Metadata-Version: 2.4
Name: aaa-eda-analyzer
Version: 0.2.0
Summary: Automated exploratory data analysis pipeline: data quality, outliers, stats testing, feature importance, VIF, and HTML/PDF reporting.
Project-URL: Homepage, https://github.com/Ali8089/EDA_Library
Project-URL: Issues, https://github.com/Ali8089/EDA_Library/issues
Author-email: Ali Awaiz Attiyab <aaattiyab2-c@my.cityu.edu.hk>
License: MIT
License-File: LICENSE
Keywords: data-analysis,data-quality,eda,feature-importance,pandas,statistics
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.9
Requires-Dist: matplotlib>=3.6
Requires-Dist: numpy>=1.23
Requires-Dist: pandas>=1.5
Requires-Dist: scikit-learn>=1.1
Requires-Dist: scipy>=1.9
Requires-Dist: seaborn>=0.12
Requires-Dist: statsmodels>=0.13
Provides-Extra: pdf
Requires-Dist: weasyprint>=59.0; extra == 'pdf'
Provides-Extra: polars
Requires-Dist: polars>=0.19; extra == 'polars'
Description-Content-Type: text/markdown

# aaa-eda-analyzer

Automated exploratory data analysis (EDA) pipeline for pandas DataFrames: data
quality checks, outlier detection, bivariate hypothesis testing, mutual
information feature importance, multicollinearity (VIF), pairwise feature
interactions, intelligent plotting, and a self-contained HTML/PDF report.

📖 **Full API reference, guards/thresholds, and detection rules:**
[docs/API.md](docs/API.md)

## Installation

```bash
pip install aaa-eda-analyzer
```

For PDF report export:

```bash
pip install "aaa-eda-analyzer[pdf]"
```

> Note: the PyPI/distribution name is `aaa-eda-analyzer`, but the import
> name stays `eda_analyzer` (see Quick start below) — this is normal and
> matches the pattern used by packages like `beautifulsoup4` (imported as
> `bs4`).

## Quick start

```python
import pandas as pd
from eda_analyzer import DataAnalyzer

df = pd.read_csv("your_data.csv")

analyzer = DataAnalyzer(df, target_col="target")
analyzer.run_all()
```

Run a subset of steps:

```python
analyzer.run_all(steps=["summarize", "data_quality", "outliers"])
```

Generate a downloadable HTML report with embedded plots:

```python
analyzer = DataAnalyzer(df, target_col="target", download=True, export_pdf=True)
analyzer.run_all()
```

Access results programmatically:

```python
analyzer.quality_report_
analyzer.outlier_report_
analyzer.bivariate_stats_
analyzer.feature_importance_
analyzer.vif_report_
analyzer.top_feature_pairs_
```

## License

MIT
