| Name | sefef JSON |
| Version |
2.1.4
JSON |
| download |
| home_page | None |
| Summary | SeFEF: Seizure Forecast Evaluation Framework |
| upload_time | 2025-02-02 15:17:26 |
| maintainer | None |
| docs_url | None |
| author | Ana Sofia Carmo |
| requires_python | None |
| license | BSD 3-clause |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
Welcome to ``SeFEF``
======================
.. image:: https://raw.githubusercontent.com/anascacais/sefef/main/docs/logo/sefef-logo.png
:align: center
:alt: SeFEF logo
|
``SeFEF`` is a Seizure Forecast Evaluation Framework written in Python.
The framework standardizes the development, evaluation, and reporting of individualized algorithms for seizure likelihood forecast.
``SeFEF`` aims to decrease development time and minimize implementation errors by automating key procedures within data preparation, training/testing, and computation of evaluation metrics.
Highlights:
-----------
- ``evaluation`` module: implements time series cross-validation.
- ``labeling`` module: automatically labels samples according to the desired pre-ictal duration and prediction latency.
- ``postprocessing`` module: processes individual predicted probabilities into a unified forecast according to the desired forecast horizon.
- ``scoring`` module: computes both deterministic and probabilistic metrics according to the horizon of the forecast.
Installation
------------
Installation can be easily done with ``pip``:
.. code:: bash
$ pip install sefef
Simple Example
--------------
The code below loads the metadata from an existing dataset from the ``examples`` folder, create a ``Dataset`` instance, and creates an adequate split for a time series cross-validation.
.. code:: python
import json
import pandas as pd
from sefef import evaluation
# read example files
files_metadata = pd.read_csv('examples/files_metadata.csv')
with open('examples/sz_onsets.txt', 'r') as f:
sz_onsets = json.load(f)
# create Dataset instance and perform TSCV
dataset = evaluation.Dataset(files_metadata, sz_onsets, sampling_frequency=128)
tscv = evaluation.TimeSeriesCV()
tscv.split(dataset, iteratively=False, plot=True)
Raw data
{
"_id": null,
"home_page": null,
"name": "sefef",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Ana Sofia Carmo",
"author_email": "anascacais@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/6b/17/8143c12d3ee6ee8d06e79e2c78a993ac0ec2083fd0419beb4616983ef7a5/sefef-2.1.4.tar.gz",
"platform": null,
"description": "Welcome to ``SeFEF``\n======================\n\n.. image:: https://raw.githubusercontent.com/anascacais/sefef/main/docs/logo/sefef-logo.png\n :align: center\n :alt: SeFEF logo\n\n|\n\n``SeFEF`` is a Seizure Forecast Evaluation Framework written in Python.\nThe framework standardizes the development, evaluation, and reporting of individualized algorithms for seizure likelihood forecast. \n``SeFEF`` aims to decrease development time and minimize implementation errors by automating key procedures within data preparation, training/testing, and computation of evaluation metrics. \n\nHighlights:\n-----------\n\n- ``evaluation`` module: implements time series cross-validation.\n- ``labeling`` module: automatically labels samples according to the desired pre-ictal duration and prediction latency.\n- ``postprocessing`` module: processes individual predicted probabilities into a unified forecast according to the desired forecast horizon.\n- ``scoring`` module: computes both deterministic and probabilistic metrics according to the horizon of the forecast. \n\n\n\nInstallation\n------------\n\nInstallation can be easily done with ``pip``:\n\n.. code:: bash\n\n $ pip install sefef\n\nSimple Example\n--------------\n\nThe code below loads the metadata from an existing dataset from the ``examples`` folder, create a ``Dataset`` instance, and creates an adequate split for a time series cross-validation.\n\n.. code:: python\n\n import json\n import pandas as pd\n from sefef import evaluation\n\n # read example files\n files_metadata = pd.read_csv('examples/files_metadata.csv')\n with open('examples/sz_onsets.txt', 'r') as f:\n sz_onsets = json.load(f)\n \n # create Dataset instance and perform TSCV\n dataset = evaluation.Dataset(files_metadata, sz_onsets, sampling_frequency=128)\n tscv = evaluation.TimeSeriesCV()\n tscv.split(dataset, iteratively=False, plot=True)\n",
"bugtrack_url": null,
"license": "BSD 3-clause",
"summary": "SeFEF: Seizure Forecast Evaluation Framework",
"version": "2.1.4",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "270ae949b7bf04633a94603826c51143afb968ed6e5eeaaf6bf54fd2ef7f2c5e",
"md5": "153d82785614b58b1b6de7ebe8a4adeb",
"sha256": "597f25b4c6f9a528387b8083a2411b3adfcc6366357af07d0e193abb81e4488e"
},
"downloads": -1,
"filename": "sefef-2.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "153d82785614b58b1b6de7ebe8a4adeb",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 23650,
"upload_time": "2025-02-02T15:17:23",
"upload_time_iso_8601": "2025-02-02T15:17:23.683414Z",
"url": "https://files.pythonhosted.org/packages/27/0a/e949b7bf04633a94603826c51143afb968ed6e5eeaaf6bf54fd2ef7f2c5e/sefef-2.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6b178143c12d3ee6ee8d06e79e2c78a993ac0ec2083fd0419beb4616983ef7a5",
"md5": "889adef00da858e75d8a3aa67ad0c8bc",
"sha256": "58e88c4a1a07d9a6aa42f5bc58d6079e6185ece8080dafa2d88cfed157469cb7"
},
"downloads": -1,
"filename": "sefef-2.1.4.tar.gz",
"has_sig": false,
"md5_digest": "889adef00da858e75d8a3aa67ad0c8bc",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 120996,
"upload_time": "2025-02-02T15:17:26",
"upload_time_iso_8601": "2025-02-02T15:17:26.327190Z",
"url": "https://files.pythonhosted.org/packages/6b/17/8143c12d3ee6ee8d06e79e2c78a993ac0ec2083fd0419beb4616983ef7a5/sefef-2.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-02 15:17:26",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "sefef"
}
