel, ConfigDict, ValidationError
+
+from damicore_tree_builder.artifacts import write_tree_artifacts
+from damicore_tree_builder.config import TreeBuildConfig
+from damicore_tree_builder.errors import TreeBuilderError
+from damicore_tree_builder.models import Tree, TreeBuildResult
+from damicore_tree_builder.neighbor_joining import build_neighbor_joining, validate_matrix
+
+
+class _LabelsArtifact(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    schema_version: Literal[1]
+    object_ids: tuple[str, ...]
+    labels: tuple[str, ...]
+
+
+def _load_labels(path: Path) -> tuple[list[str], list[str]]:
+    try:
+        artifact = _LabelsArtifact.model_validate_json(path.read_text(encoding="utf-8"))
+        object_ids = list(artifact.object_ids)
+        labels = list(artifact.labels)
+    except (OSError, ValidationError) as exc:
+        raise TreeBuilderError("Invalid labels artifact", code="artifact_validation_error") from exc
+    if (
+        len(object_ids) != len(labels)
+        or len(set(object_ids)) != len(object_ids)
+        or len(set(labels)) != len(labels)
+    ):
+        raise TreeBuilderError(
+            "labels and object_ids must have equal length and unique values",
+            code="artifact_validation_error",
+        )
+    return object_ids, labels
+
+
+def build_tree(
+    matrix_path: str | Path,
+    labels_path: str | Path,
+    output_dir: str | Path,
+    *,
+    config: TreeBuildConfig | None = None,
+) -> TreeBuildResult:
+    """Build and persist a deterministic Neighbor Joining tree."""
+    started = time.monotonic()
+    settings = config or TreeBuildConfig()
+    destination = Path(output_dir).resolve()
+    destination.mkdir(parents=True, exist_ok=True)
+    if (destination / "tree.json").exists() or (destination / "tree.nwk").exists():
+        raise TreeBuilderError(
+            "Tree outputs already exist in the output directory",
+            code="output_directory_conflict_error",
+        )
+    labels, display_labels = _load_labels(Path(labels_path).resolve())
+    try:
+        original = np.load(Path(matrix_path).resolve(), mmap_mode="r", allow_pickle=False)
+    except (OSError, ValueError) as exc:
+        raise TreeBuilderError(
+            "Distance matrix artifact is unreadable",
+            code="artifact_validation_error",
+        ) from exc
+    validate_matrix(original, labels, settings.q_block_size)
+    workspace_path = destination / "tree-work.npy"
+    workspace = np.lib.format.open_memmap(
+        workspace_path, mode="w+", dtype=np.float64, shape=original.shape
+    )
+    try:
+        for start in range(0, original.shape[0], settings.q_block_size):
+            stop = min(start + settings.q_block_size, original.shape[0])
+            workspace[start:stop] = original[start:stop]
+        workspace.flush()
+        tree = build_neighbor_joining(
+            workspace,
+            labels,
+            display_labels,
+            q_block_size=settings.q_block_size,
+        )
+        tree_path, newick_path = write_tree_artifacts(tree, destination)
+        try:
+            validated = Tree.model_validate_json(tree_path.read_text(encoding="utf-8"))
+            if len([node for node in validated.nodes if node.kind == "leaf"]) != len(labels):
+                raise TreeBuilderError(
+                    "Persisted tree lost leaves", code="artifact_validation_error"
+                )
+            newick = newick_path.read_text(encoding="utf-8")
+            # Only the terminator is checked. A semicolon inside a quoted label is data, so
+            # counting them rejects valid output this package itself produces.
+            if not newick.rstrip("\n").endswith(";"):
+                raise TreeBuilderError(
+                    "Persisted Newick artifact is malformed",
+                    code="artifact_validation_error",
+                )
+        except BaseException:
+            # The next run refuses a directory holding either artifact, so a rejected write
+            # must not survive as a file that only manual cleanup can clear.
+            tree_path.unlink(missing_ok=True)
+            newick_path.unlink(missing_ok=True)
+            raise
+        negative = sum(edge.length < 0 for edge in tree.edges)
+    finally:
+        del workspace
+        workspace_path.unlink(missing_ok=True)
+    return TreeBuildResult(
+        tree_path=tree_path,
+        newick_path=newick_path,
+        leaf_count=len(labels),
+        negative_branch_count=negative,
+        timing=time.monotonic() - started,
+    )

damicore_tree_builder-0.1.0/src/damicore_tree_builder/artifacts.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+import json
+import os
+import tempfile
+from pathlib import Path
+
+from damicore_tree_builder.models import Tree
+from damicore_tree_builder.newick import to_newick
+
+
+def _stage(path: Path, payload: 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="\n") as stream:
+            stream.write(payload)
+            stream.flush()
+            os.fsync(stream.fileno())
+    except BaseException:
+        os.unlink(temporary_name)
+        raise
+    return temporary_name
+
+
+def write_tree_artifacts(tree: Tree, destination: Path) -> tuple[Path, Path]:
+    """Publish both tree artifacts, or neither.
+
+    The two files describe one tree, 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 tree.json that no later run can clear on its own,
+    so both payloads are rendered and staged first and renamed only once both exist.
+    """
+    tree_path = destination / "tree.json"
+    newick_path = destination / "tree.nwk"
+
+    tree_text = (
+        json.dumps(
+            tree.model_dump(mode="json"),
+            indent=2,
+            sort_keys=True,
+            allow_nan=False,
+        )
+        + "\n"
+    )
+    newick_text = to_newick(tree) + "\n"
+
+    tree_temp = _stage(tree_path, tree_text)
+    try:
+        newick_temp = _stage(newick_path, newick_text)
+    except BaseException:
+        os.unlink(tree_temp)
+        raise
+
+    try:
+        os.replace(tree_temp, tree_path)
+    except BaseException:
+        os.unlink(tree_temp)
+        os.unlink(newick_temp)
+        raise
+    try:
+        os.replace(newick_temp, newick_path)
+    except BaseException:
+        # tree.json is already published; withdraw it so the directory is left as found.
+        os.unlink(newick_temp)
+        tree_path.unlink(missing_ok=True)
+        raise
+    return tree_path, newick_path

damicore_tree_builder-0.1.0/src/damicore_tree_builder/config.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class TreeBuildConfig(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    q_block_size: int = Field(default=512, gt=0)

damicore_tree_builder-0.1.0/src/damicore_tree_builder/errors.py

@@ -0,0 +1,10 @@
+from __future__ import annotations
+
+
+class TreeBuilderError(Exception):
+    def __init__(
+        self, message: str, *, code: str = "tree_builder_error", **context: object
+    ) -> None:
+        super().__init__(message)
+        self.code = code
+        self.context = context

damicore_tree_builder-0.1.0/src/damicore_tree_builder/models.py

@@ -0,0 +1,41 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class TreeNode(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    id: str
+    kind: Literal["leaf", "internal"]
+    label: str | None = 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 Tree(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    schema_version: Literal[1] = 1
+    root_id: str
+    nodes: tuple[TreeNode, ...]
+    edges: tuple[TreeEdge, ...]
+
+
+class TreeBuildResult(BaseModel):
+    model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
+
+    tree_path: Path
+    newick_path: Path
+    leaf_count: int = Field(ge=0)
+    negative_branch_count: int = Field(ge=0)
+    timing: float = Field(ge=0)

damicore_tree_builder-0.1.0/src/damicore_tree_builder/neighbor_joining.py

@@ -0,0 +1,175 @@
+from __future__ import annotations
+
+import math
+from collections.abc import Sequence
+from typing import Any
+
+import numpy as np
+import numpy.typing as npt
+
+from damicore_tree_builder.errors import TreeBuilderError
+from damicore_tree_builder.models import Tree, TreeEdge, TreeNode
+
+# Section 15.2: two Q scores closer than this, relative to the magnitude of the better one,
+# are one tie for the lexicographic rule to break.
+#
+# An exact float64 comparison asserts a precision the input never had: every distance here is
+# a ratio of integer compressed sizes, so its meaningful digits run out long before the
+# 16th. Worse, the ties the rule exists to break are precisely the ones rounding destroys --
+# with four clusters left, Q(i,j) and Q(k,l) for complementary pairs are algebraically equal
+# for *every* matrix, yet float64 detects that only about 60% of the time, and no summation
+# strategy fixes it because the cancellation happens in the final subtraction rather than in
+# the sums. A relative band restores the rule and makes the choice stable across platforms.
+_TIE_RELATIVE_TOLERANCE = 1e-9
+
+
+def _tie_band(score: float) -> float:
+    """Half-width of the tie band around `score`, scaled to its magnitude."""
+    return _TIE_RELATIVE_TOLERANCE * max(1.0, abs(score))
+
+
+def validate_matrix(
+    matrix: np.ndarray[Any, Any],
+    labels: Sequence[str],
+    block_size: int = 512,
+) -> None:
+    if matrix.ndim != 2 or matrix.shape[0] != matrix.shape[1] or matrix.shape[0] != len(labels):
+        raise TreeBuilderError(
+            "Distance matrix shape does not match labels", code="distance_matrix_validation_error"
+        )
+    if len(labels) < 2 or len(set(labels)) != len(labels):
+        raise TreeBuilderError(
+            "At least two unique labels are required", code="distance_matrix_validation_error"
+        )
+    if matrix.dtype != np.float64:
+        raise TreeBuilderError(
+            "Distance matrix must be float64",
+            code="distance_matrix_validation_error",
+        )
+    size = len(labels)
+    for row_start in range(0, size, block_size):
+        row_stop = min(row_start + block_size, size)
+        if not np.isfinite(matrix[row_start:row_stop]).all():
+            raise TreeBuilderError(
+                "Distance matrix must be finite",
+                code="distance_matrix_validation_error",
+            )
+        for row in range(row_start, row_stop):
+            if float(matrix[row, row]) != 0.0:
+                raise TreeBuilderError(
+                    "Distance matrix diagonal must be exactly zero",
+                    code="distance_matrix_validation_error",
+                )
+            # pyright: ignore is on np.array_equal, whose numpy stub is partially
+            # unknown under strict mode; the arrays themselves are fully typed.
+            symmetric = np.array_equal(  # pyright: ignore[reportUnknownMemberType]
+                matrix[row, :], matrix[:, row]
+            )
+            if not bool(symmetric):
+                raise TreeBuilderError(
+                    "Distance matrix must be bitwise symmetric",
+                    code="distance_matrix_validation_error",
+                )
+
+
+def neighbor_joining(matrix: npt.NDArray[np.floating[Any]], labels: Sequence[str]) -> Tree:
+    """Build a deterministic Neighbor Joining tree, copying the input matrix."""
+    copied = np.array(matrix, dtype=np.float64, copy=True, order="C")
+    validate_matrix(copied, labels)
+    return build_neighbor_joining(copied, list(labels), q_block_size=512)
+
+
+def build_neighbor_joining(
+    work: np.ndarray[Any, Any],
+    labels: list[str],
+    display_labels: list[str] | None = None,
+    *,
+    q_block_size: int,
+) -> Tree:
+    active = list(labels)
+    slots = {label: index for index, label in enumerate(labels)}
+    rendered_labels = display_labels or labels
+    nodes = [
+        TreeNode(id=identifier, kind="leaf", label=rendered_labels[index])
+        for index, identifier in enumerate(labels)
+    ]
+    edges: list[TreeEdge] = []
+    internal_index = 1
+
+    while len(active) > 2:
+        active.sort()
+        count = len(active)
+        # Recomputed from the matrix each round rather than carried forward, so no drift
+        # accumulates across iterations. The cost is O(r^2), which the Q scan below already
+        # pays, so nothing changes asymptotically.
+        row_sums = {
+            node: float(sum(work[slots[node], slots[other]] for other in active if other != node))
+            for node in active
+        }
+        # Section 15.2: the smallest Q wins, and pairs within the tie band are resolved by the
+        # smallest pair of IDs. `active` is sorted and pairs are visited in that order, so the
+        # running pair is always the lexicographically earliest one seen so far; a later pair
+        # therefore replaces it only by winning outright, never by tying with it.
+        best_score = math.inf
+        best_pair: tuple[str, str] | None = None
+        for block_start in range(0, count, q_block_size):
+            block_stop = min(block_start + q_block_size, count)
+            for left_index in range(block_start, block_stop):
+                left = active[left_index]
+                for right in active[left_index + 1 :]:
+                    score = (
+                        (count - 2) * float(work[slots[left], slots[right]])
+                        - row_sums[left]
+                        - row_sums[right]
+                    )
+                    if best_pair is None or score < best_score - _tie_band(best_score):
+                        best_pair = (left, right)
+                        best_score = score
+                    elif score < best_score:
+                        # Inside the band: keep the earlier pair, tighten the band's centre.
+                        best_score = score
+        # `active` holds at least three labels here, so the pair loop above always ran and
+        # `best_pair` is always set; asserting it is how the type narrows without a dead branch.
+        assert best_pair is not None
+        left, right = best_pair
+        left_slot, right_slot = slots[left], slots[right]
+        distance = float(work[left_slot, right_slot])
+        delta = (row_sums[left] - row_sums[right]) / (count - 2)
+        left_length = 0.5 * (distance + delta)
+        right_length = distance - left_length
+        internal = f"nj_{internal_index:06d}"
+        internal_index += 1
+        nodes.append(TreeNode(id=internal, kind="internal"))
+        edges.extend(
+            [
+                TreeEdge(source=internal, target=left, length=left_length),
+                TreeEdge(source=internal, target=right, length=right_length),
+            ]
+        )
+        remaining = [node for node in active if node not in (left, right)]
+        for other in remaining:
+            other_slot = slots[other]
+            left_distance = float(work[left_slot, other_slot])
+            right_distance = float(work[right_slot, other_slot])
+            updated = 0.5 * (left_distance + right_distance - distance)
+            work[left_slot, other_slot] = updated
+            work[other_slot, left_slot] = updated
+        work[left_slot, left_slot] = 0.0
+        slots.pop(left)
+        slots.pop(right)
+        slots[internal] = left_slot
+        active = [*remaining, internal]
+
+    active.sort()
+    left, right = active
+    final_length = float(work[slots[left], slots[right]]) / 2.0
+    root = "nj_root"
+    nodes.append(TreeNode(id=root, kind="internal"))
+    edges.extend(
+        [
+            TreeEdge(source=root, target=left, length=final_length),
+            TreeEdge(source=root, target=right, length=final_length),
+        ]
+    )
+    ordered_edges = tuple(sorted(edges, key=lambda edge: (edge.source, edge.target)))
+    return Tree(root_id=root, nodes=tuple(nodes), edges=ordered_edges)

damicore_tree_builder-0.1.0/src/damicore_tree_builder/newick.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+
+from damicore_tree_builder.errors import TreeBuilderError
+from damicore_tree_builder.models import Tree
+
+# Underscore is in this set on purpose. Newick converts an unquoted underscore to a blank on
+# reading, and every id this package emits contains one (`column_000001`, `nj_root`), so an
+# unquoted label reaches a conforming viewer with its digits split off from its prefix.
+_MUST_QUOTE = " \t\n\r():;,[]'_"
+
+
+def _escape(identifier: str) -> str:
+    if identifier and all(character not in identifier for character in _MUST_QUOTE):
+        return identifier
+    return "'" + identifier.replace("'", "''") + "'"
+
+
+def to_newick(tree: Tree) -> str:
+    """Render `tree` as a Newick string closed by a single terminator.
+
+    The traversal is iterative because tree depth is not bounded by the object count in any
+    useful way: Neighbor Joining produces a caterpillar of depth n-1 whenever one taxon joins
+    per round, so a recursive renderer exhausts the interpreter stack inside the supported
+    input range rather than at some unreachable extreme.
+
+    Raises
+    ------
+    TreeBuilderError
+        If the edges reach a node already on the current path. A recursive renderer ends such
+        a cycle with RecursionError; an iterative one would otherwise never terminate.
+    """
+    children: dict[str, list[tuple[str, float]]] = {}
+    for edge in tree.edges:
+        children.setdefault(edge.source, []).append((edge.target, edge.length))
+
+    # A node's own branch length belongs to the edge that reaches it, not to the node, so
+    # `body` holds each subtree rendered without it and the length is appended per edge.
+    body: dict[str, str] = {}
+    on_path: set[str] = set()
+    stack: list[tuple[str, bool]] = [(tree.root_id, False)]
+    while stack:
+        node_id, expanded = stack.pop()
+        if expanded:
+            on_path.discard(node_id)
+            descendants = sorted(children.get(node_id, []), key=lambda item: item[0])
+            prefix = ""
+            if descendants:
+                prefix = (
+                    "("
+                    + ",".join(
+                        body[child] + ":" + repr(float(length)) for child, length in descendants
+                    )
+                    + ")"
+                )
+            body[node_id] = prefix + _escape(node_id)
+            continue
+        if node_id in on_path:
+            raise TreeBuilderError(
+                "Tree edges form a cycle",
+                code="artifact_validation_error",
+                node_id=node_id,
+            )
+        on_path.add(node_id)
+        stack.append((node_id, True))
+        stack.extend((child, False) for child, _ in children.get(node_id, []))
+
+    return body[tree.root_id] + ";"