PROJECT 26 / Measured machine learning

Fit a regression and inspect its residuals

Python + statistics · 4h estimated · six activities

Open editable workspace →Complete practice pack ↓Handbook ↓

Before you begin

Python + statistics; inspect the worked fixture before beginning.
A text editor/spreadsheet for the manual route. Hosted Python/Jupyter for code exercises; applicable dependencies are in requirements.txt.
For actual AI calls, a legitimate available cloud service and authorised learner credentials; no particular provider or country is mandatory.

Free original, non-accredited practice. Self-review is not independent assessment. No particular provider, payment platform or country is mandatory; use a legitimate available route or explicitly labelled manual practice.

ACTIVITY 1 / 35 MIN ESTIMATED

Define the regression target

Regression estimates a relationship between inputs and a numeric target. A synthetic straight line is useful for checking code, but perfect fit on a designed fixture is not a real-world benchmark. Compare with a mean baseline and preserve the future test example. Separate input availability from the future value being predicted. Inspect the supplied input before using any tool. Write the decision rules in your own words and calculate one small result independently. The reference output is an answer key for this deliberately bounded fixture, not proof of general capability. Policy for this project: Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity. For learners across regions underserved or excluded by mainstream providers: verify country eligibility, language, account/identity requirements, data terms, cost, quota and connectivity before choosing a cloud service. Use only legitimate available alternatives; never bypass restrictions or invent a country/account. No service access? Complete the labelled manual/fixture route without claiming a live AI run.

Worked example

SOURCE (authored fixture):
{
  "x": [
    1,
    2,
    3,
    4
  ],
  "y": [
    5,
    8,
    11,
    14
  ],
  "test_x": 5,
  "test_y": 17
}
INDEPENDENT FIXTURE TARGET:
{
  "slope": 3,
  "intercept": 2,
  "prediction": 17,
  "absolute_error": 0,
  "mean_baseline_error": 7.5
}

Your practical task

Separate input availability from the future value being predicted.
Open input.json and expected.json from the practice pack; keep an unmodified original.
Record a manual prediction and the relevant rule before consulting the answer key.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Define the regression target — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

All training x values equal: the simple slope is undefined.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

Use the supplied fictional JSON, expected results and paper/text evidence log without a provider account. Manual or constructed completion is labelled; it is not a live cloud integration or trained-model run.

ACTIVITY 2 / 35 MIN ESTIMATED

Compute a mean baseline

Worked example

MANUAL BASELINE / compare every named field
{
  "slope": 3,
  "intercept": 2,
  "prediction": 17,
  "absolute_error": 0,
  "mean_baseline_error": 7.5
}
Keep a separate observed-result column; the answer key is not a model response.

Your practical task

Use only training targets for the naive estimate.
Open input.json and expected.json from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Compute a mean baseline — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Change the test target to 19: prediction stays 17 and absolute error becomes 2.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 3 / 35 MIN ESTIMATED

Fit and inspect a straight line

Worked example

PROJECT CONTRACT:
Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity.
HOSTED REFERENCE: open hosted-lab.ipynb or run reference.py with all fixture files together.
EXPECTED CONSTRUCTED RESULT:
{
  "slope": 3,
  "intercept": 2,
  "prediction": 17,
  "absolute_error": 0,
  "mean_baseline_error": 7.5
}

Your practical task

Calculate slope, intercept and residuals explicitly.
Open hosted-lab.ipynb and the reference code from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform Use test y while fitting: identify leakage even if error falls.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Fit and inspect a straight line — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Use test y while fitting: identify leakage even if error falls.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 4 / 35 MIN ESTIMATED

Test outside the training range

Worked example

CHANGE TESTS — predict before running:
1. All training x values equal: the simple slope is undefined.
2. Change the test target to 19: prediction stays 17 and absolute error becomes 2.
3. Use test y while fitting: identify leakage even if error falls.
Keep the original expected.json unchanged.

Your practical task

Extrapolation needs caution even when this synthetic example succeeds.
Open failure-tests.md from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform All training x values equal: the simple slope is undefined.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Test outside the training range — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

All training x values equal: the simple slope is undefined.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 5 / 35 MIN ESTIMATED

Compare model selection fairly

Regression estimates a relationship between inputs and a numeric target. A synthetic straight line is useful for checking code, but perfect fit on a designed fixture is not a real-world benchmark. Compare with a mean baseline and preserve the future test example. Choose metrics before comparing methods; do not optimise on the final test example. Review what the fixture cannot establish. Explain who owns the decision, where human approval is needed and which access or professional constraints remain. Do not describe a small educational success as production readiness, certification, legal compliance or a guarantee. Policy for this project: Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity. For learners across regions underserved or excluded by mainstream providers: verify country eligibility, language, account/identity requirements, data terms, cost, quota and connectivity before choosing a cloud service. Use only legitimate available alternatives; never bypass restrictions or invent a country/account. No service access? Complete the labelled manual/fixture route without claiming a live AI run.

Worked example

REVIEW BOUNDARY:
Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity.

ACCESS / NOT TESTED: unavailable provider, unsupported language and absent external feedback must remain explicit.

Your practical task

Choose metrics before comparing methods; do not optimise on the final test example.
Open README.md and your evidence log from the practice pack; keep an unmodified original.
Record the human decision owner, limitations and any untested service access.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Compare model selection fairly — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Change the test target to 19: prediction stays 17 and absolute error becomes 2.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 6 / 65 MIN ESTIMATED

Ship a supervised experiment record

Worked example

HANDOFF MANIFEST:
input.json — immutable source
expected.json — fixture answer key
actual.json — result actually observed
evidence-log.csv — baseline plus three changes
README.md — reproduction and access route
limitations.md — unresolved failures, rights, approvals and scope
Never bundle a credential.

Your practical task

Document the fixture design and why zero error is not a general claim.
Open README.md and your evidence log from the practice pack; keep an unmodified original.
Record the human decision owner, limitations and any untested service access.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Ship a supervised experiment record — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Use test y while fitting: identify leakage even if error falls.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

Capstone self-review

Score each criterion 0 (missing), 1 (partial), or 2 (demonstrated). A self-review pass needs at least 8/10 and 2/2 on the critical safety/limits criterion. This is learner practice feedback, not verified assessment.

Defined task and preserved input: Original input and the project policy are retained; the actual question is clear.
Checked baseline: The supplied baseline reconciles field by field; unsupported live-run claims are absent.
Three failure/change tests: All three specified changes have predictions, observed results and explanations.
Repeatable handoff: Another person can follow the README; supporting practice evidence and unresolved limits are included.
Safety, rights and access honesty — critical: Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity. Regional access route is legitimate; credentials and private data are absent; manual/constructed work is clearly labelled.

Review questions

For the supplied fixture, what is the expected slope?

The independent answer key only validates this constructed fixture. Preserve the source, rerun counterexamples, and disclose what was not tested.

How should you handle the project rule: Fit training pairs (1,5),(2,8),(3,11),(4,14). Test x=5 against y=17 only after fitting. Do not imply causal or production validity.

State the rule, test it, and record exceptions or unresolved failures.

Rules, source provenance and counterexamples make an output inspectable; an attractive result does not override policy.

If mainstream providers do not serve your region, what is the honest route?

Check legitimate available alternatives, or label the manual/fixture route and its limits.

Access includes country, identity, language, cost and data terms. Do not bypass restrictions or invent a live result.

Practice files

References and editorial limits

Original authored practice material; deterministic fixtures build-tested. Not independently expert-reviewed or learner-validated. Time estimates unvalidated.

Scikit-learn linear models

Browse all build paths → · Curriculum overview