Build a Regional Output Allocation and Boundary-Change Planner

A regional economic planning team.

Allocate a supplied regional output scenario through transparent geographic crosswalks. Keep modeled allocations separate from published local GDP estimates.

Key: source_region + target_region + crosswalk_version.

Fields: source_output, allocation_weight, boundary_date, weight_basis, uncertainty_assumption.

Each source-region allocation sums to one. Preserve unmapped regions as exceptions.

Reconcile regional boundaries and crosswalk versions.

Apply supplied allocation weights to a labeled scenario.

Compare alternatives under different weight assumptions.

Export mapped allocations with source totals and uncertainty notes.

A map linked to allocation tables, unmatched boundaries, and an assumption comparison panel.

A conserved-total geographic allocation pipeline.

A planning map that labels modeled and officially observed values differently.

Runnable local application, setup commands, and a dependency lockfile.

Versioned input data, data dictionary, acquisition instructions, and rights notes.

Calculation traces, source references, assumption records, and exported review artifacts.

A deterministic baseline and tests for normal, incomplete, contradictory, and failure-recovery cases.

A recorded complete workflow with a reproducible manifest and explicit limitations.

Allocated amounts sum to the source total within tolerance.

Boundary changes cannot silently change the covered population.

Employment weights are not presented as observed local output.

Unmapped regions remain visible rather than being dropped.

Change the crosswalk while keeping the source total fixed. Local allocations change, but the conserved total does not.

The attached starter files are prototype inputs. Expected starter answers are visible. They are not independent holdouts.

Full target: Use public regional output and geography metadata. Supply fictional allocation weights where official fine-grained output estimates do not exist.

Complete target contracts and expert review remain pending. Public observations are not historical release vintages.

GeoPandas, DuckDB, Plotly

Use an available model appropriate to the task. Record provider, model identifier, version or retrieval date, settings, cost, and latency. Use deterministic code for calculations. Models may extract, retrieve, or explain evidence. They must not invent missing records, override approval rules, or claim professional authority.

These are modeled planning allocations, not official small-area GDP statistics.

No fabricated records, source citations, professional endorsements, or expert-adjudication claims.

No future-data leakage into dated decisions, model fitting, or historical valuation inputs.

No unauthorized payments, account restrictions, regulatory filings, or production changes.

No automated appraisal certification, tax-compliance determination, or unsupported fraud accusation.

No concealed uncertainty or silently invented inputs required for a numerical conclusion.

Correct domain calculations and justified methods with documented assumptions. Weight: 30.

Source lineage, temporal integrity, rights checks, and explicit synthetic-data labels. Weight: 25.

A working application with review, export, error handling, and reproducible state. Weight: 20.

Adversarial cases, uncertainty, missing-data behavior, and sensitivity analysis. Weight: 15.

Evidence-linked conclusions that distinguish facts, assumptions, and unresolved judgments. Weight: 10. Score each dimension from zero to two. Weighted score = sum(weight * score / 2). A failed safety gate blocks acceptance.