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

good

Browse source
This commit is contained in:
Andras Schmelczer 2026-05-12 22:30:36 +01:00
parent 81a16f543c
commit 63713c3a2b
15 changed files with 492 additions and 159 deletions
Download patch file Download diff file Expand all files Collapse all files

32
pipeline/transform/test_merge.py
View file

@ -1,8 +1,6 @@
import polars as pl
from pipeline.transform.merge import (
_AREA_COLUMNS,
_STATIC_POI_DISTANCE_RENAMES,
_is_dynamic_poi_metric_column,
_less_deprived_percentile_expr,
)
@ -11,9 +9,11 @@ from pipeline.transform.merge import (
def test_less_deprived_percentile_expr_preserves_direction_and_nulls() -> None:
df = pl.DataFrame({"Income Score (rate)": [1.0, 2.0, 3.0, None]})
result = df.lazy().with_columns(
_less_deprived_percentile_expr("Income Score (rate)")
).collect()
result = (
df.lazy()
.with_columns(_less_deprived_percentile_expr("Income Score (rate)"))
.collect()
)
assert result["Income Score (rate)"].to_list() == [100.0, 50.0, 0.0, None]
@ -21,28 +21,18 @@ def test_less_deprived_percentile_expr_preserves_direction_and_nulls() -> None:
def test_less_deprived_percentile_expr_uses_exact_scale_endpoints() -> None:
df = pl.DataFrame({"Income Score (rate)": [1.0, 1.0, 2.0, 3.0, 3.0]})
result = df.lazy().with_columns(
_less_deprived_percentile_expr("Income Score (rate)")
).collect()
result = (
df.lazy()
.with_columns(_less_deprived_percentile_expr("Income Score (rate)"))
.collect()
)
assert result["Income Score (rate)"].to_list() == [100.0, 100.0, 50.0, 0.0, 0.0]
def test_dynamic_poi_metric_columns_are_area_level() -> None:
assert _is_dynamic_poi_metric_column("Distance to nearest amenity (Cafe) (km)")
assert _is_dynamic_poi_metric_column("Distance to nearest amenity (Park) (km)")
assert _is_dynamic_poi_metric_column("Number of amenities (Cafe) within 2km")
assert _is_dynamic_poi_metric_column("Number of amenities (Cafe) within 5km")
assert not _is_dynamic_poi_metric_column("Number of restaurants within 2km")
def test_static_poi_distance_columns_are_renamed_to_configured_area_features() -> None:
expected = {
"parks_nearest_km": "Distance to nearest park (km)",
"grocery_store_nearest_km": "Distance to nearest grocery store (km)",
"cafe_nearest_km": "Distance to nearest cafe (km)",
"pub_nearest_km": "Distance to nearest pub (km)",
"restaurant_nearest_km": "Distance to nearest restaurant (km)",
}
assert _STATIC_POI_DISTANCE_RENAMES == expected
assert set(expected.values()).issubset(_AREA_COLUMNS)