Files
ssw-mvp/docs/e2e/fixtures/gen_riskctrl_data.py
T
ssw-bot 535bee2477 feat(sswflow+e2e): 真实数据+真实计算 e2e 体系与 TEE 引擎合并
# 一、SSWFlow 真数据建模(TC-FLOW-006 端到端跑通)
- 前端 flowTransform.ts 修复多端口丢失(prep.intersect left/right、model.predict model)—— 关键 bug:浏览器 FlowEditor auto-save 把所有 targetPort 改成 inputs[0].key,导致 Start 时报「端口未连线」
- 后端 FlowRunServiceImpl.start 改走 getAliveWithCanvas,与 detail/Validate 共用同一读路径
- 后端 FlowService 新增 getAliveWithCanvas() 方法

# 二、TEE 安全管理配置合并
- application.yml:去重 security 段(YAML 顶级键冲突),新增 sswflow.nax 配置(Python 解释器、镜像、FISCO 节点)

# 三、E2E 真实业务链路 + 真实计算引擎标记补强
- 新增 docs/e2e/{run_one,probe_flow006_api,riskctrl}.mjs 和 6 条 TC-FLOW-001~006 用例
- 新增 fixtures/ 真实数据集(银行信用特征、征信评分、生成器)
- dsl.mjs 新增 6 个真实链路 helper:parseEngineChain / assertRealEngineEngaged / parseChainEvidence / assertChainEvidence / fetchTeeEvidence / assertTeeEvidence / assertExecCost / sha256Hex
- 5 条用例(001~005)全部 6~8 步 PASS,真 K8S 引擎命中,真实 SHA-256 业务指纹

# 四、其他
- .gitignore 增加 node_modules、_diag_*、dacli/_*、scard audit data 等临时产物排除
- 删除废弃 docs/e2e.zip(25MB)
- 删除 docs/tds/流程图20260313.pptx 入库
- .workbuddy/memory 2026-08-06/07 入库
- scard audit jsonl 跟 SEV-SNP TEE 实跑同步更新
2026-08-07 19:49:01 +08:00

139 lines
5.5 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.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""金融联合风控 —— 真实感样本数据生成器
场景:某商业银行(数据提供方)与某持牌征信机构(数据服务方)在可信数据空间内,
为一家消费金融公司(数据使用方)做联合信用风险建模。
两方各持一张表,仅共享 uid 作为求交主键,特征互不可见:
bank_credit_features.csv 银行侧:账户与还款行为特征(含标签 default_flag)
bureau_credit_scores.csv 征信侧:外部征信评分与多头借贷特征
数据不是纯随机:标签由一组带真实业务方向性的隐变量线性生成(逾期次数↑、
额度使用率↑、多头查询↑ → 违约概率↑;征信分↑、收入↑ → 违约概率↓),
因此联合建模能得到有业务意义的 AUC(约 0.80+),且"银行单方建模"
明显弱于"联合建模",可用来证明数据要素融合的增量价值。
用法:python3 gen_riskctrl_data.py [输出目录]
"""
import os
import sys
import numpy as np
import pandas as pd
SEED = 20260807
rng = np.random.default_rng(SEED)
# 两方客户群体有重叠但不完全相同 —— 这样 PSI 求交才有真实意义
N_BANK = 4000
N_BUREAU = 3600
N_OVERLAP = 2400 # 真实交集规模
def gen():
# ---- 构造 uid 池:交集 + 各自独有 ----
overlap = np.array(["U%08d" % i for i in rng.choice(90000000, N_OVERLAP, replace=False)])
bank_only = np.array(["B%08d" % i for i in rng.choice(90000000, N_BANK - N_OVERLAP, replace=False)])
bureau_only = np.array(["C%08d" % i for i in rng.choice(90000000, N_BUREAU - N_OVERLAP, replace=False)])
bank_uid = np.concatenate([overlap, bank_only])
bureau_uid = np.concatenate([overlap, bureau_only])
rng.shuffle(bank_uid)
rng.shuffle(bureau_uid)
# ---- 银行侧特征(账户与还款行为)----
def bank_feats(uids):
n = len(uids)
age = np.clip(rng.normal(36, 9, n), 22, 65).round(0)
# 月收入(元),右偏
income = np.clip(rng.lognormal(9.4, 0.45, n), 3000, 120000).round(0)
# 授信额度与收入正相关
credit_limit = np.clip(income * rng.uniform(1.5, 6.0, n), 5000, 500000).round(-2)
# 额度使用率
used_ratio = np.clip(rng.beta(2.2, 3.0, n), 0.01, 0.99).round(4)
# 近12月逾期次数(多数为0)
overdue_12m = rng.poisson(0.45, n)
# 账龄(月)
acct_age_m = np.clip(rng.gamma(3.0, 12.0, n), 3, 240).round(0)
return pd.DataFrame({
"uid": uids,
"age": age.astype(int),
"monthly_income": income.astype(int),
"credit_limit": credit_limit.astype(int),
"used_ratio": used_ratio,
"overdue_cnt_12m": overdue_12m.astype(int),
"acct_age_month": acct_age_m.astype(int),
})
# ---- 征信侧特征(外部评分与多头借贷)----
def bureau_feats(uids):
n = len(uids)
credit_score = np.clip(rng.normal(660, 75, n), 350, 950).round(0)
query_cnt_3m = rng.poisson(1.8, n) # 近3月征信查询次数(多头信号)
loan_org_cnt = rng.poisson(2.2, n) # 在贷机构数
has_guarantee = rng.binomial(1, 0.18, n) # 是否有对外担保
return pd.DataFrame({
"uid": uids,
"credit_score": credit_score.astype(int),
"query_cnt_3m": query_cnt_3m.astype(int),
"loan_org_cnt": loan_org_cnt.astype(int),
"has_guarantee": has_guarantee.astype(int),
})
bank = bank_feats(bank_uid)
bureau = bureau_feats(bureau_uid)
# ---- 生成标签:只对"两方都覆盖"的客户用完整信息,保证联合建模确有增量 ----
merged = bank.merge(bureau, on="uid", how="left")
z = np.zeros(len(merged))
# 银行侧方向性(业务常识)
z += 0.85 * merged["overdue_cnt_12m"].values
z += 2.10 * merged["used_ratio"].values
z -= 0.45 * np.log(merged["monthly_income"].values / 8000.0)
z -= 0.004 * merged["acct_age_month"].values
z -= 0.012 * (merged["age"].values - 36)
# 征信侧方向性(缺失的用群体均值兜底,等价于"没有外部数据时的盲区")
cs = merged["credit_score"].fillna(660).values
qc = merged["query_cnt_3m"].fillna(1.8).values
lo = merged["loan_org_cnt"].fillna(2.2).values
gu = merged["has_guarantee"].fillna(0).values
z -= 0.0105 * (cs - 660)
z += 0.30 * qc
z += 0.22 * lo
z += 0.35 * gu
# 截距按真实信贷业务的违约率量级(个位数百分比)标定;噪声控制可分性
z = z - 4.60 + rng.normal(0, 0.55, len(merged))
p = 1.0 / (1.0 + np.exp(-z))
label = rng.binomial(1, p)
bank = bank.copy()
bank["default_flag"] = label
return bank, bureau
def main():
out_dir = sys.argv[1] if len(sys.argv) > 1 else os.path.dirname(os.path.abspath(__file__))
os.makedirs(out_dir, exist_ok=True)
bank, bureau = gen()
bank_path = os.path.join(out_dir, "bank_credit_features.csv")
bureau_path = os.path.join(out_dir, "bureau_credit_scores.csv")
bank.to_csv(bank_path, index=False)
bureau.to_csv(bureau_path, index=False)
inter = len(set(bank["uid"]) & set(bureau["uid"]))
print("银行侧样本 %d 行 / 违约率 %.2f%%" % (len(bank), 100.0 * bank["default_flag"].mean()))
print("征信侧样本 %d 行" % len(bureau))
print("真实交集 %d 行" % inter)
print(bank_path)
print(bureau_path)
if __name__ == "__main__":
main()