yaeda 0.1.0__tar.gz

yaeda-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,34 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          enable-cache: true
+
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --extra dev --extra shap
+
+      - name: Check code formatting & lint
+        run: uv run ruff check .
+
+      - name: Run test suite
+        run: uv run pytest --cov=yaeda --cov-report=term-missing

yaeda-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,30 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  pypi-publish:
+    name: Build distribution and publish to PyPI
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/yaeda
+    permissions:
+      id-token: write # Mandatory for Trusted Publishing OIDC
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Build sdist and wheel
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/

yaeda-0.1.0/.gitignore

@@ -0,0 +1,33 @@
+# Byte-compiled / optimized files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / Packaging
+dist/
+build/
+*.egg-info/
+.eggs/
+
+# Virtual Environments (uv & venv)
+.venv/
+venv/
+ENV/
+
+# Testing & Coverage
+.pytest_cache/
+.coverage
+htmlcov/
+.ruff_cache/
+
+# Local Reports & Data
+*.html
+*.pdf
+*.json
+*.csv
+!tests/data/*.csv
+
+# IDEs & System
+.vscode/
+.idea/
+.DS_Store

yaeda-0.1.0/.python-version

@@ -0,0 +1 @@
+3.12

yaeda-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Rafael Cunha
+
+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.

yaeda-0.1.0/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.5
+Name: yaeda
+Version: 0.1.0
+Summary: Yet Another EDA - Tabular Feature Discovery, Interaction Analysis, and Error Diagnostics.
+Project-URL: Homepage, https://github.com/your-username/yaEDA
+Project-URL: Repository, https://github.com/your-username/yaEDA
+Project-URL: Issues, https://github.com/your-username/yaEDA/issues
+Author-email: Rafael Cunha <rnascunha@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: eda,feature-engineering,kaggle,machine-learning,shap,tabular
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: matplotlib>=3.7.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: scipy>=1.10.0
+Requires-Dist: seaborn>=0.12.0
+Provides-Extra: all
+Requires-Dist: shap>=0.42.0; extra == 'all'
+Requires-Dist: weasyprint>=60.0; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=4.1.0; extra == 'dev'
+Requires-Dist: pytest>=7.4.0; extra == 'dev'
+Requires-Dist: ruff>=0.4.0; extra == 'dev'
+Provides-Extra: pdf
+Requires-Dist: weasyprint>=60.0; extra == 'pdf'
+Provides-Extra: shap
+Requires-Dist: shap>=0.42.0; extra == 'shap'
+Description-Content-Type: text/markdown
+
+# yaEDA: Yet Another EDA 🚀
+
+[![CI](https://github.com/rnascunha/yaEDA/actions/workflows/ci.yml/badge.svg)](https://github.com/your-username/yaEDA/actions)
+[![PyPI version](https://img.shields.io/pypi/v/yaeda.svg)](https://pypi.org/project/yaeda/)
+[![Python versions](https://img.shields.io/pypi/pyversions/yaeda.svg)](https://pypi.org/project/yaeda/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+**yaEDA** (Yet Another EDA) is an automated exploratory data analysis, feature intelligence, and model error diagnostics engine built for competitive tabular data science and machine learning.
+
+---
+
+## Features
+
+- **Golden Feature Ranking**: Combines tree MDI, out-of-sample permutation drop, and Mutual Information into a composite rank score.
+- **Partial Dependence & ICE Curves**: Evaluates individual non-linear response curves across primary predictors.
+- **Arithmetic Synergy Engine**: Evaluates combinations ($A \times B$, $A / B$, $A \pm B$) to identify feature interactions exceeding baseline performance.
+- **KMeans & PCA Clustering**: Identifies distinct clusters and measures target alignment using mutual information.
+- **Model Error Diagnostics**: Partitions false positive/negative cohorts and residual tails with global beeswarms and local SHAP waterfall plots.
+- **Self-Contained Dashboard**: Exports standalone HTML reports with zero runtime dependencies.
+
+---
+
+## Installation
+
+```bash
+# Core package
+$ pip install yaeda
+
+# With SHAP support
+$ pip install "yaeda[shap]"
+
+# With PDF export (WeasyPrint)
+$ pip install "yaeda[pdf]"
+```
+
+Using `uv`:
+
+```bash
+$ uv add yaeda --extra shap
+```
+
+## Quickstart
+
+```python
+import pandas as pd
+from yaeda import TabularEDA
+
+df = pd.read_csv("train.csv")
+
+eda = TabularEDA(
+    df=df,
+    target="target_col",
+    target_type="classification",
+)
+
+# Generate offline HTML dashboard
+eda.to_html("report.html")
+
+# Export structured intelligence as JSON
+eda.to_json("metadata.json")
+```
+
+## Development Setup
+
+```bash
+# Clone the repository
+git clone [https://github.com/your-username/yaEDA.git](https://github.com/your-username/yaEDA.git)
+cd yaEDA
+
+# Create virtual environment and sync dependencies using uv
+uv sync --extra dev --extra all
+
+# Run test suite
+uv run pytest
+
+# Run linting
+uv run ruff check .
+```

yaeda-0.1.0/README.md

@@ -0,0 +1,78 @@
+# yaEDA: Yet Another EDA 🚀
+
+[![CI](https://github.com/rnascunha/yaEDA/actions/workflows/ci.yml/badge.svg)](https://github.com/your-username/yaEDA/actions)
+[![PyPI version](https://img.shields.io/pypi/v/yaeda.svg)](https://pypi.org/project/yaeda/)
+[![Python versions](https://img.shields.io/pypi/pyversions/yaeda.svg)](https://pypi.org/project/yaeda/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+**yaEDA** (Yet Another EDA) is an automated exploratory data analysis, feature intelligence, and model error diagnostics engine built for competitive tabular data science and machine learning.
+
+---
+
+## Features
+
+- **Golden Feature Ranking**: Combines tree MDI, out-of-sample permutation drop, and Mutual Information into a composite rank score.
+- **Partial Dependence & ICE Curves**: Evaluates individual non-linear response curves across primary predictors.
+- **Arithmetic Synergy Engine**: Evaluates combinations ($A \times B$, $A / B$, $A \pm B$) to identify feature interactions exceeding baseline performance.
+- **KMeans & PCA Clustering**: Identifies distinct clusters and measures target alignment using mutual information.
+- **Model Error Diagnostics**: Partitions false positive/negative cohorts and residual tails with global beeswarms and local SHAP waterfall plots.
+- **Self-Contained Dashboard**: Exports standalone HTML reports with zero runtime dependencies.
+
+---
+
+## Installation
+
+```bash
+# Core package
+$ pip install yaeda
+
+# With SHAP support
+$ pip install "yaeda[shap]"
+
+# With PDF export (WeasyPrint)
+$ pip install "yaeda[pdf]"
+```
+
+Using `uv`:
+
+```bash
+$ uv add yaeda --extra shap
+```
+
+## Quickstart
+
+```python
+import pandas as pd
+from yaeda import TabularEDA
+
+df = pd.read_csv("train.csv")
+
+eda = TabularEDA(
+    df=df,
+    target="target_col",
+    target_type="classification",
+)
+
+# Generate offline HTML dashboard
+eda.to_html("report.html")
+
+# Export structured intelligence as JSON
+eda.to_json("metadata.json")
+```
+
+## Development Setup
+
+```bash
+# Clone the repository
+git clone [https://github.com/your-username/yaEDA.git](https://github.com/your-username/yaEDA.git)
+cd yaEDA
+
+# Create virtual environment and sync dependencies using uv
+uv sync --extra dev --extra all
+
+# Run test suite
+uv run pytest
+
+# Run linting
+uv run ruff check .
+```

yaeda-0.1.0/pyproject.toml

@@ -0,0 +1,68 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "yaeda"
+version = "0.1.0"
+description = "Yet Another EDA - Tabular Feature Discovery, Interaction Analysis, and Error Diagnostics."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+authors = [{ name = "Rafael Cunha", email = "rnascunha@gmail.com" }]
+keywords = [
+  "eda",
+  "tabular",
+  "machine-learning",
+  "feature-engineering",
+  "kaggle",
+  "shap",
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+  "pandas>=2.0.0",
+  "numpy>=1.24.0",
+  "scipy>=1.10.0",
+  "scikit-learn>=1.3.0",
+  "matplotlib>=3.7.0",
+  "seaborn>=0.12.0",
+]
+
+[project.optional-dependencies]
+shap = ["shap>=0.42.0"]
+pdf = ["weasyprint>=60.0"]
+all = ["shap>=0.42.0", "weasyprint>=60.0"]
+dev = ["pytest>=7.4.0", "pytest-cov>=4.1.0", "ruff>=0.4.0"]
+
+[project.urls]
+Homepage = "https://github.com/your-username/yaEDA"
+Repository = "https://github.com/your-username/yaEDA"
+Issues = "https://github.com/your-username/yaEDA/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/yaeda"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+ignore = [
+  "I001",   # Ban/ignore isort import sorting checks,
+  "BLE001", # Ignore base Exception class
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-ra -q --strict-markers"

yaeda-0.1.0/src/yaeda/__init__.py

@@ -0,0 +1,28 @@
+"""tabulareda - Automated Tabular EDA & Golden Feature Engineering Toolkit."""
+
+from .analyze import TabularEDA
+from .clustering import ClusterReport, TabularClusterAnalyzer
+from .correlation import CorrelationReport, FeatureTargetAnalyzer
+from .extract import FeatureProfile, TableProfile, TabularDataProfiler
+from .feature_importance import FeatureImportanceAnalyzer, FeatureImportanceReport
+from .interaction import FeatureInteractionAnalyzer, InteractionReport
+from .model_diagnostics import ModelDiagnosticsAnalyzer, ModelDiagnosticsReport
+
+__all__ = [
+    "ClusterReport",
+    "CorrelationReport",
+    "FeatureImportanceAnalyzer",
+    "FeatureImportanceReport",
+    "FeatureInteractionAnalyzer",
+    "FeatureProfile",
+    "FeatureTargetAnalyzer",
+    "InteractionReport",
+    "ModelDiagnosticsAnalyzer",
+    "ModelDiagnosticsReport",
+    "TableProfile",
+    "TabularClusterAnalyzer",
+    "TabularDataProfiler",
+    "TabularEDA",
+]
+
+__version__ = "0.1.0"