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

lgtm

Browse source
This commit is contained in:
Andras Schmelczer 2026-06-25 22:29:52 +01:00
parent 2efa4d9f47
commit 5e73287eaf
99 changed files with 6392 additions and 1462 deletions
Download patch file Download diff file Expand all files Collapse all files

396
pipeline/transform/test_crime_spatial.py
View file

@ -1,13 +1,10 @@
import json
import numpy as np
import polars as pl
import pytest
import shapely
from pyproj import Transformer
from pipeline.transform.crime_spatial import transform_crime_spatial
from pipeline.transform.postcode_boundaries.loader import load_postcode_polygons
_TO_WGS84 = Transformer.from_crs("EPSG:27700", "EPSG:4326", always_xy=True)
@ -16,6 +13,10 @@ _CSV_HEADER = (
"LSOA code,LSOA name,Crime type,Last outcome category,Context"
)
# Average-annual-count crime column name for a window (the filterable feature).
def _raw(t: str, window: str = "7y") -> str:
return f"{t} (/yr, {window})"
def _bng_to_wgs84(x: float, y: float) -> tuple[float, float]:
lon, lat = _TO_WGS84.transform(x, y)
@ -39,12 +40,12 @@ def _write_boundaries(units_dir, features_by_district: dict[str, list[dict]]) ->
(units_dir / f"{district}.geojson").write_text(json.dumps(collection))
def _crime_row(month: str, x, y, crime_type: str) -> str:
def _crime_row(month: str, x, y, crime_type: str, location="On or near X", outcome="U") -> str:
if x is None or y is None:
lon, lat = "", ""
else:
lon, lat = _bng_to_wgs84(x, y)
return f",{month},F,F,{lon},{lat},On or near X,E01000001,L,{crime_type},U,"
return f",{month},F,F,{lon},{lat},{location},E01000001,L,{crime_type},{outcome},"
def _write_month(
@ -59,10 +60,22 @@ def _write_month(
def _run(tmp_path, crime, units, **kwargs):
output = tmp_path / "crime_by_postcode.parquet"
"""Run the transform and return (crime, by_year, records) DataFrames.
The crime table carries the average-annual-count columns ("{type} (/yr, …)"),
i.e. the raw, absolute number of recorded incidents per year.
"""
crime_out = tmp_path / "crime_by_postcode.parquet"
by_year = tmp_path / "crime_by_postcode_by_year.parquet"
transform_crime_spatial(crime, units, output, by_year, buffer_m=50.0, **kwargs)
return pl.read_parquet(output), pl.read_parquet(by_year)
records = tmp_path / "crime_records.parquet"
transform_crime_spatial(
crime, units, crime_out, by_year, records, buffer_m=50.0, **kwargs
)
return (
pl.read_parquet(crime_out),
pl.read_parquet(by_year),
pl.read_parquet(records),
)
def test_buffer_overlap_counts_for_each_postcode(tmp_path):
@ -95,17 +108,74 @@ def test_buffer_overlap_counts_for_each_postcode(tmp_path):
],
)
avg_df, _ = _run(tmp_path, crime, units)
rows = {r["postcode"]: r for r in avg_df.to_dicts()}
# Single covered month -> pooled rate x12.
assert rows["AB1 1AA"]["Burglary (avg/yr)"] == 12.0
assert rows["AB1 1AB"]["Burglary (avg/yr)"] == 12.0
assert rows["AB1 1AA"]["Robbery (avg/yr)"] == 0.0
raw_df, _, _ = _run(tmp_path, crime, units)
rows = {r["postcode"]: r for r in raw_df.to_dicts()}
# Single covered month -> pooled raw rate x12.
assert rows["AB1 1AA"][_raw("Burglary")] == 12.0
assert rows["AB1 1AB"][_raw("Burglary")] == 12.0
assert rows["AB1 1AA"][_raw("Robbery")] == 0.0
# Only the 49m robbery counts for C; the 51m one and the blank row do not.
assert rows["AB1 1AC"]["Robbery (avg/yr)"] == 12.0
assert rows["AB1 1AC"]["Burglary (avg/yr)"] == 0.0
assert rows["AB1 1AC"][_raw("Robbery")] == 12.0
assert rows["AB1 1AC"][_raw("Burglary")] == 0.0
# Anti-social behaviour had no coordinate -> nobody gets it.
assert all(r["Anti-social behaviour (avg/yr)"] == 0.0 for r in rows.values())
assert all(r[_raw("Anti-social behaviour")] == 0.0 for r in rows.values())
def test_counts_are_not_area_normalised(tmp_path):
# Three postcodes of very different footprint, each with exactly one incident
# in its buffer. The raw count must be 12/yr for ALL of them: area
# normalisation has been removed, so footprint no longer changes the number.
units = tmp_path / "units"
_write_boundaries(
units,
{
"AB1": [
_square_feature("AB1 1AA", 1000, 1000, 1010, 1010), # 10x10
_square_feature("AB1 1AB", 3000, 3000, 3010, 3020), # 10x20
_square_feature("AB1 1AC", 5000, 5000, 5040, 5040), # 40x40
]
},
)
crime = tmp_path / "crime"
_write_month(
crime,
"2024-01",
[
_crime_row("2024-01", 1005, 1005, "Burglary"),
_crime_row("2024-01", 3005, 3010, "Burglary"),
_crime_row("2024-01", 5020, 5020, "Burglary"),
],
)
raw_df, _, _ = _run(tmp_path, crime, units, min_bar_months=1)
rows = {r["postcode"]: r for r in raw_df.to_dicts()}
for pc in ("AB1 1AA", "AB1 1AB", "AB1 1AC"):
assert rows[pc][_raw("Burglary")] == pytest.approx(12.0, abs=0.05)
def test_windows_pool_only_recent_years(tmp_path):
# 2-year window vs 7-year window. An incident in the latest year sits in both
# windows; one 6 years back sits only in the 7-year window.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
)
crime = tmp_path / "crime"
# 12 covered months in 2019 (1 burglary), 12 in 2025 (1 burglary). Latest =
# 2025: 7y window = 2019..2025 (both), 2y window = 2024..2025 (only 2025).
for month in range(1, 13):
ym19 = f"2019-{month:02d}"
ym25 = f"2025-{month:02d}"
_write_month(crime, ym19, [_crime_row(ym19, 1005, 1005, "Burglary")] if month == 1 else [])
_write_month(crime, ym25, [_crime_row(ym25, 1005, 1005, "Burglary")] if month == 1 else [])
raw_df, _, _ = _run(tmp_path, crime, units)
row = raw_df.row(0, named=True)
# 7y: 2 incidents over 24 covered months -> 1/yr.
assert row[_raw("Burglary", "7y")] == pytest.approx(1.0, abs=0.05)
# 2y: 1 incident over 12 covered months -> 1/yr (the 2019 one is excluded).
assert row[_raw("Burglary", "2y")] == pytest.approx(1.0, abs=0.05)
def test_by_year_annualises_and_rolls_up(tmp_path):
@ -115,7 +185,6 @@ def test_by_year_annualises_and_rolls_up(tmp_path):
)
crime = tmp_path / "crime"
# Point at the centre of AB1 1AA, well inside its buffer.
_write_month(
crime,
"2023-01",
@ -134,7 +203,7 @@ def test_by_year_annualises_and_rolls_up(tmp_path):
],
)
_, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
_, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
assert by_year_df.height == 1
cols = set(by_year_df.columns)
assert {"Burglary (by year)", "Serious crime (by year)", "Minor crime (by year)"} <= cols
@ -150,77 +219,14 @@ def test_by_year_annualises_and_rolls_up(tmp_path):
# 2023 serious = Burglary(12) + Robbery(12) = 24; 2024 = Burglary(12).
assert serious[2023] == 24.0
assert serious[2024] == 12.0
# Coverage calendar: both years published, with their month counts.
coverage = {c["year"]: c["months"] for c in row["covered_years"]}
assert coverage == {2023: 1, 2024: 2}
def test_area_normalisation_divides_out_buffered_catchment(tmp_path):
# Three postcodes of increasing footprint, each with exactly one incident in
# its buffer. Normalisation rescales by median_catchment / buffered_area, so
# the smallest scores highest and the median-sized one is unchanged -- i.e.
# the metric is a density. Dividing by the *buffered* catchment (not the raw
# polygon) means the fixed buffer-ring floor keeps the spread gentle, so the
# tiniest postcode is not blown up out of proportion.
units = tmp_path / "units"
_write_boundaries(
units,
{
"AB1": [
_square_feature("AB1 1AA", 1000, 1000, 1010, 1010), # 10x10
_square_feature("AB1 1AB", 3000, 3000, 3010, 3020), # 10x20 (median)
_square_feature("AB1 1AC", 5000, 5000, 5020, 5020), # 20x20
]
},
)
crime = tmp_path / "crime"
_write_month(
crime,
"2024-01",
[
_crime_row("2024-01", 1005, 1005, "Burglary"),
_crime_row("2024-01", 3005, 3010, "Burglary"),
_crime_row("2024-01", 5010, 5010, "Burglary"),
],
)
avg_df, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
# Re-derive the expected values from the same buffered catchment areas: each
# postcode is 12/yr before normalisation, then x (median_buf / buffered_area).
postcodes, polygons = load_postcode_polygons(units)
buf_area = {
pc: float(shapely.area(shapely.buffer(poly, 50.0, quad_segs=8)))
for pc, poly in zip(postcodes, polygons)
}
median_buf = float(np.median(list(buf_area.values())))
expected = {pc: 12.0 * median_buf / buf_area[pc] for pc in buf_area}
rows = {r["postcode"]: r for r in avg_df.to_dicts()}
for pc, exp in expected.items():
assert rows[pc]["Burglary (avg/yr)"] == pytest.approx(exp, abs=0.1)
# Median catchment unchanged; ordering is by inverse buffered area, but the
# buffer-ring floor keeps the spread far below the ~4x raw-area ratio.
assert rows["AB1 1AB"]["Burglary (avg/yr)"] == pytest.approx(12.0, abs=0.05)
small = rows["AB1 1AA"]["Burglary (avg/yr)"]
big = rows["AB1 1AC"]["Burglary (avg/yr)"]
assert small > 12.0 > big
assert small / big < 1.5
# by-year series carries the same normalisation.
small_row = by_year_df.filter(pl.col("postcode") == "AB1 1AA").row(0, named=True)
assert small_row["Burglary (by year)"] == [
{"year": 2024, "count": pytest.approx(expected["AB1 1AA"], abs=0.1)}
]
def test_avg_yr_is_pooled_rate_over_covered_months(tmp_path):
# Uneven month coverage across years: 2023 has 1 month (2 incidents),
# 2024 has 2 months (2 incidents). The headline is the POOLED annualised
# rate over all covered months: 4 incidents / 3 months * 12 = 16/yr -- not
# the old mean-of-bars (24+12)/2 = 18, which over-weighted thin years.
def test_raw_is_pooled_rate_over_covered_months(tmp_path):
# Uneven month coverage: 2023 has 1 month (2 incidents), 2024 has 2 months
# (2 incidents). The raw figure is the POOLED annualised rate over all covered
# months: 4 incidents / 3 months * 12 = 16/yr.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
@ -238,10 +244,9 @@ def test_avg_yr_is_pooled_rate_over_covered_months(tmp_path):
_write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Burglary")])
_write_month(crime, "2024-02", [_crime_row("2024-02", 1005, 1005, "Burglary")])
avg_df, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
avg = avg_df.row(0, named=True)
assert avg["Burglary (avg/yr)"] == pytest.approx(16.0, abs=0.05)
assert raw_df.row(0, named=True)[_raw("Burglary")] == pytest.approx(16.0, abs=0.05)
# Bars remain per-year annualised: 2023 -> 24/yr (x12), 2024 -> 12/yr (x6).
row = by_year_df.row(0, named=True)
@ -251,8 +256,7 @@ def test_avg_yr_is_pooled_rate_over_covered_months(tmp_path):
def test_sporadic_type_is_not_inflated_by_years_present(tmp_path):
# A single robbery in a 24-covered-month window must read as ~0.5/yr (the
# long-run pooled rate), NOT 12/yr (the old years-with-incidents mean that
# inflated sporadic categories by up to ~15x).
# long-run pooled rate), NOT 12/yr.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
@ -266,14 +270,10 @@ def test_sporadic_type_is_not_inflated_by_years_present(tmp_path):
rows = [_crime_row(f"{year}-{month:02d}", 1005, 1005, "Robbery")]
_write_month(crime, f"{year}-{month:02d}", rows)
avg_df, by_year_df = _run(tmp_path, crime, units)
raw_df, by_year_df, _ = _run(tmp_path, crime, units)
avg = avg_df.row(0, named=True)
# 1 incident over 24 covered months -> 0.5/yr.
assert avg["Robbery (avg/yr)"] == pytest.approx(0.5, abs=0.05)
# The by-year bar still shows the 2023 incident annualised over 12 covered
# months (1/yr); 2024 is covered with zero robberies -> no bar, but the
# year IS in the coverage list so consumers may render it as a true zero.
assert raw_df.row(0, named=True)[_raw("Robbery")] == pytest.approx(0.5, abs=0.05)
row = by_year_df.row(0, named=True)
bars = {p["year"]: p["count"] for p in row["Robbery (by year)"]}
assert bars == {2023: pytest.approx(1.0, abs=0.05)}
@ -283,9 +283,8 @@ def test_sporadic_type_is_not_inflated_by_years_present(tmp_path):
def test_force_gap_years_are_excluded_not_zeroed(tmp_path):
# Two postcodes policed by different forces. force-a publishes 2023+2024;
# force-b publishes only 2023 (a 2024 gap, like Greater Manchester). The
# b-postcode's headline must pool over force-b's 12 covered months only,
# and its by-year series must NOT contain a 2024 bar or coverage entry.
# force-b publishes only 2023 (a 2024 gap). The b-postcode's raw figure must
# pool over force-b's 12 covered months only.
units = tmp_path / "units"
_write_boundaries(
units,
@ -299,25 +298,21 @@ def test_force_gap_years_are_excluded_not_zeroed(tmp_path):
for month in range(1, 13):
ym23 = f"2023-{month:02d}"
ym24 = f"2024-{month:02d}"
# force-a covers AB1 in both years; one burglary per month in 2024.
_write_month(crime, ym23, [], force="force-a")
_write_month(
crime, ym24, [_crime_row(ym24, 1005, 1005, "Burglary")], force="force-a"
)
# force-b covers CD1 in 2023 only: one burglary per month.
_write_month(
crime, ym23, [_crime_row(ym23, 9005, 9005, "Burglary")], force="force-b"
)
avg_df, by_year_df = _run(tmp_path, crime, units)
rows = {r["postcode"]: r for r in avg_df.to_dicts()}
raw_df, by_year_df, _ = _run(tmp_path, crime, units)
rows = {r["postcode"]: r for r in raw_df.to_dicts()}
# force-a postcode: 12 burglaries over 24 covered months -> 6/yr.
assert rows["AB1 1AA"]["Burglary (avg/yr)"] == pytest.approx(6.0, abs=0.05)
# force-b postcode: 12 burglaries over 12 covered months -> 12/yr. Under
# the old global calendar this would have been diluted to 6/yr by the
# uncovered 2024.
assert rows["CD1 1AA"]["Burglary (avg/yr)"] == pytest.approx(12.0, abs=0.05)
assert rows["AB1 1AA"][_raw("Burglary")] == pytest.approx(6.0, abs=0.05)
# force-b postcode: 12 burglaries over 12 covered months -> 12/yr.
assert rows["CD1 1AA"][_raw("Burglary")] == pytest.approx(12.0, abs=0.05)
by_rows = {r["postcode"]: r for r in by_year_df.to_dicts()}
b_coverage = {c["year"]: c["months"] for c in by_rows["CD1 1AA"]["covered_years"]}
@ -328,59 +323,10 @@ def test_force_gap_years_are_excluded_not_zeroed(tmp_path):
assert a_coverage == {2023: 12, 2024: 12}
def test_residue_incidents_in_uncovered_years_are_excluded(tmp_path):
# force-b stops publishing after 2023, but a force-a file contains a 2024
# incident that falls inside the b-postcode's buffer (cross-border residue,
# the Greater Manchester pattern). That incident must not produce a 2024
# bar for the b-postcode, nor leak into its pooled headline.
units = tmp_path / "units"
_write_boundaries(
units,
{
"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)],
"CD1": [_square_feature("CD1 1AA", 9000, 9000, 9010, 9010)],
},
)
crime = tmp_path / "crime"
for month in range(1, 13):
ym23 = f"2023-{month:02d}"
ym24 = f"2024-{month:02d}"
_write_month(crime, ym23, [], force="force-a")
# b's own 2023 incidents establish force-b as its home force.
_write_month(
crime,
ym23,
[_crime_row(ym23, 9005, 9005, "Burglary")] if month <= 6 else [],
force="force-b",
)
# 2024: only force-a publishes; one of its incidents lands in CD1 1AA.
_write_month(
crime,
ym24,
[_crime_row(ym24, 9005, 9005, "Burglary")] if month == 1 else [],
force="force-a",
)
avg_df, by_year_df = _run(tmp_path, crime, units)
b_row = avg_df.filter(pl.col("postcode") == "CD1 1AA").row(0, named=True)
# Pooled over force-b's 12 covered months (2023): 6 incidents -> 6/yr.
# The residue 2024 incident is excluded (force-b published 0 months in 2024).
assert b_row["Burglary (avg/yr)"] == pytest.approx(6.0, abs=0.05)
b_by = by_year_df.filter(pl.col("postcode") == "CD1 1AA").row(0, named=True)
bars = {p["year"]: p["count"] for p in b_by["Burglary (by year)"]}
assert set(bars) == {2023}
coverage = {c["year"]: c["months"] for c in b_by["covered_years"]}
assert coverage == {2023: 12}
def test_partial_years_below_min_bar_months_get_no_bar(tmp_path):
# 2023 fully covered; 2024 has only 2 published months. With the default
# 6-month minimum, 2024 must produce neither a bar (annualising x6 charts
# noise) nor a coverage entry -- but its incidents and months still count
# toward the pooled headline.
# 6-month minimum, 2024 must produce no bar -- but its incidents and months
# still count toward the pooled raw figure.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
@ -394,12 +340,10 @@ def test_partial_years_below_min_bar_months_get_no_bar(tmp_path):
ym = f"2024-{month:02d}"
_write_month(crime, ym, [_crime_row(ym, 1005, 1005, "Burglary")])
avg_df, by_year_df = _run(tmp_path, crime, units)
raw_df, by_year_df, _ = _run(tmp_path, crime, units)
# Pooled: 14 incidents over 14 covered months -> 12/yr.
assert avg_df.row(0, named=True)["Burglary (avg/yr)"] == pytest.approx(
12.0, abs=0.05
)
assert raw_df.row(0, named=True)[_raw("Burglary")] == pytest.approx(12.0, abs=0.05)
row = by_year_df.row(0, named=True)
bars = {p["year"]: p["count"] for p in row["Burglary (by year)"]}
assert set(bars) == {2023}
@ -425,52 +369,119 @@ def test_by_year_output_is_dense_with_coverage(tmp_path):
crime = tmp_path / "crime"
_write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Burglary")])
avg_df, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
assert by_year_df.height == 2
quiet = by_year_df.filter(pl.col("postcode") == "AB1 1AB").row(0, named=True)
assert quiet["Burglary (by year)"] is None
assert [c["year"] for c in quiet["covered_years"]] == [2024]
# And the headline for the quiet postcode is a genuine 0, not null.
quiet_avg = avg_df.filter(pl.col("postcode") == "AB1 1AB").row(0, named=True)
assert quiet_avg["Burglary (avg/yr)"] == 0.0
# The raw figure for the covered, crime-free postcode is a genuine 0, not null.
quiet_raw = raw_df.filter(pl.col("postcode") == "AB1 1AB").row(0, named=True)
assert quiet_raw[_raw("Burglary")] == 0.0
def test_serious_rollup_avg_yr_equals_sum_of_components(tmp_path):
# Burglary only in 2014, Robbery only in 2024 (one incident each, 2 covered
# months total). Components pool over the same covered window (each
# 1 x 12 / 2 = 6/yr) and the rollup equals their sum.
def test_serious_rollup_equals_sum_of_components(tmp_path):
# Burglary only in 2023, Robbery only in 2024 (one incident each, 2 covered
# months total, both inside the 7-year window). Components pool over the same
# covered window (each 1 x 12 / 2 = 6/yr) and the rollup equals their sum.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
)
crime = tmp_path / "crime"
_write_month(crime, "2014-01", [_crime_row("2014-01", 1005, 1005, "Burglary")])
_write_month(crime, "2023-01", [_crime_row("2023-01", 1005, 1005, "Burglary")])
_write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Robbery")])
avg_df, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
avg = avg_df.row(0, named=True)
assert avg["Burglary (avg/yr)"] == pytest.approx(6.0, abs=0.05)
assert avg["Robbery (avg/yr)"] == pytest.approx(6.0, abs=0.05)
# Rollup == sum of its component (avg/yr) columns.
assert avg["Serious crime (avg/yr)"] == pytest.approx(12.0, abs=0.05)
assert avg["Serious crime (avg/yr)"] == pytest.approx(
avg["Burglary (avg/yr)"] + avg["Robbery (avg/yr)"], abs=0.05
row = raw_df.row(0, named=True)
assert row[_raw("Burglary")] == pytest.approx(6.0, abs=0.05)
assert row[_raw("Robbery")] == pytest.approx(6.0, abs=0.05)
assert row[_raw("Serious crime")] == pytest.approx(12.0, abs=0.05)
assert row[_raw("Serious crime")] == pytest.approx(
row[_raw("Burglary")] + row[_raw("Robbery")], abs=0.05
)
# The by-year rollup series remains the per-year sum of the component bars.
serious_bars = {
p["year"]: p["count"]
for p in by_year_df.row(0, named=True)["Serious crime (by year)"]
}
assert serious_bars == {
2014: pytest.approx(12.0, abs=0.05),
2023: pytest.approx(12.0, abs=0.05),
2024: pytest.approx(12.0, abs=0.05),
}
def test_records_capture_each_counted_incident(tmp_path):
# Each (incident, postcode) match within the records window becomes a record
# row, carrying month/type/location/outcome/coords. A boundary incident
# counted for two postcodes appears once per postcode.
units = tmp_path / "units"
_write_boundaries(
units,
{
"AB1": [
_square_feature("AB1 1AA", 1000, 1000, 1010, 1010),
_square_feature("AB1 1AB", 1080, 1000, 1090, 1010),
]
},
)
crime = tmp_path / "crime"
_write_month(
crime,
"2024-03",
[
# In the buffer overlap -> recorded for both postcodes.
_crime_row("2024-03", 1045, 1005, "Burglary", location="On or near High St", outcome="Under investigation"),
# Only in AB1 1AA's buffer; null outcome (police.uk leaves ASB blank).
_crime_row("2024-03", 1005, 1005, "Anti-social behaviour", location="On or near Mill Ln", outcome=""),
],
)
_, _, records_df = _run(tmp_path, crime, units, min_bar_months=1)
assert set(records_df.columns) == {
"postcode", "month_index", "crime_type", "location", "outcome", "lat", "lon"
}
# Sorted by postcode.
assert records_df["postcode"].is_sorted()
# Burglary appears for BOTH postcodes (boundary multiplicity); ASB only for AA.
by_pc = records_df.group_by("postcode").agg(pl.col("crime_type").sort())
counts = {r["postcode"]: r["crime_type"] for r in by_pc.to_dicts()}
assert counts["AB1 1AA"] == ["Anti-social behaviour", "Burglary"]
assert counts["AB1 1AB"] == ["Burglary"]
# month_index = year*12 + (month-1) for 2024-03.
assert set(records_df["month_index"].to_list()) == {2024 * 12 + 2}
# Null outcome round-trips as null, not the string "".
asb = records_df.filter(pl.col("crime_type") == "Anti-social behaviour").row(0, named=True)
assert asb["outcome"] is None
assert asb["location"] == "On or near Mill Ln"
def test_records_window_aligns_to_the_headline_calendar_window(tmp_path):
# Records must cover exactly the longest (7y) headline window, which is
# calendar-year based. With a mid-year latest month (2025-06) the 7y window
# is calendar years 2019..2025, so an incident in 2018-09 -- which the
# headline excludes -- must also be excluded from the records, even though a
# naive rolling 84-month span (ending 2025-06) would wrongly include it. The
# first month of the earliest window year (2019-01) is kept.
units = tmp_path / "units"
_write_boundaries(
units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
)
crime = tmp_path / "crime"
_write_month(crime, "2018-09", [_crime_row("2018-09", 1005, 1005, "Burglary")])
_write_month(crime, "2019-01", [_crime_row("2019-01", 1005, 1005, "Burglary")])
_write_month(crime, "2025-06", [_crime_row("2025-06", 1005, 1005, "Burglary")])
_, _, records_df = _run(tmp_path, crime, units, min_bar_months=1)
# 2018-09 (year*12+8) is in the rolling 84-month span but NOT the 7y calendar
# window, so it is excluded; 2019-01 and 2025-06 are kept.
assert set(records_df["month_index"].to_list()) == {2019 * 12 + 0, 2025 * 12 + 5}
def test_unknown_crime_type_is_dropped_with_warning(tmp_path, capsys):
units = tmp_path / "units"
_write_boundaries(
@ -487,11 +498,10 @@ def test_unknown_crime_type_is_dropped_with_warning(tmp_path, capsys):
],
)
avg_df, _ = _run(tmp_path, crime, units)
columns = avg_df.columns
# The unknown type is dropped (no column for it) but a warning is emitted.
assert "Cyber fraud (avg/yr)" not in columns
assert "Burglary (avg/yr)" in columns
raw_df, _, _ = _run(tmp_path, crime, units)
columns = raw_df.columns
assert _raw("Cyber fraud") not in columns
assert _raw("Burglary") in columns
err = capsys.readouterr().err
assert "Cyber fraud" in err
assert "WARNING" in err
@ -515,11 +525,11 @@ def test_legacy_crime_types_are_mapped(tmp_path):
],
)
avg_df, by_year_df = _run(tmp_path, crime, units, min_bar_months=1)
row = avg_df.to_dicts()[0]
# Single postcode -> area-norm factor 1.0; single covered month -> x12.
assert row["Violence and sexual offences (avg/yr)"] == 12.0
assert row["Public order (avg/yr)"] == 12.0
raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
row = raw_df.to_dicts()[0]
# Single covered month (relative to a 2013-latest window) -> x12.
assert row[_raw("Violence and sexual offences")] == 12.0
assert row[_raw("Public order")] == 12.0
by_year_row = by_year_df.row(0, named=True)
assert by_year_row["Violence and sexual offences (by year)"] == [