Example: scikit-learn model

Trains a tiny scikit-learn model, saves it to disk, and serves it as a REST API with a single mlup run command - no serving code written.

Requirements

git clone https://github.com/nxexox/pymlup.git
cd pymlup/examples/sklearn

pip install -r requirements.txt
bash run.sh

run.sh trains a DecisionTreeClassifier (train.py), saves it to model.pkl, and starts the API with mlup run -m model.pkl.

curl -X POST http://localhost:8009/predict \
  -H "Content-Type: application/json" \
  -d '{"X": [[1, 1], [3, 3]]}'

{"predict_result": [0, 1]}