Initial commit: Complete AWS Data Platform template

- Comprehensive infrastructure as code using AWS CDK
- Real-time streaming with Kinesis, Lambda, and DynamoDB
- Batch processing with EMR, Glue, and Athena
- Data warehousing with Redshift and S3 data lake
- Machine learning platform with SageMaker
- Business intelligence with QuickSight
- Complete CI/CD pipeline with GitHub Actions
- Deployment scripts and environment configuration
- Production-ready architecture for analytics and ML workloads

Author: tysoncung

.env.example

@@ -0,0 +1,79 @@
+# AWS Data Platform Environment Configuration
+# Copy this file to .env.dev, .env.staging, or .env.prod and update values
+
+# AWS Configuration
+AWS_ACCOUNT_ID=123456789012
+AWS_REGION=us-east-1
+ENVIRONMENT=dev
+
+# Data Lake Configuration
+DATA_LAKE_BUCKET_PREFIX=my-company-data-lake
+RAW_BUCKET_NAME=data-platform-raw
+PROCESSED_BUCKET_NAME=data-platform-processed
+CURATED_BUCKET_NAME=data-platform-curated
+
+# Redshift Configuration
+REDSHIFT_CLUSTER_IDENTIFIER=data-platform-cluster
+REDSHIFT_DATABASE_NAME=analytics
+REDSHIFT_MASTER_USER=admin
+REDSHIFT_MASTER_PASSWORD=ChangeMePlease123!
+REDSHIFT_NODE_TYPE=dc2.large
+REDSHIFT_NUMBER_OF_NODES=2
+
+# EMR Configuration
+EMR_CLUSTER_NAME=data-platform-emr
+EMR_MASTER_INSTANCE_TYPE=m5.xlarge
+EMR_WORKER_INSTANCE_TYPE=m5.xlarge
+EMR_WORKER_INSTANCE_COUNT=3
+EMR_RELEASE_LABEL=emr-6.9.0
+
+# Kinesis Configuration
+KINESIS_MAIN_STREAM_SHARDS=2
+KINESIS_CLICKSTREAM_SHARDS=2
+KINESIS_IOT_STREAM_SHARDS=4
+KINESIS_RETENTION_DAYS=7
+
+# DynamoDB Configuration
+DYNAMODB_READ_CAPACITY=5
+DYNAMODB_WRITE_CAPACITY=5
+DYNAMODB_BILLING_MODE=PAY_PER_REQUEST
+
+# SageMaker Configuration
+SAGEMAKER_NOTEBOOK_INSTANCE_TYPE=ml.t3.medium
+SAGEMAKER_TRAINING_INSTANCE_TYPE=ml.m5.xlarge
+SAGEMAKER_ENDPOINT_INSTANCE_TYPE=ml.t2.medium
+
+# Monitoring Configuration
+NOTIFICATION_EMAIL=data-team@company.com
+SLACK_WEBHOOK_URL=https://hooks.slack.com/services/YOUR/WEBHOOK/URL
+PAGERDUTY_INTEGRATION_KEY=your-pagerduty-key
+
+# Security Configuration
+ENABLE_ENCRYPTION=true
+ENABLE_VPC_FLOW_LOGS=true
+ENABLE_CLOUDTRAIL=true
+KMS_KEY_ALIAS=alias/data-platform
+
+# Network Configuration
+VPC_CIDR=10.0.0.0/16
+PUBLIC_SUBNET_CIDRS=10.0.1.0/24,10.0.2.0/24
+PRIVATE_SUBNET_CIDRS=10.0.10.0/24,10.0.11.0/24
+DATABASE_SUBNET_CIDRS=10.0.20.0/24,10.0.21.0/24
+
+# Cost Management
+ENABLE_AUTO_SHUTDOWN=false
+AUTO_SHUTDOWN_TIME=19:00
+AUTO_STARTUP_TIME=07:00
+BUDGET_ALERT_THRESHOLD=1000
+
+# Feature Flags
+ENABLE_ML_PIPELINE=true
+ENABLE_REAL_TIME_ANALYTICS=true
+ENABLE_DATA_QUALITY_CHECKS=true
+ENABLE_COST_OPTIMIZATION=true
+
+# Tags
+PROJECT_NAME=DataPlatform
+COST_CENTER=DataEngineering
+OWNER=data-team@company.com
+COMPLIANCE=GDPR