• Using the modules created in here, the project establishes a pipeline to pull messages from the queue (RabbitMQ)
• Runs classification and regression on the stream data
• Trying to build an ensemble of multiple classification algorithms

• sudo rabbitmq-server start
• RabbitMQ dashboard access
• Pre-req here

• Install Elastic Search for Ubuntu - here
• sudo systemctl enable elasticsearch.service to start Elastic Search service

If you want to use RabbitMQ for the pipelines

• sudo rabbitmq-server start
• python main.py --flag=bus --host=localhost

If you want to use Kafka

• Start the Kafka instance
• Make the change - replace all dataframe instances to ConsumerKafka instances
• python main.py --flag=bus --host=localhost

• Image available here

• Docker build this project into an image
• Docker build container for RabbitMQ
• Docker build containers for Elastic Search
• Utilize GitLab CI
• Utilize Travis for CI - Write test cases