I’ve just finished Elastic‘s X-Pack Machine Learning course. Elastic’s X-pack machine learning is a fabulous technology that automates not merely anomaly detection in near-real-time, but also the construction and continuous updating of its statistical model of what is normal. It just learns the patterns in your business. It does so quickly, and the interface is so easy to use that the training is only a half-day.
The course expects its students to use Elastic’s cloud service, but I ran it on my local docker, where it worked fine after I got my compose file set up correctly. There’s not a lot to it, just making sure that Kibana knows where to find elastic search and that both of their ports are open.
version: '2' services: elasticsearch1: image: docker.elastic.co/elasticsearch/elasticsearch:5.6.0 container_name: elasticsearch environment: - cluster.name=docker-cluster - bootstrap.memory_lock=true - "ES_JAVA_OPTS=-Xms512m -Xmx512m" ulimits: memlock: soft: -1 hard: -1 mem_limit: 1g volumes: - esdata1:/usr/share/elasticsearch/data ports: - 9200:9200 networks: - esnet kibana: image: docker.elastic.co/kibana/kibana:5.6.0 environment: SERVER_NAME: kibana ELASTICSEARCH_URL: http://elasticsearch:9200 ports: - 5601:5601 networks: - esnet volumes: esdata1: driver: local networks: esnet:
I’ve been excited about Elastic stack for a couple years. I recommend this half-day, online course as a great way to familiarize yourself with Elastic stack’s simplicity and power.