Real Time Machine Learning with Google Cloud ML
In this lab you will combine a number of the components developed in earlier labs in the Data Science on Google Cloud Platform and Data Science on Google Cloud Platform: Machine Learning quests to create a real-time flight delay prediction service using Google Cloud Platform services.
The base data set that is used for the prediction service in this lab provides historic information about internal flights in the United States and has been retrieved from the US Bureau of Transport Statistics website. This data set can be used to demonstrate a wide range of data science concepts and techniques, and is used in all of the other labs in the Data Science on Google Cloud Platform and Data Science on Google Cloud Platform: Machine Learning quests.
The real time flight delay prediction service will use a Google Cloud Machine Learning model to predict whether real time flights will arrive on time or not based on the data available at the time of their departure. The prediction service will use a streaming Google Cloud Dataflow job to process simulated real-time flight event data that is fed into Google Cloud PubSub. The code for the real time flight event simulation data is written in Python and the real time machine learning prediction code is written in Java.
Configure and execute a real time flight event simulation in Python.
Configure and deploy a streaming Google Cloud Dataflow job to provide real-time flight delay predictions.
Join Qwiklabs to read the rest of this lab...and more!
- Get temporary access to the Google Cloud Console.
- Over 200 labs from beginner to advanced levels.
- Bite-sized so you can learn at your own pace.
Check for ml-engine model called flights
Confirm that FlightsMLService has been compiled
Check that the Python simulate.py script is running
Check that the real-time prediction Dataflow job is running
Check for real time predictions in BigQuery