compute_batch

Compute a county-wide geofence crash rate across several counties in one request — built for comparing counties side by side without firing a separate compute call (and downloading a full per-cell breakdown) for each.

HumanBaselines.compute_batch(
    counties: list[str],
    selections: GeofenceSelections | dict | None = None,
    *,
    summary_only: bool = True,
    **filters,
) -> BatchComputeResult

The same (bound + per-call) filters are applied to every county in counties. Pass filters as keyword args, a GeofenceSelections model, or a dict — same rules as compute.

The batch is summary-only by default (cells omitted), since the whole point is lightweight multi-county comparison. Set summary_only=False if you need each county's per-cell breakdown.

A county whose compute fails — for example a filter value it doesn't support (denominator_vmt="hpms" outside California) — comes back with error set instead of failing the whole call, so one bad county never sinks the batch.

Example

from humanbaselines import HumanBaselines

hb = HumanBaselines()

batch = hb.compute_batch(
    ["travis", "houston", "sf", "la"],
    outcome="police_reported",
    ego_vehicle=["cars", "light_trucks"],
    road_type=["arterial", "collector_local"],
)

for item in batch.results:
    if item.result:
        print(item.county, round(item.result.rate, 3))
    else:
        print(item.county, "→ error:", item.error)

Returns: BatchComputeResult

Field	Type	Description
results	list[BatchItemResult]	One entry per requested county, in the same order as counties.

Each BatchItemResult has:

Field	Type	Description
county	str	The county this entry is for.
result	ComputeResult | None	The rate result, or None if this county errored. cells is empty unless summary_only=False.
error	str | None	Error message when result is None; otherwise None.

See Methodology for how each rate is derived, and Errors for failure handling (transport-level errors still raise; per-county failures are reported inline via error).