一份快照按期次分组的变化拆解也核本期齐不齐(复核 R20):可加、比率、乘积三种模式用波动基线同一套完整性检查(comparable.period_complete:不到整周、没过完、数据没到、SQL 截掉一部分),本期不齐算不了(partial_target,「本期数据只到 2026-10-20,还差 5 天,和完整的周比没有意义」),核对不了(查不到表的范围、周号认不出算法、期次不是日期)附一句说明,只在证据面板、不进判定语(两份快照时可比性结论照旧进判定语);结论的 params 记下运行当天。期次按 periods.parse_compared 认:周号按 SQL 认算法;快照里往往只有比的两期,值都是日期、推断成按周、期次列又是直接取的日期列(原样、date(列)、DATE(列)、CAST 成日期)时按天认——昨天对上周同一天正好隔 7 天,光看值分不出是两天还是两周。可比性检查按期次分组、没给粒度时同样按它认。证据接口的一条测试(tests/test_analysis_evidence_api.py)跟着补上这一句说明的种类

This commit is contained in:
ThearchyHelios
2026-10-21 16:09:21 +08:00
parent fd8e392f48
commit f7a09eb108
6 changed files with 155 additions and 13 deletions
+56 -2
View File
@@ -57,8 +57,10 @@ async def test_a_driver_is_named_with_its_share_and_the_whole_shape_is_filled():
"columns": ["region", "week", "gmv"], "rows": "all"}]
assert result["hypothesis"] == "华东拖累" and result["probes"] == []
assert result["criterion"].endswith("以各段之和为总数")
assert {c["code"] for c in result["caveats"]} == {"headline_basis"}
# 期次是现成的一列「2026-W41」,认不出是按哪种周号算的:本期齐不齐核对不了,只附在证据面板(不进判定语)
assert {c["code"] for c in result["caveats"]} == {"headline_basis", "comparability"}
assert result["params"]["catalog"] == {"labels": {"region": "地区"}, "measures": {"gmv": "flow"}}
assert result["params"]["today"] == "2026-10-21"
async def test_the_segments_add_up_to_the_total_digit_for_digit():
@@ -163,7 +165,7 @@ async def test_drilling_down_checks_closure_against_the_parent_segment():
assert child["params"]["depth"] == 1 and child["params"]["parent"] == {"of": "A3", "key": ["华东"]}
assert child["inputs"][0]["role"] == "parent" and child["inputs"][0]["ref"] == "A3"
assert "max_drill_depth" in child["settings"]
assert {c["code"] for c in child["caveats"]} == set() # 有 parent 就不是「以各段之和为总数」
assert {c["code"] for c in child["caveats"]} == {"comparability"} # 有 parent 就不是「以各段之和为总数」
short = snap("Q4", province["sql"], ["province", "week", "gmv"],
[["沪", "2026-W41", 500], ["沪", "2026-W42", 410], ["苏", "2026-W41", 300], ["苏", "2026-W42", 290]])
unclosed = await analyze("decompose", "additive", snaps=[short], parents={"A3": top}, **params)
@@ -504,3 +506,55 @@ async def test_a_dimension_named_like_a_result_column_is_a_call_error():
error = await call_error("decompose", "ratio", snaps=[mixed], query="Q1", by="Mix", period="week", base="W41",
target="W42", numerator="refunds", denominator="orders")
assert error.code == "reserved_column" and "「Mix」" in error.message
# --------------------------------------------------------------------------
# 一份快照按期次分组:本期齐不齐(同波动基线那一套)
# --------------------------------------------------------------------------
WEEK_START = ("SELECT region, date(order_date, '-6 days', 'weekday 1') AS week, SUM(amount) AS gmv FROM orders "
"GROUP BY 1, 2")
DAY_SQL = "SELECT region, order_date AS day, SUM(amount) AS gmv FROM orders GROUP BY 1, 2"
def _two(base, target, *, sql=WEEK_START, col="week"):
rows = [["华东", base, 820], ["华东", target, 700], ["华北", base, 600], ["华北", target, 560]]
return snap("Q2", sql, ["region", col, "gmv"], rows, types={"region": "text", col: "text", "gmv": "number"})
async def test_one_snapshot_by_period_checks_the_target_is_whole():
probe = fixed_prober({("orders", "order_date"): ("2025-01-01", "2026-10-20")})
ask = {"query": "Q2", "by": ["region"], "period": "week", "measure": "gmv", "label": "销售额"}
# 运行当天 10-21:10-19 那一周没过完
partial = await analyze("decompose", "additive", snaps=[_two("2026-10-12", "2026-10-19")], probe=probe,
base="2026-10-12", target="2026-10-19", **ask)
assert partial["reason_code"] == "partial_target"
assert partial["reason"] == "本期数据只到 2026-10-20,还差 5 天,和完整的周比没有意义"
assert partial["params"]["today"] == "2026-10-21" and partial["probes"][0]["column"] == "order_date"
whole = await analyze("decompose", "additive", snaps=[_two("2026-10-05", "2026-10-12")], probe=probe,
base="2026-10-05", target="2026-10-12", **ask)
assert whole["status"] == "ok" and not [c for c in whole["caveats"] if c["code"] == "comparability"]
# 查不到表的范围:只附一句核对不了,不进判定语
unknown = await analyze("decompose", "additive", snaps=[_two("2026-10-05", "2026-10-12")],
base="2026-10-05", target="2026-10-12", **ask)
note = next(c["text"] for c in unknown["caveats"] if c["code"] == "comparability")
assert note == "没能核对本期的数据是否到齐(查不到表里这一列的日期范围)" and note not in unknown["phrase"]
ratio_rows = [["线上", "2026-10-12", 50, 1000], ["线上", "2026-10-19", 80, 1000], ["线下", "2026-10-12", 20, 1000],
["线下", "2026-10-19", 26, 1000]]
ratio_snap = snap("Q1", "SELECT channel, date(order_date, '-6 days', 'weekday 1') AS week, SUM(refund_flag) AS "
"refunds, COUNT(*) AS orders FROM orders GROUP BY 1, 2",
["channel", "week", "refunds", "orders"], ratio_rows)
refused = await analyze("decompose", "ratio", snaps=[ratio_snap], probe=probe, query="Q1", by="channel",
period="week", base="2026-10-12", target="2026-10-19", numerator="refunds",
denominator="orders")
assert refused["reason_code"] == "partial_target"
async def test_two_days_a_week_apart_from_a_plain_date_column_are_two_days():
# 期次列直接取的日期:昨天(10-20)对上周同一天,不是两周;10-20 当天的数据已经到了
probe = fixed_prober({("orders", "order_date"): ("2025-01-01", "2026-10-20")})
result = await analyze("decompose", "additive", snaps=[_two("2026-10-13", "2026-10-20", sql=DAY_SQL, col="day")],
probe=probe, query="Q2", by=["region"], period="day", base="2026-10-13",
target="2026-10-20", measure="gmv")
assert result["status"] == "ok" and not [c for c in result["caveats"] if c["code"] == "comparability"]
+1 -1
View File
@@ -136,7 +136,7 @@ async def test_the_phrase_opens_judgment_method_calculation_inputs_recompute_and
assert judged["cited"] == {"what": "phrase"} and judged["render_ok"] is True and judged["eid_ok"] is True
assert judged["origin"] == "card" and judged["item"] == "drop" and judged["label"] == "分析"
assert judged["hypothesis"] == "华东拖累" and judged["hypothesis_note"].startswith("Agent 写的假设")
assert {c["code"] for c in judged["caveats"]} == {"measure_unlabeled", "headline_basis"}
assert {c["code"] for c in judged["caveats"]} == {"measure_unlabeled", "headline_basis", "comparability"}
assert method["method"] == "decompose.additive@1" and method["method_label"] == "变化拆解(可加)"
assert {s["key"]: s["label"] for s in method["settings"]}["main_share"] == "「主要来源」的占比"
assert {s["key"] for s in method["settings"]} >= {"main_share", "concentration", "table_top_k"}
+12
View File
@@ -128,3 +128,15 @@ def test_unreadable_values_are_named():
assert pd.unreadable(["2026-W40", "上周", "2026-W41", None]) == ("shape", ["上周", None])
assert pd.unreadable(["2026-W40", "2026-W41", "2026-10-12"]) == ("mixed", ["2026-10-12"])
assert pd.unreadable(["2026-10", "2026-11"], "week") == ("grain", ["2026-10", "2026-11"])
def test_a_plain_date_column_is_a_day_even_when_two_values_are_a_week_apart():
plain = "SELECT region, order_date AS day, SUM(amount) AS gmv FROM orders GROUP BY 1, 2"
starts = ("SELECT region, date(order_date, '-6 days', 'weekday 1') AS week, SUM(amount) AS gmv FROM orders "
"GROUP BY 1, 2")
assert pd.plain_day(plain, "day", "sqlite") and pd.plain_day(plain.replace("order_date AS", "DATE(order_date) AS"),
"day", "sqlite")
assert not pd.plain_day(starts, "week", "sqlite")
assert pd.parse_compared(["2026-10-13", "2026-10-20"], plain, "day", "sqlite")[1] == "day"
assert pd.parse_compared(["2026-10-12", "2026-10-19"], starts, "week", "sqlite")[1] == "week"
assert pd.parse_compared(["2026-09-01", "2026-10-01"], plain, "day", "sqlite")[1] == "month"