Files
Gset/bench.py
T
treeandClaude Opus 5.5 e9616af34d 修复 P0:根因判定、退服率口径、影响评估与告警关联量化
- 根因判定改为三级(衍生关系/时间窗/疑似)并带置信度;小区退服告警 ±2 分钟匹配;
  衍生告警按父告警归类;优先选随业务恢复清除的告警;时间窗按历史流水 95% 分位数标定
- 退服率按日历统计周期计算;站点数分母支持站名关键字;重复退服率除以全部站点;
  月均按统计周期自然月数;导出与看板同一口径
- 影响评估新增受影响用户·小时与 500 米邻站覆盖补偿
- 新增告警—退服关联量化(支持度/置信度/提升度)及 /api/association,根因页展示
- 新增 tests/(扰动数据集留出检验、指标口径检验)与 bench.py;旧库启动时自动迁移

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 14:43:34 +08:00

72 lines
3.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""性能与时长计算准确率测试(对应开题报告的预期目标),走 Flask 接口,结果可直接写入论文测试章节。
- 单批 10000 条退服流水导入(预览校验 + 确认入库 + 新记录根因分析)≤ 15 秒
- 单次全量退服时长计算与根因分析 ≤ 8 秒
- 退服时长计算准确率 ≥ 98%(以生成器真值为准),并核对人工上报时长差错的检出
运行:python bench.py 数据库建在 tests/_work 下,不影响 data/outage.db
"""
import io
import os
import sys
import time
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests'))
import harness # noqa: E402 设置数据库路径
from harness import check, core, finish, generate # noqa: E402
if os.path.exists(os.environ['OUTAGE_DB']):
os.remove(os.environ['OUTAGE_DB'])
core.DB_PATH = os.environ['OUTAGE_DB']
started = time.time()
import app as webapp # noqa: E402 导入时 init_db:建库 + 样例数据入库 + 全量分析
print(f'首次建库、样例入库与全量分析: {time.time() - started:.2f} s')
client = webapp.app.test_client()
client.post('/login', json={'username': 'admin', 'password': 'admin123'})
def timed(label, request):
begin = time.time()
response = request()
elapsed = time.time() - begin
print(f'{label}: {elapsed:.2f} s(HTTP {response.status_code})')
return response, elapsed
# 10000 条新流水:同一站点库,取生成序列第 6001~16000 条,避免与样例数据重复
_, alarms_big, outages_big = generate('bench', rows=16000)
batch = outages_big.iloc[6000:16000]
upload = io.BytesIO(batch.to_csv(index=False).encode('utf-8-sig'))
response, t_preview = timed('导入预览 10000 条', lambda: client.post(
'/api/import/preview', data={'file': (upload, 'batch.csv')}, content_type='multipart/form-data'))
preview = response.get_json()
print(f' 合格 {preview["ok"]},问题 {preview["bad"]},上报时长差错 {preview["diff"]}')
response, t_confirm = timed('导入确认(入库 + 新记录根因分析)', lambda: client.post(
'/api/import/confirm', json={'token': preview['token']}))
check('单批 10000 条导入 ≤ 15 s', t_preview + t_confirm <= 15, f'({t_preview + t_confirm:.2f} s)')
upload = io.BytesIO(alarms_big.to_csv(index=False).encode('utf-8-sig'))
response, _ = timed(f'告警预览 {len(alarms_big)} 条', lambda: client.post(
'/api/import/preview', data={'file': (upload, 'alarm.csv')}, content_type='multipart/form-data'))
timed('告警确认(入库 + 全量重新标定与关联)', lambda: client.post(
'/api/import/confirm', json={'token': response.get_json()['token']}))
total = core.query('SELECT COUNT(*) AS n FROM outages')[0]['n']
response, t_analyze = timed(f'全量根因分析 /api/analyze({total} 条,含时间窗标定)',
lambda: client.post('/api/analyze'))
core.data_changed()
response, t_dashboard = timed('看板首次请求(全量时长与指标重算)', lambda: client.get('/api/dashboard'))
check('全量时长计算与根因分析 ≤ 8 s', t_analyze + t_dashboard <= 8, f'({t_analyze + t_dashboard:.2f} s)')
df = core.full_frame()
true_minutes = (core.pd.to_datetime(df['end_time']) - df['start']).dt.total_seconds() / 60
accuracy = ((df['duration_min'] - true_minutes).abs() < 0.05).mean() * 100
check('退服时长计算准确率 ≥ 98%', accuracy >= 98, f'({accuracy:.2f}%)')
injected = (df['reported_min'] - true_minutes).abs() > 1
missed = int((injected & ~df['dur_diff']).sum())
false_alarm = int((~injected & df['dur_diff']).sum())
check('人工上报时长差错全部检出且无误报', missed == 0 and false_alarm == 0,
f'(注入 {int(injected.sum())} 条,标记 {int(df["dur_diff"].sum())} 条)')
finish()