EvalML is available for Python 3.6+. It can be installed with pip or conda.
To install evalml with pip, run the following command:
pip install evalml
For older Python versions (3.6.0 in particular), you must install pip >= 18.0 and setuptools > 40.0.0 in order to install evalml.
pip >= 18.0
setuptools > 40.0.0
EvalML includes several optional dependencies. The xgboost and catboost packages support pipelines built around those modeling libraries. The plotly and ipywidgets packages support plotting functionality in automl searches. These dependencies are recommended, and are included with EvalML by default but are not required in order to install and use EvalML.
EvalML’s core dependencies are listed in core-requirements.txt in the source code, and optional requirements are isted in requirements.txt.
To install EvalML with only the core required dependencies, download the EvalML source from pypi to access the requirements files. Then run the following:
pip install evalml --no-dependencies
pip install -r core-requirements.txt
To install evalml with conda run the following command:
conda install -c conda-forge evalml
To install evalml with only core dependencies run the following command:
conda install -c conda-forge evalml-core
Additionally, if you are using pip to install EvalML, it is recommended you first install the following packages using conda: * numba (needed for shap and prediction explanations) * graphviz if you’re using EvalML’s plotting utilities
The XGBoost library may not be pip-installable in some Windows environments. If you are encountering installation issues, please try installing XGBoost from Github before installing EvalML or install evalml with conda.
In order to run on Mac, LightGBM requires the OpenMP library to be installed, which can be done with HomeBrew by running
brew install libomp