Metadata-Version: 2.1
Name: fathom-lib
Version: 0.1.8
Summary: Fathom lib
Home-page: https://github.com/fathom-io/fathom-lib
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/fathom-io/fathom-lib/issues
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: cycler (==0.10.0)
Requires-Dist: decorator (==4.4.2)
Requires-Dist: joblib (==0.15.1)
Requires-Dist: kiwisolver (==1.2.0)
Requires-Dist: matplotlib (==3.2.2)
Requires-Dist: networkx (==2.4)
Requires-Dist: numpy (==1.18.5)
Requires-Dist: pandas (==1.0.4)
Requires-Dist: pyparsing (==2.4.7)
Requires-Dist: python-dateutil (==2.8.1)
Requires-Dist: pytz (==2020.1)
Requires-Dist: scikit-learn (==0.23.1)
Requires-Dist: scipy (==1.4.1)
Requires-Dist: six (==1.15.0)
Requires-Dist: threadpoolctl (==2.1.0)
Requires-Dist: dataclasses-json (==0.5.1)
Requires-Dist: rethinkdb (==2.4.7)
Requires-Dist: pytest (==5.4.3)
Requires-Dist: xgboost (==1.1.1)
Requires-Dist: lifelines (==0.25.2)
Requires-Dist: shap (==0.35.0)
Requires-Dist: Pillow (==7.2.0)
Requires-Dist: fire (==0.3.1)
Requires-Dist: pyod (==0.8.0)
Requires-Dist: mlflow
Requires-Dist: simplejson
Requires-Dist: keras-tuner
Requires-Dist: autokeras
Requires-Dist: holoviews (==1.13.5)
Requires-Dist: lightgbm (==3.0.0)
Requires-Dist: channels (==3.0.3)
Requires-Dist: plotly (==4.14.3)
Requires-Dist: jinja2 (==2.11.3)

Fathom Python library
=====================

This is a library that helps in defining model pipelines.

Modules:
- `component_autogeneration` - generates schemas for defining Machine Learning components
- `experimentation` - generates scripts for mlflow to run experiments
- `metrics` - defines non-standard metrics for predictive maintenance models
- `models` - wrappers for predictive maintenance models (XGBoostAFT)
- `transformers` - defines non-standard scikit-learn transformations
- `validation` - defines validation algorithms for predictive maintanence

Development
-----------

### Run tests

```
pytest tests
```

