Metadata-Version: 2.1
Name: pycyclops
Version: 0.1.1
Summary: Framework for healthcare ML implementation
Home-page: https://github.com/VectorInstitute/cyclops
License: Apache-2.0
Author: Vector AI Engineering
Author-email: cyclops@vectorinstitute.ai
Requires-Python: ==3.9.7
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Requires-Dist: ConfigArgParse (>=1.5.3,<2.0.0)
Requires-Dist: Flask-Caching (>=1.10.1,<2.0.0)
Requires-Dist: SQLAlchemy (>=1.4.32,<2.0.0)
Requires-Dist: alibi (>=0.6.5,<0.7.0)
Requires-Dist: alibi-detect (>=0.9.1,<0.10.0)
Requires-Dist: black (>=22.1.0,<23.0.0)
Requires-Dist: colorama (>=0.4.4,<0.5.0)
Requires-Dist: dash (>=2.4.1,<3.0.0)
Requires-Dist: dash-bootstrap-components (>=1.1.0,<2.0.0)
Requires-Dist: dash-cool-components (==0.1.8)
Requires-Dist: dash-iconify (>=0.1.2,<0.2.0)
Requires-Dist: dash-mantine-components (>=0.10.2,<0.11.0)
Requires-Dist: dask[dataframe] (>=2022.9.1,<2023.0.0)
Requires-Dist: hydra-core (>=1.2.0,<2.0.0)
Requires-Dist: llvmlite (==0.38.0)
Requires-Dist: matplotlib (>=3.5.1,<4.0.0)
Requires-Dist: nb-black (>=1.0.7,<2.0.0)
Requires-Dist: numpydoc (>=1.2,<2.0)
Requires-Dist: pandas (>=1.4.1,<2.0.0)
Requires-Dist: plotly (==5.7.0)
Requires-Dist: pre-commit (>=2.17.0,<3.0.0)
Requires-Dist: prefect (==2.0b6)
Requires-Dist: psycopg2-binary (>=2.9.3,<3.0.0)
Requires-Dist: pyarrow (>=7.0.0,<8.0.0)
Requires-Dist: pylint (>=2.12.2,<3.0.0)
Requires-Dist: pyparsing (==3.0.8)
Requires-Dist: pyproject-flake8 (==5.0.4)
Requires-Dist: pytest (>=7.1.1,<8.0.0)
Requires-Dist: pytest-cov (>=3.0.0,<4.0.0)
Requires-Dist: python-dotenv (>=0.19.2,<0.20.0)
Requires-Dist: seaborn (>=0.11.2,<0.12.0)
Requires-Dist: shap (>=0.40.0,<0.41.0)
Requires-Dist: tables (>=3.7.0,<4.0.0)
Requires-Dist: torch (>=1.11.0,<2.0.0)
Requires-Dist: torchxrayvision (>=0.0.37,<0.0.38)
Requires-Dist: xgboost (>=1.5.2,<2.0.0)
Project-URL: Documentation, https://vectorinstitute.github.io/cyclops/
Project-URL: Repository, https://github.com/VectorInstitute/cyclops
Description-Content-Type: text/markdown

![cyclops Logo](https://github.com/VectorInstitute/cyclops/blob/main/docs/source/theme/static/cyclops_logo-dark.png?raw=true)

--------------------------------------------------------------------------------

[![Code checks](https://github.com/VectorInstitute/cyclops/actions/workflows/code_checks.yml/badge.svg)](https://github.com/VectorInstitute/cyclops/actions/workflows/code_checks.yml)
[![Documentation and Coverage Report](https://github.com/VectorInstitute/cyclops/actions/workflows/docs_deploy.yml/badge.svg)](https://github.com/VectorInstitute/cyclops/actions/workflows/docs_deploy.yml)

``cyclops`` is a framework for facilitating research and deployment of ML models
in the health (or clinical) setting. It provides three high-level features:


* Data Querying and Processing
* Rigorous Evaluation
* Drift Detection toolkit

``cyclops`` also provides a library of use-cases on clinical datasets. The implemented
use-cases include:

* Mortality decompensation prediction


## 🐣 Getting Started

### Setup Python virtual environment and install dependencies

The development environment has been tested on ``python = 3.9.7``.

The python virtual environment can be setup using
[poetry](https://python-poetry.org/docs/#installation). Hence, make sure it is
installed and then run:

```bash
poetry install
source $(poetry env info --path)/bin/activate
```

> ⚠️ ``poetry`` is the preferred installation method since it also installs
the ``cyclops`` package, and is tested. There is also an ``environment.yaml``
and ``requirements.txt`` to install dependencies using
[Miniconda](https://docs.conda.io/en/latest/miniconda.html) or
[pip](https://pypi.org/project/pip/), however is not tested frequently.


## 📚 [Documentation](https://vectorinstitute.github.io/cyclops/)

## 🎓 Notebooks

To use jupyter notebooks, the python virtual environment can be installed and
used inside an Ipython kernel. After activating the virtual environment, run:

```bash
python3 -m ipykernel install --user --name <name_of_kernel>
```

Now, you can navigate to the notebook's ``Kernel`` tab and set it as
``<name_of_kernel>``.

Tutorial notebooks in ``tutorials`` can be useful to view the
functionality of the framework.

