change cluster size and machine #11

	name: Deploy and Run PySpark Job on Dataproc

	on:
	push:
	branches:
	- main

	jobs:
	deploy:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout repository
	uses: actions/checkout@v2

	# Authenticate using the correct auth action
	- name: Authenticate with Google Cloud
	uses: google-github-actions/auth@v1
	with:
	credentials_json: ${{ secrets.GCP_SA_KEY }}

	# Set up Google Cloud SDK
	- name: Set up Google Cloud SDK
	uses: google-github-actions/setup-gcloud@v1
	with:
	project_id: "liqour-store-etl"

	- name: Setup Terraform
	uses: hashicorp/setup-terraform@v1
	with:
	terraform_version: 1.5.7

	- name: Terraform init and validate
	run: \|
	terraform init
	terraform validate

	- name: Terraform apply
	run: \|
	terraform apply -auto-approve

	# Step to upload the PySpark job script from GitHub repo to the GCS bucket
	- name: Upload PySpark job to GCS
	run: \|
	gsutil cp main.py gs://liquor-store-bucket/main.py

	# Instantiate the Dataproc workflow template
	- name: Run Dataproc Workflow Template
	run: \|
	gcloud dataproc workflow-templates instantiate liquor-store-etl-workflow \
	--region us-central1

Provide feedback