MLOps pipeline with DVC and CML using Github Actions and IBM Cloud

model-deploy-on-release Python Package and Test

Video Demo

Documentation and Implementation Guide

• Data Versioning: DVC
• Machine Learning Pipeline: DVC Pipeline (preprocess, train, evaluate)
• CI/CD: Unit testing with Pytest, pre-commit and Github Actions
• CML: Continuous Machine Learning and Github Actions
• Deploy on release: Github Actions and IBM Watson
• Monitoring: OpenScale
• Infrastructure-as-a-code: Terraform script

• DVC
• Python3 and pip
• Access to IBM Cloud Object Storage

Setup your credentials on ~/.aws/credentials and ~/.aws/config. DVC works perfectly with IBM Obejct Storage, although it uses S3 protocol, you can also see this in other portions of the repository.

~/.aws/credentials

[default]
aws_access_key_id = {{Key ID}}
aws_secret_access_key = {{Access Key}}

In order to activate pre-commit testing you need pre-commit

Installing pre-commit with pip

pip install pre-commit

Installing pre-commit on your local repository. Keep in mind this creates a Github Hook.

pre-commit install

Now everytime you make a commit, it will run some tests defined on .pre-commit-config.yaml before allowing your commit.

Example

$ git commit -m "Example commit"
black....................................................................Passed
pytest-check.............................................................Passed

Download data from the DVC repository(analog to git pull)

dvc pull

Reproduces the pipeline using DVC

dvc repro

✂️ Preprocessing pipeline

dvc run -n preprocess -d ./src/preprocess_data.py -d data/weatherAUS.csv \
-o ./data/weatherAUS_processed.csv -o ./data/features.csv \
python3 ./src/preprocess_data.py ./data/weatherAUS.csv

📘 Training pipeline

dvc run -n train -d ./src/train.py -d ./data/weatherAUS_processed.csv \
 -d ./src/model.py \
-o ./models/model.joblib \
python3 ./src/train.py ./data/weatherAUS_processed.csv ./src/model.py 200

📊 Evaluate pipeline

dvc run -n evaluate -d ./src/evaluate.py -d ./data/weatherAUS_processed.csv \
-d ./src/model.py -d ./models/model.joblib -o ./results/metrics.json \
-o ./results/precision_recall_curve.png -o ./results/roc_curve.png \
python3 ./src/evaluate.py ./data/weatherAUS_processed.csv ./src/model.py ./models/model.joblib

🔐 IBM Credentials

Fill the credentials_example.yaml file and rename it to credentials.yaml to be able to run the scripts that require IBM keys. ⚠️ Never upload this file to GitHub!

To use Git Actions to deploy your model, you'll need to encrypt it, to do that run the command bellow and choose a strong password.

gpg --symmetric --cipher-algo AES256 credentials.yaml 

Now in the GitHub page for the repository, go to Settings->Secrets and add the keys to the following secrets:

AWS_ACCESS_KEY_ID (Bucket Credential)
AWS_SECRET_ACCESS_KEY (Bucket Credential)
IBM_CREDENTIALS_PASS (password for the encrypted file)