Cedar 2: compare baselines without leaking the future
Advanced forecasting lab · Build expanding-window evaluations and keep model selection separate from final evidence.
Existing companion · depth review pendingOpen collection →Read deeply.
Put your understanding to work.
Explore a topic as a collection of learning resources. Choose a chapter, work through a question, inspect the data or return to an explanation.
Explore the SQL reference collection →201 topic collections. Page 11 of 17. Existing companions are not automatically complete study units.
Cedar 3: audit forecast uncertainty instead of promising certainty
Advanced forecasting lab · Freeze an empirical error band, measure held-out coverage and distinguish an interval from a guarantee.
Existing companion · depth review pendingOpen collection →Cedar 4: defend a forecasting recommendation
Advanced portfolio and interview exercise · Explain backtest evidence, planning scenarios and monitoring limits without overstating a model.
Existing companion · depth review pendingOpen collection →Cobalt 1: define the contract before building the model
Advanced analytics engineering · Choose model grain, validate source changes and reconcile metrics before writing an incremental loader.
Existing companion · depth review pendingOpen collection →Cobalt 2: make incremental changes replay safely
Advanced engineering lab · Handle late arrivals, stale updates, deletion tombstones and rollback without hiding source conflicts.
Existing companion · depth review pendingOpen collection →Cobalt 3: join history at the right point in time
Advanced warehouse modelling · Test interval boundaries, overlaps and missing dimension records before trusting historical attribution.
Existing companion · depth review pendingOpen collection →Cobalt 4: review a model change like an analytics engineer
Advanced portfolio and interview exercise · Turn tests, lineage and reconciliations into a defensible model-change review.
Existing companion · depth review pendingOpen collection →Meridian 1: catch leakage before measuring a model
Advanced evaluation lab · Audit feature timing, split boundaries and an implausibly strong result before trusting a score.
Existing companion · depth review pendingOpen collection →Meridian 2: choose a threshold with a capacity limit
Advanced decision lab · Reconcile precision, recall, error costs and a hard review-capacity constraint.
Existing companion · depth review pendingOpen collection →Meridian 3: evaluate once, then inspect the slices
Advanced model-review lab · Reconcile a held-out confusion table with workflow-level results without overclaiming.
Existing companion · depth review pendingOpen collection →Meridian 4: defend a release decision with evidence
Advanced career exercise · Turn evaluation results into a clear decision memo, monitoring plan and honest portfolio story.
Existing companion · depth review pendingOpen collection →Understand working files, staging and commits
Git & collaboration · Shared foundation workshop · Create an inspectable local change history without publishing anything.
Existing companion · depth review pendingOpen collection →One useful next step
Start learning. Build understanding.
Explore the introductory learning, then create a free account to continue, save learning notes and track supported lessons. Registration and email verification cost nothing.