mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
cc4bf4394e
Review feedback (#1481): the address batcher and the Modelling Run batcher implemented the same greedy packing; the core moves to utilities/grouped_batching.py and both become thin wrappers. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
24 lines
898 B
Python
24 lines
898 B
Python
"""Pack a Modelling Run's resolved properties into SQS-message-sized batches.
|
|
|
|
Batches stay postcode-grouped — properties sharing a postcode ride the same
|
|
message so the workers' prediction cohort cache keeps paying (ADR-0055), the
|
|
same packing the trigger script has been running.
|
|
"""
|
|
|
|
from backend.app.modelling.property_filters import FilteredProperty
|
|
from utilities.grouped_batching import iter_grouped_batches
|
|
|
|
BATCH_SIZE = 50
|
|
|
|
|
|
def pack_postcode_batches(
|
|
properties: list[FilteredProperty], batch_size: int = BATCH_SIZE
|
|
) -> list[list[FilteredProperty]]:
|
|
"""Pack *properties* into batches of ~*batch_size*, never splitting a
|
|
postcode across batches. A single postcode larger than *batch_size*
|
|
becomes its own oversized batch."""
|
|
return list(
|
|
iter_grouped_batches(
|
|
properties, key=lambda p: p.postcode or "", max_batch_size=batch_size
|
|
)
|
|
)
|