| | Learn More About Apache Spark's Machine Learning and Structured Streaming | | | | | | Hi David,
The application of machine learning to geolocation data is being used to identify patterns and trends, for smarter advertising, vehicle location or price optimization, recommendations, anomaly detection, and more. Leveraging geolocation data requires processing events in real time, applying machine learning models to add value, and providing scalable, fast storage. Join us on Tuesday October 30, 2018 for this complimentary tutorial in which we'll walk through how to do real-time analysis of popular Uber locations using Apache APIs by doing the following: - Brief overview of Machine Learning Clustering
- Use Spark ML to perform cluster analysis on public Uber data to train and save a model of popular trip locations.
- Use the saved ML model with Apache Spark Structured Streaming and the Kafka API in a data processing pipeline to enrich Uber events with cluster locations and store the results in MapR-DB, a JSON document store.
- Explore and Query the continuous rapid results using Spark SQL with MapR-DB.
| | | | | |
This email was sent to dasmith1973.blog@blogger.com.
To unsubscribe or update your email subscription, please visit our communication preference center.
Posts
No comments:
Post a Comment