guzhujushi
e9624cb3a7
src/stats/descriptive.py 由用户本人实现，这里做审查 + 代修。
describe:
- 真 bug：df_num.describe().T 把表转反（行=变量、列=指标），而 docstring 与
test_describe_reports_expected_keys 定的是"行=指标、列=变量"。转置后
.loc[指标名] = <按变量索引的 Series> 与列名零交集，pandas 不报错，直接把
missing / missing_ratio / skewness / kurtosis 四行整行填成 NaN（静默丢数据）；
weights 分支则报 cannot set a row with mismatched columns。去掉 .T 一处修好三件事
- 补 median 行（pandas 只有 50%，测试契约定的是 median）
- 入参放宽到 list / tuple / ndarray（00_quickstart.py 传的就是 ndarray）
- weights 校验补齐：维度 / 长度 / NaN / 负值 / 和为 0（原先和为 0 时裸抛 ZeroDivisionError）
- docstring 按 4.7 补 Parameters / Returns / Raises
zscore: 修 RET505；docstring 补齐；DataFrame 取列处按坑 8 用 cast 收窄
coefficient_of_variation: 均值为 0 改抛 ValueError（取值问题不是类型问题）；
空数组提前报错（原先静默 nan + RuntimeWarning）；错别字与文案修正
tests: 去掉 test_stats.py 的模块级 pytestmark —— 它把 6 条测试全部跳过（含已实现的
describe），正是决策 26 要禁的写法。改为逐条 skip 未实现的 5 条，并新增 20 条用例。
验证：pytest 102 passed / 39 skipped（原 82/40）；ruff All checks passed；pyright 0 errors。
examples/01_clean_and_describe.py 填掉 TODO(L0)，实测 exit 0。
docs: STATUS.md L0 8/12 + 决策 35/36 + 三处待拍板口径；CHANGELOG 记录；
personal-pitfalls 追加第 11 条（pandas 对不齐就静默填 NaN）
243 lines
8.2 KiB
Python
243 lines
8.2 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"
|
||
|
||
|
||
@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)
|
||
|
||
|
||
@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
|
||
def test_correlation_matrix_diagonal_is_one(rng):
|
||
from mcm_toolkit.stats import correlation_matrix
|
||
|
||
x = rng.normal(size=(200, 4))
|
||
c = correlation_matrix(x)
|
||
assert np.allclose(np.diag(np.asarray(c)), 1.0)
|
||
|
||
|
||
# ------------------------------------------------------ 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_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)
|