metahq-core 0.1.1__tar.gz

metahq_core-0.1.1/.gitignore

@@ -0,0 +1,213 @@
+# 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/
+.tox/
+.nox/
+.coverage
+.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__/
+
+# Mac
+.DS_Store
+
+

metahq_core-0.1.1/PKG-INFO

@@ -0,0 +1,34 @@
+Metadata-Version: 2.4
+Name: metahq-core
+Version: 0.1.1
+Summary: Core API for the meta-hq CLI.
+Author-email: Parker Hicks <parker.hicks@cuanschutz.edu>, Faisal Alquaddoomi <faisal.alquaddoomi@cuanschutz.edu>
+Keywords: CLI,Data Curation,Database,Public Biomedical Data
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Requires-Dist: duckdb>=1.4.0
+Requires-Dist: networkx>=3.0
+Requires-Dist: numpy>=2.3.0
+Requires-Dist: polars>=1.27.0
+Requires-Dist: pyarrow>=10.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pymongo>=4.13.0
+Requires-Dist: pyyaml>=5.1
+Requires-Dist: rank-bm25>=0.2.2
+Provides-Extra: dev
+Requires-Dist: black; extra == 'dev'
+Requires-Dist: flake8; extra == 'dev'
+Requires-Dist: isort; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Provides-Extra: test
+Requires-Dist: pytest-benchmark; extra == 'test'
+Requires-Dist: pytest-cov; extra == 'test'
+Requires-Dist: pytest>=8.0; extra == 'test'

metahq_core-0.1.1/pyproject.toml

@@ -0,0 +1,83 @@
+[project]
+name = "metahq-core"
+dynamic = ["version"]
+description = "Core API for the meta-hq CLI."
+readme = "README.md"
+requires-python = ">=3.11"
+authors = [
+    {name = "Parker Hicks", email = "parker.hicks@cuanschutz.edu"},
+    {name = "Faisal Alquaddoomi", email = "faisal.alquaddoomi@cuanschutz.edu"},
+]
+keywords = ["CLI", "Database", "Data Curation", "Public Biomedical Data"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
+dependencies = [
+    "networkx>=3.0", 
+    "numpy>=2.3.0",
+    "polars>=1.27.0",
+    "pymongo>=4.13.0",
+    "pyarrow>=10.0.0",
+    "pydantic>=2.0.0",
+    "pyyaml>=5.1",
+    "duckdb>=1.4.0",
+    "rank-bm25>=0.2.2",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0",
+    "pytest-cov",
+    "black",
+    "isort",
+    "flake8",
+    "mypy",
+]
+
+test = [
+    "pytest>=8.0",
+    "pytest-cov",
+    "pytest-benchmark",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.version]
+path = "src/metahq_core/__init__.py"
+
+[tool.hatch.build.targets.sdist]
+exclude = ["/.git", "/__pycache__", "*.pyc"]
+include = ["src/metahq_core"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/metahq_core"]
+
+[tool.black]
+line-length = 88
+target-version = ['py38']
+include = '\.pyi?$'
+
+[tool.isort]
+profile = "black"
+multi_line_output = 3
+
+[tool.mypy]
+python_version = "3.11"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]

metahq_core-0.1.1/src/metahq_core/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.1"

metahq_core-0.1.1/src/metahq_core/curations/_multiprocess_propagator.py

@@ -0,0 +1,121 @@
+"""
+Helper class to facilitate propagation of annotations by chunks.
+
+Author: Parker Hicks
+Date: 2025-09-26
+
+Last updated: 2025-11-18 by Parker Hicks
+"""
+
+from __future__ import annotations
+
+import multiprocessing as mp
+import os
+from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from metahq_core.logger import setup_logger
+from metahq_core.util.alltypes import NpIntMatrix
+from metahq_core.util.progress import progress_bar
+
+if TYPE_CHECKING:
+    import logging
+
+
+PROCESS_POOL_THRESHOLD = os.environ.get("PROCESS_POOL_THRESHOLD", 40)
+
+type Executor = ProcessPoolExecutor | ThreadPoolExecutor
+
+class MultiprocessPropagator:
+    """Exists to allow multiprocessing within the Propagator class."""
+
+    def __init__(self, logger=None, loglevel=20, verbose=True):
+
+        if logger is None:
+            logger = setup_logger(__name__, level=loglevel)
+        self.log: logging.Logger = logger
+        self.verbose: bool = verbose
+
+    @staticmethod
+    def _process_chunk(args):
+        """
+        Worker function for matrix dot product between annotation chunk
+        and ontology relationship matrix.
+
+        This is the function split between workers.
+        """
+        chunk_idx, chunk, family = args
+        result = np.einsum("ij,jk->ik", chunk, family)
+
+        return chunk_idx, result
+
+    def multiprocess_propagate(
+        self,
+        n_indices,
+        split: list,
+        family: NpIntMatrix,
+        n_processes: int | None = None,
+        desc="Propagating",
+    ):
+        """Multiprocessing propagation"""
+        if n_processes is None:
+            n_processes = mp.cpu_count() - 1
+
+        final_shape = (
+            n_indices,
+            family.shape[1],
+        )
+
+        propagated = np.empty(final_shape, dtype=np.int32)
+        args_list = [(i, chunk, family) for i, chunk in enumerate(split)]
+
+        executor = (
+            ThreadPoolExecutor
+            if len(args_list) < int(PROCESS_POOL_THRESHOLD)
+            else ProcessPoolExecutor
+        )
+
+        with executor(max_workers=n_processes) as _executor:
+            if self.verbose:
+                results = self._execute_verbose(_executor, args_list, desc)
+            else:
+                results = self._execute_silent(_executor, args_list)
+
+        # combine
+        start = 0
+        for _, result in sorted(results, key=lambda x: x[0]):
+            nsamples = result.shape[0]
+            end = start + nsamples
+            propagated[start:end] = result
+            start = end
+
+        return propagated
+
+    def _execute_silent(self, executor: Executor, args_list: list) -> list:
+        futures = {
+            executor.submit(self._process_chunk, args): args for args in args_list
+        }
+        return [future.result() for future in as_completed(futures)]
+
+    def _execute_verbose(
+        self,
+        executor: Executor,
+        args_list: list,
+        desc: str,
+    ) -> list:
+        with progress_bar(padding="    ") as progress:
+            task = progress.add_task(desc, total=len(args_list))
+
+            futures = {
+                executor.submit(self._process_chunk, args): args for args in args_list
+            }
+            results = []
+            for future in as_completed(futures):
+                result = future.result()
+                results.append(result)
+                progress.update(task, description=desc, advance=1)
+                progress.refresh()
+
+        return results