guzhujushi
95f5266563
用户 2026-10-03 拍板方案 A（见决策 41），由 Codex 落地。
拆成三个函数:
- correlation_matrix -> 数值系数矩阵（对角线 1.0）
- correlation_pvalues -> 数值 p 值矩阵（对角线 NaN）
- correlation_table -> 星标字符串表（对角线 1.000 不带星）
三者共用 _check_corr_args 守卫与成对删缺失口径；correlation_table 在最外层调另外两个。
理由: 字符串表做不了后续计算（挑高相关对、喂聚类/PCA、画热力图），反过来随时能格式化；
一旦返回字符串，数值信息不可逆地丢失。
顺带修掉两处:
- 对角线 p 值由 0.0 改成 NaN —— 写 0 会被下游读成"极显著"，而"自己和自己"没有 p 值
- p 值与 r 现在用同一批观测: 先成对 dropna() 再算，并同样尊重 min_periods。
此前 corr 是成对删缺失、pearsonr 不删，两者样本量不同，r 与 p 对不上
- p 值只算上三角再镜像（成对变量的 p 天然对称），省一半重复计算
tests: test_correlation_matrix_diagonal_is_one 摘掉 xfail 转正；新增 8 条
（数值性+对称性、非数值列跳过、p 值对照解析式 t = r*sqrt((n-2)/(1-r^2))、
对角线 NaN、成对删缺失口径、min_periods、对角线无星标、表格与数值输出一致）。
测试 105 passed / 38 skipped / 1 xfail -> 114 passed / 38 skipped / 0 xfail。
验证: pytest 114 passed / 38 skipped；ruff All checks passed；pyright 0 errors。
docs: STATUS.md（L0 9/12 + 决策 41 + 下一步）；CHANGELOG；
personal-pitfalls 追加第 14 条（把"能看的表"和"能算的表"塞进同一个返回值）；
roadmap 记录 correlation_matrix 的两个伴随函数
384 lines
13 KiB
Python
384 lines
13 KiB
Python
"""stats 包测试。
|
||
|
||
原则（见 docs/02-architecture.md §5）：**测已知解析解，不测实现细节**。
|
||
|
||
未实现的函数**逐条** `skip`——**不要**用模块级 `pytestmark`：那会把同文件里
|
||
已经写好的函数一起跳过，绿灯就是假的（决策 26 / 个人易错点 9）。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
import pytest
|
||
|
||
_NOT_IMPLEMENTED = "未实现：见 docs/03-roadmap.md L1"
|
||
|
||
|
||
def _pearson_p_from_r(r: float, n: int) -> float:
|
||
"""Pearson 相关系数的 p 值**解析式**（测解析解，不测实现细节）：
|
||
|
||
``t = r * sqrt((n - 2) / (1 - r^2))``，``p = 2 * P(T > |t|)``，``T ~ t(n - 2)``。
|
||
"""
|
||
from scipy import stats as sps
|
||
|
||
t_stat = r * np.sqrt((n - 2) / (1 - r**2))
|
||
return float(2 * sps.t.sf(abs(t_stat), n - 2))
|
||
|
||
|
||
@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
|
||
def test_bootstrap_ci_matches_normal_theory_on_large_n(rng):
|
||
"""大样本下 bootstrap 百分位区间应逼近正态解析区间（±10% 容差）。"""
|
||
from mcm_toolkit.stats import bootstrap_ci
|
||
|
||
x = rng.normal(10, 2, size=5000)
|
||
r = bootstrap_ci(x, statistic=np.mean, confidence=0.95, n_resamples=5000, random_state=0)
|
||
se = x.std(ddof=1) / np.sqrt(x.size)
|
||
assert abs((r.params["high"] - r.params["low"]) - 2 * 1.96 * se) < 0.1 * 2 * 1.96 * se
|
||
|
||
|
||
@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
|
||
def test_bootstrap_ci_works_for_arbitrary_statistic(rng):
|
||
"""bootstrap 的核心价值：任意统计量都能给区间（这里用中位数）。"""
|
||
from mcm_toolkit.stats import bootstrap_ci
|
||
|
||
x = rng.lognormal(0, 1, size=2000)
|
||
r = bootstrap_ci(x, statistic=np.median, random_state=0)
|
||
assert r.params["low"] < r.params["high"]
|
||
assert r.params["low"] < np.median(x) < r.params["high"]
|
||
|
||
|
||
@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
|
||
def test_bootstrap_ci_is_reproducible(rng):
|
||
from mcm_toolkit.stats import bootstrap_ci
|
||
|
||
x = rng.normal(size=500)
|
||
a = bootstrap_ci(x, statistic=np.mean, random_state=123)
|
||
b = bootstrap_ci(x, statistic=np.mean, random_state=123)
|
||
assert a.params["low"] == b.params["low"]
|
||
|
||
|
||
@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
|
||
def test_confidence_interval_matches_scipy(rng):
|
||
from scipy import stats
|
||
|
||
from mcm_toolkit.stats import confidence_interval
|
||
|
||
x = rng.normal(5, 1, size=50)
|
||
lo, hi = confidence_interval(x, confidence=0.95, method="t")
|
||
ref = stats.t.interval(0.95, len(x) - 1, loc=x.mean(), scale=stats.sem(x))
|
||
assert np.allclose([lo, hi], ref, rtol=1e-6)
|
||
|
||
|
||
def test_correlation_matrix_diagonal_is_one(rng):
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
x = pd.DataFrame(rng.normal(size=(200, 4)), columns=["a", "b", "c", "d"])
|
||
c = correlation_matrix(x)
|
||
|
||
assert np.allclose(np.diag(np.asarray(c)), 1.0)
|
||
|
||
|
||
def test_correlation_matrix_is_numeric_and_symmetric(rng):
|
||
"""方案 A：返回**数值**矩阵（不是带星标的字符串表），能直接参与后续计算。"""
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
x = pd.DataFrame(rng.normal(size=(200, 3)), columns=["a", "b", "c"])
|
||
c = correlation_matrix(x)
|
||
|
||
assert all(np.issubdtype(dtype, np.floating) for dtype in c.dtypes)
|
||
assert np.allclose(np.asarray(c), np.asarray(x.corr(method="pearson", min_periods=1)))
|
||
assert np.allclose(np.asarray(c), np.asarray(c.T))
|
||
|
||
|
||
def test_correlation_matrix_runs_on_multicolumn_frame(rng):
|
||
"""回归：`if numeric_cols == 0` 拿 Index 跟 0 比，多列数值表当场 ValueError 崩掉。"""
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
x = pd.DataFrame(rng.normal(size=(50, 3)), columns=["a", "b", "c"])
|
||
out = correlation_matrix(x)
|
||
|
||
assert out.shape == (3, 3)
|
||
assert list(out.columns) == ["a", "b", "c"]
|
||
assert list(out.index) == ["a", "b", "c"]
|
||
|
||
|
||
def test_correlation_matrix_skips_non_numeric_columns(rng):
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
x = pd.DataFrame({"a": rng.normal(size=30), "b": rng.normal(size=30), "city": ["X"] * 30})
|
||
assert list(correlation_matrix(x).columns) == ["a", "b"]
|
||
|
||
|
||
def test_correlation_matrix_rejects_bad_input():
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
with pytest.raises(TypeError):
|
||
correlation_matrix([[1.0, 2.0]])
|
||
with pytest.raises(ValueError):
|
||
correlation_matrix(pd.DataFrame({"city": ["X", "Y"]}))
|
||
with pytest.raises(ValueError):
|
||
correlation_matrix(pd.DataFrame({"a": [1.0, 2.0]}), method="bogus") # type: ignore[arg-type]
|
||
|
||
|
||
def test_correlation_pvalues_matches_analytic_formula(rng):
|
||
from mcm_toolkit.stats import correlation_matrix, correlation_pvalues
|
||
|
||
x = pd.DataFrame(rng.normal(size=(80, 3)), columns=["a", "b", "c"])
|
||
corr = correlation_matrix(x)
|
||
p = correlation_pvalues(x)
|
||
|
||
for i in ["a", "b", "c"]:
|
||
for j in ["a", "b", "c"]:
|
||
if i == j:
|
||
continue
|
||
assert p.loc[i, j] == pytest.approx(_pearson_p_from_r(corr.loc[i, j], 80))
|
||
|
||
|
||
def test_correlation_pvalues_diagonal_is_nan(rng):
|
||
"""对角线写 0 会被下游读成"极显著"；"自己和自己相关"没有 p 值，必须是 NaN。"""
|
||
from mcm_toolkit.stats import correlation_pvalues
|
||
|
||
p = correlation_pvalues(pd.DataFrame(rng.normal(size=(50, 2)), columns=["a", "b"]))
|
||
|
||
assert np.isnan(p.loc["a", "a"])
|
||
assert np.isnan(p.loc["b", "b"])
|
||
|
||
|
||
def test_correlation_pvalues_uses_the_same_observations_as_r(rng):
|
||
"""含缺失时 p 要和 r 用**同一批**观测：成对删缺失，而不是整行删、也不是干脆不删。"""
|
||
from mcm_toolkit.stats import correlation_pvalues
|
||
|
||
a = rng.normal(size=40)
|
||
b = rng.normal(size=40)
|
||
a[[3, 7, 11]] = np.nan
|
||
x = pd.DataFrame({"a": a, "b": b})
|
||
|
||
pair = x.dropna()
|
||
r = float(np.corrcoef(pair["a"], pair["b"])[0, 1])
|
||
|
||
assert correlation_pvalues(x).loc["a", "b"] == pytest.approx(_pearson_p_from_r(r, len(pair)))
|
||
|
||
|
||
def test_correlation_pvalues_respects_min_periods(rng):
|
||
from mcm_toolkit.stats import correlation_pvalues
|
||
|
||
a = rng.normal(size=10)
|
||
a[:5] = np.nan
|
||
x = pd.DataFrame({"a": a, "b": rng.normal(size=10)})
|
||
|
||
assert np.isnan(correlation_pvalues(x, min_periods=6).loc["a", "b"])
|
||
assert np.isfinite(correlation_pvalues(x, min_periods=5).loc["a", "b"])
|
||
|
||
|
||
def test_correlation_table_diagonal_has_no_stars():
|
||
"""对角线是"自己和自己"，不该有显著性星标；完全负相关则必然是 ***。"""
|
||
from mcm_toolkit.stats import correlation_table
|
||
|
||
x = pd.DataFrame({"a": np.arange(30.0), "b": np.arange(30.0) * -2.0})
|
||
table = correlation_table(x)
|
||
|
||
assert table.loc["a", "a"] == "1.000"
|
||
assert table.loc["a", "b"] == "-1.000***"
|
||
|
||
|
||
def test_correlation_table_matches_the_numeric_outputs(rng):
|
||
from mcm_toolkit.stats import correlation_matrix, correlation_pvalues, correlation_table
|
||
|
||
x = pd.DataFrame(rng.normal(size=(60, 3)), columns=["a", "b", "c"])
|
||
corr = correlation_matrix(x)
|
||
p = correlation_pvalues(x)
|
||
table = correlation_table(x)
|
||
|
||
assert list(table.columns) == list(corr.columns)
|
||
assert table.loc["a", "a"] == "1.000"
|
||
assert np.isnan(p.loc["a", "a"])
|
||
|
||
pv = p.loc["a", "b"]
|
||
stars = "***" if pv < 0.001 else "**" if pv < 0.01 else "*" if pv < 0.05 else ""
|
||
value = corr.loc["a", "b"]
|
||
assert table.loc["a", "b"] == f"{value:.3f}" + stars
|
||
|
||
|
||
# ------------------------------------------------------ stats: describe
|
||
|
||
|
||
def test_describe_reports_expected_keys(rng):
|
||
from mcm_toolkit.stats import describe
|
||
|
||
table = describe(rng.normal(size=(100, 3)))
|
||
for key in ["mean", "std", "min", "max", "median"]:
|
||
assert key in table.index
|
||
|
||
|
||
def test_describe_rows_are_metrics_and_columns_are_variables():
|
||
"""方向约定：行 = 指标，列 = 变量。多转置一次就反了。"""
|
||
from mcm_toolkit.stats import describe
|
||
|
||
df = pd.DataFrame({"a": [1.0, 2.0, 3.0], "b": [10.0, 20.0, 30.0]})
|
||
table = describe(df)
|
||
|
||
assert list(table.columns) == ["a", "b"]
|
||
assert table.loc["mean", "a"] == pytest.approx(2.0)
|
||
assert table.loc["max", "b"] == pytest.approx(30.0)
|
||
assert table.loc["median", "b"] == pytest.approx(20.0)
|
||
|
||
|
||
def test_describe_missing_and_shape_rows_are_not_nan():
|
||
"""曾经的静默 bug：转置后 `.loc[指标名] = <按变量索引的 Series>` 对不上列，
|
||
整行会被填成 NaN —— 不报错，但数据全丢。"""
|
||
from mcm_toolkit.stats import describe
|
||
|
||
df = pd.DataFrame({"a": [1.0, np.nan, 3.0, 4.0], "b": [1.0, 2.0, 3.0, 4.0]})
|
||
table = describe(df)
|
||
|
||
assert table.loc["missing", "a"] == pytest.approx(1.0)
|
||
assert table.loc["missing", "b"] == pytest.approx(0.0)
|
||
assert table.loc["missing_ratio", "a"] == pytest.approx(0.25)
|
||
assert table.loc["missing_ratio", "b"] == pytest.approx(0.0)
|
||
assert table.loc["skewness", "b"] == pytest.approx(0.0, abs=1e-12)
|
||
extra = table.loc[["missing", "missing_ratio", "skewness", "kurtosis"]]
|
||
assert not bool(extra.isna().all(axis=None))
|
||
|
||
|
||
def test_describe_skips_non_numeric_columns():
|
||
from mcm_toolkit.stats import describe
|
||
|
||
df = pd.DataFrame({"a": [1.0, 2.0], "city": ["X", "Y"]})
|
||
table = describe(df)
|
||
|
||
assert list(table.columns) == ["a"]
|
||
|
||
|
||
def test_describe_accepts_ndarray_list_and_series(rng):
|
||
"""兄弟函数都收 ndarray / list，describe 没理由只收 DataFrame。"""
|
||
from mcm_toolkit.stats import describe
|
||
|
||
assert "mean" in describe(rng.normal(size=(50, 2))).index
|
||
assert "mean" in describe([[1.0, 2.0], [3.0, 4.0]]).index
|
||
assert "mean" in describe(pd.Series([1.0, 2.0, 3.0])).index
|
||
|
||
|
||
def test_describe_weighted_rows_match_manual_formula():
|
||
from mcm_toolkit.stats import describe
|
||
|
||
df = pd.DataFrame({"a": [1.0, 2.0, 3.0]})
|
||
w = np.array([1.0, 1.0, 2.0])
|
||
table = describe(df, weights=w)
|
||
|
||
expect_mean = np.average(df["a"], weights=w)
|
||
expect_std = np.sqrt(np.average((df["a"] - expect_mean) ** 2, weights=w))
|
||
assert table.loc["weighted_mean", "a"] == pytest.approx(expect_mean)
|
||
assert table.loc["weighted_std", "a"] == pytest.approx(expect_std)
|
||
|
||
|
||
@pytest.mark.parametrize(
|
||
("weights", "exc"),
|
||
[
|
||
(np.ones(2), ValueError),
|
||
(np.zeros(3), ValueError),
|
||
(np.array([1.0, -1.0, 1.0]), ValueError),
|
||
(np.array([1.0, np.nan, 1.0]), ValueError),
|
||
("abc", TypeError),
|
||
],
|
||
)
|
||
def test_describe_rejects_bad_weights(weights, exc):
|
||
from mcm_toolkit.stats import describe
|
||
|
||
with pytest.raises(exc):
|
||
describe(pd.DataFrame({"a": [1.0, 2.0, 3.0]}), weights=weights)
|
||
|
||
|
||
def test_describe_rejects_unsupported_type_and_all_text_frame():
|
||
from mcm_toolkit.stats import describe
|
||
|
||
with pytest.raises(TypeError):
|
||
describe({"a": [1.0]})
|
||
with pytest.raises(ValueError):
|
||
describe(pd.DataFrame({"city": ["X", "Y"]}))
|
||
|
||
|
||
# ------------------------------------------------------ stats: zscore
|
||
|
||
|
||
def test_zscore_matches_manual_formula():
|
||
from mcm_toolkit.stats import zscore
|
||
|
||
x = np.array([1.0, 2.0, 3.0, 4.0])
|
||
assert np.allclose(np.asarray(zscore(x)), (x - x.mean()) / x.std())
|
||
|
||
|
||
def test_zscore_is_per_column_and_keeps_frame(rng):
|
||
from mcm_toolkit.stats import zscore
|
||
|
||
df = pd.DataFrame({"a": rng.normal(size=200), "b": rng.normal(5, 3, size=200)})
|
||
out = zscore(df)
|
||
|
||
assert isinstance(out, pd.DataFrame)
|
||
assert list(out.columns) == ["a", "b"]
|
||
assert np.allclose(np.asarray(out).mean(axis=0), 0.0, atol=1e-12)
|
||
assert np.allclose(np.asarray(out).std(axis=0), 1.0, atol=1e-12)
|
||
|
||
|
||
def test_zscore_constant_column_stays_zero():
|
||
from mcm_toolkit.stats import zscore
|
||
|
||
assert np.allclose(np.asarray(zscore([2.0, 2.0, 2.0])), 0.0)
|
||
|
||
|
||
def test_zscore_rejects_bad_type_and_all_text_frame():
|
||
from mcm_toolkit.stats import zscore
|
||
|
||
with pytest.raises(TypeError):
|
||
zscore("abc")
|
||
with pytest.raises(ValueError):
|
||
zscore(pd.DataFrame({"city": ["X"]}))
|
||
|
||
|
||
# ------------------------------------------- stats: coefficient_of_variation
|
||
|
||
|
||
def test_coefficient_of_variation_matches_manual_formula():
|
||
from mcm_toolkit.stats import coefficient_of_variation
|
||
|
||
x = np.array([1.0, 2.0, 3.0, 4.0])
|
||
assert coefficient_of_variation(x) == pytest.approx(x.std() / x.mean())
|
||
|
||
|
||
def test_coefficient_of_variation_accepts_single_column_frame():
|
||
from mcm_toolkit.stats import coefficient_of_variation
|
||
|
||
df = pd.DataFrame({"a": [1.0, 2.0, 3.0]})
|
||
single = coefficient_of_variation([1.0, 2.0, 3.0])
|
||
assert coefficient_of_variation(df) == pytest.approx(single)
|
||
|
||
|
||
def test_coefficient_of_variation_uses_absolute_mean():
|
||
"""均值为负时 CV 仍是**正数**：符号不该被读成"波动更小"。"""
|
||
from mcm_toolkit.stats import coefficient_of_variation
|
||
|
||
x = np.array([-1.0, -2.0, -3.0, -4.0])
|
||
assert coefficient_of_variation(x) == pytest.approx(x.std() / abs(x.mean()))
|
||
assert coefficient_of_variation(x) > 0
|
||
|
||
|
||
def test_coefficient_of_variation_zero_mean_is_value_error():
|
||
"""均值为 0 是**取值**问题不是类型问题：必须是 ValueError 而不是 TypeError。"""
|
||
from mcm_toolkit.stats import coefficient_of_variation
|
||
|
||
with pytest.raises(ValueError):
|
||
coefficient_of_variation([-1.0, 1.0])
|
||
|
||
|
||
def test_coefficient_of_variation_rejects_empty_2d_and_bad_type():
|
||
from mcm_toolkit.stats import coefficient_of_variation
|
||
|
||
with pytest.raises(ValueError):
|
||
coefficient_of_variation([])
|
||
with pytest.raises(ValueError):
|
||
coefficient_of_variation([[1.0, 2.0], [3.0, 4.0]])
|
||
with pytest.raises(ValueError):
|
||
coefficient_of_variation(pd.DataFrame({"a": [1.0], "b": [2.0]}))
|
||
with pytest.raises(TypeError):
|
||
coefficient_of_variation(5.0)
|