<p align="left">
<img src="https://raw.githubusercontent.com/NLeSC/mcfly/master/mcflylogo_with_regression.png" width="200"/>
</p>
[](https://github.com/NLeSC/mcfly/actions/workflows/CI_build.yml)
[](https://scrutinizer-ci.com/g/NLeSC/mcfly/statistics/)
[](https://pypi.python.org/pypi/mcfly/)
[](https://doi.org/10.5281/zenodo.596127)
[](http://mybinder.org:/repo/nlesc/mcfly)
<!-- The first 12 lines are skipped while generating 'long description' (see setup.py)) -->
The goal of mcfly is to ease the use of deep learning technology for time series classification and regression. The advantage of deep learning is that it can handle raw data directly, without the need to compute signal features. Deep learning does not require expert domain knowledge about the data, and has been shown to be competitive with conventional machine learning techniques. As an example, you can apply mcfly on accelerometer data for activity classification, as shown in [the tutorial](https://github.com/NLeSC/mcfly-tutorial).
If you use mcfly in your research, please cite the following software paper:
D. van Kuppevelt, C. Meijer, F. Huber, A. van der Ploeg, S. Georgievska, V.T. van Hees. _Mcfly: Automated deep learning on time series._
SoftwareX,
Volume 12,
2020.
[doi: 10.1016/j.softx.2020.100548](https://doi.org/10.1016/j.softx.2020.100548)
## Installation
Prerequisites:
- Python 3.7, 3.8, 3.9 or 3.10
- pip
- Tensorflow 2
Installing all dependencies in separate conda environment:
```sh
conda env create -f environment.yml
# activate this new environment
source activate mcfly
```
To install the package, run in the project directory:
`pip install mcfly`
## Visualization
We build a tool to visualize the configuration and performance of the models. The tool can be found on http://nlesc.github.io/mcfly/. To run the model visualization on your own computer, cd to the `html` directory and start up a python web server:
`python -m http.server 8888 &`
Navigate to `http://localhost:8888/` in your browser to open the visualization. For a more elaborate description of the visualization see [user manual](https://mcfly.readthedocs.io/en/latest/user_manual.html).
## User documentation
[User and code documentation](https://mcfly.readthedocs.io).
## Contributing
You are welcome to contribute to the code via pull requests. Please have a look at the [NLeSC guide](https://nlesc.gitbooks.io/guide/content/software/software_overview.html) for guidelines about software development.
We use numpy-style docstrings for code documentation.
## Licensing
Source code and data of mcfly are licensed under the Apache License, version 2.0.
Raw data
{
"_id": null,
"home_page": "https://github.com/NLeSC/mcfly",
"name": "mcfly",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "Python",
"author": "",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/c4/02/e71ce41f317b3e552cae138c899101ca6fbc2f6b55714172ab11aa810eca/mcfly-4.0.0.tar.gz",
"platform": null,
"description": "<p align=\"left\">\n <img src=\"https://raw.githubusercontent.com/NLeSC/mcfly/master/mcflylogo_with_regression.png\" width=\"200\"/>\n</p>\n\n[](https://github.com/NLeSC/mcfly/actions/workflows/CI_build.yml)\n[](https://scrutinizer-ci.com/g/NLeSC/mcfly/statistics/)\n[](https://pypi.python.org/pypi/mcfly/)\n[](https://doi.org/10.5281/zenodo.596127)\n[](http://mybinder.org:/repo/nlesc/mcfly)\n<!-- The first 12 lines are skipped while generating 'long description' (see setup.py)) -->\n\nThe goal of mcfly is to ease the use of deep learning technology for time series classification and regression. The advantage of deep learning is that it can handle raw data directly, without the need to compute signal features. Deep learning does not require expert domain knowledge about the data, and has been shown to be competitive with conventional machine learning techniques. As an example, you can apply mcfly on accelerometer data for activity classification, as shown in [the tutorial](https://github.com/NLeSC/mcfly-tutorial).\n\nIf you use mcfly in your research, please cite the following software paper:\n\nD. van Kuppevelt, C. Meijer, F. Huber, A. van der Ploeg, S. Georgievska, V.T. van Hees. _Mcfly: Automated deep learning on time series._\nSoftwareX,\nVolume 12,\n2020.\n[doi: 10.1016/j.softx.2020.100548](https://doi.org/10.1016/j.softx.2020.100548)\n\n## Installation\nPrerequisites:\n- Python 3.7, 3.8, 3.9 or 3.10\n- pip\n- Tensorflow 2\n\nInstalling all dependencies in separate conda environment:\n```sh\nconda env create -f environment.yml\n\n# activate this new environment\nsource activate mcfly\n```\n\nTo install the package, run in the project directory:\n\n`pip install mcfly`\n\n\n## Visualization\nWe build a tool to visualize the configuration and performance of the models. The tool can be found on http://nlesc.github.io/mcfly/. To run the model visualization on your own computer, cd to the `html` directory and start up a python web server:\n\n`python -m http.server 8888 &`\n\nNavigate to `http://localhost:8888/` in your browser to open the visualization. For a more elaborate description of the visualization see [user manual](https://mcfly.readthedocs.io/en/latest/user_manual.html).\n\n\n## User documentation\n[User and code documentation](https://mcfly.readthedocs.io).\n\n## Contributing\nYou are welcome to contribute to the code via pull requests. Please have a look at the [NLeSC guide](https://nlesc.gitbooks.io/guide/content/software/software_overview.html) for guidelines about software development.\n\nWe use numpy-style docstrings for code documentation.\n\n\n## Licensing\nSource code and data of mcfly are licensed under the Apache License, version 2.0.\n",
"bugtrack_url": null,
"license": "Apache Software License 2.0",
"summary": "Deep learning for time series data",
"version": "4.0.0",
"split_keywords": [
"python"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "87248b09fb59e7a1a499edb97b686b42",
"sha256": "52044646fccf338982863677186cab7e08f5a536b3f95b313ec60a1ce0c01cf5"
},
"downloads": -1,
"filename": "mcfly-4.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "87248b09fb59e7a1a499edb97b686b42",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 24830,
"upload_time": "2022-12-21T14:00:37",
"upload_time_iso_8601": "2022-12-21T14:00:37.549791Z",
"url": "https://files.pythonhosted.org/packages/55/a3/51d8e4709d371f19252342400e677e44b684ae54c395ee372eb5828ff6f8/mcfly-4.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "78f14bc940e9553cec83827a9a2185d7",
"sha256": "3dc9dbcc06da7f168a48bf6d67bb5c33ed9a427507e3b967cf3c517d5696e93c"
},
"downloads": -1,
"filename": "mcfly-4.0.0.tar.gz",
"has_sig": false,
"md5_digest": "78f14bc940e9553cec83827a9a2185d7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 19409,
"upload_time": "2022-12-21T14:00:38",
"upload_time_iso_8601": "2022-12-21T14:00:38.952157Z",
"url": "https://files.pythonhosted.org/packages/c4/02/e71ce41f317b3e552cae138c899101ca6fbc2f6b55714172ab11aa810eca/mcfly-4.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-21 14:00:38",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "NLeSC",
"github_project": "mcfly",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mcfly"
}
JSON
