andras/perfect-postcode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 2 Wiki Activity Actions

..

Browse source
This commit is contained in:
Andras Schmelczer 2026-07-03 18:39:34 +01:00
parent 1ee796b282
commit ab688243d7
36 changed files with 307 additions and 135 deletions
Download patch file Download diff file Expand all files Collapse all files

4
pipeline/transform/crime.py
View file

@ -126,7 +126,7 @@ def transform_crime(
# Sum per-incident weights directly: a 2021 LSOA can receive incidents
# carrying different `_weight`s in the same month (split 2011 parent at
# 1/N alongside an unsplit one at 1), so `_weight.first() * len` would
# apply one row's weight to all of them — and nondeterministically so,
# apply one row's weight to all of them, and nondeterministically so,
# since `first` after a join has no ordering guarantee.
filtered.group_by("LSOA code", "year", "Crime type")
.agg(pl.col("_weight").sum().alias("count"))
@ -194,7 +194,7 @@ def _write_crime_by_year(
)
yearly_per_type = (
# Per-incident weight sum, not `_weight.first() * len` — see the
# Per-incident weight sum, not `_weight.first() * len`. See the
# matching comment in transform_crime.
filtered.group_by("LSOA code", "Crime type", "year")
.agg(pl.col("_weight").sum().alias("count"))