tablassert 7.5.2__tar.gz → 8.0.1__tar.gz

tablassert-8.0.1/PKG-INFO

@@ -0,0 +1,122 @@
+Metadata-Version: 2.4
+Name: tablassert
+Version: 8.0.1
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Database
+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: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Rust
+Classifier: Framework :: Pydantic
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Environment :: Console
+Requires-Dist: biolink-model>=4.4.3
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: polars>=1.39.0
+Requires-Dist: rapidfuzz>=3.14.3
+Requires-Dist: pydantic>=2.12.5
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: cyclopts>=1.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: fastexcel>=0.20.2
+Requires-Dist: smolagents>=1.26.0 ; extra == 'agent'
+Requires-Dist: dspy>=3.2.1 ; extra == 'agent'
+Requires-Dist: litellm>=1.93.0 ; extra == 'agent'
+Requires-Dist: scikit-learn>=1.8.0 ; extra == 'qc'
+Requires-Dist: sentence-transformers>=5.3.0 ; extra == 'qc'
+Requires-Dist: polars[rtcompat]>=1.40.1 ; extra == 'rt'
+Provides-Extra: agent
+Provides-Extra: qc
+Provides-Extra: rt
+License-File: LICENSE
+Summary: Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in.
+Keywords: knowledge graph,bioinformatics,entity resolution,ner,ncats translator,kgx,yaml configuration,table mining,declarative pipeline,data quality control,tablassert
+Author-email: Skye Lane Goetz <sgoetz@isbscience.org>
+License-Expression: Apache-2.0
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Documentation, https://skyeav.github.io/Tablassert/
+Project-URL: Homepage, https://github.com/SkyeAv/Tablassert
+Project-URL: Source, https://github.com/SkyeAv/Tablassert
+
+# Tablassert
+
+[![PyPI](https://img.shields.io/pypi/v/tablassert.svg)](https://pypi.org/project/tablassert/)
+[![Python](https://img.shields.io/pypi/pyversions/tablassert.svg)](https://pypi.org/project/tablassert/)
+[![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
+[![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
+
+Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution built in and optional quality control.
+
+```bash
+pip install tablassert
+tablassert build-kg config.yaml
+```
+
+**[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorials, configuration reference, and API docs.
+
+## Installation
+
+```bash
+pip install tablassert
+```
+
+The base install builds knowledge graphs from CSV/TSV/Excel sources. Optional extras (`rt`, `qc`,
+`agent`) add CPU-compatible Polars, the three-stage QC audit, and the autonomous agent — see the
+[Installation guide](https://skyeav.github.io/Tablassert/installation/) for the full matrix. QC is opt-in
+at build time (`build-kg --qc`); see the [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for the
+complete flag reference.
+
+## Quick Demo
+
+```python
+from pathlib import Path
+from tablassert.lib import resolve_many
+
+results = resolve_many(col="gene", entities=["TP53", "BRCA1"], fullmap=Path("/path/to/fullmap"), taxon="9606")
+# [{"original_gene": "TP53", "gene": "HGNC:11998", "gene_name": "TP53", ...}, ...]
+```
+
+Point `resolve_many()` at a fullmap database to resolve any iterable of entity strings to CURIEs — no
+LazyFrame setup or NLP preprocessing required. See the
+[Batch Resolution API](https://skyeav.github.io/Tablassert/api/lib/) for the full reference; for
+YAML-configured pipeline builds use `tablassert build-kg config.yaml`.
+
+## Key Features
+
+Declarative YAML configs, built-in entity resolution, optional three-stage QC, and KGX-compliant NDJSON
+output — with lazy Polars pipelines over an embedded redb resolution database. See the
+[documentation](https://skyeav.github.io/Tablassert/) for the full feature overview and use-case gallery.
+
+## Developing
+
+```bash
+uv sync --group dev --extra qc
+uv run maturin develop --manifest-path rust/Cargo.toml
+make check
+```
+
+See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full development loop, quality gates, and pull request guidelines.
+
+## License
+
+[Apache License 2.0](LICENSE)
+
+## Contributors
+
+[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology
+
+[Gwênlyn Glusman](mailto:gglusman@isbscience.org) — Institute for Systems Biology
+
+Jared C. Roach — Institute for Systems Biology
+

tablassert-8.0.1/README.md

@@ -0,0 +1,70 @@
+# Tablassert
+
+[![PyPI](https://img.shields.io/pypi/v/tablassert.svg)](https://pypi.org/project/tablassert/)
+[![Python](https://img.shields.io/pypi/pyversions/tablassert.svg)](https://pypi.org/project/tablassert/)
+[![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
+[![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
+
+Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution built in and optional quality control.
+
+```bash
+pip install tablassert
+tablassert build-kg config.yaml
+```
+
+**[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorials, configuration reference, and API docs.
+
+## Installation
+
+```bash
+pip install tablassert
+```
+
+The base install builds knowledge graphs from CSV/TSV/Excel sources. Optional extras (`rt`, `qc`,
+`agent`) add CPU-compatible Polars, the three-stage QC audit, and the autonomous agent — see the
+[Installation guide](https://skyeav.github.io/Tablassert/installation/) for the full matrix. QC is opt-in
+at build time (`build-kg --qc`); see the [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for the
+complete flag reference.
+
+## Quick Demo
+
+```python
+from pathlib import Path
+from tablassert.lib import resolve_many
+
+results = resolve_many(col="gene", entities=["TP53", "BRCA1"], fullmap=Path("/path/to/fullmap"), taxon="9606")
+# [{"original_gene": "TP53", "gene": "HGNC:11998", "gene_name": "TP53", ...}, ...]
+```
+
+Point `resolve_many()` at a fullmap database to resolve any iterable of entity strings to CURIEs — no
+LazyFrame setup or NLP preprocessing required. See the
+[Batch Resolution API](https://skyeav.github.io/Tablassert/api/lib/) for the full reference; for
+YAML-configured pipeline builds use `tablassert build-kg config.yaml`.
+
+## Key Features
+
+Declarative YAML configs, built-in entity resolution, optional three-stage QC, and KGX-compliant NDJSON
+output — with lazy Polars pipelines over an embedded redb resolution database. See the
+[documentation](https://skyeav.github.io/Tablassert/) for the full feature overview and use-case gallery.
+
+## Developing
+
+```bash
+uv sync --group dev --extra qc
+uv run maturin develop --manifest-path rust/Cargo.toml
+make check
+```
+
+See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full development loop, quality gates, and pull request guidelines.
+
+## License
+
+[Apache License 2.0](LICENSE)
+
+## Contributors
+
+[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology
+
+[Gwênlyn Glusman](mailto:gglusman@isbscience.org) — Institute for Systems Biology
+
+Jared C. Roach — Institute for Systems Biology

{tablassert-7.5.2 → tablassert-8.0.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "7.5.2"
+version = "8.0.1"
 description = "Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in."
 authors = [
     { name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
@@ -20,6 +20,7 @@ keywords = [
 ]
 readme = "README.md"
 license = "Apache-2.0"
+license-files = ["LICENSE"]
 classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Development Status :: 5 - Production/Stable",
@@ -28,38 +29,30 @@ classifiers = [
     "Intended Audience :: Developers",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Database",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: Implementation :: CPython",
+    "Programming Language :: Rust",
     "Framework :: Pydantic",
-    "Operating System :: OS Independent",
+    "Operating System :: POSIX :: Linux",
+    "Operating System :: MacOS :: MacOS X",
     "Environment :: Console",
 ]
 requires-python = ">=3.11"
 dependencies = [
-    "duckdb>=1.5.0",
-    "fastexcel>=0.19.0",
-    "httpx>=0.28.1",
-    "lazy-loader>=0.5",
+    "biolink-model>=4.4.3",
     "loguru>=0.7.3",
-    "optimum-onnx>=0.1.0",
-    "orjson>=3.11.7",
-    "playwright>=1.58.0,<1.59",
     "polars>=1.39.0",
-    "polars-hash>=0.5.6",
-    "pyarrow>=23.0.1",
+    "rapidfuzz>=3.14.3",
     "pydantic>=2.12.5",
-    "pyexcel>=0.7.4",
     "pyyaml>=6.0.3",
-    "rapidfuzz>=3.14.3",
-    "scikit-learn>=1.8.0",
-    "sentence-transformers>=5.3.0",
-    "sqlite-utils>=3.39",
     "cyclopts>=1.0.0",
     "rich>=13.0.0",
-    "xxhash>=3.6.0",
-    "diskcache>=5.6.3",
+    "fastexcel>=0.20.2",
 ]
 
 [project.urls]
@@ -68,11 +61,15 @@ Source = "https://github.com/SkyeAv/Tablassert"
 Documentation = "https://skyeav.github.io/Tablassert/"
 
 [build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+requires = ["maturin>=1.10,<2.0"]
+build-backend = "maturin"
 
-[tool.hatch.build.targets.wheel]
-packages = ["./src/tablassert"]
+[tool.maturin]
+python-source = "src"
+module-name = "tablassert.rs"
+bindings = "pyo3"
+manifest-path = "rust/Cargo.toml"
+features = ["extension-module"]
 
 [project.scripts]
 tablassert = "tablassert.cli:APP"
@@ -82,15 +79,20 @@ rt = [
     "polars[rtcompat]>=1.40.1",
 ]
 qc = [
-    "onnxruntime>=1.24.4",
+    "scikit-learn>=1.8.0",
+    "sentence-transformers>=5.3.0",
 ]
-qc-cuda = [
-    "onnxruntime-gpu>=1.24.4",
+agent = [
+    "smolagents>=1.26.0",
+    "dspy>=3.2.1",
+    "litellm>=1.93.0",
 ]
 
 [dependency-groups]
 dev = [
     "mkdocs>=1.6.1",
+    "mkdocs-material>=9.6.0",
+    "maturin>=1.10,<2.0",
     "pre-commit>=4.5.1",
     "pyright>=1.1.411",
     "pytest>=9.0.2",
@@ -100,14 +102,55 @@ dev = [
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-markers = ["network: requires internet", "gpu: requires CUDAExecutionProvider"]
+addopts = "--cov=tablassert --cov-report=term-missing"
+markers = ["network: requires internet"]
+
+[tool.coverage.run]
+source = ["src/tablassert"]
 
 [tool.ruff]
-line-length = 120
+line-length = 150
 indent-width = 4
 target-version = "py311"
 
+[tool.ruff.lint]
+select = [
+    "E4", # pycodestyle E4xx
+    "E7", # pycodestyle E7xx
+    "E9", # pycodestyle E9xx
+    "F", # pyflakes
+    "RUF100", # stale noqa
+    "B", # flake8-bugbear
+    "SIM", # flake8-simplify
+    "C4", # flake8-comprehensions
+    "PT", # flake8-pytest-style
+    "RUF", # ruff-specific
+    "TID", # flake8-tidy-imports
+    "I", # isort
+    "PIE", # flake8-pie
+    "RET", # flake8-return
+    "UP", # pyupgrade
+]
+ignore = [
+    "UP042", # keep enum/str-conversion behavior as-is
+]
+
+[tool.ruff.lint.isort]
+# Align isort with `format.skip-magic-trailing-comma = true` (avoids the ruff incompatibility warning).
+split-on-trailing-comma = false
+
 [tool.ruff.format]
 quote-style = "double"
 indent-style = "space"
 skip-magic-trailing-comma = true
+
+[tool.pyright]
+include = ["src", "tests"]
+pythonVersion = "3.11"
+strictListInference = true
+strictDictionaryInference = true
+strictSetInference = true
+reportMissingTypeStubs = false
+reportUnusedImport = true
+reportUnusedVariable = true
+reportDuplicateImport = true