From the course: Data Science on Google Cloud Platform: Predictive Analytics
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Running a prediction - Google Cloud Tutorial
From the course: Data Science on Google Cloud Platform: Predictive Analytics
Running a prediction
- [Instructor] Now that everything is all set up, we can finally get down to running the predictions. I'm going to show you how to run predictions using the Cloud Shell command line. We can, of course, do this using Rest APIs or the client libraries for ML. The following is a command to run a prediction: g-cloud ml-engine predict, name of the model, name of the version to use and the input data. G-cloud is the command, ML engine is the model, predict is the function being executed. The model parameter is used to provide the name of the model we created in Cloud ML. The version is used to provide the version name we created in Cloud ML. The json-instances parameter is used to pass the name of the file that contains the feature where it will set. Let us run the command now. You will see that the command may sometime take time to execute, depending upon the resource settings of the job. The command uses the model we built and deployed earlier in Cloud Storage, and makes predictions on…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.