Skip to content

Data Prep

Data Prep #4

Workflow file for this run

# Train model, evaluate and test champion model, build containerized model, and deploy model
name: Data Prep
on:
workflow_dispatch:
# schedule:
# - cron: '00 4 * * *' # Runs at 4:00 AM UTC every day
jobs:
data_prep:
runs-on: ubuntu-latest
steps:
# Checks-out repository under $GITHUB_WORKSPACE, so the job can access it
# Use cache action to cache the virtual environment (https://stackoverflow.com/a/62639424)
- uses: actions/checkout@v4
- name: Set up Python 3.10.*
uses: actions/setup-python@v4
with:
python-version: 3.10.*
- name: Get pip cache dir
id: pip-cache
run: echo "PIP_CACHE_DIR=$(pip cache dir)" >> $GITHUB_ENV
# Use cache action to cache the virtual environment
- name: Cache pip dependencies
uses: actions/cache@v3
with:
path: ${{ env.PIP_CACHE_DIR }}
key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
restore-keys: |
${{ runner.os }}-pip-
- name: Install dependencies
run: |
make install
- name: Add project path to sys.path
run: |
echo "PYTHONPATH=${{github.workspace}}" >> $GITHUB_ENV
- name: Prepare data
run: |
make prep_data
- name: Setup Feast
run: |
make setup_feast
- name: Split data
run: |
make split_data