https://github.com/floriank13/skyimages

Download and manage sky images for solar power forecasting.
https://github.com/floriank13/skyimages

data dataset datasets energy forecasting machine-learning python python-package pytorch

Last synced: about 1 month ago
JSON representation

Download and manage sky images for solar power forecasting.

• Host: GitHub
• URL: https://github.com/floriank13/skyimages
• Owner: FlorianK13
• License: mit
• Created: 2022-08-31T06:37:10.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-07-21T07:52:31.000Z (almost 2 years ago)
• Last Synced: 2025-05-13T03:59:33.193Z (about 1 month ago)
• Topics: data, dataset, datasets, energy, forecasting, machine-learning, python, python-package, pytorch
• Language: Python
• Homepage:
• Size: 65.4 KB
• Stars: 13
• Watchers: 1
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# skyimages

[![PyPI - Downloads](https://img.shields.io/pypi/dm/skyimages?label=pypi%20downloads)](https://pypistats.org/packages/skyimages)

[![GitHub issues by-label](https://img.shields.io/github/issues-raw/FlorianK13/skyimages/good%20first%20issue?label=Contribute%3A%20Good%20first%20issue)](https://github.com/FlorianK13/skyimages/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)

Download sky images for solar power forecasting as pytorch-ready datasets.

The package is still in early development and not stable. Please report bugs in the [Issues](https://github.com/FlorianK13/skyimages/issues).

## Installation using pypi

From release v0.0.1, `skyimages` will be installable via pip:

```bash

pip install skyimages

```

## Installation using github

Download ``skyimages`` from

[github](https://github.com/FlorianK13/skyimages).

Change the CWD to the download folder `skyimages/` and install

the package using pip.

```bash

git clone [email protected]:FlorianK13/skyimages.git

cd skyimages

pip install .

```

## Getting started

To download the dataset SKIPP'D ([source](https://arxiv.org/abs/2207.00913)) and use it as a pytorch torchvision dataset,

run the following code in python

```python

from skyimages.dataset import SKIPPDDataSet

import torch

traindata = SKIPPDDataSet(download=True)

testdata = SKIPPDDataSet(download=True, train=False)

trainloader = torch.utils.data.DataLoader(

    traindata, batch_size=200, shuffle=True, num_workers=0

)

testloader = torch.utils.data.DataLoader(

    testdata, batch_size=20, shuffle=False, num_workers=0

)

```

## Implemented data sets

* [SKIPPD](https://arxiv.org/abs/2207.00913)

## Contributing

Contributions and cooperations are highly welcome. If interested, just create an issue and we can discuss further details.