# clairvoyance2
> clairvoyance2: a Unified Toolkit for Medical Time Series
**⚠️ The library is in pre-alpha / dev. API will change without warning.**
**clairvoyance2** is a library that unifies time series tasks for the medicine and healthcare use case. It provides tools for manipulating multi-dimensional time series, as well as static data, and implements models for: time series prediction, individualized treatment effects estimation, time-to-event analysis (*upcoming*), and model interpretability (*upcoming*). **clairvoyance2** is primarily focussed on machine learning models.
## Installation
`pip install git+https://github.com/vanderschaarlab/clairvoyance2.git`
## Models
| Model | Status |
|-|-|
| **Prediction (Forecasting)** |
| RNN | ✅ Implemented |
| Seq2Seq | ✅ Implemented |
| [NeuralLaplace](https://github.com/samholt/NeuralLaplace) | 🔲 Planned |
| **Imputation** |
| {f,b}fill & Mean | ✅ Implemented |
| [HyperImpute](https://proceedings.mlr.press/v162/jarrett22a/jarrett22a.pdf) | 🔲
| **Individualized Treatment Effects** |
| [CRN](https://openreview.net/forum?id=BJg866NFvB) | ✅ Implemented |
| [SyncTwin](https://proceedings.neurips.cc/paper/2021/hash/19485224d128528da1602ca47383f078-Abstract.html) | ⚙️ Experimental |
| [TE-CDE](https://proceedings.mlr.press/v162/seedat22b/seedat22b.pdf) | 🔲 Planned |
| **Time-to-event Analysis** |
| [Dynamic DeepHit](https://pubmed.ncbi.nlm.nih.gov/30951460/) | 🔲 Planned |
| **Interpretability** |
| [DynaMask](http://proceedings.mlr.press/v139/crabbe21a/crabbe21a.pdfsa) | 🔲 Planned |
## Tutorials
* [📔 Basic Usage](tutorials/basic_usage.ipynb)
* [📔 Example: CRN](tutorials/crn.ipynb)
* [📔 Example: SyncTwin](tutorials/synctwin.ipynb)
## Contact
If you wish to reach about to us specifically about `clairvoyance2` (bugs, suggestions, problems, ...) please message
Evgeny on [LinkedIn](https://www.linkedin.com/in/e-s-saveliev/) for now, until we set up an official communication channel.
Raw data
{
"_id": null,
"home_page": "https://www.vanderschaar-lab.com/",
"name": "clairvoyance2",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "Evgeny Saveliev",
"author_email": "e.s.saveliev@gmail.com",
"download_url": "",
"platform": "any",
"description": "# clairvoyance2\r\n\r\n> clairvoyance2: a Unified Toolkit for Medical Time Series\r\n\r\n**\u26a0\ufe0f The library is in pre-alpha / dev. API will change without warning.**\r\n\r\n**clairvoyance2** is a library that unifies time series tasks for the medicine and healthcare use case. It provides tools for manipulating multi-dimensional time series, as well as static data, and implements models for: time series prediction, individualized treatment effects estimation, time-to-event analysis (*upcoming*), and model interpretability (*upcoming*). **clairvoyance2** is primarily focussed on machine learning models.\r\n\r\n\r\n\r\n\r\n## Installation\r\n\r\n`pip install git+https://github.com/vanderschaarlab/clairvoyance2.git`\r\n\r\n\r\n\r\n## Models\r\n\r\n| Model | Status |\r\n|-|-|\r\n| **Prediction (Forecasting)** |\r\n| RNN | \u2705 Implemented |\r\n| Seq2Seq | \u2705 Implemented |\r\n| [NeuralLaplace](https://github.com/samholt/NeuralLaplace) | \ud83d\udd32 Planned |\r\n| **Imputation** |\r\n| {f,b}fill & Mean | \u2705 Implemented |\r\n| [HyperImpute](https://proceedings.mlr.press/v162/jarrett22a/jarrett22a.pdf) | \ud83d\udd32\r\n| **Individualized Treatment Effects** |\r\n| [CRN](https://openreview.net/forum?id=BJg866NFvB) | \u2705 Implemented |\r\n| [SyncTwin](https://proceedings.neurips.cc/paper/2021/hash/19485224d128528da1602ca47383f078-Abstract.html) | \u2699\ufe0f Experimental |\r\n| [TE-CDE](https://proceedings.mlr.press/v162/seedat22b/seedat22b.pdf) | \ud83d\udd32 Planned |\r\n| **Time-to-event Analysis** |\r\n| [Dynamic DeepHit](https://pubmed.ncbi.nlm.nih.gov/30951460/) | \ud83d\udd32 Planned |\r\n| **Interpretability** |\r\n| [DynaMask](http://proceedings.mlr.press/v139/crabbe21a/crabbe21a.pdfsa) | \ud83d\udd32 Planned |\r\n\r\n\r\n\r\n## Tutorials\r\n\r\n* [\ud83d\udcd4 Basic Usage](tutorials/basic_usage.ipynb)\r\n* [\ud83d\udcd4 Example: CRN](tutorials/crn.ipynb)\r\n* [\ud83d\udcd4 Example: SyncTwin](tutorials/synctwin.ipynb)\r\n\r\n\r\n## Contact\r\n\r\nIf you wish to reach about to us specifically about `clairvoyance2` (bugs, suggestions, problems, ...) please message\r\nEvgeny on [LinkedIn](https://www.linkedin.com/in/e-s-saveliev/) for now, until we set up an official communication channel.\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "clairvoyance2: a Unified Toolkit for Medical Time Series",
"version": "0.0.1",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4267b3721aece9fc35848d139e4666358a52e81fcec11de5364b9eb54ff2e00c",
"md5": "c7227290a08adaa1ad86174cd9e169a0",
"sha256": "b7a7985d5214ee85f453aef7680605a5d6ece6921f69223eb3f4ae45decf8eb3"
},
"downloads": -1,
"filename": "clairvoyance2-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c7227290a08adaa1ad86174cd9e169a0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 99700,
"upload_time": "2023-03-18T21:35:21",
"upload_time_iso_8601": "2023-03-18T21:35:21.864840Z",
"url": "https://files.pythonhosted.org/packages/42/67/b3721aece9fc35848d139e4666358a52e81fcec11de5364b9eb54ff2e00c/clairvoyance2-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-18 21:35:21",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "clairvoyance2"
}
JSON