Metadata-Version: 2.4
Name: hea
Version: 0.1.1
Summary: Linear Models with Python
License-Expression: GPL-3.0-or-later
License-File: LICENSE
Requires-Python: >=3.10.0
Requires-Dist: matplotlib>=3.10.0
Requires-Dist: numpy>=2.2.2
Requires-Dist: polars>=1.20.0
Requires-Dist: pyarrow>=24.0.0
Requires-Dist: rdatasets>=0.2.10
Requires-Dist: scikit-sparse>=0.5.0
Requires-Dist: scipy>=1.15.1
Provides-Extra: bench
Requires-Dist: formulae>=0.5.4; extra == 'bench'
Requires-Dist: formulaic>=1.1.1; extra == 'bench'
Requires-Dist: pandas>=2.0.0; extra == 'bench'
Description-Content-Type: text/markdown

# hea: Linear Models with Python

> hea v. (Cantonese) 
> 1. to kill time; to hang around  
> 2. to do something without putting much care or effort into it. 

This project started as an laid-back exercise of implementing R's `lm`, `lme`, `glm` and `gam` in Python, and later evolved into my private benchmark for coding agents (and it finally gets some momentum after trying with Opus 4.7).

## Usage

```python
from hea import lm, data

gala = data('gala', package='faraway')
m = lm('Species ~ Area + Adjacent + Elevation + Nearest + Scruz', gala)
m.summary()
```

See more [examples](./example/).