tanml 0.1.10__tar.gz

tanml-0.1.10/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Tanmay Sah and Dolly Sah
+
+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.

tanml-0.1.10/MANIFEST.in

@@ -0,0 +1,4 @@
+include README.md
+include LICENSE
+include pyproject.toml
+recursive-include tanml/ui/assets *

tanml-0.1.10/PKG-INFO

@@ -0,0 +1,240 @@
+Metadata-Version: 2.4
+Name: tanml
+Version: 0.1.10
+Summary: Automated validation toolkit for tabular ML models—MRM, credit risk, insurance, and other regulated use cases.
+Author: Tanmay Sah, Dolly Sah
+Maintainer: Tanmay Sah, Dolly Sah
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/tdlabs-ai/tanml
+Project-URL: Source, https://github.com/tdlabs-ai/tanml
+Project-URL: Issues, https://github.com/tdlabs-ai/tanml/issues
+Project-URL: Documentation, https://github.com/tdlabs-ai/tanml#readme
+Keywords: model validation,model risk management,model governance,SR 11-7,tabular ML,credit risk,insurance analytics,explainability,XAI,SHAP,stress testing,reporting,docx,streamlit,xgboost,lightgbm,catboost
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Financial and Insurance Industry
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+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 :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.26
+Requires-Dist: scipy>=1.11
+Requires-Dist: pandas>=2.0
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: statsmodels>=0.14
+Requires-Dist: xgboost>=2.0
+Requires-Dist: lightgbm>=4.3
+Requires-Dist: catboost>=1.2
+Requires-Dist: shap>=0.44
+Requires-Dist: numba>=0.58
+Requires-Dist: matplotlib>=3.8
+Requires-Dist: seaborn>=0.13
+Requires-Dist: Pillow>=10.0
+Requires-Dist: python-docx>=1.1.2
+Requires-Dist: pyarrow>=14.0
+Requires-Dist: openpyxl>=3.1
+Requires-Dist: pyreadstat>=1.2
+Requires-Dist: streamlit>=1.36
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Dynamic: license-file
+
+# TanML: Automated Model Validation Toolkit for Tabular Machine Learning
+
+
+
+
+
+[![PyPI](https://img.shields.io/pypi/v/tanml.svg)](https://pypi.org/project/tanml/)
+[![Downloads](https://pepy.tech/badge/tanml)](https://pepy.tech/project/tanml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Give Feedback](https://img.shields.io/badge/Feedback-Give%20Now-blue?style=for-the-badge)](https://forms.gle/oG2JHvt7tLXE5Atu7)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17317165.svg)](https://doi.org/10.5281/zenodo.17317165)
+
+
+> **TanML bridges the gap between data science tools (for building models) and governance requirements (for validating them). It's not just an ML library—it's a validation workflow with built-in documentation.**
+
+* **Status:** Beta (`0.x`)
+* **License:** MIT
+* **Python:** 3.8–3.13
+* **OS:** Linux / macOS / Windows (incl. WSL)
+
+---
+
+## Table of Contents
+
+- Why TanML?
+- Install
+- Quick Start (UI)
+- Optional CLI Flags
+- Reports
+- Data Privacy
+- Troubleshooting
+- Contributing
+- License & Citation
+
+---
+
+## Why TanML?
+
+* **End-to-end workflow:** Data Profiling → Preprocessing → Feature Ranking → Model Development → Evaluation → Reports—all in one UI.
+* **Audit-ready Word reports:** Generate editable .docx documents for stakeholders and compliance reviews.
+* **Built for regulated industries:** Designed for MRM, credit risk, insurance, and SR 11-7 contexts.
+* **No code required:** Fully UI-driven—no Python knowledge needed.
+* **Robust evaluation:** Drift detection, stress testing, SHAP explainability, cluster coverage.
+* **Works with your stack:** scikit-learn, XGBoost, LightGBM, CatBoost.
+
+---
+
+## Install
+
+We strongly recommend using a virtual environment to isolate dependencies:
+
+```bash
+# Create and activate virtual environment
+python -m venv .venv
+source .venv/bin/activate  # Linux/Mac
+# .venv\Scripts\activate   # Windows
+
+# Install TanML
+pip install tanml
+```
+
+## Quick Start (UI)
+
+```bash
+tanml ui
+```
+
+* Opens at **[http://127.0.0.1:8501](http://127.0.0.1:8501)**
+* **Upload limit ~2 GB** (preconfigured)
+* **Telemetry disabled by default**
+
+---
+
+## Optional CLI Flags
+
+Most users just run `tanml ui`. These help on teams/servers:
+
+```bash
+# Share on LAN
+tanml ui --public
+
+# Different port
+tanml ui --port 9000
+
+# Headless (server/CI; no auto-open browser)
+tanml ui --headless
+
+# Larger limit (e.g., 2 GB)
+tanml ui --max-mb 2048
+```
+
+Env var equivalents (Linux/macOS bash):
+
+```bash
+TANML_SERVER_ADDRESS=0.0.0.0 TANML_PORT=9000 TANML_MAX_MB=2048 tanml ui
+```
+
+Windows PowerShell:
+
+```powershell
+$env:TANML_SERVER_ADDRESS="0.0.0.0"; $env:TANML_PORT="9000"; $env:TANML_MAX_MB="2048"; tanml ui
+```
+
+**Defaults:** address `127.0.0.1`, port `8501`, limit `2048 MB`, telemetry **OFF**.
+
+---
+
+## Reports
+
+TanML generates audit-ready Word reports (.docx) programmatically:
+
+* **Model Development Report** — Cross-validation metrics, diagnostics, and performance summary
+* **Model Evaluation Report** — Train/Test comparison, drift analysis, stress testing, SHAP explainability
+* **Feature Power Ranking Report** — Feature importance scores, correlation analysis
+
+Reports are generated via `tanml/ui/reports/generators.py` and exported directly from the UI.
+
+---
+
+## Data Privacy
+
+- TanML runs locally; no data is sent to external services.
+- Telemetry is disabled by default (and can be forced off via `--no-telemetry`).
+- UI artifacts and reports are written under `./tanml_runs/<session>/` in your working directory.
+
+---
+
+## Troubleshooting
+
+* **Page didn’t open?** Visit `http://127.0.0.1:8501` or run `tanml ui --port 9000`.
+* **Large CSVs are slow/heavy?** Prefer **Parquet**; CSV → DataFrame can use several GB RAM.
+* **Artifacts missing?** Check `./tanml_runs/<session>/artifacts/`.
+* **Corporate networks:** use `tanml ui --public` to share on LAN.
+
+---
+
+## Contributing
+
+We welcome issues and PRs!
+
+- Create a virtual environment and install dev extras:
+  - `python -m venv .venv && source .venv/bin/activate` (or `\.venv\Scripts\activate` on Windows)
+  - `pip install -e .[dev]`
+- Format/lint: `black . && isort .`
+- Run tests: `pytest`
+
+Before opening a PR, please describe the change and include a brief test or reproduction steps where applicable.
+
+---
+
+## License & Citation
+
+**License:** MIT. See [LICENSE](https://github.com/tdlabs-ai/tanml/blob/main/LICENSE).  
+SPDX-License-Identifier: MIT
+
+© 2025 Tanmay Sah and Dolly Sah. You may use, modify, and distribute this software with appropriate attribution.
+
+### How to cite
+
+If TanML helps your work or publications, please cite:
+
+> Sah, T., & Sah, D. (2025). *TanML: Automated Model Validation Toolkit for Tabular Machine Learning* [Software]. Zenodo. [https://doi.org/10.5281/zenodo.17317165](https://doi.org/10.5281/zenodo.17317165)
+
+Or in BibTeX (version-agnostic):
+
+```bibtex
+@software{tanml_2025,
+  author       = {Sah, Tanmay and Sah, Dolly},
+  title        = {TanML: Automated Model Validation Toolkit for Tabular Machine Learning},
+  year         = {2025},
+  publisher    = {Zenodo},
+  doi          = {10.5281/zenodo.17317165},
+  url          = {https://doi.org/10.5281/zenodo.17317165},
+  license      = {MIT}
+}
+```
+
+A machine-readable citation file (`CITATION.cff`) is included for citation tools and GitHub’s “Cite this repository” button.
+
+
+
+
+
+

tanml-0.1.10/README.md

@@ -0,0 +1,184 @@
+# TanML: Automated Model Validation Toolkit for Tabular Machine Learning
+
+
+
+
+
+[![PyPI](https://img.shields.io/pypi/v/tanml.svg)](https://pypi.org/project/tanml/)
+[![Downloads](https://pepy.tech/badge/tanml)](https://pepy.tech/project/tanml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Give Feedback](https://img.shields.io/badge/Feedback-Give%20Now-blue?style=for-the-badge)](https://forms.gle/oG2JHvt7tLXE5Atu7)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17317165.svg)](https://doi.org/10.5281/zenodo.17317165)
+
+
+> **TanML bridges the gap between data science tools (for building models) and governance requirements (for validating them). It's not just an ML library—it's a validation workflow with built-in documentation.**
+
+* **Status:** Beta (`0.x`)
+* **License:** MIT
+* **Python:** 3.8–3.13
+* **OS:** Linux / macOS / Windows (incl. WSL)
+
+---
+
+## Table of Contents
+
+- Why TanML?
+- Install
+- Quick Start (UI)
+- Optional CLI Flags
+- Reports
+- Data Privacy
+- Troubleshooting
+- Contributing
+- License & Citation
+
+---
+
+## Why TanML?
+
+* **End-to-end workflow:** Data Profiling → Preprocessing → Feature Ranking → Model Development → Evaluation → Reports—all in one UI.
+* **Audit-ready Word reports:** Generate editable .docx documents for stakeholders and compliance reviews.
+* **Built for regulated industries:** Designed for MRM, credit risk, insurance, and SR 11-7 contexts.
+* **No code required:** Fully UI-driven—no Python knowledge needed.
+* **Robust evaluation:** Drift detection, stress testing, SHAP explainability, cluster coverage.
+* **Works with your stack:** scikit-learn, XGBoost, LightGBM, CatBoost.
+
+---
+
+## Install
+
+We strongly recommend using a virtual environment to isolate dependencies:
+
+```bash
+# Create and activate virtual environment
+python -m venv .venv
+source .venv/bin/activate  # Linux/Mac
+# .venv\Scripts\activate   # Windows
+
+# Install TanML
+pip install tanml
+```
+
+## Quick Start (UI)
+
+```bash
+tanml ui
+```
+
+* Opens at **[http://127.0.0.1:8501](http://127.0.0.1:8501)**
+* **Upload limit ~2 GB** (preconfigured)
+* **Telemetry disabled by default**
+
+---
+
+## Optional CLI Flags
+
+Most users just run `tanml ui`. These help on teams/servers:
+
+```bash
+# Share on LAN
+tanml ui --public
+
+# Different port
+tanml ui --port 9000
+
+# Headless (server/CI; no auto-open browser)
+tanml ui --headless
+
+# Larger limit (e.g., 2 GB)
+tanml ui --max-mb 2048
+```
+
+Env var equivalents (Linux/macOS bash):
+
+```bash
+TANML_SERVER_ADDRESS=0.0.0.0 TANML_PORT=9000 TANML_MAX_MB=2048 tanml ui
+```
+
+Windows PowerShell:
+
+```powershell
+$env:TANML_SERVER_ADDRESS="0.0.0.0"; $env:TANML_PORT="9000"; $env:TANML_MAX_MB="2048"; tanml ui
+```
+
+**Defaults:** address `127.0.0.1`, port `8501`, limit `2048 MB`, telemetry **OFF**.
+
+---
+
+## Reports
+
+TanML generates audit-ready Word reports (.docx) programmatically:
+
+* **Model Development Report** — Cross-validation metrics, diagnostics, and performance summary
+* **Model Evaluation Report** — Train/Test comparison, drift analysis, stress testing, SHAP explainability
+* **Feature Power Ranking Report** — Feature importance scores, correlation analysis
+
+Reports are generated via `tanml/ui/reports/generators.py` and exported directly from the UI.
+
+---
+
+## Data Privacy
+
+- TanML runs locally; no data is sent to external services.
+- Telemetry is disabled by default (and can be forced off via `--no-telemetry`).
+- UI artifacts and reports are written under `./tanml_runs/<session>/` in your working directory.
+
+---
+
+## Troubleshooting
+
+* **Page didn’t open?** Visit `http://127.0.0.1:8501` or run `tanml ui --port 9000`.
+* **Large CSVs are slow/heavy?** Prefer **Parquet**; CSV → DataFrame can use several GB RAM.
+* **Artifacts missing?** Check `./tanml_runs/<session>/artifacts/`.
+* **Corporate networks:** use `tanml ui --public` to share on LAN.
+
+---
+
+## Contributing
+
+We welcome issues and PRs!
+
+- Create a virtual environment and install dev extras:
+  - `python -m venv .venv && source .venv/bin/activate` (or `\.venv\Scripts\activate` on Windows)
+  - `pip install -e .[dev]`
+- Format/lint: `black . && isort .`
+- Run tests: `pytest`
+
+Before opening a PR, please describe the change and include a brief test or reproduction steps where applicable.
+
+---
+
+## License & Citation
+
+**License:** MIT. See [LICENSE](https://github.com/tdlabs-ai/tanml/blob/main/LICENSE).  
+SPDX-License-Identifier: MIT
+
+© 2025 Tanmay Sah and Dolly Sah. You may use, modify, and distribute this software with appropriate attribution.
+
+### How to cite
+
+If TanML helps your work or publications, please cite:
+
+> Sah, T., & Sah, D. (2025). *TanML: Automated Model Validation Toolkit for Tabular Machine Learning* [Software]. Zenodo. [https://doi.org/10.5281/zenodo.17317165](https://doi.org/10.5281/zenodo.17317165)
+
+Or in BibTeX (version-agnostic):
+
+```bibtex
+@software{tanml_2025,
+  author       = {Sah, Tanmay and Sah, Dolly},
+  title        = {TanML: Automated Model Validation Toolkit for Tabular Machine Learning},
+  year         = {2025},
+  publisher    = {Zenodo},
+  doi          = {10.5281/zenodo.17317165},
+  url          = {https://doi.org/10.5281/zenodo.17317165},
+  license      = {MIT}
+}
+```
+
+A machine-readable citation file (`CITATION.cff`) is included for citation tools and GitHub’s “Cite this repository” button.
+
+
+
+
+
+

tanml-0.1.10/pyproject.toml

@@ -0,0 +1,112 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tanml"
+version = "0.1.10"
+description = "Automated validation toolkit for tabular ML models—MRM, credit risk, insurance, and other regulated use cases."
+readme = { file = "README.md", content-type = "text/markdown" }
+requires-python = ">=3.8"
+license = "MIT"
+license-files = ["LICENSE"]
+
+
+keywords = [
+  "model validation",
+  "model risk management",
+  "model governance",
+  "SR 11-7",
+  "tabular ML",
+  "credit risk",
+  "insurance analytics",
+  "explainability",
+  "XAI",
+  "SHAP",
+  "stress testing",
+  "reporting",
+  "docx",
+  "streamlit",
+  "xgboost",
+  "lightgbm",
+  "catboost"
+]
+
+
+
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: Financial and Insurance Industry",
+  "Natural Language :: English",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Topic :: Scientific/Engineering :: Information Analysis",
+  "Topic :: Scientific/Engineering :: Visualization"
+]
+
+
+authors = [
+  { name = "Tanmay Sah" },
+  { name = "Dolly Sah" }
+]
+
+maintainers = [
+  { name = "Tanmay Sah" },
+  { name = "Dolly Sah" }
+]
+
+dependencies = [
+  "numpy>=1.26",
+  "scipy>=1.11",
+  "pandas>=2.0",
+  "scikit-learn>=1.3",
+  "statsmodels>=0.14",
+  "xgboost>=2.0",
+  "lightgbm>=4.3",
+  "catboost>=1.2",
+  "shap>=0.44",
+  "numba>=0.58",
+  "matplotlib>=3.8",
+  "seaborn>=0.13",
+  "Pillow>=10.0",
+  "python-docx>=1.1.2",
+
+  "pyarrow>=14.0",
+  "openpyxl>=3.1",
+  "pyreadstat>=1.2",
+  "streamlit>=1.36"
+]
+
+
+[project.optional-dependencies]
+dev = ["pytest", "black", "isort"]
+
+[project.scripts]
+tanml = "tanml.cli.main:main"
+
+[project.urls]
+Homepage = "https://github.com/tdlabs-ai/tanml"
+Source = "https://github.com/tdlabs-ai/tanml"
+Issues = "https://github.com/tdlabs-ai/tanml/issues"
+Documentation = "https://github.com/tdlabs-ai/tanml#readme"
+
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["tanml*"]
+
+[tool.setuptools.package-data]
+"tanml.ui.assets" = ["*.png", "*.jpg", "*.svg"] 

tanml-0.1.10/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

tanml-0.1.10/tanml/__init__.py

@@ -0,0 +1,22 @@
+# tanml/__init__.py
+"""
+TanML - Industrial-Grade Model Validation Framework
+
+TanML provides comprehensive model validation, testing, and reporting
+for machine learning models in production environments.
+
+Quick Start:
+    # Launch the UI
+    tanml ui
+    
+    # Or run checks programmatically
+    from tanml.checks.stress_test import StressTestCheck
+    from tanml.checks.explainability.shap_check import SHAPCheck
+"""
+
+__version__ = "0.1.8"
+
+__all__ = [
+    "__version__",
+]
+

tanml-0.1.10/tanml/__main__.py

@@ -0,0 +1,4 @@
+from tanml.cli.main import main
+
+if __name__ == "__main__":
+    main()

tanml-0.1.10/tanml/analysis/__init__.py

@@ -0,0 +1,46 @@
+# tanml/analysis/__init__.py
+"""
+Analysis module for TanML.
+
+This module contains reusable business logic for data analysis,
+separated from the UI layer for better maintainability and testability.
+
+Modules:
+    - drift: Feature drift analysis (PSI, KS statistics)
+    - clustering: Input cluster coverage analysis
+    - correlation: Feature correlation and VIF analysis
+    - benchmarking: Model comparison and benchmarking
+
+Example:
+    from tanml.analysis import calculate_psi, calculate_ks
+    
+    psi_scores = calculate_psi(train_df, test_df, numeric_cols)
+    ks_scores = calculate_ks(train_df, test_df, numeric_cols)
+"""
+
+from tanml.analysis.drift import (
+    calculate_psi,
+    calculate_ks,
+    analyze_drift,
+)
+
+from tanml.analysis.clustering import (
+    analyze_cluster_coverage,
+)
+
+from tanml.analysis.correlation import (
+    calculate_correlation_matrix,
+    calculate_vif,
+)
+
+__all__ = [
+    # Drift analysis
+    "calculate_psi",
+    "calculate_ks", 
+    "analyze_drift",
+    # Clustering
+    "analyze_cluster_coverage",
+    # Correlation
+    "calculate_correlation_matrix",
+    "calculate_vif",
+]