JensandClaude Opus 5
dd87a62e8f
Four ways a selection produced a confident number about a different area than the operator drew: Flood hazard divided the inundated cells by every cell in the drawn rectangle, including cells the VMM raster does not model at all. A selection reaching past the modelled extent therefore reported a diluted risk share, turning missing data into an implied absence of risk. Terrain, bathymetry and thematic raster already divided by valid cells; flood hazard was the outlier. It now reports the three populations separately, states model coverage next to the drawn area, and returns a null fraction rather than a zero when nothing was modelled. geometry_mask selects a cell when its centre falls inside the geometry, so a rectangle smaller than one cell — or one landing between four centres — selected nothing and the analysis returned zeros indistinguishable on screen from "we looked and there is nothing here". On a 100 m population raster a 40 m rectangle over a city block reported no inhabitants. Selection now falls back to the touched cells and says that it did, since the answer then covers more ground than was requested. rasterio.mask applies the same centre rule when cropping, so that call is widened too; the cells that count are still decided by the centre rule wherever it selects anything. The object count treated any feature touching the selection as whole, while intersection_area clipped it — two headline numbers on one panel describing different populations. The count stays whole-feature, which is what "objecten" means to an operator, but now reports how many the edge cuts and is marked an estimate when it does. The area_weighted_sum branch reuses that same count instead of issuing its own near-identical query. Partitioned selection de-duplicated the count on source_feature_id but returned the raw rows, so a building on a municipal boundary was counted once and drawn twice. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
162 lines
5.1 KiB
Python
162 lines
5.1 KiB
Python
"""The object count and the area metric must describe the same selection.
|
|
|
|
``intersection_area`` clips a feature to the drawn rectangle, but the object
|
|
count treated any feature that merely touches the rectangle as wholly inside.
|
|
For a rectangle across a built-up area that overstates the count at every
|
|
edge, and the two headline numbers on the same panel then describe different
|
|
populations: "1.000 gebouwen" next to the clipped area of rather fewer.
|
|
|
|
The count now reports how many features lie entirely inside and how many are
|
|
cut by the selection edge, and is marked as an estimate when any are.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from app.services.vector_feature_service import VectorFeatureService
|
|
|
|
|
|
def test_a_count_without_partial_features_is_exact() -> None:
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=120,
|
|
fully_covered_feature_count=120,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] == 0
|
|
assert disclosure["is_estimate"] is False
|
|
assert disclosure["warning"] is None
|
|
|
|
|
|
def test_features_cut_by_the_selection_edge_are_reported() -> None:
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=120,
|
|
fully_covered_feature_count=98,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] == 22
|
|
assert disclosure["is_estimate"] is True
|
|
assert "22" in disclosure["warning"]
|
|
assert "rand" in disclosure["warning"]
|
|
|
|
|
|
def test_a_selection_of_only_partial_features_is_still_coherent() -> None:
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=3,
|
|
fully_covered_feature_count=0,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] == 3
|
|
assert disclosure["is_estimate"] is True
|
|
|
|
|
|
def test_an_empty_selection_makes_no_claim() -> None:
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=0,
|
|
fully_covered_feature_count=0,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] == 0
|
|
assert disclosure["is_estimate"] is False
|
|
assert disclosure["warning"] is None
|
|
|
|
|
|
def test_a_preclipped_full_area_selection_has_no_edge_effect() -> None:
|
|
"""Selecting the whole work area cuts nothing; the count is exact."""
|
|
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=500,
|
|
fully_covered_feature_count=None,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] is None
|
|
assert disclosure["is_estimate"] is False
|
|
assert disclosure["warning"] is None
|
|
|
|
|
|
def test_an_inconsistent_covered_count_never_produces_a_negative() -> None:
|
|
disclosure = VectorFeatureService.count_disclosure(
|
|
total_feature_count=10,
|
|
fully_covered_feature_count=14,
|
|
)
|
|
|
|
assert disclosure["partially_covered_feature_count"] == 0
|
|
assert disclosure["is_estimate"] is False
|
|
|
|
|
|
class _ScalarQuery:
|
|
def __init__(self, value):
|
|
self.value = value
|
|
|
|
def filter(self, *args): # noqa: ANN002, ARG002
|
|
return self
|
|
|
|
def scalar(self):
|
|
return self.value
|
|
|
|
|
|
class _SequenceSession:
|
|
"""Answers the summary's scalar queries in order: covered count, then metrics."""
|
|
|
|
def __init__(self, values):
|
|
self.values = iter(values)
|
|
|
|
def query(self, *args): # noqa: ANN002, ARG002
|
|
return _ScalarQuery(next(self.values))
|
|
|
|
|
|
def _buildings_dataset():
|
|
from uuid import uuid4
|
|
|
|
from app.models import Dataset
|
|
|
|
return Dataset(
|
|
id=uuid4(),
|
|
project_id=uuid4(),
|
|
name="grb-buildings.geojson",
|
|
dataset_type="vector",
|
|
dataset_role="reference",
|
|
source_name="grb",
|
|
reference_layer_name="buildings",
|
|
source_metadata={"theme": "buildings"},
|
|
)
|
|
|
|
|
|
BBOX = {"min_x": 5.0, "min_y": 51.1, "max_x": 5.2, "max_y": 51.3, "crs": "EPSG:4326"}
|
|
|
|
|
|
def test_summary_reports_the_edge_cut_next_to_the_object_count() -> None:
|
|
summary = VectorFeatureService.summarize_features_by_bbox(
|
|
_SequenceSession([88, 125_000.0]),
|
|
dataset=_buildings_dataset(),
|
|
bbox=BBOX,
|
|
total_feature_count=100,
|
|
)
|
|
|
|
assert summary["feature_count"] == 100
|
|
assert summary["fully_covered_feature_count"] == 88
|
|
assert summary["partially_covered_feature_count"] == 12
|
|
assert "12 van de 100" in summary["selection_edge_warning"]
|
|
|
|
count_metric = next(
|
|
item for item in summary["metrics"] if item["aggregation_method"] == "feature_count"
|
|
)
|
|
assert count_metric["is_estimate"] is True
|
|
assert "doorgesneden" in count_metric["warning"]
|
|
|
|
# The clipped area metric is exact and must not inherit the count's caveat.
|
|
area_metric = next(
|
|
item for item in summary["metrics"] if item["aggregation_method"] == "intersection_area"
|
|
)
|
|
assert area_metric["is_estimate"] is False
|
|
|
|
|
|
def test_summary_stays_exact_when_the_selection_cuts_nothing() -> None:
|
|
summary = VectorFeatureService.summarize_features_by_bbox(
|
|
_SequenceSession([100, 125_000.0]),
|
|
dataset=_buildings_dataset(),
|
|
bbox=BBOX,
|
|
total_feature_count=100,
|
|
)
|
|
|
|
assert summary["partially_covered_feature_count"] == 0
|
|
assert summary["selection_edge_warning"] is None
|