autodq 0.1.0__tar.gz

autodq-0.1.0/.github/workflows/publish-pypi.yml

@@ -0,0 +1,71 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: Version to verify and publish
+        required: true
+        default: "0.1.0"
+        type: string
+
+jobs:
+  build:
+    name: Verify and build AutoDQ ${{ inputs.version }}
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    env:
+      EXPECTED_VERSION: ${{ inputs.version }}
+
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.13"
+          cache: pip
+      - name: Install AutoDQ and release tools
+        run: python -m pip install -e ".[dev]"
+      - name: Verify requested version
+        run: >-
+          python -c "import os; from autodq import __version__;
+          expected = os.environ['EXPECTED_VERSION'];
+          assert __version__ == expected,
+          f'Expected {expected}, found {__version__}'"
+      - name: Run acceptance suite
+        run: |
+          python -m unittest discover -s tests
+          autodq --version
+          autodq validate examples/sales_analysis.adql
+          autodq validate examples/sales_auto.adql
+      - name: Build distributions
+        run: python -m build
+      - name: Inspect distributions
+        run: |
+          python -m twine check dist/*
+          python scripts/check_distribution.py dist
+      - name: Store verified distributions
+        uses: actions/upload-artifact@v7
+        with:
+          name: autodq-${{ inputs.version }}-distributions
+          path: dist/
+          if-no-files-found: error
+
+  publish:
+    name: Publish AutoDQ ${{ inputs.version }} to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/autodq
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download verified distributions
+        uses: actions/download-artifact@v8
+        with:
+          name: autodq-${{ inputs.version }}-distributions
+          path: dist/
+      - name: Publish distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

autodq-0.1.0/.github/workflows/publish-testpypi.yml

@@ -0,0 +1,59 @@
+name: Publish to TestPyPI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    name: Build and verify distributions
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.13"
+          cache: pip
+      - name: Install AutoDQ and release tools
+        run: python -m pip install -e ".[dev]"
+      - name: Run acceptance suite
+        run: |
+          python -m unittest discover -s tests
+          autodq --version
+          autodq validate examples/sales_analysis.adql
+          autodq validate examples/sales_auto.adql
+      - name: Build distributions
+        run: python -m build
+      - name: Inspect distributions
+        run: |
+          python -m twine check dist/*
+          python scripts/check_distribution.py dist
+      - name: Store distributions
+        uses: actions/upload-artifact@v7
+        with:
+          name: python-package-distributions
+          path: dist/
+          if-no-files-found: error
+
+  publish:
+    name: Publish AutoDQ 0.1.0 to TestPyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/autodq
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download distributions
+        uses: actions/download-artifact@v8
+        with:
+          name: python-package-distributions
+          path: dist/
+      - name: Publish distributions to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/

autodq-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,49 @@
+name: Tests
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  compatibility:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - name: Install AutoDQ and release tools
+        run: python -m pip install -e ".[dev]"
+      - name: Run test suite
+        run: python -m unittest discover -s tests
+      - name: Verify command line and ADQL
+        run: |
+          autodq --version
+          autodq validate examples/sales_analysis.adql
+          autodq validate examples/sales_auto.adql
+
+  distribution:
+    runs-on: ubuntu-latest
+    needs: compatibility
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.13"
+          cache: pip
+      - name: Install release tools
+        run: python -m pip install -e ".[dev]"
+      - name: Build distributions
+        run: python -m build
+      - name: Inspect distributions
+        run: |
+          python -m twine check dist/*
+          python scripts/check_distribution.py dist

autodq-0.1.0/CHANGELOG.md

@@ -0,0 +1,28 @@
+# Changelog
+
+All notable AutoDQ changes are recorded here. Versions follow semantic
+versioning and Python package releases follow PEP 440.
+
+## 0.1.0 - 2026-07-22
+
+Initial alpha release candidate.
+
+### Added
+
+- End-to-end profiling, diagnosis, recommendations, interactive cleaning, and validation.
+- Feature engineering, regression and classification, prediction uncertainty, SHAP explanations, and BLUE diagnostics.
+- Reusable visualizations, galleries, reports, and standalone HTML dashboards.
+- Multi-workspace projects, multi-dataset operations, and model persistence.
+- `project.auto()` review, clean, and full workflow presets.
+- ADQL as a standalone cell-based language with rich VS Code notebook output.
+- ADQL `AUTO` support with full public workflow options and rich stage summaries.
+- Command-line tools, bundled VS Code extension and `.adql` icons, wheel and source distributions.
+- Automated compatibility matrix configured for Python 3.10–3.13 on Linux,
+  macOS, and Windows.
+- Tokenless TestPyPI publishing workflow using GitHub Trusted Publishing.
+- Protected, version-gated production PyPI Trusted Publishing workflow.
+
+### Release status
+
+- Local wheel and source-distribution checks pass.
+- TestPyPI and PyPI publication remain deliberate external release steps.

autodq-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Joseph Ubani
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

autodq-0.1.0/MANIFEST.in

@@ -0,0 +1,16 @@
+include LICENSE
+include CHANGELOG.md
+include README.md
+include pyproject.toml
+include requirements.txt
+include requirements-dev.txt
+
+recursive-include docs *.md
+recursive-include examples *.adql *.py
+recursive-include .github *.yml
+recursive-include scripts *.py
+recursive-include tests *.py
+
+global-exclude *.py[cod]
+global-exclude __pycache__
+global-exclude .DS_Store

autodq-0.1.0/PKG-INFO

@@ -0,0 +1,267 @@
+Metadata-Version: 2.4
+Name: autodq
+Version: 0.1.0
+Summary: AutoDQ Analytics: Automated Data Quality, Cleaning, Visualization, and Reporting Framework
+Author: Joseph Ubani
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/josephubani/autodq-analytics
+Project-URL: Issues, https://github.com/josephubani/autodq-analytics/issues
+Project-URL: Repository, https://github.com/josephubani/autodq-analytics.git
+Keywords: analytics,data-cleaning,data-quality,data-science,machine-learning
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+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 :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: joblib>=1.3
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: numpy>=1.24
+Requires-Dist: openpyxl>=3.1
+Requires-Dist: pandas>=2.0
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: scipy>=1.10
+Requires-Dist: shap>=0.44
+Requires-Dist: statsmodels>=0.14
+Requires-Dist: xlrd>=2.0.1
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
+Requires-Dist: twine>=6.0; extra == "dev"
+Dynamic: license-file
+
+# AutoDQ Analytics
+
+AutoDQ is an end-to-end analytics workflow framework for tabular data. It
+profiles datasets, diagnoses quality problems, recommends and reviews cleaning
+actions, engineers features, trains explainable models, generates
+visualizations and dashboards, and runs complete workflows from Python,
+Jupyter, the command line, or standalone `.adql` notebooks.
+
+## Highlights
+
+- CSV, XLSX, and XLS dataset loading
+- Dataset profiling, semantic inference, and quality scoring
+- Missing-value, duplicate, outlier, datatype, and leakage diagnosis
+- Knowledge-aware cleaning recommendations and approval workflows
+- Manual row editing, domain validation, outlier treatment, and audit trails
+- Descriptive statistics, distribution analysis, and correlations
+- Feature engineering and ML-readiness analysis
+- Regression and classification with prediction uncertainty
+- SHAP explanations and publication-ready SHAP plots
+- BLUE regression diagnostics, visual interpretation, and prescriptions
+- Reusable visualization objects, galleries, HTML reports, and dashboards
+- Multi-workspace project isolation and model persistence
+- `project.auto()` for an automated workflow
+- ADQL files with executable notebook cells and rich VS Code output
+
+## Requirements
+
+- Python 3.10 or newer
+- macOS, Linux, or Windows
+
+## Installation
+
+Install the released package from PyPI:
+
+```bash
+python -m pip install autodq
+```
+
+Until the first PyPI release, install directly from the project source:
+
+```bash
+git clone https://github.com/josephubani/autodq-analytics.git
+cd autodq-analytics
+python -m venv .venv
+source .venv/bin/activate
+python -m pip install .
+```
+
+On Windows PowerShell, activate the environment with:
+
+```powershell
+.venv\Scripts\Activate.ps1
+```
+
+For editable development and release tools:
+
+```bash
+python -m pip install -e ".[dev]"
+```
+
+## Python quick start
+
+```python
+from autodq import AutoDQ
+
+project = AutoDQ("datasets/sample/sales.csv", target="Revenue")
+
+profile = project.profile()
+diagnosis = project.diagnose()
+recommendations = project.recommend()
+review = project.review_cleaning()
+
+review.approve_all()
+project.clean()
+validation = project.validate_cleaning()
+
+chart = project.visualize(
+    chart="bar",
+    x="Region",
+    y="Revenue",
+    title="Revenue by Region",
+    x_label="Region",
+    y_label="Average revenue",
+    theme="journal",
+)
+chart.show()
+```
+
+## ADQL notebooks
+
+ADQL is AutoDQ's standalone analytics language. A `.adql` file can contain
+named executable cells and markdown cells, while retaining project state
+between executions.
+
+```adql
+# %% [Dataset]
+DATASET "sales.csv" TARGET Revenue;
+
+# %% [Data quality]
+PROFILE;
+DIAGNOSE;
+RECOMMEND;
+
+# %% [Regional analysis]
+SELECT Region,
+       SUM(Revenue) AS total_revenue,
+       COUNT(*) AS transactions
+FROM CURRENT
+GROUP BY Region
+ORDER BY total_revenue DESC;
+
+# %% [Visualization]
+VISUALIZE bar X Region Y Revenue
+    TITLE "Revenue by Region"
+    THEME journal;
+```
+
+Run the same automatic workflow available as `project.auto()` directly from
+an ADQL cell:
+
+```adql
+# %% [Automatic workflow]
+AUTO MODE full
+    VISUALIZE true
+    APPLY_FEATURES true
+    ALGORITHM random_forest_regressor
+    REPORT "reports/auto-report.html"
+    CONTINUE_ON_ERROR true;
+```
+
+`review` mode analyzes data and prepares cleaning actions without applying
+them. `clean` applies approved cleaning actions. `full` continues through
+modeling, prediction, and explainability when a target is available. The ADQL
+notebook renders the automatic stages, status, timing, and next actions as a
+collapsible rich result.
+
+Run the file from a terminal:
+
+```bash
+autodq run analysis.adql
+```
+
+Inspect or validate cells without executing the workflow:
+
+```bash
+autodq cells analysis.adql
+autodq validate analysis.adql
+```
+
+Run through a particular cell:
+
+```bash
+autodq run analysis.adql --through-cell 3
+```
+
+## VS Code support
+
+The Python distribution bundles the AutoDQ ADQL extension. Install it with:
+
+```bash
+autodq vscode install
+```
+
+Reload VS Code after installation. `.adql` files then receive syntax
+highlighting, named notebook cells, rich tables and charts, cell-by-cell
+execution, and an AutoDQ file icon.
+
+## Command-line interface
+
+```text
+autodq --version
+autodq run workflow.adql
+autodq validate workflow.adql
+autodq cells workflow.adql
+autodq vscode path
+autodq vscode install
+```
+
+The package can also be executed as a Python module:
+
+```bash
+python -m autodq --version
+```
+
+## Development
+
+Run the test suite:
+
+```bash
+python -m unittest discover -s tests
+```
+
+References: [Python API](docs/API_REFERENCE.md),
+[ADQL language](docs/ADQL_SPEC.md), [release guide](docs/RELEASING.md), and
+[changelog](CHANGELOG.md).
+
+Build and verify release artifacts:
+
+```bash
+python -m build
+python -m twine check dist/*
+python scripts/check_distribution.py dist
+```
+
+For the complete release process, see the
+[AutoDQ release guide](https://github.com/josephubani/autodq-analytics/blob/main/docs/RELEASING.md).
+
+## Documentation
+
+- [ADQL language reference](https://github.com/josephubani/autodq-analytics/blob/main/docs/ADQL_SPEC.md)
+- [System architecture](https://github.com/josephubani/autodq-analytics/blob/main/docs/ARCHITECTURE.md)
+- [Plugin development](https://github.com/josephubani/autodq-analytics/blob/main/docs/PLUGIN_GUIDE.md)
+- [Project roadmap](https://github.com/josephubani/autodq-analytics/blob/main/docs/ROADMAP.md)
+- [Package and release procedure](https://github.com/josephubani/autodq-analytics/blob/main/docs/RELEASING.md)
+
+## License
+
+AutoDQ is released under the
+[MIT License](https://github.com/josephubani/autodq-analytics/blob/main/LICENSE).
+
+## Author
+
+Joseph Ubani  
+Master of Data Analytics, University of Niagara Falls Canada