← All workshopsRead Repair the Night-Shift Model Without Breaking the Day Shift

Evaluating and Improving Models

Decide whether the greenhouse revision can enter a trial

BOTIE

Reuse residuals and absolute values to return one candidate error per observed temperature.
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

Reuse residuals and absolute values to return one candidate error per observed temperature.

The candidate must improve the task without hiding a group regression or missing its runtime requirement.

Inspect the component calculation
Keep the size of each error(
  Residuals: Observed minus predicted(
    Observed values: Observed temperatures
    Predictions: Candidate predictions
  )
)
Examples and results
Observed temperatures
  1. 010
  2. 110
  3. 210
  4. 310
Candidate predictions
  1. 09
  2. 19
  3. 29
  4. 39
Required result
  1. 01
  2. 11
  3. 21
  4. 31
Observed temperatures
  1. 010
  2. 110
Candidate predictions
  1. 010
  2. 110
Required result
  1. 00
  2. 10
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

The workshop checks recorded predictions and one runtime value. The Python task fits models; real deployment evidence also needs uncertainty, workload and monitoring. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.

The new shift breaks every declared requirement

This check uses the pieces from “Carry the repair through all requirements”.

BOTIE

The candidate makes both shift errors larger and takes 11 ms. The policy still requires gain 0.5, group increase at most 0.25, and runtime at most 10 ms. Predict every reason to hold.
Observed temperatures
  1. 010
  2. 110
Baseline predictions
  1. 09
  2. 19
Candidate predictions
  1. 08
  2. 17
Shift per observation
  1. 0day
  2. 1night
Declared trial policy
{
  "minGain": 0.5,
  "maxIncrease": 0.25,
  "maxMs": 10
}
Recorded candidate runtime in ms
11

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.

If the fresh shift changes the next candidate, where will its independent assessment come from?

Retain the failure as a regression test and reserve new evidence for the next release decision.

The workshop checks recorded predictions and one runtime value. The Python task fits models; real deployment evidence also needs uncertainty, workload and monitoring.

Work through the Python challenges →
Continue the coursePlanning for More Than One Possible Outcome →
← Should This Change the Prediction?