← All workshopsRead Keeping a Prediction Consistent Across Requests

Deploying and Maintaining Models

Predict a batch in order

BOTIE

Multiply each row by the weight vector, then add the same bias to each result.
Ready to test
0 passed · 0 failed · 2 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

Multiply each row by the weight vector, then add the same bias to each result.

Botie receives a validated batch and one fixed parameter state. Each returned prediction must remain attached to its request.

Multiply feature rows by the saved weight vector and add the same bias to every row's result.

Examples and results
Feature rows
12
34
Saved weights
  1. 02
  2. 1-1
Bias
1
Required result
  1. 01
  2. 13
Feature rows
23
Saved weights
  1. 00.5
  2. 12
Bias
-1
Required result
  1. 06
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

Inputs must already satisfy the saved feature and preprocessing contract. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

A batch includes the zero-feature baseline

This check uses the pieces from “Serve a batch without losing request order”.

BOTIE

Botie receives three rows with three features each. Apply the same fitted weights and intercept to every row, and return predictions in request order. The middle row has all features at zero.
Feature rows
120
000
2-13
Saved weights
  1. 02
  2. 1-1
  3. 20.5
Bias
4

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

What must accompany row order if responses can finish asynchronously?

Keep stable request identity and model version with predictions when a real service reorders work.

Inputs must already satisfy the saved feature and preprocessing contract.

Work through the Python challenges →
Continue the courseKnowing Which Model Produced an Answer →
← Checking What Arrives at the Model