This project is the demo of the article BentoML: Create an ML Powered Prediction Service in Minutes.

• src: consists of Python scripts
• config: consists of configuration files
• data: consists of data
• processors: consists of all scikit-learn's transformers used to process the new input

1. Clone this branch:

git clone --branch bentoml_demo https://github.com/khuyentran1401/customer_segmentation.git

2. Create and activate a virtual environment:

python3 -m venv venv
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Pull data

dvc pull

To run all flows, type:

python src/main.py

To serve the trained model, run:

bentoml serve src/bentoml_app.py:service --reload

Now you should be able to interact with the API by going to http://127.0.0.1:5000 and clicking the "Try it out" button:

To send requests to the newly started service in Python, run:

python src/predict.py

Details of predict.py:

import requests

prediction = requests.post(
    "http://127.0.0.1:5000/predict",
    headers={"content-type": "application/json"},
    data='{"Income": 58138, "Recency": 58, "Complain": 0,"age": 64,"total_purchases": 25,"enrollment_years": 10,"family_size": 1}',
).text

print(prediction)

Output:

1

To open a Streamlit app, run:

streamlit run src/streamlit_app.py

then go to http://localhost:8501. You should see a web app like below: