/prjctr-course-prodml-test

Primary LanguageJupyter Notebook

Prjctr course "Machine Learning in Production" test task

Stage 1

Open the notebook and run it to the last cell to get a trained model at ./model.joblib.

Kaggle CLI should be installed.

Or:

  1. Install train dependencies (use virtual environment):
pip install -r requirements.train.txt

  1. Download CommonLib Readability Prize dataset and unzip data to ./commonlitreadabilityprize/.

  2. Run train script to get a trained model at ./model.joblib:

python train.py

Stage 2

  1. Install API dependencies (use virtual environment):
pip install -r requirements.api.txt
  1. Run server:
python -m uvicorn api:app
  1. Test predict using ./example.json:
curl -H "Content-Type: application/json" --data "@example.json" -X POST http://localhost:8000/predict
  1. Output should be:
[-0.8]

Stage 3

Try:

curl -H "Content-Type: application/json" --data "@example.json" -X POST https://guarded-fortress-68184.herokuapp.com/predict

or open https://guarded-fortress-68184.herokuapp.com/