mlops-architecture/.gitea/workflows/dvc-data-update.yaml

44 lines
929 B
YAML

name: DVC Data Validation
on:
push:
paths:
- "**.dvc"
- "dvc.yaml"
- "dvc.lock"
env:
GIT_SSL_NO_VERIFY: "true"
jobs:
validate-data:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.10"
- name: Install dependencies
run: |
pip install dvc pandas
- name: Pull updated data
run: dvc pull
- name: Validate data
run: |
python -c "
import pandas as pd
import sys
# TODO: 실제 데이터 경로와 검증 로직으로 수정
# df = pd.read_csv('data/dataset.csv')
# assert len(df) > 0, 'Dataset is empty'
# assert df.isnull().sum().sum() == 0, 'Dataset has null values'
print('Data validation passed')
"