pyexplainer is a python package that generates explainable Machine Learning predictions from the so-called 'black-box model' such as random forest, moreover, pyexplainer provides interactive visualisation that simplifies the decision-making process for Software Engineering.
Here is a snapshot of how it works pipeline alt text
How to cite pyexplainer
- python = "3.8"
- scikit-learn = "0.24.1"
- numpy = "1.20.1"
- scipy = "1.6.1"
- ipywidgets = "7.6.3"
- ipython = "7.21.0"
- pandas = "1.2.3"
- statsmodels = "0.12.2"
The list of dependencies is shown upder pyproject.toml file, however the installer takes care of installing them for you.
Installing pyexplainer is easily done using pip, simply run the following:
$ pip install pyexplainer
This will also install the necessary dependencies.
For more approaches to install, please click here
If you'd like to clone from source, you can do it in two simple steps as follows:
> git clone https://github.com/awsm-research/pyExplainer.git > cd pyExplainer
To repeat our experiment, you can go to replication-package branch usinig the below command:
> git checkout replication-package
Then follow the instructions in README.md of replication-package branch.
For information on how to use pyexplainer, refer to the official documentation: