Metadata-Version: 2.1
Name: regdata
Version: 0.1.3
Summary: A collection of regression datasets
Home-page: https://github.com/patel-zeel/regdata
Author: Zeel B Patel
Author-email: patel_zeel@iitgn.ac.in
License: MIT
Platform: UNKNOWN
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# RegData

Collection of regression datasets.

* Get data in any framework: ```torch```, ```tensorflow``` or ```numpy```

## Install
```bash
pip install regdata
```
## Quick example

```python
import regdata as rd
rd.set_backend('torch') # numpy, tf (numpy is default)
X, y, X_test = rd.Step().get_data()
```

## Plot datasets to have a quick glance

```python
import regdata as rd
rd.Olympic().plot()
```

Checkout all plots [here](https://nbviewer.jupyter.org/github/patel-zeel/regdata/blob/main/notebooks/visualize.ipynb).

## Datasets

```python
from regdata import (
    Step,
    Olympic,
    Smooth1D
)
```

## References

* [Step](http://inverseprobability.com/talks/notes/deep-gaussian-processes.html)
* [Olympic](http://inverseprobability.com/talks/notes/deep-gaussian-processes.html)
* [Smooth1D](http://www.stat.cmu.edu/~kass/papers/bars.pdf) - Example 2

