Files
Gset/data_gen.py
T
treeandClaude Opus 5.5 0e070a64fe P1:闭环时限管控、治理成效评估、站型阈值系数与接口测试
- 闭环状态流转自动记录接单/闭环时间,状态值校验;按断站分级判定响应时限
  (及时/超时/超时未响应/未到期/无记录),新增及时响应率、平均闭环时长、超时未闭环指标与筛选
- 新增治理成效评估 /api/effect:分界日期前后指标对比与问题站点逐站改善判定
- 新增站型阈值系数(实际阈值 = 场景阈值 × 站型系数)及配置接口与页面
- 样例数据新增接单/闭环时间(独立随机数,原字段不变),导入支持并校验
- 新增 tests/test_api.py(权限、导入模板、闭环流程、站型系数、成效评估、无数据边界)
- 修复:新流水无告警匹配时根因分析报错;空筛选时超长站点清单返回 500

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 15:14:06 +08:00

305 lines
17 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.
# -*- coding: utf-8 -*-
"""
第 18 题 · 基站退服数据生成器(Data-Generated-Core-Py/data.py 的改进版)
================================================================
字段口径与 data.py 完全一致:
data_outage.csv 退服记录 record_id, ne_id, cell_id, district, vendor, start_time, end_time,
duration_min, cause_category, cause_detail, cause_code, ticket_id, closed,
handle_time, close_time(后两列为本版新增:接单时间、闭环时间)
data_alarm.csv 告警流 alarm_id, ne_id, alarm_code, alarm_name, alarm_level, category,
start_time, clear_time, duration_s, cleared, parent_alarm_id
sites.csv 站点库 ne_id, site_name, district, scene, site_type, vendor, cells, lng, lat
相对 data.py 的改进(对齐 _数据集总索引.md 第 18 题要求:站号、起止时间、原因码、厂家、片区):
1. 新增站点库:南宁 7 个城区 × 5 类通信场景 × 3 类站型,站号固定,退服可按站点汇聚;
2. 新增原因码 cause_code,编码体系参照《中兴 5G NR 基站日常故障处理指导手册》章节;
3. 退服与告警联动生成:每次退服产生“小区退服”告警及对应根因告警(含衍生关系 parent_alarm_id),
另混入背景告警与时间窗内的干扰告警,用于检验根因关联算法;
4. 约 1.5% 的上报时长存在人工计算错误,用于检验系统自动计算与核对;
5. 分布贴近现网:长尾时长(沿用 data.py 分段)、问题站点重复退服、夏季雷雨停电高发、割接集中在凌晨。
数据为合成数据,论文中须注明。仅依赖标准库,可单独运行:python data_gen.py --rows 6000
注意:固定随机种子保证每次生成的数据完全相同。修改代码时不要调整随机数的调用顺序,否则数据会变化。
"""
import argparse
import csv
import datetime
import os
import random
DISTRICTS = { # 片区 -> 中心经纬度
'青秀区': (108.385, 22.816), '兴宁区': (108.368, 22.853), '江南区': (108.273, 22.781),
'西乡塘区': (108.306, 22.836), '良庆区': (108.393, 22.752), '邕宁区': (108.487, 22.758), '武鸣区': (108.275, 23.159),
}
VENDORS = ['厂家A', '厂家B', '厂家C']
# 场景 -> [(片区, 地标)] 地标名用于生成站名,均为南宁城区真实地名
LANDMARKS = {
'商圈': [('青秀区', '万象城'), ('青秀区', '航洋国际'), ('青秀区', '东盟商务区'), ('兴宁区', '朝阳广场'),
('兴宁区', '三街两巷'), ('江南区', '沙井万达'), ('西乡塘区', '西大商圈'), ('良庆区', '五象万达')],
'高校': [('西乡塘区', '广西大学'), ('西乡塘区', '广西民族大学'), ('青秀区', '广西医科大学'),
('西乡塘区', '南宁师范大学'), ('邕宁区', '南宁学院'), ('武鸣区', '武鸣大学城')],
'交通枢纽': [('青秀区', '南宁东站'), ('西乡塘区', '南宁火车站'), ('江南区', '吴圩国际机场'),
('江南区', '江南客运站'), ('青秀区', '埌东客运站'), ('西乡塘区', '安吉客运站')],
'城中村': [('江南区', '沙井村'), ('西乡塘区', '秀厢村'), ('西乡塘区', '石埠'), ('兴宁区', '三塘'),
('良庆区', '大沙田'), ('邕宁区', '蒲庙'), ('武鸣区', '城厢'), ('青秀区', '长塘')],
'工业园区': [('西乡塘区', '高新区'), ('江南区', '经开区'), ('武鸣区', '东盟经开区'),
('邕宁区', '新兴产业园'), ('良庆区', '五象产业园')],
}
# 场景 -> (每个地标站点数, 站型权重[宏站, 室分, 分布式皮基站], 退服倾向系数)
SCENE_CFG = {
'商圈': (6, [3, 4, 3], 0.9), '高校': (6, [5, 3, 2], 0.8), '交通枢纽': (6, [4, 4, 2], 0.7),
'城中村': (5, [9, 1, 0], 1.6), '工业园区': (5, [8, 2, 0], 1.2),
}
TYPE_CODE = {'宏站': '宏站', '室分': '室分', '分布式皮基站': '皮站'} # 站型 -> 站名中的简写
# 原因大类 / 细项 / 原因码(参照中兴手册章节)—— 大类与细项沿用 data.py
CAUSES = {
'传输中断': [('光缆被挖断', 'TR01'), ('光模块损坏', 'TR02'), ('传输误码超限', 'TR03'), ('上游设备掉电', 'TR04')],
'电源故障': [('市电停电', 'PW01'), ('蓄电池失效', 'PW02'), ('开关电源模块故障', 'PW03')],
'设备硬件': [('BBU 主控板故障', 'HW01'), ('RRU 功放故障', 'HW02'), ('GPS 失锁', 'HW03'), ('单板复位', 'HW04')],
'天馈故障': [('驻波比超标', 'AN01'), ('馈线进水', 'AN02'), ('天线被破坏', 'AN03')],
'机房环境': [('空调故障', 'EN01'), ('机房高温', 'EN02'), ('漏水', 'EN03')],
'割接施工': [('计划割接', 'OP01'), ('施工误碰光缆', 'OP02'), ('设备搬迁', 'OP03')],
'其他': [('原因待查', 'OT01'), ('业主断电', 'OT02')],
}
# 各场景原因大类权重,顺序同 CAUSES(城中村停电多、园区施工多、室分为主场景机房/业主问题多)
CAUSE_W = {
'商圈': [22, 20, 18, 6, 12, 10, 12], '高校': [24, 24, 20, 8, 8, 10, 6], '交通枢纽': [26, 18, 24, 8, 8, 12, 4],
'城中村': [22, 38, 14, 10, 6, 4, 6], '工业园区': [30, 20, 14, 8, 6, 18, 4],
}
# 告警库:沿用 data.py ALARM_LIB,补充 ALM-113~116 以覆盖割接、主控板、开关电源、漏水
ALARM_LIB = {
'小区退服': ('ALM-101', '小区退服', '严重'),
'传输中断': [('ALM-102', 'BBU 链路断', '严重'), ('ALM-103', '光模块收发异常', '重要'), ('ALM-110', '传输误码超限', '次要')],
'电源故障': [('ALM-105', '市电停电', '严重'), ('ALM-106', '蓄电池欠压', '重要'), ('ALM-115', '开关电源模块故障', '重要')],
'设备硬件': [('ALM-114', 'BBU 主控板故障', '严重'), ('ALM-111', 'PRRU 离线', '重要'), ('ALM-108', 'GPS 失锁', '次要'),
('ALM-112', '时钟不同步', '次要')],
'天馈故障': [('ALM-104', 'RRU 驻波比过高', '重要'), ('ALM-109', 'VSWR 告警', '重要')],
'机房环境': [('ALM-107', '机房温度过高', '重要'), ('ALM-116', '机房水浸告警', '重要')],
'割接施工': [('ALM-113', '网元人工闭塞/复位', '次要')],
}
# 根因告警相对退服开始的提前量(分钟):停电有蓄电池后备、高温有过热保护延时;未列出的类别为 (0, 8)
LEAD = {'电源故障': (20, 240), '机房环境': (15, 150), '割接施工': (0, 20), '天馈故障': (0, 25)}
T0 = datetime.datetime(2026, 1, 1)
DAYS = 273 # 2026-01-01 ~ 2026-09-30
MONTH_W = [0.8, 0.75, 0.9, 1.0, 1.15, 1.35, 1.45, 1.4, 1.1] # 各月退服权重:夏季雷雨、高温停电高发
FMT = '%Y-%m-%d %H:%M:%S'
OUTAGE_HEAD = ['record_id', 'ne_id', 'cell_id', 'district', 'vendor', 'start_time', 'end_time', 'duration_min',
'cause_category', 'cause_detail', 'cause_code', 'ticket_id', 'closed', 'handle_time', 'close_time']
ALARM_HEAD = ['alarm_id', 'ne_id', 'alarm_code', 'alarm_name', 'alarm_level', 'category', 'start_time',
'clear_time', 'duration_s', 'cleared', 'parent_alarm_id']
SITE_HEAD = ['ne_id', 'site_name', 'district', 'scene', 'site_type', 'vendor', 'cells', 'lng', 'lat']
def gen_sites(rng):
"""生成站点库:每个地标周围若干站点,同一地标同一厂家组网。"""
sites = []
used_ids = set()
for scene, marks in LANDMARKS.items():
per_mark, type_weights, _ = SCENE_CFG[scene]
for district, mark in marks:
center_lng, center_lat = DISTRICTS[district]
# 地标位置在片区中心附近随机偏移
mark_lng = center_lng + rng.uniform(-.03, .03)
mark_lat = center_lat + rng.uniform(-.025, .025)
vendor = rng.choice(VENDORS)
for k in range(per_mark):
site_type = rng.choices(list(TYPE_CODE), type_weights)[0]
number = rng.randint(10000, 99999)
while number in used_ids:
number = rng.randint(10000, 99999)
used_ids.add(number)
if site_type == '宏站':
cells = 3
else:
cells = rng.choice([1, 2, 4, 6])
lng = round(mark_lng + rng.uniform(-.006, .006), 6)
lat = round(mark_lat + rng.uniform(-.005, .005), 6)
sites.append({
'ne_id': 'gNodeB-%05d' % number,
'site_name': '%s%s-%s%02d' % (district[:-1], mark, TYPE_CODE[site_type], k + 1),
'district': district, 'scene': scene, 'site_type': site_type, 'vendor': vendor,
'cells': cells, 'lng': lng, 'lat': lat,
})
return sites
def gen_duration(rng, category):
"""退服时长(分钟),沿用 data.py 的长尾分段:多数短退服,少数超长。割接受窗口限制偏短,停电、机房类偏长。"""
factor = {'割接施工': .88, '电源故障': 1.08, '机房环境': 1.05}.get(category, 1)
r = rng.random() * factor
if r < 0.62:
return rng.randint(5, 60)
if r < 0.88:
return rng.randint(61, 360)
if r < 0.97:
return rng.randint(361, 1440)
return rng.randint(1441, 7200)
def gen_start(rng, category):
"""退服开始时间:按月份权重抽日期;割接集中在凌晨,停电/机房一半发生在午后。"""
while True:
day = rng.randrange(DAYS)
month = (T0 + datetime.timedelta(days=day)).month
if rng.random() < MONTH_W[month - 1] / max(MONTH_W):
break
if category == '割接施工':
minute = rng.randint(0, 6 * 60) # 夜间维护窗口 00:00-06:00
elif category in ('电源故障', '机房环境') and rng.random() < .5:
minute = rng.randint(12 * 60, 20 * 60) # 午后雷雨、高温
else:
minute = rng.randint(0, 24 * 60 - 1)
return T0 + datetime.timedelta(days=day, minutes=minute)
def add_alarm(rng, alarms, ne_id, category, start, end, parent=''):
"""生成一条告警追加到 alarms 列表,返回告警编号。end 为 None 表示未清除。"""
if category == '小区退服':
code, name, level = ALARM_LIB['小区退服']
else:
code, name, level = rng.choice(ALARM_LIB[category])
alarm_id = 'ALM%08d' % (len(alarms) + 1)
if end:
clear_time = end.strftime(FMT)
duration = int((end - start).total_seconds())
cleared = '是'
else:
clear_time = ''
duration = 0
cleared = '否'
alarms.append({'alarm_id': alarm_id, 'ne_id': ne_id, 'alarm_code': code, 'alarm_name': name, 'alarm_level': level,
'category': category, 'start_time': start.strftime(FMT), 'clear_time': clear_time,
'duration_s': duration, 'cleared': cleared, 'parent_alarm_id': parent})
return alarm_id
def generate(n=6000, seed=2026, out='.'):
rng = random.Random(seed + 18)
sites = gen_sites(rng)
# 站点退服倾向 = 场景系数 × 站点系数;约 12% 的站点是问题站点,系数明显更高(会被判为高频重复站点)
weights = []
for site in sites:
if rng.random() < .12:
site_factor = rng.uniform(4, 8)
else:
site_factor = rng.uniform(.5, 1.5)
weights.append(SCENE_CFG[site['scene']][2] * site_factor)
categories = list(CAUSES)
outages = []
alarms = []
for i in range(n):
site = sites[rng.choices(range(len(sites)), weights)[0]]
ne_id = site['ne_id']
category = rng.choices(categories, CAUSE_W[site['scene']])[0]
detail, code = rng.choice(CAUSES[category])
start = gen_start(rng, category)
duration = gen_duration(rng, category)
end = start + datetime.timedelta(minutes=duration)
# 约 1.5% 的流水为人工计算错误:跨天时漏算整天,或按整点取整后再差半小时
reported = duration
if rng.random() < .015:
if duration > 1440:
reported = duration % 1440
else:
reported = max(5, round(duration / 60) * 60 + rng.choice([-30, 30]))
cell_id = '460-11-%s-%02d' % (ne_id[-5:], rng.randint(1, site['cells']))
# 最近 10 天的退服大多还没闭环,更早的 93% 已闭环
is_recent = (T0 + datetime.timedelta(days=DAYS) - start).days < 10
if is_recent:
closed = rng.choice(['否', '否', '是'])
else:
closed = rng.choices(['是', '否'], [93, 7])[0]
outages.append({
'record_id': 'TF%07d' % (3000001 + i), 'ne_id': ne_id, 'cell_id': cell_id,
'district': site['district'], 'vendor': site['vendor'], 'start_time': start.strftime(FMT),
'end_time': end.strftime(FMT), 'duration_min': reported, 'cause_category': category,
'cause_detail': detail, 'cause_code': code, 'ticket_id': 'GD%06d' % (200001 + i), 'closed': closed,
})
# 联动告警:根因告警先于退服发生 -> 小区退服告警(约 65% 记录了父告警 parent_alarm_id)
root_alarm = ''
if category in ALARM_LIB:
lead_min, lead_max = LEAD.get(category, (0, 8))
alarm_start = start - datetime.timedelta(minutes=rng.randint(lead_min, lead_max))
root_alarm = add_alarm(rng, alarms, ne_id, category, alarm_start, end)
if category == '电源故障' and rng.random() < .6: # 停电导致传输设备掉电,衍生传输告警
add_alarm(rng, alarms, ne_id, '传输中断', start, end, root_alarm)
if rng.random() < .65:
parent = root_alarm
else:
parent = ''
add_alarm(rng, alarms, ne_id, '小区退服', start, end, parent)
# 约 7% 的退服前出现一条无关的干扰告警,检验算法能否按优先级排除
if rng.random() < .07:
noise_category = rng.choice(['传输中断', '设备硬件', '天馈故障', '机房环境'])
noise_start = start - datetime.timedelta(minutes=rng.randint(0, 12))
noise_end = noise_start + datetime.timedelta(minutes=rng.randint(2, 30))
add_alarm(rng, alarms, ne_id, noise_category, noise_start, noise_end)
# 闭环过程时间:用独立的随机数生成器,不改变上面已有数据的随机序列。
# 接单(响应)时间 = 退服开始 + 响应时延:75% 在 1.5 小时内,18% 在 1.5~5 小时,7% 超过 5 小时;
# 已闭环的闭环时间 = max(恢复时间, 接单时间) + 10 分钟 ~ 10 小时(复核、回单);
# 未闭环的一半已接单(处理中),一半未接单(待处理)。
flow_rng = random.Random(seed + 1018)
for outage in outages:
start = datetime.datetime.strptime(outage['start_time'], FMT)
end = datetime.datetime.strptime(outage['end_time'], FMT)
r = flow_rng.random()
if r < .75:
delay = flow_rng.randint(3, 90)
elif r < .93:
delay = flow_rng.randint(91, 300)
else:
delay = flow_rng.randint(301, 1440)
handle = start + datetime.timedelta(minutes=delay)
if outage['closed'] == '是':
close = max(end, handle) + datetime.timedelta(minutes=flow_rng.randint(10, 600))
outage['handle_time'] = handle.strftime(FMT)
outage['close_time'] = close.strftime(FMT)
else:
outage['handle_time'] = handle.strftime(FMT) if flow_rng.random() < .5 else ''
outage['close_time'] = ''
# 背景告警:与退服无关的日常闪断告警
for _ in range(n):
site = rng.choice(sites)
category = rng.choice(['传输中断', '设备硬件', '天馈故障', '机房环境', '电源故障'])
alarm_start = T0 + datetime.timedelta(minutes=rng.randint(0, DAYS * 1440))
alarm_end = alarm_start + datetime.timedelta(minutes=rng.choice([1, 3, 8, 20, 45]))
add_alarm(rng, alarms, site['ne_id'], category, alarm_start, alarm_end)
alarms.sort(key=lambda alarm: alarm['start_time'])
os.makedirs(out, exist_ok=True)
outputs = [('sites.csv', sites, SITE_HEAD), ('data_outage.csv', outages, OUTAGE_HEAD), ('data_alarm.csv', alarms, ALARM_HEAD)]
for filename, rows, header in outputs:
with open(os.path.join(out, filename), 'w', newline='', encoding='utf-8-sig') as f:
writer = csv.DictWriter(f, fieldnames=header)
writer.writeheader()
writer.writerows(rows)
return len(sites), len(outages), len(alarms)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='第18题基站退服数据生成器')
parser.add_argument('--rows', type=int, default=6000, help='退服记录条数,默认 6000')
parser.add_argument('--seed', type=int, default=2026)
parser.add_argument('--out', default=os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data'))
args = parser.parse_args()
n_sites, n_outages, n_alarms = generate(args.rows, args.seed, args.out)
print('站点 %d 个,退服记录 %d 条,告警 %d 条 -> %s' % (n_sites, n_outages, n_alarms, args.out))