浅念
276 lines
12 KiB
Python
276 lines
12 KiB
Python
"""统计查询纯函数(Phase 2 Task 9,spec §7.6): 五表现有数据聚合——卡片/
|
|
漏斗/趋势/分布/推送健康,无新表。
|
|
|
|
数据形态: 单租户 collect_stats(该租户 session)+ 跨租户 merge_stats(应用层
|
|
合并)——**逐库查询、应用层合并,绝不用 SQLite ATTACH**(spec §7.6: ATTACH
|
|
默认上限 10 个附加库,租户一多就炸;本模块零 ATTACH 调用)。
|
|
|
|
指标口径(歧义处已定死,Phase 3 前端照此展示):
|
|
- 会话数: conversations 行数,**不要求有消息**——统计口径是"发生的会话",
|
|
与数据视图列表"至少一条消息"(jc 列表语义)不同,两者有意并存。
|
|
- 线索数: 该会话的 customer_profiles.raw_info 含 phone/whatsapp/email
|
|
(推送预检的"contact 三选一")任一**非 _ 前缀键**且值非空——wechat 不算
|
|
(推送侧只认三选一);与 contact_pipeline.normalize_contacts 的归一化键
|
|
同名(中英文别名入库前已归一)。
|
|
- 高意向数: evaluations.intent_level == "interested" 的会话数。
|
|
- 推送成功率: lead_push_logs 的 success/(success+failed);skipped(预检
|
|
不满足必拒)与 pending(未终态)不进分母;分母 0 → None(前端展示"—")。
|
|
- 漏斗: 会话 → 留资 → 评估完成(有 evaluations 行)→ 推送成功(该会话有
|
|
过 success 日志;日志自身不另受时间窗约束——会话本体已在窗内)。
|
|
- 趋势: 按日分组,**北京日界** date(created_at, '+8 hours')——created_at
|
|
库内为 naive UTC(models 约定),容器部署 TZ=Asia/Shanghai,业务日界以
|
|
北京为准(代码按 naive UTC 存储 + 固定 +8 偏移分组,不依赖进程本地时区,
|
|
测试环境与生产同口径);无数据的日期不产出行(前端补零)。
|
|
- 分布: intent 三级 / source / site(client_info 的 site 键,JSON 取键,
|
|
与 data_routes 的 site 筛选同一姿势;无 site 键的会话不计)/ country
|
|
top10(IP 经 ip_service.resolve_country 逐行归国——iptocc 是内存库,
|
|
逐行查 N 会话在几百量级毫秒级可接受,故不在 SQL 里做)。
|
|
- 推送健康: 四状态(pending/success/failed/skipped)计数 + duplicated
|
|
(outcome 字段,200 但对方判重——不是错误)计数。
|
|
|
|
时间筛选: from_dt/to_dt 为 naive UTC 边界(由 stats_routes 经 data_routes
|
|
的 _parse_dt 解析,日期-only 的 to 含当日全天,边界含)。会话锚定的指标滤
|
|
conversations.created_at;推送锚定的指标(成功率/推送健康)滤
|
|
lead_push_logs.created_at——两套锚点各自与本体表同窗。
|
|
"""
|
|
from collections import Counter, defaultdict
|
|
|
|
from sqlalchemy import ColumnElement, and_, func, or_, select
|
|
|
|
from app.engine.models import (
|
|
Conversation,
|
|
CustomerProfile,
|
|
Evaluation,
|
|
IntentLevel,
|
|
LeadPushLog,
|
|
)
|
|
from app.engine.services.ip_service import resolve_country
|
|
|
|
# 线索判定的联系方式键(三选一;wechat 不算——与推送预检同口径)
|
|
CONTACT_KEYS = ("phone", "whatsapp", "email")
|
|
INTENT_KEYS = ("interested", "not_interested", "pending")
|
|
PUSH_STATUS_KEYS = ("pending", "success", "failed", "skipped")
|
|
COUNTRY_TOP_N = 10
|
|
# 北京日界偏移(SQLite date() 修饰符): 见模块 docstring"趋势"条
|
|
_TZ_BEIJING = "+8 hours"
|
|
|
|
|
|
def _empty_stats() -> dict:
|
|
"""零数据形态(无租户可查/空库)——与 collect_stats 输出同构。"""
|
|
return {
|
|
"cards": {
|
|
"conversations": 0, "leads": 0, "high_intent": 0,
|
|
"push_success_rate": None},
|
|
"funnel": {
|
|
"conversations": 0, "leads": 0, "evaluated": 0,
|
|
"push_succeeded": 0},
|
|
"trend": [],
|
|
"distributions": {
|
|
"intent": {k: 0 for k in INTENT_KEYS},
|
|
"source": {},
|
|
"site": {},
|
|
"country": []},
|
|
"push_health": {
|
|
"pending": 0, "success": 0, "failed": 0, "skipped": 0,
|
|
"duplicated": 0},
|
|
}
|
|
|
|
|
|
def _contact_any() -> ColumnElement:
|
|
"""SQL 布尔: raw_info 三选一键任一非空(NULL/空白串都不算)。"""
|
|
conds = []
|
|
for key in CONTACT_KEYS:
|
|
value = CustomerProfile.raw_info[key].as_string()
|
|
conds.append(and_(value.is_not(None), func.trim(value) != ""))
|
|
return or_(*conds)
|
|
|
|
|
|
def _range(column, from_dt, to_dt) -> list:
|
|
"""闭区间条件列表(边界含;None 边界不加条件)。"""
|
|
conds = []
|
|
if from_dt is not None:
|
|
conds.append(column >= from_dt)
|
|
if to_dt is not None:
|
|
conds.append(column <= to_dt)
|
|
return conds
|
|
|
|
|
|
def _push_rate(health: dict) -> float | None:
|
|
"""success/(success+failed);分母 0 → None。"""
|
|
done = health["success"] + health["failed"]
|
|
return health["success"] / done if done else None
|
|
|
|
|
|
def _sorted_counts(counter: dict) -> dict:
|
|
"""分布字典定序: 计数倒序、同数按 key 升序(JSON 对象保序,前端展示稳)。"""
|
|
return dict(sorted(counter.items(), key=lambda kv: (-kv[1], kv[0])))
|
|
|
|
|
|
async def collect_stats(
|
|
session, *, from_dt=None, to_dt=None) -> dict:
|
|
"""单租户统计: 在该租户库的 session 上跑全部聚合,输出指标 dict。
|
|
|
|
只读不写;所有计数走 SQL 聚合(例外: country 逐行 IP 归国,见模块
|
|
docstring)。"""
|
|
conv_range = _range(Conversation.created_at, from_dt, to_dt)
|
|
log_range = _range(LeadPushLog.created_at, from_dt, to_dt)
|
|
|
|
# ---- 卡片 + 漏斗(会话锚定) ------------------------------------------------
|
|
conversations = (await session.execute(
|
|
select(func.count()).select_from(Conversation).where(*conv_range)
|
|
)).scalar() or 0
|
|
leads = (await session.execute(
|
|
select(func.count())
|
|
.select_from(Conversation)
|
|
.join(CustomerProfile,
|
|
CustomerProfile.conversation_id == Conversation.id)
|
|
.where(*conv_range, _contact_any())
|
|
)).scalar() or 0
|
|
high_intent = (await session.execute(
|
|
select(func.count())
|
|
.select_from(Conversation)
|
|
.join(Evaluation, Evaluation.conversation_id == Conversation.id)
|
|
.where(*conv_range,
|
|
Evaluation.intent_level == IntentLevel.interested)
|
|
)).scalar() or 0
|
|
evaluated = (await session.execute(
|
|
select(func.count())
|
|
.select_from(Conversation)
|
|
.join(Evaluation, Evaluation.conversation_id == Conversation.id)
|
|
.where(*conv_range)
|
|
)).scalar() or 0
|
|
push_succeeded = (await session.execute(
|
|
select(func.count()).select_from(Conversation).where(
|
|
*conv_range,
|
|
Conversation.id.in_(
|
|
select(LeadPushLog.conversation_id)
|
|
.where(LeadPushLog.status == "success")))
|
|
)).scalar() or 0
|
|
|
|
# ---- 推送健康(日志锚定) --------------------------------------------------
|
|
health = {k: 0 for k in PUSH_STATUS_KEYS}
|
|
for status, count in (await session.execute(
|
|
select(LeadPushLog.status, func.count())
|
|
.where(*log_range).group_by(LeadPushLog.status))).all():
|
|
if status in health: # 未知状态不计(防御 imported/手改数据)
|
|
health[status] = count
|
|
health["duplicated"] = (await session.execute(
|
|
select(func.count()).select_from(LeadPushLog).where(
|
|
*log_range, LeadPushLog.outcome == "duplicated")
|
|
)).scalar() or 0
|
|
|
|
# ---- 趋势(北京日界) ------------------------------------------------------
|
|
day = func.date(Conversation.created_at, _TZ_BEIJING)
|
|
conv_per_day = dict((await session.execute(
|
|
select(day, func.count()).where(*conv_range).group_by(day)
|
|
)).all())
|
|
lead_stmt = (
|
|
select(day, func.count())
|
|
.select_from(Conversation)
|
|
.join(CustomerProfile,
|
|
CustomerProfile.conversation_id == Conversation.id)
|
|
.where(*conv_range, _contact_any())
|
|
.group_by(day))
|
|
lead_per_day = dict((await session.execute(lead_stmt)).all())
|
|
trend = [
|
|
{"date": d, "conversations": conv_per_day[d],
|
|
"leads": lead_per_day.get(d, 0)}
|
|
for d in sorted(set(conv_per_day) | set(lead_per_day))
|
|
]
|
|
|
|
# ---- 分布 -----------------------------------------------------------------
|
|
intent = {k: 0 for k in INTENT_KEYS}
|
|
for level, count in (await session.execute(
|
|
select(Evaluation.intent_level, func.count())
|
|
.join(Conversation, Conversation.id == Evaluation.conversation_id)
|
|
.where(*conv_range).group_by(Evaluation.intent_level))).all():
|
|
intent[level.value if hasattr(level, "value") else str(level)] = count
|
|
|
|
source = Counter()
|
|
for src, count in (await session.execute(
|
|
select(Conversation.source, func.count())
|
|
.where(*conv_range).group_by(Conversation.source))).all():
|
|
source[src.value if hasattr(src, "value") else str(src)] = count
|
|
|
|
site_expr = Conversation.client_info["site"].as_string()
|
|
site = Counter()
|
|
for site_slug, count in (await session.execute(
|
|
select(site_expr, func.count())
|
|
.where(*conv_range, site_expr.is_not(None)).group_by(site_expr)
|
|
)).all():
|
|
site[site_slug] = count
|
|
|
|
# country: 逐行 IP 归国(iptocc 内存库,几百会话毫秒级——见模块 docstring)
|
|
country = Counter()
|
|
for (ip,) in (await session.execute(
|
|
select(Conversation.client_info["ip"].as_string())
|
|
.where(*conv_range))).all():
|
|
country[resolve_country(ip or "")] += 1
|
|
|
|
return {
|
|
"cards": {
|
|
"conversations": conversations,
|
|
"leads": leads,
|
|
"high_intent": high_intent,
|
|
"push_success_rate": _push_rate(health)},
|
|
"funnel": {
|
|
"conversations": conversations,
|
|
"leads": leads,
|
|
"evaluated": evaluated,
|
|
"push_succeeded": push_succeeded},
|
|
"trend": trend,
|
|
"distributions": {
|
|
"intent": intent,
|
|
"source": _sorted_counts(source),
|
|
"site": _sorted_counts(site),
|
|
"country": [
|
|
{"country": name, "count": count}
|
|
for name, count in country.most_common(COUNTRY_TOP_N)]},
|
|
"push_health": health,
|
|
}
|
|
|
|
|
|
def merge_stats(parts: list[dict]) -> dict:
|
|
"""跨租户应用层合并(逐库结果求和;比率/排序合并后重算重排)。
|
|
|
|
parts 为空 → 零数据形态。合并语义: 标量求和;趋势按日期键合并;
|
|
intent/source/site 按 key 求和;country 计数合并后重取 top N。"""
|
|
if not parts:
|
|
return _empty_stats()
|
|
out = _empty_stats()
|
|
|
|
trend = defaultdict(lambda: {"conversations": 0, "leads": 0})
|
|
intent = {k: 0 for k in INTENT_KEYS}
|
|
source: Counter = Counter()
|
|
site: Counter = Counter()
|
|
country: Counter = Counter()
|
|
|
|
for part in parts:
|
|
for key in ("conversations", "leads", "high_intent"):
|
|
out["cards"][key] += part["cards"][key]
|
|
for key in ("conversations", "leads", "evaluated", "push_succeeded"):
|
|
out["funnel"][key] += part["funnel"][key]
|
|
for row in part["trend"]:
|
|
trend[row["date"]]["conversations"] += row["conversations"]
|
|
trend[row["date"]]["leads"] += row["leads"]
|
|
for key, count in part["distributions"]["intent"].items():
|
|
intent[key] = intent.get(key, 0) + count
|
|
source.update(part["distributions"]["source"])
|
|
site.update(part["distributions"]["site"])
|
|
for item in part["distributions"]["country"]:
|
|
country[item["country"]] += item["count"]
|
|
for key in out["push_health"]:
|
|
out["push_health"][key] += part["push_health"][key]
|
|
|
|
out["cards"]["push_success_rate"] = _push_rate(out["push_health"])
|
|
out["trend"] = [
|
|
{"date": d, **counts} for d, counts in sorted(trend.items())]
|
|
out["distributions"] = {
|
|
"intent": intent,
|
|
"source": _sorted_counts(source),
|
|
"site": _sorted_counts(site),
|
|
"country": [
|
|
{"country": name, "count": count}
|
|
for name, count in country.most_common(COUNTRY_TOP_N)]},
|
|
return out
|