mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 00:21:58 +00:00
ThearchyHelios
83cd5da72e
- tests/fixtures/acceptance/retail_trends.py（python -m tests.fixtures.acceptance.retail_trends <db> [--today]，数据源名 retail_trends，不动 retail.py）：华东线下客单价降到七成带来的销售额下降（主要来自华东）；三成线下订单转到线上造成的退款率辛普森（各渠道都降、整体升，结构为主）；订单数的常规波动；取消单激增；线上销售额连涨十周以上；线上销售额的变化来自订单数；西南一家小店的退款率看着高但样本太少；本周没过完（和上周不可比，周一时本周还没有数据、那一题期望算不了）。订单数按店按周定好、金额在窄区间随机、退款按渠道比例挑，各效应不靠运气 - tests/fixtures/eval/analysis_suite.json：八道题，问法用使用者的说法（上周销售额为什么下降？退款率为什么上升了？上周订单数下降算不算异常？……），各配一个贡献或判定期望，订单数、取消单两题另配一个不必需的「一个数」 - 测试：同一个今天逐字节相同；四个不同的今天（周三、周日、周六、跨年）上用 app.analysis.run 按题集的期望 SQL 核对八个效应；周一那一题照实算不了；走接口导入题集、逐题试算，分析期望都算得出、判定和埋的效应一致；真运行的算期望（作答前后对得上、阈值按设置快照、参数对不上照实说）、读作答运行里的分析结论和引用、重评老结果、从头到尾评一题（助手剧本搭查库 → 分析卡 → 报告，对且可追溯、逐题 E1 等价已证明）
171 lines
8.3 KiB
Python
171 lines
8.3 KiB
Python
"""分析题用的虚构零售库（docs/design/analysis-round/00-总方案.md §3.8、D14）。店名、金额都是编的，和任何真实业务无关。
|
||
|
||
python -m tests.fixtures.acceptance.retail_trends <输出 .db 路径> [--today YYYY-MM-DD]
|
||
|
||
生成「今天」之前 26 周的订单（截止昨天），随机数种子固定：同一个「今天」生成的库逐字节一样。和 retail.py（retail_demo）分开：
|
||
那边的测试断言了它的比例、地区排序，在里面埋效应会改掉后面全部的随机序列，60 天也不够放回 8 周以上的历史里看。
|
||
|
||
相对「上一个整周」（上周一到上周日，下面叫「上周」，它前一周叫「上上周」）埋了这些效应，各放在不互相干扰的指标或段上：
|
||
|
||
1. 销售额（已支付的金额）上周比上上周下降，主要来自华东：华东线下上周的客单价降到七成，订单数不变。
|
||
2. 退款率的辛普森：线上、线下各自的退款率上周都比上上周低，整体却升了——上周起三成线下订单转到了线上，线上的退款率本来
|
||
就高（结构变化为主）。
|
||
3. 订单数（不含取消）的常规波动：线下每周有 ±5% 的起伏，上周比上上周少一点，在常规波动范围内，不该叫异常。
|
||
4. 取消单激增：平常每周二十来单，上周是三倍多，明显超出常规波动。
|
||
5. 线上销售额持续上升：线上订单每周多 4%（上周又加上转过来的那三成），最近十几周周周都涨。
|
||
6. 线上销售额上周的变化主要来自订单数，客单价没变。
|
||
7. 西南只有一家小店，近四周的退款率看着比华东高，样本太少，差异不足以下结论。
|
||
8. 本周还没过完（截止昨天）：拿本周和上周比，不可比。今天是周一时本周还没有数据，那一题的期望算不了。
|
||
|
||
订单数每家店每周按定好的数生成（不逐笔抽随机），金额在很窄的区间里随机，退款单按每周每个渠道定好的比例挑：各效应不靠运气
|
||
成立。tests/test_retail_trends_fixture.py 在几个不同的「今天」上用平台的算子，按题集的期望 SQL 逐个核对。
|
||
|
||
评测的分析题集（tests/fixtures/eval/analysis_suite.json）按数据源名 SOURCE_NAME 对上这个库：生成之后登记成这个名字的只读
|
||
数据源，再导入题集（POST /api/evals/suites/import），题目的期望都按这个库算。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import random
|
||
import sqlite3
|
||
from datetime import date, timedelta
|
||
from pathlib import Path
|
||
|
||
WEEKS = 26
|
||
DAYS = WEEKS * 7
|
||
SEED = 20261021
|
||
#: 分析题集里写的数据源名
|
||
SOURCE_NAME = "retail_trends"
|
||
ONLINE, OFFLINE = "线上", "线下"
|
||
|
||
#: (门店 id, 店名, 地区)：西南只有一家小店（第 7 条效应的小样本）
|
||
STORES = [
|
||
(1, "青禾一号店", "华东"), (2, "青禾二号店", "华东"), (3, "青禾三号店", "华东"),
|
||
(4, "青禾四号店", "华南"), (5, "青禾五号店", "华南"), (6, "青禾六号店", "华南"),
|
||
(7, "青禾七号店", "华北"), (8, "青禾八号店", "华北"),
|
||
(9, "青禾九号店", "西南"),
|
||
]
|
||
SMALL_STORE = 9
|
||
#: 每家店每天的线下订单数（平常的水平）
|
||
OFFLINE_DAILY = {1: 16, 2: 14, 3: 12, 4: 14, 5: 12, 6: 10, 7: 12, 8: 10, 9: 1}
|
||
#: 每家店每天的线上订单数（上周的水平；往前每周少 4%）
|
||
ONLINE_DAILY = {1: 7, 2: 6, 3: 5, 4: 6, 5: 5, 6: 5, 7: 5, 8: 4, 9: 0.5}
|
||
ONLINE_GROWTH = 1.04
|
||
#: 线下每周的起伏（±）；上周比上上周再少这么多
|
||
OFFLINE_SWING = 0.05
|
||
LAST_WEEK_DIP = 0.975
|
||
#: 上周起线下订单转到线上的比例
|
||
SHIFT = 0.3
|
||
#: 金额的区间（元）；华东线下上周的客单价乘这个数
|
||
PRICE = (140.0, 180.0)
|
||
EAST_DROP = 0.7
|
||
#: 各渠道的退款率：上上周及以前、上周起
|
||
REFUND_RATE = {ONLINE: (0.10, 0.09), OFFLINE: (0.04, 0.034)}
|
||
#: 每周的取消单数和起伏；上周的倍数
|
||
CANCELLED_WEEKLY = 24
|
||
CANCEL_SWING = 0.15
|
||
CANCEL_SPIKE = 3.2
|
||
|
||
SCHEMA = """
|
||
CREATE TABLE stores (id INTEGER PRIMARY KEY, name TEXT NOT NULL, region TEXT NOT NULL);
|
||
CREATE TABLE orders (
|
||
id INTEGER PRIMARY KEY,
|
||
store_id INTEGER NOT NULL REFERENCES stores(id),
|
||
order_date DATE NOT NULL,
|
||
channel TEXT NOT NULL,
|
||
amount REAL NOT NULL,
|
||
status TEXT NOT NULL
|
||
);
|
||
"""
|
||
|
||
|
||
def _spread(count: int, days: list[date]) -> list[date]:
|
||
"""一周里的 count 单按天摊开：尽量平均，多出来的几单从这一周的头几天起各加一单。"""
|
||
if not days or count <= 0:
|
||
return []
|
||
base, extra = divmod(count, len(days))
|
||
return [d for i, d in enumerate(days) for _ in range(base + (1 if i < extra else 0))]
|
||
|
||
|
||
def build(path: Path | str, today: date | None = None) -> Path:
|
||
"""生成到 path（已存在就覆盖）。today 缺省取运行这一天；订单截止 today 的前一天。"""
|
||
path = Path(path)
|
||
if path.exists():
|
||
path.unlink()
|
||
today = today or date.today()
|
||
rng = random.Random(SEED)
|
||
first, last = today - timedelta(days=DAYS), today - timedelta(days=1)
|
||
monday = today - timedelta(days=today.weekday())
|
||
# 第 j 周：本周 j = 0、上周 j = 1……最早的那一周可能不完整。每周的起伏先抽好（个数和「今天」是星期几无关）
|
||
oldest = (monday - (first - timedelta(days=first.weekday()))).days // 7
|
||
swing = {j: 1 + rng.uniform(-OFFLINE_SWING, OFFLINE_SWING) for j in range(oldest, -1, -1)}
|
||
cancel = {j: 1 + rng.uniform(-CANCEL_SWING, CANCEL_SWING) for j in range(oldest, -1, -1)}
|
||
swing[1] = swing[2] * LAST_WEEK_DIP
|
||
cancel[1] = CANCEL_SPIKE
|
||
|
||
def days_of(j: int) -> list[date]:
|
||
start = monday - timedelta(days=7 * j)
|
||
return [d for d in (start + timedelta(days=k) for k in range(7)) if first <= d <= last]
|
||
|
||
def price(store: int, channel: str, j: int) -> float:
|
||
amount = rng.uniform(*PRICE)
|
||
if j == 1 and channel == OFFLINE and _REGION[store] == "华东":
|
||
amount *= EAST_DROP
|
||
return round(amount, 2)
|
||
|
||
rows: list[list] = []
|
||
for j in range(oldest, -1, -1):
|
||
days = days_of(j)
|
||
if not days:
|
||
continue
|
||
share = len(days) / 7
|
||
week: dict[str, list[list]] = {ONLINE: [], OFFLINE: []}
|
||
for store, _, _ in STORES:
|
||
online = round(7 * share * ONLINE_DAILY[store] * ONLINE_GROWTH ** (1 - j))
|
||
offline = round(7 * share * OFFLINE_DAILY[store] * swing[j])
|
||
if j <= 1:
|
||
moved = round(offline * SHIFT)
|
||
online, offline = online + moved, offline - moved
|
||
for channel, count in ((ONLINE, online), (OFFLINE, offline)):
|
||
for day in _spread(count, days):
|
||
row = [store, day.isoformat(), channel, price(store, channel, j), "paid"]
|
||
week[channel].append(row)
|
||
rows.append(row)
|
||
# 退款：每个渠道按这一周的比例挑（西南那家小店另算：每周一单线下退款）
|
||
for channel, pool in week.items():
|
||
usual = [r for r in pool if r[0] != SMALL_STORE]
|
||
rate = REFUND_RATE[channel][1 if j <= 1 else 0]
|
||
for row in rng.sample(usual, round(len(usual) * rate)):
|
||
row[4] = "refunded"
|
||
small = [r for r in week[OFFLINE] if r[0] == SMALL_STORE]
|
||
if small:
|
||
small[0][4] = "refunded"
|
||
# 取消单：另外的单（不占上面的订单数），店、渠道、日子随机
|
||
for _ in range(round(CANCELLED_WEEKLY * share * cancel[j])):
|
||
store = rng.choice([s for s, _, _ in STORES if s != SMALL_STORE])
|
||
channel = OFFLINE if rng.random() < 0.6 else ONLINE
|
||
rows.append([store, rng.choice(days).isoformat(), channel, price(store, channel, j), "cancelled"])
|
||
rows.sort(key=lambda r: (r[1], r[0], r[2], r[4], r[3]))
|
||
db = sqlite3.connect(path)
|
||
db.executescript(SCHEMA)
|
||
db.executemany("INSERT INTO stores VALUES (?, ?, ?)", STORES)
|
||
db.executemany("INSERT INTO orders VALUES (?, ?, ?, ?, ?, ?)", [(i, *r) for i, r in enumerate(rows, start=1)])
|
||
db.commit()
|
||
db.close()
|
||
return path
|
||
|
||
|
||
_REGION = {store: region for store, _, region in STORES}
|
||
|
||
|
||
def main() -> None:
|
||
parser = argparse.ArgumentParser(description="生成分析题用的虚构零售库")
|
||
parser.add_argument("path")
|
||
parser.add_argument("--today", type=date.fromisoformat, default=None)
|
||
args = parser.parse_args()
|
||
print(build(args.path, args.today))
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|