The automated validator tool provides a comprehensive and systematic evaluation of ML models, with a focus on fairness, performance, statistical validity, and transparency. The tool consists of a web-based user interface that allows users to upload their data, select their models, and run the validation process, as well as a backend engine that performs the modelling and evaluation process and finally generates the corresponding reports and visualizations.
The tool provides the following functionalities:
- Model Replication
- Automated development of benchmark model
- Automated Feature Selection
- Model Evaluation on Transparency, Generic Performance, Fairness, Statistical Metrics
- Report Generation
- User Interface
- Python
- Dash
- Joblib
- Scikit-learn
- Poetry
- K-Nearest Neighbours
- Decision Tree
- XGBoost
- Logistic Regression
- Support Vector Machine
- Random Forest
- Download the package and put its contents to a directory of your choice.
- Install Python 3.6.2 on your local machine, if it's not already installed. You can download this version from the official Python website.
- Open Command Prompt/Bash
- Install
virtualenvpackage (if not already installed)pip install virtualenv
- Create a new virtual environment
virtualenv myenv
- Activate the virtual environment
source myenv/bin/activate
- Install
Poetryon your local machine by running the following command in your terminal or command prompt:py -m pip install poetry
- Install the required packages from the Poetry file by navigating to the root directory of the package and running the following command
poetry install
- Run the app.py file in the root directory of the package to start the application.
poetry run python app.py
- Home Page
- Result Page
