Repository files navigation

• Option 1: use the supplied fileenvironment.yml to create a new environment with conda
• Option 2: use the supplied filerequirements.txt to create a new environment with pip

• Create a directory for the project and initialize git.
  • As you work on the code, continually commit changes. Trained models you want to use in production must be committed to GitHub.
• Connect your local git repo to GitHub.
• Setup GitHub Actions on your repo. You can use one of the pre-made GitHub Actions if at a minimum it runs pytest and flake8 on push and requires both to pass without error.
  • Make sure you set up the GitHub Action to have the same version of Python as you used in development.

• Download census.csv and commit it to dvc.
• This data is messy, try to open it in pandas and see what you get.
• To clean it, use your favorite text editor to remove all spaces.

• Using the starter code, write a machine learning model that trains on the clean data and saves the model. Complete any function that has been started.
• Write unit tests for at least 3 functions in the model code.
• Write a function that outputs the performance of the model on slices of the data.
  • Suggestion: for simplicity, the function can just output the performance on slices of just the categorical features.
• Write a model card using the provided template.

• Create a RESTful API using FastAPI this must implement:
  • GET on the root giving a welcome message.
  • POST that does model inference.