# EristroPy: End-to-End Entropy Analysis of Time Series Signals
## Overview and Introduction
Welcome to EristroPy, a powerful Python package designed for end-to-end entropy analysis of time series signals via entropy. EristroPy provides an all-in-one solution for researchers and practitioners looking to perform entropy/variability analysis of time series data.
For more detailed information, check out the [documentation](https://zblanks.github.io/eristropy/).
## Features & Benefits
EristroPy offers a multitude of features aimed at simplifying the time series analysis process:
- **Automatic Signal Stationarity**: Ensure the validity of your entropy and variability analyses by automatically rendering signals stationary.
- **Scalable Entropy Calculations**: Utilizes Numba's just-in-time compilation for efficient sample and permutation entropy calculations.
- **Optimal Parameter Selection**: Provides intelligent suggestions for entropy measure parameters through rigorous statistical approaches.
## Installation
The easiest way to install EristroPy is using pip by calling:
```bash
pip install eristropy
```
## Usage
Using EristroPy, you can go from having the base time series signals, to a coherent & optimized entropy estimates in just a few lines of code. For instance, consider the following problem of estimating the sample entropy of some synthetic time series signals:
```python
import numpy as np
import pandas as pd
from eristropy.stationarity import StationarySignals
from eristropy.sample_entropy import SampleEntropy
signal_ids = np.repeat(["signal_1", "signal_2"], 100)
timestamps = np.tile(np.arange(100), 2)
rng = np.random.default_rng(17)
signal_1_values = rng.uniform(-5, 5, size=(100,))
signal_2_values = rng.uniform(-5, 5, size=(100,))
values = np.concatenate((signal_1_values, signal_2_values))
df = pd.DataFrame({
"signal_id": signal_ids,
"timestamp": timestamps,
"value": values
})
signals = StationarySignals(df, method="difference")
stationary_df = signals.make_stationary_signals()
sampen = SampleEntropy(stationary_df)
result_df = sampen.compute_all_sampen(optimize=True, estimate_uncertainty=True)
```
In just a few lines of code, you have access to state-of-the-art results that follows & implements best practices. It's that easy!
## License
EristroPy is released under the MIT License. See the [LICENSE](LICENSE.md) file for more details.
Raw data
{
"_id": null,
"home_page": "https://zblanks.github.io/eristropy",
"name": "eristropy",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9,<3.12",
"maintainer_email": "",
"keywords": "entropy,time-series,optimization",
"author": "Zachary Blanks",
"author_email": "zdb6dz@virginia.edu",
"download_url": "https://files.pythonhosted.org/packages/6f/98/e9c20a5a7a5a9d336df21583efb7fa175394aa7f3cce2d05380363b0ad2e/eristropy-0.1.0.tar.gz",
"platform": null,
"description": "# EristroPy: End-to-End Entropy Analysis of Time Series Signals\n\n## Overview and Introduction\n\nWelcome to EristroPy, a powerful Python package designed for end-to-end entropy analysis of time series signals via entropy. EristroPy provides an all-in-one solution for researchers and practitioners looking to perform entropy/variability analysis of time series data.\n\nFor more detailed information, check out the [documentation](https://zblanks.github.io/eristropy/).\n\n## Features & Benefits\n\nEristroPy offers a multitude of features aimed at simplifying the time series analysis process:\n\n- **Automatic Signal Stationarity**: Ensure the validity of your entropy and variability analyses by automatically rendering signals stationary. \n- **Scalable Entropy Calculations**: Utilizes Numba's just-in-time compilation for efficient sample and permutation entropy calculations. \n- **Optimal Parameter Selection**: Provides intelligent suggestions for entropy measure parameters through rigorous statistical approaches.\n\n## Installation\n\nThe easiest way to install EristroPy is using pip by calling:\n\n```bash\npip install eristropy\n```\n\n## Usage\nUsing EristroPy, you can go from having the base time series signals, to a coherent & optimized entropy estimates in just a few lines of code. For instance, consider the following problem of estimating the sample entropy of some synthetic time series signals:\n\n```python\nimport numpy as np\nimport pandas as pd\nfrom eristropy.stationarity import StationarySignals\nfrom eristropy.sample_entropy import SampleEntropy\n\nsignal_ids = np.repeat([\"signal_1\", \"signal_2\"], 100)\ntimestamps = np.tile(np.arange(100), 2)\nrng = np.random.default_rng(17)\nsignal_1_values = rng.uniform(-5, 5, size=(100,))\nsignal_2_values = rng.uniform(-5, 5, size=(100,))\nvalues = np.concatenate((signal_1_values, signal_2_values))\n\ndf = pd.DataFrame({\n \"signal_id\": signal_ids,\n \"timestamp\": timestamps,\n \"value\": values\n})\n\nsignals = StationarySignals(df, method=\"difference\")\nstationary_df = signals.make_stationary_signals()\n\nsampen = SampleEntropy(stationary_df)\nresult_df = sampen.compute_all_sampen(optimize=True, estimate_uncertainty=True)\n```\n\nIn just a few lines of code, you have access to state-of-the-art results that follows & implements best practices. It's that easy!\n\n\n## License\nEristroPy is released under the MIT License. See the [LICENSE](LICENSE.md) file for more details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "EristroPy: End-to-end entropy analysis of time series signals",
"version": "0.1.0",
"project_urls": {
"Homepage": "https://zblanks.github.io/eristropy",
"Repository": "https://github.com/zblanks/eristropy"
},
"split_keywords": [
"entropy",
"time-series",
"optimization"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "88ea3bbff7adf41712ef7d6c6a5f276a58ca855a9cf2de1c50d5c0382a7412c4",
"md5": "6fde48b821de98c2c6a881c48eafb676",
"sha256": "a35b08b13d0604b1ad77a486c8d6484d1b5e1c4379ff9be53b8ac6387a98c5a4"
},
"downloads": -1,
"filename": "eristropy-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6fde48b821de98c2c6a881c48eafb676",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9,<3.12",
"size": 24706,
"upload_time": "2023-09-19T19:35:53",
"upload_time_iso_8601": "2023-09-19T19:35:53.876584Z",
"url": "https://files.pythonhosted.org/packages/88/ea/3bbff7adf41712ef7d6c6a5f276a58ca855a9cf2de1c50d5c0382a7412c4/eristropy-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6f98e9c20a5a7a5a9d336df21583efb7fa175394aa7f3cce2d05380363b0ad2e",
"md5": "8fc6c4901bee0cff6e3d64940c40b7bd",
"sha256": "961e2d923adabf5f5ff3bbc988b8d69841de1430405f5e6258383f127e7c2695"
},
"downloads": -1,
"filename": "eristropy-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "8fc6c4901bee0cff6e3d64940c40b7bd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9,<3.12",
"size": 21034,
"upload_time": "2023-09-19T19:35:55",
"upload_time_iso_8601": "2023-09-19T19:35:55.451792Z",
"url": "https://files.pythonhosted.org/packages/6f/98/e9c20a5a7a5a9d336df21583efb7fa175394aa7f3cce2d05380363b0ad2e/eristropy-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-19 19:35:55",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "zblanks",
"github_project": "eristropy",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "eristropy"
}
JSON
