election-game/backend/data/pipeline/tests/test_population_attributes.py

88 lines
3.2 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from pathlib import Path
import openpyxl
import pytest
from election_data.attributes import _coordinates, _town_rows, parse_hakka, parse_income
from election_data.population import parse_indigenous, parse_population
pytestmark = pytest.mark.unit
def population_row(
code: str = "68000010001", ages: dict[int, int] | None = None, total: int | None = None
) -> dict:
ages = ages or {}
row = {"district_code": code, "site_id": "桃園市桃園區", "village": "示例里"}
for a in range(100):
row[f"people_age_{a:03d}_m"] = str(ages.get(a, 0))
row[f"people_age_{a:03d}_f"] = "0"
row["people_age_100up_m"] = str(ages.get(100, 0))
row["people_age_100up_f"] = "0"
row["people_total"] = str(total if total is not None else sum(ages.values()))
return row
class TestPopulation:
def test_bands_and_adults(self) -> None:
[p] = parse_population([population_row(ages={5: 10, 20: 3, 29: 2, 64: 4, 65: 1, 100: 2})])
assert p.band_counts() == {"20-29": 5, "30-39": 0, "40-49": 0, "50-64": 4, "65+": 3}
assert p.adults == 12
assert p.total == 22
def test_mismatched_total_is_logged(self, caplog: pytest.LogCaptureFixture) -> None:
parse_population([population_row(ages={30: 5}, total=9)])
assert "不符" in caplog.text
def test_indigenous(self) -> None:
row = {
"district_code": "68000130001",
"indigenous_plain_total_m": "3",
"indigenous_plain_total_f": "4",
"indigenous_mountain_total_m": "10",
"indigenous_mountain_total_f": "",
}
[i] = parse_indigenous([row])
assert (i.lowland, i.highland) == (7, 10)
def test_parse_income_normalizes_and_skips_totals() -> None:
text = (
'"縣市別","村里","納稅單位(戶)","綜合所得總額","平均數","中位數"\n'
'"台北市松山區","中崙里","1464","2745453","1875","857"\n'
'"臺北市松山區","合計","9","9","9","9"\n'
'"臺北市松山區","壞資料","x","1","1","1"\n'
)
[row] = parse_income(text)
assert (row.site, row.village, row.households, row.median) == ("臺北市松山區", "中崙里", 1464, 857.0)
def test_parse_hakka() -> None:
text = "area_name,AreaCode,Ratio\n68000 ,68000040 ,0.71 \nbad,123,0.5\n"
assert parse_hakka(text) == {"68000040": 0.71}
def test_town_rows_reads_two_space_rows(tmp_path: Path) -> None:
wb = openpyxl.Workbook()
ws = wb.active
ws.append(["表1 常住人口"])
ws.append([" 桃園市", 100])
ws.append(["  桃園區", 10, 5])
ws.append(["  Taoyuan Dist"])
path = tmp_path / "t.xlsx"
wb.save(path)
assert _town_rows(path) == {"桃園區": [10, 5]}
def test_coordinates_filters_bad_points(tmp_path: Path) -> None:
xml = tmp_path / "t.xml"
xml.write_text(
"<ArrayOfOpenData_3>"
"<OpenData_3><負責人>某人</負責人><WGS84X>121.3</WGS84X><WGS84Y>24.9</WGS84Y></OpenData_3>"
"<OpenData_3><WGS84X></WGS84X><WGS84Y></WGS84Y></OpenData_3>"
"<OpenData_3><WGS84X>0</WGS84X><WGS84Y>0</WGS84Y></OpenData_3>"
"</ArrayOfOpenData_3>",
encoding="utf-8",
)
assert list(_coordinates(xml)) == [(121.3, 24.9)]