Skip to content
Managing machine learning life-cycle with MLflow tutorial
Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
backend - addind default database for mlflow Nov 26, 2019
notebooks Add files via upload Nov 29, 2019

Managing ML-lifecycle with MLflow


  1. Clone this repository using git or download using Github interface

  2. Install miniconda distribution for python 3.7 -> link

  3. Open Anaconda Prompt (Miniconda 3) navigate to the tutorial folder and install requirements:

    • Optional: you can create separate conda environment for this tutorial from environment file:
      conda env create -f conda.yaml
      conda activate mlflow-tutorial
    • Installing requirements from requirements.txt file:
      pip install -r requirements.txt -f
  4. Launch Jupyter Lab from from the tutorial directory:

    jupyter lab
  5. Launch MLflow server:

    mlflow server --backend-store-uri="sqlite:///C:\\path\\to\\project_folder\\backend\\mlflow_data.db" 
    • Parameters:

      • backend-store-uri - URI to which to persist experiment and run data (sqlite database in our case).
      • default-artifact-root - Local or S3 URI to store artifacts, for new experiments (local folder in our case).
    • Hint: you can launch MLflow server also from terminal inside Jupyter Lab interface.

  6. Make sure that you can access mlflow server and jupyter notebook from your browser :

Note: There could be some minor changes in the dependencies and files, thus make sure to double-check prior to the event. Note: Tutorial functionality was tested on Windows 10.

Congrats! You are ready good to go!

You can’t perform that action at this time.