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

idk

Browse source
This commit is contained in:
Andras Schmelczer 2026-06-02 13:46:18 +01:00
parent a04ac2d857
commit d43da9708c
47 changed files with 4120 additions and 573 deletions
Download patch file Download diff file Expand all files Collapse all files

13
pipeline/transform/crime_spatial.py
View file

@ -259,11 +259,14 @@ def _write_avg_yr(
"""
months = np.array([months_in_year[year] for year in years], dtype=np.float64)
per_year = counts.astype(np.float64) * 12.0 / months[None, None, :]
# Average over the years each type is actually observed anywhere -- the same
# per-type x-span the by-year chart plots (server-rs/.../crime_by_year.rs).
type_year_present = counts.sum(axis=0) > 0 # (n_types, n_years)
years_per_type = np.clip(type_year_present.sum(axis=1), 1, None).astype(np.float64)
avg = per_year.sum(axis=2) / years_per_type[None, :] # (n_postcodes, n_types)
# Average over the years *this postcode* actually has incidents of *this
# type* -- the same per-(postcode, type) x-span the by-year chart plots
# (server-rs/.../crime_by_year.rs), so the headline equals the mean of the
# by-year bars. Dividing by a global years-present count (years a type
# appeared anywhere in England) would deflate postcodes whose incidents
# cluster in only a few years of the ~13-year window.
years_present = np.clip((counts > 0).sum(axis=2), 1, None).astype(np.float64)
avg = per_year.sum(axis=2) / years_present # (n_postcodes, n_types)
avg = np.round(avg * norm[:, None], 1).astype(np.float32)
data: dict[str, np.ndarray] = {"postcode": postcodes}