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

119 lines
5.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import numpy as np
import pytest
from election_data.cells import AgeLeanModel, fit_age_lean, ipf, village_cells
from election_data.elections import PARTY_A, PARTY_B, PARTY_C
from election_data.lean import LEAN_KEYS, LeanParams, Observation, base_turnout, lean_shares
pytestmark = pytest.mark.unit
AGES = ("20-29", "30-39", "40-49", "50-64", "65+")
def obs(a: int, b: int, c: int, other: int = 0, weight: float = 1.0, contested=None) -> Observation:
valid = a + b + c + other
return Observation(
weight=weight,
valid=valid,
ballots=valid,
electors=int(valid / 0.7),
votes={PARTY_A: a, PARTY_B: b, PARTY_C: c, "其他": other},
contested=frozenset(contested or {PARTY_A, PARTY_B, PARTY_C}),
)
class TestLean:
def test_shares_sum_to_one(self) -> None:
shares = lean_shares([obs(400, 350, 200, 50), obs(450, 400, 100, 50)])
assert shares is not None
assert set(shares) == set(LEAN_KEYS)
assert sum(shares.values()) == pytest.approx(1.0)
def test_core_never_exceeds_mean(self) -> None:
shares = lean_shares([obs(500, 300, 200)])
assert shares is not None
assert shares["a_core"] <= 0.5 + 1e-9
assert shares["a_core"] + shares["a_lean"] < 0.5
def test_volatility_lowers_core(self) -> None:
steady = lean_shares([obs(500, 400, 100), obs(500, 400, 100)])
swingy = lean_shares([obs(700, 200, 100), obs(300, 600, 100)])
assert steady is not None and swingy is not None
assert swingy["a_core"] < steady["a_core"]
def test_uncontested_party_is_ignored(self) -> None:
# 第三勢力只在第二次選舉參選:平均只看那一次(0.2),而不是兩次平均(0.1)。
# 甲、乙平均各 0.45,三者合計 1.1 > 1,所以等比例縮放成 0.2 / 1.1。
shares = lean_shares(
[obs(500, 500, 0, contested={PARTY_A, PARTY_B}), obs(400, 400, 200)],
LeanParams(third_to_middle=0.0),
)
assert shares is not None
assert shares["c_lean"] == pytest.approx(0.2 / 1.1, abs=1e-6)
def test_no_valid_votes(self) -> None:
assert lean_shares([Observation(1.0, 0, 0, 0, {}, frozenset())]) is None
def test_base_turnout_weighted(self) -> None:
o1 = Observation(3.0, 70, 70, 100, {}, frozenset())
o2 = Observation(1.0, 50, 50, 100, {}, frozenset())
assert base_turnout([o1, o2]) == pytest.approx(0.65)
class TestIpf:
def test_matches_marginals(self) -> None:
seed = np.ones((2, 3))
rows = np.array([30.0, 70.0])
cols = np.array([20.0, 50.0, 30.0])
fitted = ipf(seed, rows, cols)
assert fitted.sum(axis=1) == pytest.approx(rows)
assert fitted.sum(axis=0) == pytest.approx(cols)
def test_rejects_inconsistent_targets(self) -> None:
with pytest.raises(ValueError):
ipf(np.ones((2, 2)), np.array([1.0, 1.0]), np.array([1.0, 2.0]))
class TestEcologicalRegression:
def test_recovers_known_association(self) -> None:
rng = np.random.default_rng(7)
leans = LEAN_KEYS
truth = rng.dirichlet(np.ones(len(leans)) * 3, size=len(AGES))
ages, lean_rows = [], []
for _ in range(400):
counts = rng.integers(50, 500, size=len(AGES)).astype(float)
share = counts / counts.sum()
lean = share @ truth
ages.append(dict(zip(AGES, counts, strict=True)))
lean_rows.append(dict(zip(leans, lean, strict=True)))
model = fit_age_lean(ages, lean_rows, AGES, leans)
assert np.abs(model.matrix - truth).max() < 0.02
assert model.matrix.sum(axis=1) == pytest.approx(np.ones(len(AGES)))
def test_ridge_shrinks_toward_overall_mean(self) -> None:
rng = np.random.default_rng(3)
leans = LEAN_KEYS
ages, lean_rows = [], []
for _ in range(200):
counts = rng.integers(50, 500, size=len(AGES)).astype(float)
lean = rng.dirichlet(np.ones(len(leans)) * 5)
ages.append(dict(zip(AGES, counts, strict=True)))
lean_rows.append(dict(zip(leans, lean, strict=True)))
loose = fit_age_lean(ages, lean_rows, AGES, leans, ridge=0.0)
tight = fit_age_lean(ages, lean_rows, AGES, leans, ridge=1e6)
spread = lambda m: (m.matrix.max(axis=0) - m.matrix.min(axis=0)).max() # noqa: E731
assert spread(tight) < 0.01
assert spread(tight) < spread(loose)
def test_village_cells_respect_marginals(self) -> None:
model = AgeLeanModel(AGES, LEAN_KEYS, np.full((5, 6), 1 / 6))
ages = dict(zip(AGES, [100, 200, 150, 250, 300], strict=True))
lean = dict(zip(LEAN_KEYS, [0.2, 0.1, 0.25, 0.1, 0.25, 0.1], strict=True))
cells = np.array(village_cells(model, ages, lean)).reshape(5, 6)
assert cells.sum(axis=1) == pytest.approx(list(ages.values()), abs=0.05)
assert cells.sum(axis=0) == pytest.approx([x * 1000 for x in lean.values()], abs=0.05)
def test_empty_village(self) -> None:
model = AgeLeanModel(AGES, LEAN_KEYS, np.full((5, 6), 1 / 6))
assert village_cells(model, dict.fromkeys(AGES, 0), dict.fromkeys(LEAN_KEYS, 1 / 6)) == [0.0] * 30