Install Certifai reference model package

Prerequisites

• Download the Certifai toolkit
• Python 3.6
• Conda or another virtual environment manager (recommended)

Install Certifai reference model package

1. Create a virtual environment

   conda create -n certifai-reference-models python=3.6

2. Activate the environment

   conda activate certifai-reference-models

3. From the folder where you installed the Certifai Toolkit, install the reference model package

   MAC or Linux users:

   pip install reference_models/packages/*

   Windows PowerShell users:

   Get-ChildItem .\reference_models/packages\*.zip | ForEach-Object -Process { pip install $_ }

4. Verify that the Certifai Reference Model packages have been installed by starting the Server.

   startCertifaiModelServer

• If you are asked to allow an external connection, click 'Deny' as the models only need to be available locally.

• The output is similar to the example below:

  Adding route: /heart_disease_rf/predict using function certifaiReferenceModelServer.healthcare_heart_disease_prediction.randomForest.predict:predict_heart_disease_rf

  Info

  Your reference model server is running locally on port 5111. Each model has its own endpoint. For example, the Random Forest Heart Disease model is at http://127.0.0.1:5111/heart_disease_rf/predict.

NEXT STEPS:

Use the reference models to run example scans.