Skip to content

Data Cleaning

Data Cleaning #21627

Workflow file for this run

name: Data Cleaning
on:
push:
paths:
- 'cleansing/full.py'
schedule:
- cron: '0 7/12 * * *'
workflow_dispatch:
inputs:
whotriggered:
description: 'Manual Trigger'
default: 'Why'
required: false
jobs:
build:
runs-on: ubuntu-latest
steps:
- name: Checkout current repo
uses: actions/checkout@v2
with:
path: covid19-eu-data-cleansing
- name: Checkout raw data repo
uses: actions/checkout@v2
with:
token: ${{ secrets.ACCESS_TOKEN }}
repository: covid19-eu-zh/covid19-eu-data
path: covid19-eu-data
- name: List contents in current folder
run: |
pwd
ls
- name: Copy raw dataset to current repo
run: |
echo "create dataset folder in current repo"
mkdir -p covid19-eu-data-cleansing/dataset
echo "Copy raw dataset to current repo"
cp -r covid19-eu-data/dataset/* covid19-eu-data-cleansing/dataset/
- uses: actions/setup-python@v1
with:
python-version: '3.x'
- name: Install Python Requirements
working-directory: ./covid19-eu-data-cleansing/cleansing
run: pip install -r requirements.txt
- name: Clean up dataset
working-directory: ./covid19-eu-data-cleansing
run: |
DB_FOLDER=db
echo "Creating folder $DB_FOLDER"
mkdir -p $DB_FOLDER
echo "Cleaning up data and save as json in $DB_FOLDER"
python cleansing/full.py
echo "All files in $DB_FOLDER"
ls -alht $DB_FOLDER
echo "git add commit"
git config --local user.email "[email protected]"
git config --local user.name "GitHub Action"
git status
git add .
git commit -m "Update Datasets" || echo "Nothing to update"
git status
- name: Push changes
uses: ad-m/github-push-action@master
with:
directory: covid19-eu-data-cleansing
branch: master
github_token: ${{ secrets.GITHUB_TOKEN }}