Batch inference on the Build Your Own AI Platform track. Batch scoring runs a version over a table and writes predictions back. It is how many decisions are made overnight. It must be restartable.
This lesson assumes you already worked through An inference API.
The idea in practice
Write predictions with the version id and the time. Skip already scored keys if the job restarts.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'Batch inference',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
A batch job that cannot resume and double-writes on retry. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Define the output columns, including version id.
Self-check
- Say Batch inference in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.