This video focuses on executing a prediction using the Cloud ML command line.
- [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 the prediction dataset.…
The results return in an array.…
- Evaluating the machine learning tools in GCP
- Understanding the predictive analytics process
- Building models
- Training models with jobs
- Building and running predictions
- Best practices for cost control, testing, and performance monitoring
Skill Level Intermediate
Predictive Customer Analyticswith Kumaran Ponnambalam1h 37m Intermediate
1. ML Options in GCP
2. Cloud ML Basics
3. Model Building with Cloud ML
4. Predictions in Cloud ML
5. Cloud ML Best Practices
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.