差异检验拿不到 p 值照实说、敏感性只在真实的各组里找离群值(复核 R8、R9):一对都拿不到 p 值(比率有一组样本量为 0;均值、逐行有一组不到 2 个样本,或均值、标准差为空)时算不了,契约 REASONS 加 untestable,原因写哪一组怎么了(「华东只有 1 个样本、华南只有 1 个样本,算不了差异」),不再判 ok + 可能只是样本波动;只有一部分拿不到的,那几对不算进比了几对、不参与校正,表里写清哪一组怎么了,判定语后接「另有 n 对算不了(…)」(契约 CAVEATS 加 untested,排在判定语附带说明的前面)。逐行模式比三组以上时,离均值最远的那一笔只在真实的各组里找(原来池子里混着各对的「其余各组合计」,第一组以外的离群值删不到它自己那一组,漏报 outlier_sensitive),去掉以后由各组重建每一对的「其余」合计再检验

This commit is contained in:
ThearchyHelios
2026-10-21 15:56:16 +08:00
parent 460af221f9
commit 427a6df23c
4 changed files with 104 additions and 30 deletions
+40 -2
View File
@@ -136,6 +136,44 @@ async def test_two_periods_of_the_same_group():
async def test_a_group_with_one_value_cannot_be_tested():
s = snap("Q1", "SELECT channel, amount FROM orders", ["channel", "amount"], [["线上", 5], ["线下", 4], ["线下", 6]])
result = await analyze("differ", "rows", snaps=[s], query="Q1", by="channel", value="amount")
assert result["verdict"]["code"] == "no_evidence" and result["values"]["p"] is None
assert result["table"]["rows"][0][-1] == "样本不够,算不了"
assert result["status"] == "refused" and result["reason_code"] == "untestable"
assert result["reason"] == "线上只有 1 个样本,算不了差异"
assert result["phrase"] == "差异检验没有做成:线上只有 1 个样本,算不了差异"
async def test_no_pair_with_a_p_value_is_refused_not_said_to_be_noise():
sql = "SELECT region, AVG(amount) AS m, 0 AS sd, COUNT(*) AS n FROM orders GROUP BY 1"
means = snap("Q1", sql, ["region", "m", "sd", "n"], [["华东", 120, 0, 1], ["华南", 80, 0, 1]])
mean = await analyze("differ", "mean", snaps=[means], query="Q1", by="region", mean="m", sd="sd", n="n",
label="客单价")
assert mean["reason_code"] == "untestable" and mean["reason"] == "华东只有 1 个样本、华南只有 1 个样本,算不了差异"
assert mean["verdict"] is None and mean["settings"] == {"differ_alpha": 0.05, "min_n": 30}
rows = snap("Q2", "SELECT region, amount FROM orders", ["region", "amount"], [["华东", 120], ["华南", 80]])
one = await analyze("differ", "rows", snaps=[rows], query="Q2", by="region", value="amount")
assert one["reason"] == "华东只有 1 个样本、华南只有 1 个样本,算不了差异"
zero = await rate([["华东", 0, 0], ["华南", 3, 10]])
assert zero["reason_code"] == "untestable" and zero["reason"] == "华东的样本量为 0,算不了差异"
async def test_pairs_without_a_p_value_are_named_and_not_counted():
result = await rate([["西南", 80, 1000], ["华东", 40, 1000], ["华北", 0, 0]])
rows = {r[0]: r for r in result["table"]["rows"]}
assert rows["华北"][-1] == "华北的样本量为 0,算不了" and rows["华北"][10] is None
note = next(c for c in result["caveats"] if c["code"] == "untested")
assert note["text"] == "另有 1 对算不了(华北的样本量为 0)"
# 华北一单都没有:西南的其余合计就是华东,两对都站得住;华北那一对不算进「比了几对」
assert result["phrase"] == ("比了 2 对,2 对差异站得住:西南的退款率(8.0%)高于其余各地区(4.0%);华东的退款率(4.0%)"
"低于其余各地区(8.0%);另有 1 对算不了(华北的样本量为 0)")
assert {"code": "multiple_comparisons", "text": "比了 2 对,已按次数校正"} in result["caveats"]
async def test_the_outlier_is_looked_for_in_the_real_groups_not_in_the_pooled_rest():
# 三组各和其余合计比:最远的那一笔在第二组(华南)。只在真实的各组里找、由各组重建「其余」合计,去掉它以后华南高出来就站得住
base = [10, 11, 9, 10, 12, 8, 10, 11, 10, 9, 11, 10]
rows = ([["华东", v] for v in base] + [["华南", v + 2] for v in base[:-1]] + [["华南", 100]]
+ [["华北", v] for v in base])
s = snap("Q1", "SELECT region, amount FROM orders", ["region", "amount"], rows)
result = await analyze("differ", "rows", snaps=[s], query="Q1", by="region", value="amount", label="客单价")
assert result["verdict"]["code"] == "no_evidence"
assert {"code": "outlier_sensitive", "text": "去掉最大的一笔后,差异变得站得住"} in result["caveats"]
assert math.isfinite(float(result["values"]["diff"]))