From e9616af34d0df9ad4f74b78aef877d36d2b5950d Mon Sep 17 00:00:00 2001 From: treehell Date: Wed, 18 Nov 2026 14:43:34 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=20P0=EF=BC=9A=E6=A0=B9?= =?UTF-8?q?=E5=9B=A0=E5=88=A4=E5=AE=9A=E3=80=81=E9=80=80=E6=9C=8D=E7=8E=87?= =?UTF-8?q?=E5=8F=A3=E5=BE=84=E3=80=81=E5=BD=B1=E5=93=8D=E8=AF=84=E4=BC=B0?= =?UTF-8?q?=E4=B8=8E=E5=91=8A=E8=AD=A6=E5=85=B3=E8=81=94=E9=87=8F=E5=8C=96?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - 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 --- .gitignore | 3 + README.md | 40 +++- app.py | 58 +++-- bench.py | 71 ++++++ core.py | 438 +++++++++++++++++++++++++++++------ static/js/pages/Impact.js | 23 +- static/js/pages/RootCause.js | 41 +++- tests/harness.py | 173 ++++++++++++++ tests/test_kpi.py | 87 +++++++ tests/test_rootcause.py | 54 +++++ 10 files changed, 869 insertions(+), 119 deletions(-) create mode 100644 bench.py create mode 100644 tests/harness.py create mode 100644 tests/test_kpi.py create mode 100644 tests/test_rootcause.py diff --git a/.gitignore b/.gitignore index 313b001..0f54d87 100644 --- a/.gitignore +++ b/.gitignore @@ -18,3 +18,6 @@ Thumbs.db desktop.ini .DS_Store ~$* + +# 测试生成的临时数据库与数据 +tests/_work/ diff --git a/README.md b/README.md index aef5078..6b4ceab 100644 --- a/README.md +++ b/README.md @@ -25,10 +25,11 @@ Python + Flask + SQLite 后端,React 19 + [Liquid Glass UI](https://tsdsj.gith ``` Local-sever/ ├── app.py Flask 路由:认证与权限、增删改查、导入、统计、导出、日志、用户;托管前端页面 -├── core.py 核心算法:建库入库、两级根因关联、时长与考核指标 +├── core.py 核心算法:建库入库、时间窗标定、三级根因关联、告警关联量化、时长与考核指标 ├── importer.py 数据导入:读取 Excel/CSV、自动识别文件类型、逐行校验(见下方“支持导入的文件”) ├── data_gen.py 第 18 题数据生成器(Data-Generated-Core-Py/data.py 的改进版,字段口径一致) -├── publish_online.py 同步到 ../Online-sever(1Panel 线上版) +├── bench.py 性能与时长准确率测试(对应开题报告预期目标) +├── tests/ 根因准确率扰动测试、考核指标口径测试(见下方“测试”) ├── data/ sites.csv / data_outage.csv / data_alarm.csv 种子数据,outage.db 自动生成 ├── static/ 前端(全部可直接阅读和修改) │ ├── index.html 页面入口,importmap 把 'vendor' / 'echarts' 指向 vendor/ 下的文件 @@ -42,8 +43,6 @@ Local-sever/ │ │ ├── components/ ui(卡片/指标/标签/下拉)、DataTable(表格+分页)、FormDialog、EChart、icons │ │ └── pages/ index.js 页面注册表 + 10 个业务页面,一页一个文件 │ └── vendor/ 第三方库(React、液态玻璃组件库、htm、ECharts),压缩文件,不要手改 -├── tools/vendor-build/ 只在升级第三方库时使用,见下文 -└── _legacy_frontend/ 最早的原生 JS 前端,仅供对照,可删除 ``` ## 修改前端 @@ -68,7 +67,7 @@ html`<${Section} title="标题" span=${6}><${EChart} option=${opt}/>= 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() diff --git a/core.py b/core.py index 7bbc5a8..3e6a189 100644 --- a/core.py +++ b/core.py @@ -38,9 +38,10 @@ SCENE_DEFAULT = { '工业园区': (180, 5, 120, 7), } -# 时间窗规则:(告警类别, 判定根因, 告警最多早于退服多少分钟),按优先级从高到低排列。 +# 时间窗规则:(告警类别, 判定根因, 默认时间窗:告警最多早于退服多少分钟),按优先级从高到低排列。 # 割接操作最先排除;停电有蓄电池后备、机房高温有过热保护延时,所以窗口放宽; # 停电往往同时引起传输告警,因为电源优先级更高,这种情况归为电源故障。 +# 实际使用的窗口由 calibrate_windows() 按历史流水标定(只会放宽,不会小于这里的默认值)。 RULES = [ ('割接施工', '割接施工', 30), ('电源故障', '电源故障', 300), @@ -49,6 +50,21 @@ RULES = [ ('天馈故障', '天馈故障', 30), ('设备硬件', '设备硬件', 15), ] +DEFAULT_WINDOW = {category: window for category, _, window in RULES} +PRIORITY = {category: rank for rank, (category, _, _) in enumerate(RULES)} + +MATCH_TOL_MIN = 2 # 第一级:“小区退服”告警与退服开始时间允许相差的分钟数(网管与工单系统时钟不完全同步) +CLEAR_TOL_MIN = 15 # 告警清除与业务恢复相差在此范围内,视为“随业务恢复清除”,作为根因的佐证 +SUSPECT_FACTOR = 3 # 第三级:时间窗放宽到几倍仍命中的,判为“疑似”根因(置信度低) +WINDOW_MAX = 720 # 标定后的时间窗上限(分钟) +CALIB_QUANTILE = 0.95 # 标定取历史提前量的分位数 +CALIB_MIN_SAMPLES = 30 # 某类样本少于此数时不标定,沿用默认窗口 + +# 覆盖补偿:退服站点周边 COVER_RADIUS_M 米内每有一个邻站,受影响用户和话务损失按 COVER_STEP 递减(邻站吸收部分话务), +# 最低保留 COVER_FLOOR。室分站主要覆盖室内,室外邻站补偿有限,递减幅度减半。 +COVER_RADIUS_M = 500 +COVER_STEP = 0.1 +COVER_FLOOR = 0.4 ADVICE = { '电源故障': ['核查市电及开关电源状态,必要时调度油机发电', '检测蓄电池组容量,老化电池纳入更换计划', '评估加装智能电表与远程动环监控'], @@ -123,23 +139,38 @@ CREATE TABLE IF NOT EXISTS sites(ne_id TEXT PRIMARY KEY, site_name TEXT, distric CREATE TABLE IF NOT EXISTS outages(id INTEGER PRIMARY KEY, record_id TEXT, ne_id TEXT, cell_id TEXT, start_time TEXT, end_time TEXT, duration_min REAL, reported_min REAL, cause_category TEXT, cause_detail TEXT, cause_code TEXT, ticket_id TEXT, root_cause TEXT, evidence TEXT, status TEXT DEFAULT '待处理', - handler TEXT, remark TEXT); + handler TEXT, remark TEXT, confidence TEXT); CREATE INDEX IF NOT EXISTS ix_out_ne ON outages(ne_id, start_time); CREATE TABLE IF NOT EXISTS alarms(alarm_id TEXT PRIMARY KEY, ne_id TEXT, alarm_code TEXT, alarm_name TEXT, alarm_level TEXT, category TEXT, start_time TEXT, clear_time TEXT, duration_s INTEGER, cleared TEXT, parent_alarm_id TEXT); CREATE INDEX IF NOT EXISTS ix_alarm_ne ON alarms(ne_id, start_time); CREATE TABLE IF NOT EXISTS logs(id INTEGER PRIMARY KEY, username TEXT, action TEXT, detail TEXT, ts TEXT); +CREATE TABLE IF NOT EXISTS windows(category TEXT PRIMARY KEY, window_min REAL, default_min REAL, samples INTEGER, + source TEXT, updated_at TEXT); """ +def migrate(): + """旧版数据库补字段:outages.confidence(根因判定置信度)。补了字段返回 True,需要重新做一次全量分析。""" + with db() as conn: + columns = {row['name'] for row in conn.execute('PRAGMA table_info(outages)')} + if 'confidence' not in columns: + conn.execute('ALTER TABLE outages ADD COLUMN confidence TEXT') + return True + return False + + def init_db(): """启动时调用:建表;数据库文件是第一次创建时,再写入默认账号、场景阈值,并导入 data/ 下的样例数据。""" is_first_run = not os.path.exists(DB_PATH) os.makedirs(os.path.dirname(DB_PATH), exist_ok=True) with db() as conn: conn.executescript(SCHEMA) + upgraded = migrate() if not is_first_run: + if upgraded: + analyze_all() # 旧库升级:按新算法重新标定时间窗并补上置信度 return now = datetime.now().strftime(TIME_FMT) @@ -218,88 +249,279 @@ def save_sites(df): # ================================================================ 5. 根因关联分析 -def analyze(outages): +def read_alarms(ne_ids=None, categories=None): + """读取告警(可按基站、类别过滤),时间列解析为 datetime,开始时间列改名为 alarm_time。""" + conditions = [] + args = [] + if ne_ids is not None: + ne_ids = list(ne_ids) + if not ne_ids: + return pd.DataFrame(columns=['alarm_id', 'ne_id', 'alarm_name', 'category', 'alarm_time', 'clear_time', + 'parent_alarm_id']) + # 基站很多时(导入全网工参后)不用 IN (?, ?, ...),避免超过 SQLite 的参数个数上限 + conditions.append('ne_id IN (SELECT value FROM json_each(?))') + args.append(pd.Series(ne_ids).to_json(orient='values', force_ascii=False)) + if categories is not None: + conditions.append('category IN (SELECT value FROM json_each(?))') + args.append(pd.Series(list(categories)).to_json(orient='values', force_ascii=False)) + sql = 'SELECT alarm_id, ne_id, alarm_name, category, start_time, clear_time, parent_alarm_id FROM alarms' + if conditions: + sql += ' WHERE ' + ' AND '.join(conditions) + with db() as conn: + alarms = pd.read_sql(sql, conn, params=args) + alarms['start_time'] = pd.to_datetime(alarms['start_time'], errors='coerce', format='mixed') + alarms['clear_time'] = pd.to_datetime(alarms['clear_time'], errors='coerce', format='mixed') + alarms = alarms.dropna(subset=['start_time']) + return alarms.rename(columns={'start_time': 'alarm_time'}) + + +def still_active(alarm_clear, outage_start): + """告警在退服开始时仍未清除(允许 1 分钟误差)才可能是退服的原因。""" + return alarm_clear.isna() | (alarm_clear >= outage_start - pd.Timedelta(minutes=1)) + + +def calibrate_windows(until=None): """ - 两级根因判定。outages 需含 id, ne_id, start_time 三列,返回 [(根因, 证据, id), ...]。 - 第一级 衍生关系:同站、同一时刻的“小区退服”告警如果带 parent_alarm_id,直接取父告警的类别 - (网管已经给出因果链,最可靠); - 第二级 时间窗: 否则回溯同站在退服前仍未清除的告警,按 RULES 的优先级取第一个命中的类别; - 都没有命中判为“其他”。 + 用历史流水标定各类根因告警的时间窗(告警最多早于退服多少分钟),结果写入 windows 表并返回 {类别: 分钟}。 + 样本:已闭环、上报原因属于规则类别的退服(until 指定时只用该日期之前的,便于留出检验); + 在同站、同类别、退服时仍未清除、提前量不超过 WINDOW_MAX 的告警中,取离退服最近的一条,记其提前量; + 窗口:提前量的 95% 分位数,不小于默认窗口、不大于 WINDOW_MAX;样本少于 30 条时沿用默认窗口。 + 这样时间窗随本地网络的实际情况(蓄电池后备时长、动环告警延时等)自动调整,而不是写死在代码里。 + """ + categories = list(DEFAULT_WINDOW) + sql = ("SELECT id, ne_id, start_time, cause_category FROM outages WHERE status = '已闭环' " + "AND cause_category IN (SELECT value FROM json_each(?))") + args = [pd.Series(categories).to_json(orient='values', force_ascii=False)] + if until: + sql += ' AND start_time < ?' + args.append(until) + with db() as conn: + outages = pd.read_sql(sql, conn, params=args) + outages['start_time'] = pd.to_datetime(outages['start_time']) + + alarms = read_alarms(outages['ne_id'].unique(), categories) + pairs = outages.merge(alarms, left_on=['ne_id', 'cause_category'], right_on=['ne_id', 'category']) + lead = (pairs['start_time'] - pairs['alarm_time']).dt.total_seconds() / 60 + usable = still_active(pairs['clear_time'], pairs['start_time']) & (lead >= -5) & (lead <= WINDOW_MAX) + pairs = pairs[usable].assign(lead=lead[usable].clip(lower=0)) + nearest = pairs.sort_values('lead').drop_duplicates('id') + + now = datetime.now().strftime(TIME_FMT) + result = {} + rows = [] + for category in categories: + leads = nearest.loc[nearest['cause_category'] == category, 'lead'] + default = DEFAULT_WINDOW[category] + if len(leads) >= CALIB_MIN_SAMPLES: + window = float(min(max(leads.quantile(CALIB_QUANTILE), default), WINDOW_MAX)) + source = '历史标定' + else: + window = float(default) + source = '默认(样本不足)' + result[category] = round(window, 1) + rows.append((category, round(window, 1), default, int(len(leads)), source, now)) + with db() as conn: + conn.execute('DELETE FROM windows') + conn.executemany('INSERT INTO windows VALUES(?,?,?,?,?,?)', rows) + return result + + +def load_windows(): + """当前使用的时间窗 {类别: 分钟};未标定的类别用默认窗口。""" + windows = dict(DEFAULT_WINDOW) + for row in query('SELECT category, window_min FROM windows'): + if row['category'] in windows and row['window_min']: + windows[row['category']] = row['window_min'] + return windows + + +def window_table(): + """时间窗明细(页面展示用)。""" + saved = {row['category']: row for row in query('SELECT * FROM windows')} + rows = [] + for category, _, default in RULES: + row = saved.get(category) or {'window_min': default, 'samples': 0, 'source': '默认', 'updated_at': ''} + rows.append(dict(category=category, priority=PRIORITY[category] + 1, default_min=default, + window_min=row['window_min'], samples=row['samples'], source=row['source'], + updated_at=row['updated_at'])) + return rows + + +def analyze(outages, windows=None): + """ + 三级根因判定。outages 需含 id, ne_id, start_time, end_time 四列,返回 [(根因, 证据, 置信度, id), ...]。 + 预处理 衍生告警归并:告警带 parent_alarm_id 且父告警属于根因类别时,按父告警的类别和名称计 + (如停电引起的传输告警归为电源故障); + 第一级 衍生关系(置信度高):同站“小区退服”告警与退服开始相差不超过 MATCH_TOL_MIN 分钟、且带父告警, + 直接取父告警类别; + 第二级 时间窗(置信度中):同站在退服时仍未清除、提前量在该类时间窗内的告警; + 第三级 疑似(置信度低):时间窗放宽到 SUSPECT_FACTOR 倍才命中的告警,提示人工复核; + 多条命中时依次比较:级别 → 是否随业务恢复清除(清除与恢复相差 ≤ CLEAR_TOL_MIN 分钟)→ 规则优先级 → 时间早; + 都没有命中判为“其他”。 """ if outages.empty: return [] + windows = windows or load_windows() - # 只取涉及到的基站的告警,避免全表读取 - ne_ids = tuple(outages['ne_id'].dropna().unique()) - placeholders = ','.join('?' * len(ne_ids)) - with db() as conn: - alarms = pd.read_sql(f'SELECT alarm_id, ne_id, alarm_name, category, start_time, clear_time, parent_alarm_id ' - f'FROM alarms WHERE ne_id IN ({placeholders})', conn, params=ne_ids, - parse_dates=['start_time', 'clear_time']) - alarms = alarms.rename(columns={'start_time': 'alarm_time'}) - - outages = outages[['id', 'ne_id', 'start_time']].copy() + outages = outages[['id', 'ne_id', 'start_time', 'end_time']].copy() outages['start_time'] = pd.to_datetime(outages['start_time']) + outages['end_time'] = pd.to_datetime(outages['end_time']) + alarms = read_alarms(outages['ne_id'].dropna().unique()) - results = {} # 退服 id -> (根因, 证据) + # ---- 预处理:衍生告警按父告警计 + alarms['root_cat'] = alarms['category'] + alarms['root_name'] = alarms['alarm_name'] + parents = alarms.drop_duplicates('alarm_id').set_index('alarm_id') + parent_id = alarms['parent_alarm_id'].fillna('') + parent_cat = parent_id.map(parents['category']) + linked = parent_cat.isin(DEFAULT_WINDOW) + alarms.loc[linked, 'root_cat'] = parent_cat[linked] + alarms.loc[linked, 'root_name'] = parent_id[linked].map(parents['alarm_name']) + # 证据里显示的告警名:衍生告警写成“传输告警(衍生自 市电停电)” + alarms['show_name'] = alarms['alarm_name'] + alarms.loc[linked, 'show_name'] = alarms.loc[linked, 'alarm_name'] + '(衍生自 ' + alarms.loc[linked, 'root_name'] + ')' - # ---- 第一级:衍生关系。找到带父告警的“小区退服”告警,再查出父告警的类别 - child_alarms = alarms[(alarms['category'] == '小区退服') & alarms['parent_alarm_id'].fillna('').ne('')] - child_alarms = child_alarms[['ne_id', 'alarm_time', 'parent_alarm_id']].rename(columns={'alarm_time': 'start_time'}) - parent_alarms = alarms.drop(columns=['ne_id', 'parent_alarm_id']) - child_with_parent = child_alarms.merge(parent_alarms, left_on='parent_alarm_id', right_on='alarm_id') - matched = outages.merge(child_with_parent, on=['ne_id', 'start_time']).drop_duplicates('id') + results = {} # 退服 id -> (根因, 证据, 置信度) + + # ---- 第一级:衍生关系 + child = alarms[(alarms['category'] == '小区退服') & linked][['ne_id', 'alarm_time', 'root_cat', 'root_name']] + matched = outages.merge(child, on='ne_id') + gap = (matched['alarm_time'] - matched['start_time']).abs() + matched = matched[gap <= pd.Timedelta(minutes=MATCH_TOL_MIN)].assign(gap=gap) + matched = matched.sort_values(['id', 'gap']).drop_duplicates('id') for row in matched.itertuples(): - if row.category in CAUSES: - evidence = f'衍生关系:{row.alarm_name}@{row.alarm_time:%m-%d %H:%M}' - results[row.id] = (row.category, evidence) + results[row.id] = (row.root_cat, f'衍生关系:{row.root_name} → 小区退服@{row.alarm_time:%m-%d %H:%M}', '高') - # ---- 第二级:时间窗。把剩余退服与同站的根因类告警两两配对,逐条规则打标 + # ---- 第二、三级:时间窗与疑似 remaining = outages[~outages['id'].isin(results)] - pairs = remaining.merge(alarms[alarms['category'] != '小区退服'], on='ne_id') - minutes_before = (pairs['start_time'] - pairs['alarm_time']).dt.total_seconds() / 60 - # 告警在退服时仍未清除(允许 1 分钟误差)才可能是原因 - still_active = pairs['clear_time'].isna() | (pairs['clear_time'] >= pairs['start_time'] - pd.Timedelta(minutes=1)) + candidates = alarms[(alarms['category'] != '小区退服') & alarms['root_cat'].isin(DEFAULT_WINDOW)] + pairs = remaining.merge(candidates, on='ne_id') + lead = (pairs['start_time'] - pairs['alarm_time']).dt.total_seconds() / 60 + window = pairs['root_cat'].map(windows).astype(float) + active = still_active(pairs['clear_time'], pairs['start_time']) & (lead >= -5) + pairs['tier'] = np.select([active & (lead <= window), active & (lead <= window * SUSPECT_FACTOR)], [0, 1], 9) + clear_gap = (pairs['clear_time'] - pairs['end_time']).abs() + pairs['sync'] = clear_gap <= pd.Timedelta(minutes=CLEAR_TOL_MIN) + pairs['unsync'] = ~pairs['sync'] + pairs['prio'] = pairs['root_cat'].map(PRIORITY) - pairs['rank'] = 99 # 命中规则的序号,越小优先级越高;99 表示没有命中 - for rank, (category, _, window) in enumerate(RULES): - hit = ((pairs['category'] == category) & (minutes_before <= window) & (minutes_before >= -5) - & still_active & (pairs['rank'] > rank)) - pairs.loc[hit, 'rank'] = rank - - # 每条退服取优先级最高、时间最早的一条告警作为根因 - best = pairs[pairs['rank'] < 99].sort_values(['id', 'rank', 'alarm_time']).drop_duplicates('id') + best = pairs[pairs['tier'] < 9].sort_values(['id', 'tier', 'unsync', 'prio', 'alarm_time']).drop_duplicates('id') for row in best.itertuples(): - evidence = f'时间窗:{row.alarm_name}@{row.alarm_time:%m-%d %H:%M}' - results[row.id] = (RULES[row.rank][1], evidence) + sync_note = ',随业务恢复清除' if row.sync else '' + if row.tier == 0: + results[row.id] = (row.root_cat, f'时间窗:{row.show_name}@{row.alarm_time:%m-%d %H:%M}{sync_note}', '中') + else: + results[row.id] = (row.root_cat, f'疑似(超出时间窗):{row.show_name}@{row.alarm_time:%m-%d %H:%M}' + f'{sync_note},建议人工复核', '低') output = [] for outage_id in outages['id']: - cause, evidence = results.get(outage_id, ('其他', '时间窗内无关联告警')) - output.append((cause, evidence, int(outage_id))) + cause, evidence, confidence = results.get(outage_id, ('其他', '时间窗内无关联告警', '低')) + output.append((cause, evidence, confidence, int(outage_id))) return output -def analyze_all(ids=None): - """对指定 id(不传则全部)的退服流水重新做根因分析并写回数据库,返回分析条数。""" - sql = 'SELECT id, ne_id, start_time FROM outages' - if ids: - sql += ' WHERE id IN (' + ','.join(str(i) for i in ids) + ')' +def analyze_all(ids=None, recalibrate=True): + """ + 对指定 id 的退服流水(ids=None 表示全部)重新做根因分析并写回数据库,返回分析条数。 + 全量分析前先按历史流水重新标定时间窗(recalibrate=False 时沿用已有窗口)。 + """ + if ids is not None and len(ids) == 0: + return 0 + if ids is None and recalibrate: + calibrate_windows() + + sql = 'SELECT id, ne_id, start_time, end_time FROM outages' + if ids is not None: + sql += ' WHERE id IN (' + ','.join(str(int(i)) for i in ids) + ')' with db() as conn: outages = pd.read_sql(sql, conn) results = analyze(outages) with db() as conn: - conn.executemany('UPDATE outages SET root_cause=?, evidence=? WHERE id=?', results) + conn.executemany('UPDATE outages SET root_cause=?, evidence=?, confidence=? WHERE id=?', results) data_changed() return len(results) +def association(filters=None): + """ + 告警类别与退服的关联强度,规则为“同站出现 X 类告警 → 其后 W 分钟内发生退服”(W 为该类时间窗): + 告警数 n_A、命中数 n_AB(其后 W 分钟内同站发生退服的告警数) + 支持度 support = 开始前 W 分钟内同站有 X 类告警的退服数 ÷ 退服总数,即 P(X 类告警 | 退服) + 置信度 confidence = n_AB ÷ n_A,即 P(退服 | X 类告警) + 提升度 lift = 置信度 ÷ P0,P0 = 退服数 × W ÷(站点数 × 统计时长),即随机一个 W 分钟窗口内遇到退服的概率 + 提升度 > 1 说明该类告警出现后退服概率高于随机水平,数值越大关联越强。 + """ + filters = filters or {} + df = frame(filters) + lo, hi = period_bounds(filters) + minutes = max((hi - lo).total_seconds() / 60, 1440) + n_sites = max(site_count(filters), 1) + windows = load_windows() + + site_where, site_args = site_conditions(filters) + ne_ids = [row['ne_id'] for row in query('SELECT ne_id FROM sites' + site_where, site_args)] + alarms = read_alarms(ne_ids, list(DEFAULT_WINDOW)) + alarms = alarms[(alarms['alarm_time'] >= lo) & (alarms['alarm_time'] < hi)] + outages = df[['id', 'ne_id', 'start']].dropna().sort_values('start') + + rows = [] + for category, _, _ in RULES: + window = windows[category] + tolerance = pd.Timedelta(minutes=window) + cat_alarms = alarms.loc[alarms['category'] == category, ['ne_id', 'alarm_time']].sort_values('alarm_time') + hits = 0 + if len(cat_alarms) and len(outages): + forward = pd.merge_asof(cat_alarms, outages, left_on='alarm_time', right_on='start', by='ne_id', + direction='forward', tolerance=tolerance) + hits = int(forward['start'].notna().sum()) + covered = 0 + if len(cat_alarms) and len(outages): + backward = pd.merge_asof(outages, cat_alarms, left_on='start', right_on='alarm_time', by='ne_id', + direction='backward', tolerance=tolerance) + covered = int(backward['alarm_time'].notna().sum()) + p0 = min(len(outages) * window / (n_sites * minutes), 1) if len(outages) else 0 + confidence = hits / len(cat_alarms) if len(cat_alarms) else 0 + rows.append(dict( + category=category, window_min=window, alarms=len(cat_alarms), hits=hits, + support=round(covered / len(outages) * 100, 2) if len(outages) else 0, + confidence=round(confidence * 100, 2), + lift=round(confidence / p0, 2) if p0 else 0, + )) + return rows + + # ================================================================ 6. 指标核算 +def site_cover(): + """ + 各站覆盖补偿系数 {ne_id: 系数}:COVER_RADIUS_M 米内的邻站数 n,系数 = max(COVER_FLOOR, 1 − COVER_STEP × n), + 室分站递减幅度减半。距离按经纬度近似换算(城市范围内误差可忽略);没有经纬度的站系数为 1。 + """ + sites = pd.DataFrame(query('SELECT ne_id, site_type, lng, lat FROM sites')) + if sites.empty: + return {} + sites = sites.dropna(subset=['lng', 'lat']) + if sites.empty: + return {} + lat0 = np.radians(sites['lat'].astype(float).mean()) + x = sites['lng'].to_numpy(float) * 111320 * np.cos(lat0) + y = sites['lat'].to_numpy(float) * 110540 + neighbors = np.zeros(len(sites), dtype=int) + for begin in range(0, len(sites), 1000): # 分块计算,站点很多时不会一次占用大量内存 + dx = x[begin:begin + 1000, None] - x[None, :] + dy = y[begin:begin + 1000, None] - y[None, :] + neighbors[begin:begin + 1000] = ((dx * dx + dy * dy) <= COVER_RADIUS_M ** 2).sum(axis=1) - 1 + step = np.where(sites['site_type'].eq('室分'), COVER_STEP / 2, COVER_STEP) + factor = np.clip(1 - step * neighbors, COVER_FLOOR, 1) + return dict(zip(sites['ne_id'], factor.round(3))) + + def full_frame(): """ 全部退服流水 + 站点信息 + 场景阈值,并计算派生字段: - is_long 是否超长、dur_diff 上报时长差错、affected_users 受影响用户、loss_gb 业务损失、level 断站分级。 + is_long 是否超长、dur_diff 上报时长差错、cover_factor 覆盖补偿系数、affected_users 受影响用户、 + user_hours 受影响用户·小时、loss_gb 业务损失、level 断站分级。 结果缓存到数据变化为止(见 data_changed)。 """ global _frame_cache @@ -319,11 +541,18 @@ def full_frame(): df['is_long'] = df['duration_min'] >= long_min df['dur_diff'] = (df['reported_min'] - df['duration_min']).abs() > 1 # 人工上报时长与系统计算相差超过 1 分钟 - # 影响评估:受影响用户 = 小区数 × 单小区在线用户 × 忙闲时系数;业务损失 = 小区数 × 单小区话务 × 系数 × 时长 + # 影响评估: + # 受影响用户 = 小区数 × 单小区在线用户 × 忙闲时系数 × 覆盖补偿系数(同一时刻掉线的用户数) + # 受影响用户·小时 = 受影响用户 × 退服时长(小时),反映影响的持续程度 + # 业务损失 = 小区数 × 单小区每小时话务 × 忙闲时系数 × 覆盖补偿系数 × 退服时长(小时) busy_factor = np.where(df['start'].dt.hour.between(9, 22), 1.0, 0.35) # 9-22 点为忙时 cells = df['cells'].fillna(3).astype(float) - df['affected_users'] = (cells * df['users_per_cell'].fillna(200) * busy_factor).round().astype(int) - df['loss_gb'] = (cells * df['gb_per_cell_h'].fillna(10) * busy_factor * df['duration_min'] / 60).round(2) + df['cover_factor'] = df['ne_id'].map(site_cover()).fillna(1.0).astype(float) + hours = df['duration_min'] / 60 + users = cells * df['users_per_cell'].fillna(200) * busy_factor * df['cover_factor'] + df['affected_users'] = users.round().astype(int) + df['user_hours'] = (users * hours).round(1) + df['loss_gb'] = (cells * df['gb_per_cell_h'].fillna(10) * busy_factor * df['cover_factor'] * hours).round(2) # 断站分级(按整列一次计算,比逐行判断快几十倍): # 重要:超长,且是关键场景或时长超过阈值 2 倍 @@ -362,8 +591,49 @@ def frame(filters=None): return df.copy() -def site_count(filters=None): - """满足站点类筛选条件(场景、片区、站型、厂家)的站点数,用作退服率的分母。""" +def period_bounds(filters=None): + """ + 统计周期 [起, 止)。有月份 / 日期范围筛选时取筛选范围(同时有则取交集), + 否则取全部退服流水首日 0 点到末日 24 点。 + """ + filters = filters or {} + df = full_frame() + if df.empty: + today = pd.Timestamp.now().normalize() + lo, hi = today, today + pd.Timedelta(days=1) + else: + lo = df['start'].min().normalize() + hi = df['start'].max().normalize() + pd.Timedelta(days=1) + + lowers = [] + uppers = [] + if filters.get('month'): + month_start = pd.Timestamp(filters['month'] + '-01') + lowers.append(month_start) + uppers.append(month_start + pd.offsets.MonthBegin(1)) + if filters.get('date_from'): + lowers.append(pd.Timestamp(filters['date_from'])) + if filters.get('date_to'): + uppers.append(pd.Timestamp(filters['date_to']) + pd.Timedelta(days=1)) + if lowers: + lo = max(lowers) + if uppers: + hi = min(uppers) + if hi <= lo: + hi = lo + pd.Timedelta(days=1) + return lo, hi + + +def period(filters=None): + """统计周期的 (分钟数, 自然月数):分钟数是退服率的时间分母,月数是“月均”的分母。""" + lo, hi = period_bounds(filters) + minutes = (hi - lo).total_seconds() / 60 + months = len(pd.period_range(lo, hi - pd.Timedelta(seconds=1), freq='M')) + return minutes, max(months, 1) + + +def site_conditions(filters=None): + """站点类筛选(场景、片区、站型、厂家、站名/站号关键字)对应的 WHERE 子句与参数。""" filters = filters or {} column_of = {'scene': 'scene', 'region': 'district', 'site_type': 'site_type', 'vendor': 'vendor'} conditions = [] @@ -372,30 +642,42 @@ def site_count(filters=None): if filters.get(key): conditions.append(f'{column} = ?') args.append(filters[key]) - - sql = 'SELECT COUNT(*) AS n FROM sites' - if conditions: - sql += ' WHERE ' + ' AND '.join(conditions) - return query(sql, args)[0]['n'] + if filters.get('site'): + conditions.append('(instr(site_name, ?) > 0 OR instr(ne_id, ?) > 0)') # 与 frame() 一样区分大小写 + args += [filters['site'], filters['site']] + if not conditions: + return '', [] + return ' WHERE ' + ' AND '.join(conditions), args -def kpis(df, n_sites=None): +def site_count(filters=None): + """满足站点类筛选条件的站点数,用作退服率、重复退服率的分母。""" + where, args = site_conditions(filters) + return query('SELECT COUNT(*) AS n FROM sites' + where, args)[0]['n'] + + +def kpis(df, n_sites=None, minutes=None, months=None): """ - 运维考核指标。 + 运维考核指标。n_sites / minutes / months 为站点数、统计时长(分钟)、统计月数,不传时按全量计算。 退服率 = 总退服时长 ÷(站点数 × 统计时长);网络可用率 = 1 − 退服率 + 重复退服率 = 高频重复站点数 ÷ 站点数 根因判定准确率 = 上报原因与系统判定一致的比例(只统计上报原因已填写的记录) """ - if not n_sites: + if n_sites is None: n_sites = site_count() + if minutes is None or months is None: + default_minutes, default_months = period() + minutes = minutes or default_minutes + months = months or default_months if df.empty: return dict(count=0, total_h=0, avg_min=0, outage_rate=0, availability=100, long_ratio=0, repeat_rate=0, - users=0, loss_gb=0, sites=n_sites, acc=0, dur_fix=0, closed=0) + users=0, user_h=0, loss_gb=0, sites=n_sites, acc=0, dur_fix=0, closed=0) total_minutes = df['duration_min'].sum() - period_minutes = max((df['start'].max() - df['start'].min()).total_seconds() / 60, 1) - outage_rate = total_minutes / (n_sites * period_minutes) * 100 + denominator = max(n_sites, 1) * max(minutes, 1) + outage_rate = total_minutes / denominator * 100 - stats = site_stats(df) + stats = site_stats(df, months) known = df[df['cause_category'].isin(CAUSES) & df['root_cause'].notna()] if len(known): @@ -410,8 +692,9 @@ def kpis(df, n_sites=None): outage_rate=round(outage_rate, 4), availability=round(100 - outage_rate, 4), long_ratio=round(df['is_long'].mean() * 100, 2), - repeat_rate=round(stats['repeat'].mean() * 100, 2), + repeat_rate=round(stats['repeat'].sum() / max(n_sites, 1) * 100, 2), users=int(df['affected_users'].sum()), + user_h=int(round(float(df['user_hours'].sum()))), loss_gb=round(df['loss_gb'].sum(), 1), sites=n_sites, acc=accuracy, @@ -420,19 +703,23 @@ def kpis(df, n_sites=None): ) -def site_stats(df): +def site_stats(df, months=None): """ - 站点维度统计,按累计退服时长从大到小排序。 + 站点维度统计,按累计退服时长从大到小排序。months 为统计周期的自然月数,不传时按全量周期。 超长退服站点 long:月均超长退服 ≥ 1 次 高频重复站点 repeat:月均退服次数 ≥ 场景次数阈值 """ if df.empty: - return pd.DataFrame(columns=['site_name', 'count', 'total_min', 'long', 'repeat']) + return pd.DataFrame(columns=['ne_id', 'site_name', 'region', 'scene', 'site_type', 'count', 'total_min', + 'avg_min', 'max_min', 'long_count', 'users', 'user_h', 'long_min', 'freq_count', + 'top_cause', 'long', 'repeat']) + if months is None: + months = period()[1] stats = df.groupby(['ne_id', 'site_name', 'region', 'scene', 'site_type'], dropna=False).agg( count=('id', 'size'), total_min=('duration_min', 'sum'), avg_min=('duration_min', 'mean'), max_min=('duration_min', 'max'), long_count=('is_long', 'sum'), users=('affected_users', 'sum'), - long_min=('long_min', 'first'), freq_count=('freq_count', 'first'), + user_h=('user_hours', 'sum'), long_min=('long_min', 'first'), freq_count=('freq_count', 'first'), ).reset_index() # 主要根因:每站出现次数最多的根因;次数相同时取名称排序靠前的(与 pandas 的 mode 结果一致) @@ -441,11 +728,12 @@ def site_stats(df): top_cause = cause_counts.drop_duplicates('ne_id').set_index('ne_id')['root_cause'] stats['top_cause'] = stats['ne_id'].map(top_cause).fillna('') - months = max(df['month'].nunique(), 1) + months = max(months, 1) stats['long'] = stats['long_count'] / months >= 1 stats['repeat'] = stats['count'] / months >= stats['freq_count'].fillna(4) stats['total_min'] = stats['total_min'].round(1) stats['avg_min'] = stats['avg_min'].round(1) + stats['user_h'] = stats['user_h'].round(1) return stats.sort_values('total_min', ascending=False) diff --git a/static/js/pages/Impact.js b/static/js/pages/Impact.js index 4f8a5b3..c063575 100644 --- a/static/js/pages/Impact.js +++ b/static/js/pages/Impact.js @@ -9,7 +9,8 @@ const BENCH_COLUMNS = [ {key: 'scene', title: '场景'}, {key: 'sites', title: '站点数'}, {key: 'count', title: '退服次数'}, {key: 'total_h', title: '累计时长(h)'}, {key: 'avg_min', title: '平均时长(min)'}, {key: 'outage_rate', title: '退服率(%)'}, {key: 'availability', title: '可用率(%)'}, {key: 'long_ratio', title: '超长占比(%)'}, {key: 'repeat_rate', title: '重复退服率(%)'}, - {key: 'users', title: '受影响用户', render: num}, {key: 'loss_gb', title: '业务损失(GB)', render: num}, + {key: 'users', title: '受影响用户', render: num}, {key: 'user_h', title: '用户·小时', render: num}, + {key: 'loss_gb', title: '业务损失(GB)', render: num}, ]; /** 场景柱状图配置:最大的场景用强调色标出 */ @@ -24,14 +25,15 @@ export default function Impact() { const {filters} = useApp(); const {data} = useFetch('/api/dashboard', filters); if (!data) return html`<${Loading}/>`; - const {kpi: k, bench} = data; + const {kpi: k, bench, period} = data; return html`
- <${Section} title="影响评估"> + <${Section} title="影响评估" hint=${`统计周期 ${period.days} 天(${period.months} 个月)· ${num(k.sites)} 个站`}>
- <${Kpi} title="受影响用户" value=${num(k.users)} unit="人次" sub="小区数 × 单小区在线用户 × 忙闲时系数"/> - <${Kpi} title="业务损失" value=${num(k.loss_gb)} unit="GB" sub="小区话务 × 退服时长"/> + <${Kpi} title="受影响用户" value=${num(k.users)} unit="人次" sub="小区数 × 单小区在线用户 × 忙闲时 × 覆盖补偿"/> + <${Kpi} title="受影响用户·小时" value=${num(k.user_h)} unit="人·h" sub="受影响用户 × 退服时长"/> + <${Kpi} title="业务损失" value=${num(k.loss_gb)} unit="GB" sub="小区话务 × 忙闲时 × 覆盖补偿 × 退服时长"/> <${Kpi} title="退服率" value=${fixed(k.outage_rate)} unit="%"/> <${Kpi} title="网络可用率" value=${fixed(k.availability)} unit="%"/> <${Kpi} title="平均退服时长" value=${k.avg_min} unit="min"/> @@ -42,8 +44,15 @@ export default function Impact() { <${Section} span=${6} title="分场景退服率" hint="单位:%"> <${EChart} option=${sceneBar(bench, bench.map(x => x.outage_rate))}/> - <${Section} span=${6} title="分场景受影响用户" hint="单位:万人次"> - <${EChart} option=${sceneBar(bench, bench.map(x => +(x.users / 1e4).toFixed(1)))}/> + <${Section} span=${6} title="分场景受影响用户·小时" hint="单位:万人·h"> + <${EChart} option=${sceneBar(bench, bench.map(x => +(x.user_h / 1e4).toFixed(1)))}/> + + <${Section} title="口径说明"> +
+ 退服率 = 总退服时长 ÷(站点数 × 统计周期);统计周期取顶栏的月份 / 日期范围,未筛选时为全部流水首日至末日。 + 重复退服率 = 高频重复站点数 ÷ 站点数。“月均”按统计周期的自然月数计算。 + 覆盖补偿:站点 500 米内每有一个邻站,受影响用户与话务损失下降 10%(室分站 5%),最低保留 40%。 +
<${Section} title="通信场景运维考核指标横向对标"> <${DataTable} rowKey="scene" columns=${BENCH_COLUMNS} rows=${bench}/> diff --git a/static/js/pages/RootCause.js b/static/js/pages/RootCause.js index 3a1cd50..91625cc 100644 --- a/static/js/pages/RootCause.js +++ b/static/js/pages/RootCause.js @@ -7,11 +7,23 @@ import {Cause, LevelTag, Loading, Section, Select, StatusTag} from '../component const PAGE_SIZE = 15; +const WINDOW_COLUMNS = [ + {key: 'priority', title: '优先级'}, {key: 'category', title: '告警类别', render: v => html`<${Cause} value=${v}/>`}, + {key: 'default_min', title: '默认'}, {key: 'window_min', title: '当前'}, {key: 'samples', title: '标定样本', render: num}, + {key: 'source', title: '来源'}, +]; +const ASSOC_COLUMNS = [ + {key: 'category', title: '告警类别', render: v => html`<${Cause} value=${v}/>`}, {key: 'window_min', title: '窗口(分)'}, + {key: 'alarms', title: '告警数', render: num}, {key: 'hits', title: '其后退服', render: num}, + {key: 'support', title: '支持度(%)'}, {key: 'confidence', title: '置信度(%)'}, {key: 'lift', title: '提升度'}, +]; + export default function RootCause() { const {filters, isAdmin} = useApp(); const toast = useToast(); const {data: confusion} = useFetch('/api/confusion', filters); const {data: stats} = useFetch('/api/stats', {...filters, dim: 'root_cause'}); + const {data: assoc, reload: reloadAssoc} = useFetch('/api/association', filters); const [lastRun, setLastRun] = useState(null); const [running, setRunning] = useState(false); @@ -20,6 +32,7 @@ export default function RootCause() { try { const r = await api('/api/analyze', {method: 'POST'}); setLastRun(r); + reloadAssoc(); toast({message: `全量分析完成:${num(r.n)} 条,耗时 ${r.elapsed}s,准确率 ${r.acc}%`, tone: 'success'}); } catch (e) { toast({message: e.message, tone: 'error'}); @@ -27,7 +40,7 @@ export default function RootCause() { setRunning(false); }; - if (!confusion || !stats) return html`<${Loading}/>`; + if (!confusion || !stats || !assoc) return html`<${Loading}/>`; // 交叉矩阵:matrix[i][j] = 上报原因 i、系统判定 j 的条数;对角线 i === j 为判定一致 const {causes, matrix} = confusion; @@ -75,19 +88,32 @@ export default function RootCause() {
<${Section} span=${5} title="根因判定规则" extra=${runButton}>
- 第一级 · 告警衍生关系:“小区退服”告警若带 parent_alarm_id,直接取父告警类别作为根因。
- 第二级 · 时间窗关联:回溯同站在退服前仍未清除的告警,按优先级取首个命中:
- ① 割接施工 30 分钟 ② 电源故障 300 分钟(考虑蓄电池后备)③ 机房环境 180 分钟(考虑过热保护延时)
- ④ 传输中断 15 分钟 ⑤ 天馈故障 30 分钟 ⑥ 设备硬件 15 分钟
- 停电衍生的传输告警因优先级归为电源故障;均未命中判为“其他”,派单现场核查。 + 预处理 · 衍生告警归并:带父告警的告警按父告警类别计(停电引起的传输告警归为电源故障)。
+ 第一级 · 衍生关系(置信度高):与退服开始相差 ≤ 2 分钟的“小区退服”告警带父告警时,取父告警类别。
+ 第二级 · 时间窗(置信度中):同站在退服时仍未清除、提前量在该类时间窗内的告警。
+ 第三级 · 疑似(置信度低):时间窗放宽到 3 倍才命中,提示人工复核。
+ 多条命中时依次比较:级别 → 是否随业务恢复清除(±15 分钟)→ 规则优先级 → 时间早。 + 时间窗在每次全量分析时按已闭环流水的提前量 95% 分位数重新标定(不小于默认值);均未命中判为“其他”。
参与校验${num(total)} 条
判定准确率${total ? (hit / total * 100).toFixed(2) : 0}%
+ ${confusion.by_confidence.map(c => html` +
置信度${c.level}${num(c.n)} 条 / ${c.acc}%
`)}
上次分析${lastRun ? `${num(lastRun.n)} 条 / ${lastRun.elapsed}s` : '—'}
<${Section} span=${7} title="上报原因 × 系统判定根因 交叉矩阵" hint="对角线为判定一致"><${EChart} option=${matrixChart}/> + <${Section} span=${5} title="时间窗标定" hint="单位:分钟"> + <${DataTable} rowKey="category" columns=${WINDOW_COLUMNS} rows=${assoc.windows}/> + + <${Section} span=${7} title="告警 → 退服 关联强度" hint="提升度 > 1 表示该类告警出现后退服概率高于随机"> + <${DataTable} rowKey="category" columns=${ASSOC_COLUMNS} rows=${assoc.rows}/> +
+ 支持度 = 开始前 W 分钟内有该类告警的退服 ÷ 退服总数;置信度 = 其后 W 分钟内发生退服的告警 ÷ 该类告警总数; + 提升度 = 置信度 ÷ 随机一个 W 分钟窗口内遇到退服的概率(W 为该类时间窗)。 +
+ <${Section} title="根因维度统计" hint="柱高为平均退服时长(分钟)"><${EChart} height=${260} option=${causeChart}/> <${AdviceList}/>
`; @@ -108,7 +134,8 @@ function AdviceList() { const columns = [ {key: 'ne_id', title: '基站编号'}, {key: 'site_name', title: '基站名称'}, {key: 'scene', title: '场景'}, {key: 'start_time', title: '退服开始'}, {key: 'duration_min', title: '时长(分)'}, - {key: 'root_cause', title: '根因', render: v => html`<${Cause} value=${v}/>`}, {key: 'evidence', title: '关联告警证据'}, + {key: 'root_cause', title: '根因', render: v => html`<${Cause} value=${v}/>`}, {key: 'confidence', title: '置信度'}, + {key: 'evidence', title: '关联告警证据'}, {key: 'level', title: '分级', render: v => html`<${LevelTag} value=${v}/>`}, {key: 'status', title: '状态', render: v => html`<${StatusTag} value=${v}/>`}, {key: 'advice', title: '处置建议', wrap: true}, diff --git a/tests/harness.py b/tests/harness.py new file mode 100644 index 0000000..0573ede --- /dev/null +++ b/tests/harness.py @@ -0,0 +1,173 @@ +"""测试公共工具:在 tests/_work 下的临时数据库里加载数据集并调用 core 的分析逻辑,不影响 data/outage.db。""" +import os +import random +import sys + +PROJECT = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) +sys.path.insert(0, PROJECT) +WORK = os.path.join(PROJECT, 'tests', '_work') +os.makedirs(WORK, exist_ok=True) +os.environ['OUTAGE_DB'] = os.path.join(WORK, 'app.db') # 必须在 import core 之前设置 + +import pandas as pd # noqa: E402 +from werkzeug.security import generate_password_hash # noqa: E402 + +import core # noqa: E402 +import data_gen # noqa: E402 +import importer # noqa: E402 + +FAILED = [] + + +def check(name, ok, detail=''): + """打印一条检查结果;失败的记入 FAILED,脚本结束时以非 0 退出码返回。""" + print(f" [{'通过' if ok else '失败'}] {name} {detail}") + if not ok: + FAILED.append(name) + + +def finish(): + print('\n全部检查通过' if not FAILED else f'\n{len(FAILED)} 项未通过:' + '、'.join(FAILED)) + sys.exit(1 if FAILED else 0) + + +def use_db(name): + """切换到 tests/_work/.db(删除重建)。""" + path = os.path.join(WORK, f'{name}.db') + if os.path.exists(path): + os.remove(path) + core.DB_PATH = path + core.data_changed() + with core.db() as conn: + conn.executescript(core.SCHEMA) + for scene, values in core.SCENE_DEFAULT.items(): + conn.execute('INSERT INTO scenes VALUES(?,?,?,?,?)', (scene, *values)) + conn.execute("INSERT INTO users(username, password, role, created_at) VALUES('admin', ?, 'admin', '')", + (generate_password_hash('admin123'),)) # 测试库的接口测试账号 + + +def load(name, sites, alarms, outages, calibrate_until=None): + """建库并写入 sites / alarms / outages(全文本 DataFrame),做根因分析,返回 full_frame()。 + calibrate_until 指定时,时间窗只用该日期之前的流水标定(留出检验,避免用测试数据标定)。""" + use_db(name) + with core.db() as conn: + sites.to_sql('sites', conn, if_exists='append', index=False) + core.save_alarms(alarms.astype(object).where(alarms.notna(), None)) + good, _ = importer.validate_outages(outages) + core.save_outages(good) + if calibrate_until: + core.calibrate_windows(until=calibrate_until) + core.analyze_all(recalibrate=False) + else: + core.analyze_all() + core.data_changed() + return core.full_frame() + + +def read_dir(directory): + def read(filename): + return pd.read_csv(os.path.join(directory, filename), encoding='utf-8-sig', dtype=str) + return read('sites.csv'), read('data_alarm.csv'), read('data_outage.csv') + + +def sample_data(): + return read_dir(os.path.join(PROJECT, 'data')) + + +def generate(name, lead=None, rows=6000, seed=2026): + """用 data_gen 生成一份数据到 tests/_work/gen_;lead 可覆盖告警提前量分布。""" + out = os.path.join(WORK, 'gen_' + name) + saved = dict(data_gen.LEAD) + if lead is not None: + data_gen.LEAD.clear() + data_gen.LEAD.update(lead) + try: + data_gen.generate(n=rows, seed=seed, out=out) + finally: + data_gen.LEAD.clear() + data_gen.LEAD.update(saved) + return read_dir(out) + + +def score(df): + """以生成器真值(cause_category)计算总体准确率与各类 precision / recall。""" + d = df[df['cause_category'].isin(core.CAUSES)] + if d.empty: + return 0.0, [] + accuracy = (d['cause_category'] == d['root_cause']).mean() * 100 + rows = [] + for cause in core.CAUSES: + tp = ((d['cause_category'] == cause) & (d['root_cause'] == cause)).sum() + precision = tp / max((d['root_cause'] == cause).sum(), 1) * 100 + recall = tp / max((d['cause_category'] == cause).sum(), 1) * 100 + f1 = 2 * precision * recall / (precision + recall) if precision + recall else 0 + rows.append((cause, round(precision, 1), round(recall, 1), round(f1, 1))) + return round(accuracy, 2), rows + + +# ---------------------------------------------------------------- 扰动工具(固定随机种子,结果可复现) +rng = random.Random(7) + + +def root_alarm_mask(alarms, outages): + """每条退服的“真根因告警”:同站、清除时间 = 退服恢复时间、类别 = 上报原因、本身不是衍生告警。""" + key = set(zip(outages['ne_id'], outages['end_time'], outages['cause_category'])) + parent = alarms['parent_alarm_id'].fillna('') + return pd.Series([(n, c, cat) in key and p == '' + for n, c, cat, p in zip(alarms['ne_id'], alarms['clear_time'], alarms['category'], parent)], + index=alarms.index) + + +def no_parent(alarms, keep=0.0): + """去掉父告警关系(keep 为保留比例)。""" + alarms = alarms.copy() + alarms['parent_alarm_id'] = [p if rng.random() < keep else '' for p in alarms['parent_alarm_id'].fillna('')] + return alarms + + +def drop_root(alarms, outages, fraction): + """随机删掉一部分真根因告警(网管漏报 / 动环未接入)。""" + mask = root_alarm_mask(alarms, outages) + drop = [i for i in alarms.index[mask] if rng.random() < fraction] + return alarms.drop(drop) + + +def skew_cell_alarm(alarms, max_seconds=120): + """“小区退服”告警时刻比工单开始时间晚 5~max_seconds 秒(两套系统时钟不同步)。""" + alarms = alarms.copy() + is_cell = alarms['category'] == '小区退服' + times = pd.to_datetime(alarms.loc[is_cell, 'start_time']) + times = times + pd.to_timedelta([rng.randint(5, max_seconds) for _ in range(len(times))], unit='s') + alarms.loc[is_cell, 'start_time'] = times.dt.strftime(core.TIME_FMT) + return alarms + + +def jitter_clear(alarms, outages, max_minutes=10): + """真根因告警的清除时刻与业务恢复不再完全相同,随机偏移 ±max_minutes 分钟。""" + alarms = alarms.copy() + mask = root_alarm_mask(alarms, outages) + times = pd.to_datetime(alarms.loc[mask, 'clear_time']) + times = times + pd.to_timedelta([rng.randint(-max_minutes * 60, max_minutes * 60) for _ in range(len(times))], + unit='s') + alarms.loc[mask, 'clear_time'] = times.dt.strftime(core.TIME_FMT) + return alarms + + +def add_noise(alarms, outages, fraction): + """一部分退服开始前 0~12 分钟出现一条无关的短时告警(与 data_gen 的干扰告警同分布)。""" + rows = [] + for ne_id, start in zip(outages['ne_id'], pd.to_datetime(outages['start_time'])): + if rng.random() < fraction: + category = rng.choice(['传输中断', '设备硬件', '天馈故障', '机房环境']) + begin = start - pd.Timedelta(minutes=rng.randint(0, 12)) + end = begin + pd.Timedelta(minutes=rng.randint(2, 30)) + rows.append(dict(alarm_id=f'NZ{len(rows):07d}', ne_id=ne_id, alarm_code='', alarm_name='干扰' + category, + alarm_level='次要', category=category, start_time=begin.strftime(core.TIME_FMT), + clear_time=end.strftime(core.TIME_FMT), duration_s='', cleared='是', + parent_alarm_id='')) + return pd.concat([alarms, pd.DataFrame(rows)], ignore_index=True) + + +# 比 data_gen 默认更宽的告警提前量(传输/设备也可能提前半小时,停电后备可达 7 小时) +WIDE_LEAD = {'电源故障': (10, 420), '机房环境': (10, 240), '割接施工': (0, 45), '天馈故障': (0, 45), + '传输中断': (0, 30), '设备硬件': (0, 30)} diff --git a/tests/test_kpi.py b/tests/test_kpi.py new file mode 100644 index 0000000..d84f787 --- /dev/null +++ b/tests/test_kpi.py @@ -0,0 +1,87 @@ +"""考核指标口径、影响评估与关联量化检验(仓库样例数据)。 + +运行:python tests/test_kpi.py +""" +import calendar + +from harness import check, core, finish, load, sample_data # 先导入 harness:它把数据库指向 tests/_work + +import app as webapp # noqa: E402 + +s, a, o = sample_data() +full = load('kpi', s, a, o) +N = core.site_count() +DAYS = 273 # 样例数据 2026-01-01 ~ 2026-09-30 + + +def calendar_rate(df, n_sites, days): + return round(df['duration_min'].sum() / (n_sites * days * 1440) * 100, 4) + + +print('== 1. 统计周期') +minutes, months = core.period() +check('全量周期 = 273 天、9 个月', (round(minutes / 1440), months) == (DAYS, 9), f'({minutes / 1440} 天, {months} 月)') +check('全量退服率按日历周期', core.kpis(full, N)['outage_rate'] == calendar_rate(full, N, DAYS)) +for m in ['2026-02', '2026-07']: + f = {'month': m} + days = calendar.monthrange(*map(int, m.split('-')))[1] + k = core.kpis(core.frame(f), N, *core.period(f)) + check(f'{m} 月退服率按 {days} 天', k['outage_rate'] == calendar_rate(core.frame(f), N, days), f'({k["outage_rate"]}%)') + +print('\n== 2. 稀疏筛选') +counts = full.groupby('ne_id').size().sort_values() +ne = counts.index[0] +f = {'site': ne} +df = core.frame(f) +k = core.kpis(df, core.site_count(f), *core.period(f)) +check('单站筛选分母为 1 个站', k['sites'] == 1, f'({k["sites"]})') +check('单站退服率按 273 天', k['outage_rate'] == calendar_rate(df, 1, DAYS), f'({k["outage_rate"]}%)') +day = df['start_time'].iloc[0][:10] +f = {'site': ne, 'date_from': day, 'date_to': day} +df = core.frame(f) +k = core.kpis(df, core.site_count(f), *core.period(f)) +check('单站单日退服率按 1 站 × 1 天', k['outage_rate'] == calendar_rate(df, 1, 1), f'({k["outage_rate"]}%)') + +print('\n== 3. 月均口径:单独查看一个站与全量查看判定一致') +whole = core.site_stats(full, months).set_index('ne_id') +flips = 0 +for ne in whole.index: + f = {'site': ne} + one = core.site_stats(core.frame(f), core.period(f)[1]).set_index('ne_id').loc[ne] + flips += (bool(one['long']) != bool(whole.loc[ne, 'long'])) + (bool(one['repeat']) != bool(whole.loc[ne, 'repeat'])) +check('超长 / 高频判定翻转数为 0', flips == 0, f'({flips})') +check('重复退服率分母为全部站点', core.kpis(full, N)['repeat_rate'] == round(whole['repeat'].sum() / N * 100, 2)) + +print('\n== 4. 导出与看板同一口径') +client = webapp.app.test_client() +client.post('/login', json={'username': 'admin', 'password': 'admin123'}) +for scene in core.SCENES: + dash = client.get('/api/dashboard', query_string={'scene': scene}).get_json()['kpi']['outage_rate'] + f = {'scene': scene} + exported = core.kpis(core.frame(f), core.site_count(f), *core.period(f))['outage_rate'] + check(f'{scene} 看板 = 导出', dash == exported, f'({dash}% / {exported}%)') +response = client.get('/api/export/stats', query_string={'scene': '商圈'}) +check('导出接口可用', response.status_code == 200) + +print('\n== 5. 影响评估') +corr = full['user_hours'].corr(full['duration_min']) +check('受影响用户·小时与时长正相关(修复前受影响用户与时长 r = 0.03)', corr > 0.5, f'(r = {corr:.3f})') +expected = full['affected_users'] * full['duration_min'] / 60 +relative = ((full['user_hours'] - expected).abs() / expected.clip(lower=1)).max() +check('用户·小时 = 受影响用户 × 时长', relative < 0.02, f'(最大相对误差 {relative:.4f},来自用户数取整)') +check('覆盖补偿系数在 [0.4, 1]', full['cover_factor'].between(core.COVER_FLOOR, 1).all(), + f'(均值 {full["cover_factor"].mean():.2f})') +isolated = core.site_cover() +check('有邻站的站补偿系数 < 1', min(isolated.values()) < 1) +print(f' 用户·小时合计 {core.kpis(full, N)["user_h"]:,.0f},覆盖补偿系数分布 ' + f'{full.drop_duplicates("ne_id")["cover_factor"].value_counts().sort_index().to_dict()}') + +print('\n== 6. 告警—退服关联量化') +rows = core.association() +for r in rows: + print(f' {r["category"]:<6} 窗口 {r["window_min"]:>6} 分 告警 {r["alarms"]:>5} 支持度 {r["support"]:>6}% ' + f'置信度 {r["confidence"]:>6}% 提升度 {r["lift"]:>6}') +check('6 类告警均有关联指标', len(rows) == 6 and all(r['alarms'] > 0 for r in rows)) +check('各类提升度 > 1(告警出现后退服概率高于随机)', all(r['lift'] > 1 for r in rows)) +check('关联接口可用', client.get('/api/association').status_code == 200) +finish() diff --git a/tests/test_rootcause.py b/tests/test_rootcause.py new file mode 100644 index 0000000..1bd975f --- /dev/null +++ b/tests/test_rootcause.py @@ -0,0 +1,54 @@ +"""根因判定准确率检验:基线 + 6 组扰动数据集,时间窗只用 1~6 月流水标定,在 7~9 月(留出集)上计分。 + +运行:python tests/test_rootcause.py +""" +from harness import (WIDE_LEAD, add_noise, check, core, drop_root, finish, generate, jitter_clear, load, no_parent, + sample_data, score, skew_cell_alarm) + +SPLIT = '2026-07-01' # 之前的流水用于标定时间窗,之后的用于计分 + +s, a, o = sample_data() +sw, aw, ow = generate('wide', lead=WIDE_LEAD) + +# (名称, 数据, 准确率下限);下限为 None 的只报告不判定——根因告警缺失时,缺失的那部分本来就无法从告警判出 +SCENARIOS = [ + ('S0 基线(仓库样例数据)', (s, a, o), 90), + ('S1 去掉父告警(只靠时间窗)', (s, no_parent(a), o), 90), + ('S2 小区退服告警时刻偏 5-120 秒', (s, skew_cell_alarm(a), o), 90), + ('S3 S1 + 20% 根因告警缺失', (s, drop_root(no_parent(a), o, .2), o), None), + ('S4 S1 + 30% 退服前干扰告警', (s, add_noise(no_parent(a), o, .3), o), 90), + ('S5 S1 + 告警提前量变宽', (sw, no_parent(aw), ow), 90), + ('S6 综合(S5 + 时刻偏移 + 30% 父告警 + 清除时刻 ±10 分 + 15% 缺失 + 25% 干扰)', + # 先删根因告警再扰动清除时刻:drop_root 靠“清除时间 = 恢复时间”识别根因告警 + (sw, add_noise(jitter_clear(skew_cell_alarm(drop_root(no_parent(aw, keep=.3), ow, .15)), ow), ow, .25), ow), + None), +] + +summary = [] +for name, (sites, alarms, outages), floor in SCENARIOS: + df = load('rootcause', sites, alarms, outages, calibrate_until=SPLIT) + test = df[df['start_time'] >= SPLIT] + accuracy, rows = score(test) + other = (test['root_cause'] == '其他').mean() * 100 + print(f'\n== {name}\n 留出集 {len(test)} 条,准确率 {accuracy}%,判为“其他” {other:.1f}%') + print(' 类别 precision recall F1') + for cause, precision, recall, f1 in rows: + print(f' {cause:<8} {precision:>7} {recall:>7} {f1:>6}') + confidence = test.groupby('confidence').apply(lambda x: (x['cause_category'] == x['root_cause']).mean() * 100, + include_groups=False).round(1) + print(' 各置信度准确率:', confidence.to_dict(), ' 条数:', test['confidence'].value_counts().to_dict()) + print(' 时间窗:', {w['category']: w['window_min'] for w in core.window_table()}) + summary.append((name, accuracy)) + if floor is not None: + check(f'{name.split()[0]} 准确率 ≥ {floor}%', accuracy >= floor, f'({accuracy}%)') + else: + # 缺失场景的理论上限:真根因告警仍在的比例;判定应接近它,且“高/中”置信度的判定仍应可靠 + reliable = test[test['confidence'].isin(['高', '中'])] + rel_acc = (reliable['cause_category'] == reliable['root_cause']).mean() * 100 + check(f'{name.split()[0]} 高/中置信度判定准确率 ≥ 90%', rel_acc >= 90, f'({rel_acc:.1f}%,' + f'占 {len(reliable) / len(test) * 100:.0f}%)') + +print('\n汇总(留出集准确率):') +for name, accuracy in summary: + print(f' {accuracy:>6}% {name}') +finish()