staran 0.5.0__py3-none-any.whl → 0.6.1__py3-none-any.whl

staran/schemas/aum/__init__.py

@@ -1,26 +1,29 @@
 """
-AUM业务表结构定义模块
+新疆工行代发长尾客户表结构定义模块
 
-包含AUM (资产管理)业务相关的所有标准表结构：
-- 客户行为特征表 (AUMBehaviorSchema)  
-- 资产平均值表 (AUMAssetAvgSchema)
-- 资产配置表 (AUMAssetConfigSchema)
-- 月度统计表 (AUMMonthlyStatSchema)
+包含新疆工行代发长尾客户相关的所有表结构：
+- 代发长尾客户行为特征表 (XinjiangICBCDaifaLongtailBehaviorSchema)  
+- 代发长尾客户资产平均值表 (XinjiangICBCDaifaLongtailAssetAvgSchema)
+- 代发长尾客户资产配置表 (XinjiangICBCDaifaLongtailAssetConfigSchema)
+- 代发长尾客户月度统计表 (XinjiangICBCDaifaLongtailMonthlyStatSchema)
+
+数据库: xinjiang_icbc_daifa_longtail
+业务范围: 代发长尾客户（资产10k-100k）
 
 这些表结构可以用于：
-1. 特征工程流水线
-2. 数据模型构建
+1. 代发长尾客户特征工程
+2. 提升模型和防流失模型构建
 3. 业务文档生成
 4. 数据质量检查
 """
 
 from typing import Dict
 from ...features.schema import TableSchema
-from ..document_generator import SchemaDocumentGenerator
+from ...tools.document_generator import SchemaDocumentGenerator
 
 
-class AUMBehaviorSchema:
-    """AUM客户行为特征表 - A表结构定义（严格按照已提供给行方的字段）"""
+class XinjiangICBCDaifaLongtailBehaviorSchema:
+    """新疆工行代发长尾客户行为特征表 - 严格按照已提供给行方的字段"""
     
     # 统计指标定义 - 与原始定义完全一致
     _STATS = [
@@ -36,8 +39,8 @@ class AUMBehaviorSchema:
     
     @staticmethod
     def create() -> TableSchema:
-        """创建客户行为特征表结构 - 严格按照已提供给行方的字段定义"""
-        schema = TableSchema('bi_hlwj_dfcw_f1_f4_wy')
+        """创建新疆工行代发长尾客户行为特征表结构"""
+        schema = TableSchema('xinjiang_icbc_daifa_hlwj_dfcw_f1_f4_wy')
         schema.add_primary_key('party_id', 'string')
         schema.add_date_field('data_dt', 'string')
         
@@ -52,7 +55,7 @@ class AUMBehaviorSchema:
         schema.add_field("orderidcount", "int", comment="订单数", aggregatable=True)
         schema.add_field("label", "float", comment="标签值（如是否购买）", aggregatable=True)
         
-        # productamount and m1 ~ m4 的含义描述 - 严格按照原始定义
+        # productamount and m1 ~ m4 的含义描述
         m_fields = {
             "productamount": "购买金额",
             "m1": "去重订单数",
@@ -61,246 +64,147 @@ class AUMBehaviorSchema:
             "m4": "去重产品品类数",
         }
 
-        # 使用循环注册 productamount and m1~m4 各统计字段 - 严格按照原始逻辑
+        # 使用循环注册 productamount and m1~m4 各统计字段
         for prefix, meaning in m_fields.items():
-            for stat_key, stat_desc in AUMBehaviorSchema._STATS:
+            for stat_key, stat_desc in XinjiangICBCDaifaLongtailBehaviorSchema._STATS:
                 field_name = f"{prefix}_{stat_key}"
                 description = f"{meaning}的{stat_desc}"
                 schema.add_field(field_name, "float", comment=description, aggregatable=True)
 
-        # 其他字段 - 严格按照原始定义
+        # 其他字段
         schema.add_field("life_day", "float", comment="客户生命周期天数", aggregatable=True)
         schema.add_field("gender", "float", comment="性别（编码）", aggregatable=True)
         schema.add_field("open_day", "float", comment="开户天数", aggregatable=True)
         
-        schema.set_monthly_unique(False)  # A表每人每日记录
-        return schema
-        schema.add_field("FREQ_BRANCH_CODE", "string", comment="常用网点代码")
-        schema.add_field("CROSS_REGION_TXN", "string", comment="跨地区交易情况")
-        
-        schema.set_monthly_unique(False)  # A表每人每天一条记录
+        schema.set_monthly_unique(False)  # 每人每日记录
         return schema
 
 
-class AUMAssetAvgSchema:
-    """AUM资产平均值表 - B表结构定义（严格按照已提供给行方的字段）"""
+class XinjiangICBCDaifaLongtailAssetAvgSchema:
+    """新疆工行代发长尾客户资产平均值表"""
     
     @staticmethod
     def create() -> TableSchema:
-        """创建资产平均值表结构 - 严格按照原始定义"""
-        schema = TableSchema('bi_hlwj_zi_chan_avg_wy')
+        """创建新疆工行代发长尾客户资产平均值表结构"""
+        schema = TableSchema('xinjiang_icbc_daifa_hlwj_zi_chan_avg_wy')
         schema.add_primary_key('party_id', 'string')
         schema.add_date_field('data_dt', 'string')
         
-        # 基础余额字段 - 严格按照原始定义
+        # 基础余额字段
         schema.add_field("asset_total_bal", "decimal", comment="总资产余额", aggregatable=True)
         schema.add_field("liab_total_bal", "decimal", comment="总负债余额", aggregatable=True)
-        schema.add_field("dpsit_total_bal", "decimal", comment="存款总余额", aggregatable=True)
-        schema.add_field("loan_total_bal", "decimal", comment="贷款总余额", aggregatable=True)
-        schema.add_field("card_total_bal", "decimal", comment="信用卡总余额", aggregatable=True)
-        schema.add_field("mid_busi_total_bal", "decimal", comment="中间业务总余额", aggregatable=True)
-
-        # Register average balance fields - 严格按照原始逻辑
-        for period in ["month", "year", "3", "6", "12"]:
-            schema.add_field(
-                f"avg_asset_bal_{period}", "decimal", comment=f"平均资产余额 ({period}期)", aggregatable=True
-            )
-        for period in ["3", "12"]:
-            schema.add_field(
-                f"avg_dpsit_bal_{period}", "decimal", comment=f"平均存款余额 ({period}期)", aggregatable=True
-            )
+        schema.add_field("net_asset_bal", "decimal", comment="净资产余额", aggregatable=True)
         
-        schema.set_monthly_unique(True)  # B表每人每月唯一
+        # 存款相关字段
+        schema.add_field("dep_bal", "decimal", comment="存款余额", aggregatable=True)
+        schema.add_field("current_dep_bal", "decimal", comment="活期存款余额", aggregatable=True)
+        schema.add_field("time_dep_bal", "decimal", comment="定期存款余额", aggregatable=True)
+        
+        # 理财投资字段
+        schema.add_field("wealth_bal", "decimal", comment="理财余额", aggregatable=True)
+        schema.add_field("fund_bal", "decimal", comment="基金余额", aggregatable=True)
+        schema.add_field("insurance_bal", "decimal", comment="保险余额", aggregatable=True)
+        
+        schema.set_monthly_unique(True)  # 每人每月一条记录
         return schema
 
 
-class AUMAssetConfigSchema:
-    """AUM资产配置表 - C表结构定义（严格按照已提供给行方的字段）"""
+class XinjiangICBCDaifaLongtailAssetConfigSchema:
+    """新疆工行代发长尾客户资产配置表"""
     
     @staticmethod
     def create() -> TableSchema:
-        """创建资产配置表结构 - 严格按照原始定义"""
-        schema = TableSchema('bi_hlwj_zi_chang_month_total_zb')
+        """创建新疆工行代发长尾客户资产配置表结构"""
+        schema = TableSchema('xinjiang_icbc_daifa_hlwj_zi_chan_config_wy')
         schema.add_primary_key('party_id', 'string')
         schema.add_date_field('data_dt', 'string')
         
-        # asset_fields - 严格按照原始定义
-        asset_fields = [
-            ("seg_asset_total", "总资产余额"),
-            ("indv_consm_loan_amt", "个人消费贷款余额"),
-            ("indv_house_loan_amt", "个人住房贷款余额"),
-            ("indv_oper_loan_amt", "个人经营贷款余额"),
-            ("dpsit_bal", "存款余额"),
-            ("tbond_bal", "国债余额"),
-            ("fund_bal", "基金余额"),
-            ("bond_bal", "债券余额"),
-            ("gold_bal", "黄金余额"),
-            ("wcurr_chrem_bal", "外币现钞余额"),
-            ("presv_mgmt_secu_bal", "保值管理证券余额"),
-            ("insure_form_bal", "保险单余额"),
-            ("crdt_card_od_bal", "信用卡透支余额"),
-            ("crdt_card_con_amt", "信用卡消费金额"),
-            ("semi_crdt_card_od_bal", "准贷记卡透支余额"),
-            ("semi_crdt_card_con_amt", "准贷记卡消费金额"),
-            ("inter_card_con_amt", "国际卡消费金额"),
-            ("inter_card_od_bal", "国际卡透支余额"),
-            ("crdt_card_dpsit_bal", "信用卡存款余额"),
-            ("semi_crdt_card_dpsit_bal", "准贷记卡存款余额"),
-            ("inter_card_dpsit_bal", "国际卡存款余额"),
-            ("silver_bal", "白银余额"),
-            ("agent_solid_silver_bal", "代发实物白银余额"),
-            ("pt_bal", "个人养老金余额"),
-            ("pd_bal", "个人养老金存款余额"),
-            ("other_metal_bal", "其他金属余额"),
-            ("curr_dpsit_bal", "活期存款余额"),
-            ("time_dpsit_bal", "定期存款余额"),
-            ("oil_bal", "石油余额"),
-            ("fx_bal", "外汇余额"),
-        ]
-
-        # 严格按照原始循环逻辑注册字段
-        for field_name, desc in asset_fields:
-            schema.add_field(field_name, "decimal", comment=desc, aggregatable=True)
+        # 资产配置比例字段
+        schema.add_field("cash_ratio", "float", comment="现金类资产占比", aggregatable=True)
+        schema.add_field("fixed_income_ratio", "float", comment="固收类资产占比", aggregatable=True)
+        schema.add_field("equity_ratio", "float", comment="权益类资产占比", aggregatable=True)
+        schema.add_field("alternative_ratio", "float", comment="另类资产占比", aggregatable=True)
         
-        schema.set_monthly_unique(True)  # C表每人每月唯一
+        # 风险偏好相关
+        schema.add_field("risk_level", "int", comment="风险偏好等级(1-5)", aggregatable=True)
+        schema.add_field("investment_experience", "int", comment="投资经验年限", aggregatable=True)
+        
+        # 配置变化指标
+        schema.add_field("config_change_freq", "int", comment="配置调整频率", aggregatable=True)
+        schema.add_field("rebalance_count", "int", comment="再平衡次数", aggregatable=True)
+        
+        schema.set_monthly_unique(True)
         return schema
 
 
-class AUMMonthlyStatSchema:
-    """AUM月度统计表 - D表结构定义（严格按照已提供给行方的字段）"""
+class XinjiangICBCDaifaLongtailMonthlyStatSchema:
+    """新疆工行代发长尾客户月度统计表"""
     
     @staticmethod
     def create() -> TableSchema:
-        """创建月度统计表结构 - 严格按照原始定义"""
-        schema = TableSchema('bi_hlwj_realy_month_stat_wy')
-        schema.add_primary_key('party_id', 'string')  # 修正主键名称
+        """创建新疆工行代发长尾客户月度统计表结构"""
+        schema = TableSchema('xinjiang_icbc_daifa_hlwj_monthly_stat_wy')
+        schema.add_primary_key('party_id', 'string')
         schema.add_date_field('data_dt', 'string')
         
-        # channels字典 - 严格按照原始定义
-        channels = {
-            "CASH_DEPIST": "现金",
-            "REMIT": "汇款",
-            "YY": "邮政储蓄",
-            "UNIONPAY": "银联",
-            "FIN_ASSET": "理财产品",
-            "CORP_ACCT": "对公账户",
-        }
-
-        # 注册存入和取出字段 - 严格按照原始逻辑
-        for prefix, desc in channels.items():
-            schema.add_field(f"{prefix}_IN", "decimal", comment=f"{desc}存入金额", aggregatable=True)
-            schema.add_field(f"{prefix}_OUT", "decimal", comment=f"{desc}取出金额", aggregatable=True)
-
-        # 其他特定字段 - 严格按照原始定义
-        schema.add_field("AGENT_SALARY_IN", "decimal", comment="代发工资存入金额", aggregatable=True)
-        schema.add_field("CREDIT_CARD_OUT", "decimal", comment="信用卡取出金额", aggregatable=True)
-        schema.add_field("DEBIT_CARD_OUT", "decimal", comment="借记卡取出金额", aggregatable=True)
-        schema.add_field("BATCH_DEDUCT_OUT", "decimal", comment="批量扣款金额", aggregatable=True)
-
-        # 定义字段结构：交易渠道、指标、时间范围、描述前缀 - 严格按照原始定义
-        fields = [
-            ("DEBIT_CARD", "借记卡", "MON3"),
-            ("CREDIT_CARD", "信用卡", "MON3"),
-            ("THIRD_PAYMENT", "第三方支付", "MON3"),
-            ("MOBBANK", "手机银行", "MON12"),
-            ("TELBANK", "电话银行", "MON12"),
-        ]
-
-        # 定义交易指标 - 严格按照原始定义
-        metrics = [
-            ("TX_CNT", "交易次数"),
-            ("TX_AMT", "交易金额"),
-        ]
-
-        # 自动注册 - 严格按照原始逻辑
-        for channel, desc, period in fields:
-            for metric_code, metric_desc in metrics:
-                field_name = f"{channel}_{metric_code}_{period}"
-                description = f"{desc}{metric_desc}（近{period[-2:]}个月）"
-                schema.add_field(field_name, "decimal", comment=description, aggregatable=True)
-
-        # 其他固定字段 - 严格按照原始定义
-        schema.add_field(
-            "COUNTER_TX_CNT_MON12", "int", comment="柜台交易次数（近12个月）", aggregatable=True
-        )
-        schema.add_field(
-            "WEBBANK_TX_CNT_MON12", "int", comment="网银交易次数（近12个月）", aggregatable=True
-        )
-
-        # 编号国家（1~5） - 严格按照原始循环逻辑
-        for i in range(1, 6):
-            schema.add_field(
-                f"Y1_OVERS_CTY{i}_CNT", "int", comment=f"近一年境外国家{i}的交易次数", aggregatable=True
-            )
-            schema.add_field(
-                f"Y1_OVERS_CNT_CTY{i}_CD",
-                "string",
-                comment=f"近一年境外国家{i}的交易次数（编码）",
-            )
-            schema.add_field(
-                f"Y1_OVERS_CTY{i}_AMT", "decimal", comment=f"近一年境外国家{i}的交易金额", aggregatable=True
-            )
-            schema.add_field(
-                f"Y1_OVERS_AMT_CTY{i}_CD",
-                "string",
-                comment=f"近一年境外国家{i}的交易金额（编码）",
-            )
-
-        # 其他国家 - 严格按照原始定义
-        schema.add_field(
-            "Y1_OVERS_OTHER_CTY_CNT", "int", comment="近一年其他境外国家的交易次数", aggregatable=True
-        )
-        schema.add_field(
-            "Y1_OVERS_OTHER_CTY_AMT", "decimal", comment="近一年其他境外国家的交易金额", aggregatable=True
-        )
+        # 月度交易统计
+        schema.add_field("monthly_txn_count", "int", comment="月度交易笔数", aggregatable=True)
+        schema.add_field("monthly_txn_amount", "decimal", comment="月度交易金额", aggregatable=True)
+        schema.add_field("monthly_deposit_amount", "decimal", comment="月度存入金额", aggregatable=True)
+        schema.add_field("monthly_withdraw_amount", "decimal", comment="月度取出金额", aggregatable=True)
+        
+        # 代发工资相关统计
+        schema.add_field("salary_amount", "decimal", comment="月度代发工资金额", aggregatable=True)
+        schema.add_field("salary_date", "string", comment="代发工资日期")
+        schema.add_field("salary_stability", "float", comment="工资稳定性指数", aggregatable=True)
+        
+        # 长尾客户特征
+        schema.add_field("longtail_score", "float", comment="长尾客户评分", aggregatable=True)
+        schema.add_field("upgrade_potential", "float", comment="提升潜力评分", aggregatable=True)
+        schema.add_field("churn_risk", "float", comment="流失风险评分", aggregatable=True)
         
-        schema.set_monthly_unique(True)  # D表每人每月唯一
+        # 活跃度指标
+        schema.add_field("login_days", "int", comment="月度登录天数", aggregatable=True)
+        schema.add_field("channel_usage", "string", comment="渠道使用情况")
+        
+        schema.set_monthly_unique(True)
         return schema
 
 
-def get_aum_schemas() -> Dict[str, TableSchema]:
-    """获取所有AUM业务表结构"""
+def get_xinjiang_icbc_daifa_longtail_schemas() -> Dict[str, TableSchema]:
+    """获取新疆工行代发长尾客户所有表结构"""
     return {
-        'behavior': AUMBehaviorSchema.create(),
-        'asset_avg': AUMAssetAvgSchema.create(), 
-        'asset_config': AUMAssetConfigSchema.create(),
-        'monthly_stat': AUMMonthlyStatSchema.create()
+        'daifa_longtail_behavior': XinjiangICBCDaifaLongtailBehaviorSchema.create(),
+        'daifa_longtail_asset_avg': XinjiangICBCDaifaLongtailAssetAvgSchema.create(),
+        'daifa_longtail_asset_config': XinjiangICBCDaifaLongtailAssetConfigSchema.create(),
+        'daifa_longtail_monthly_stat': XinjiangICBCDaifaLongtailMonthlyStatSchema.create(),
     }
 
 
-def export_aum_docs(output_dir: str = "./docs", format_type: str = "markdown") -> Dict[str, str]:
-    """
-    导出AUM表结构文档
-    
-    Args:
-        output_dir: 输出目录
-        format_type: 文档格式 ('markdown' 或 'pdf')
-        
-    Returns:
-        生成的文档文件路径字典
-    """
-    schemas = get_aum_schemas()
+def export_xinjiang_icbc_daifa_longtail_docs(output_dir: str = "./docs") -> Dict[str, str]:
+    """导出新疆工行代发长尾客户表结构文档"""
     generator = SchemaDocumentGenerator()
+    schemas = get_xinjiang_icbc_daifa_longtail_schemas()
+    exported_files = {}
     
-    results = {}
     for table_type, schema in schemas.items():
         file_path = generator.export_schema_doc(
-            schema=schema,
-            business_domain="AUM",
+            schema, 
+            business_domain="新疆工行代发长尾客户", 
             table_type=table_type,
-            output_dir=output_dir,
-            format_type=format_type
+            output_dir=output_dir
         )
-        results[table_type] = file_path
+        exported_files[table_type] = file_path
     
-    return results
+    return exported_files
 
 
+# 导出主要组件
 __all__ = [
-    'AUMBehaviorSchema',
-    'AUMAssetAvgSchema', 
-    'AUMAssetConfigSchema',
-    'AUMMonthlyStatSchema',
-    'get_aum_schemas',
-    'export_aum_docs'
+    'XinjiangICBCDaifaLongtailBehaviorSchema',
+    'XinjiangICBCDaifaLongtailAssetAvgSchema', 
+    'XinjiangICBCDaifaLongtailAssetConfigSchema',
+    'XinjiangICBCDaifaLongtailMonthlyStatSchema',
+    'get_xinjiang_icbc_daifa_longtail_schemas',
+    'export_xinjiang_icbc_daifa_longtail_docs'
 ]

{staran-0.5.0.dist-info → staran-0.6.1.dist-info}/METADATA

@@ -1,48 +1,70 @@
 Metadata-Version: 2.4
 Name: staran
-Version: 0.5.0
+Version: 0.6.1
 Summary: staran - 高性能Python工具库
 Home-page: https://github.com/starlxa/staran
 Author: StarAn
-Author-email: starlxa@icloud.com
+Author-email: StarAn <starlxa@icloud.com>
+License: MIT
+Project-URL: Homepage, https://github.com/starlxa/staran
+Project-URL: Bug Reports, https://github.com/starlxa/staran/issues
+Project-URL: Source, https://github.com/starlxa/staran
+Keywords: machine-learning,feature-engineering,data-processing,sql-generation
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: datetime
-Requires-Dist: calendar
-Requires-Dist: re
 Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license-file
-Dynamic: requires-dist
 Dynamic: requires-python
-Dynamic: summary
 
-# Star## ✨ v0.4.2 新特性
+# Star## Staran ✨ v0.6.1 新特性
 
-- 📋 **独立Schema模块** - 专门的表结构定义和管理模块
+- � **完善的包管理** - 优化setup.py配置，移除不必要的标准库依赖
+- �📋 **独立Schema模块** - 专门的表结构定义和管理模块
 - 📄 **文档自动生成** - 支持Markdown/PDF/HTML格式的技术文档生成
 - 🏢 **业务域支持** - AUM等业务领域的标准表结构定义
-- 🔗 **无缝集成** - Schema与特征工程examples模块完美集成
+- 🔗 **无缝集成** - Schema与特征工程模块完美集成
 - 🛠️ **模块化引擎架构** - 独立的引擎模块，支持Spark、Hive、图灵平台
 - 🔧 **统一接口设计** - 所有引擎提供一致的SQL生成、执行和下载接口
 - 🎯 **继承复用架构** - TuringEngine继承SparkEngine，复用SQL生成逻辑
 - 📦 **清晰代码分离** - SQL生成与平台特定执行逻辑完全分离
 - 🚀 **易于扩展** - 新增数据库支持只需实现BaseEngine接口
 - 📁 **独立引擎存储** - engines/文件夹专门存放所有数据库引擎
-- 🔄 **向后兼容** - 保持对原有API的完全兼容工程工具包
+- 🔄 **向后兼容** - 保持对原有API的完全兼容
+
+## 🎯 专为机器学习设计的Python工具包
+
+Staran是一个强大的特征工程和数据处理工具包，提供从数据到模型的完整解决方案。特别针对工银图灵平台优化，让特征工程和模型训练变得前所未有的简单。
+
+## ✨ v0.6.1 新特性
+
+- 🔧 **完善的包管理** - 优化setup.py配置，移除不必要的标准库依赖
+- 🛠️ **模块化引擎架构** - 独立的引擎模块，支持Spark、Hive、图灵平台
+- 🔧 **统一接口设计** - 所有引擎提供一致的SQL生成、执行和下载接口
+- 🎯 **继承复用架构** - TuringEngine继承SparkEngine，复用SQL生成逻辑
+- 📦 **清晰代码分离** - SQL生成与平台特定执行逻辑完全分离
+- 🚀 **易于扩展** - 新增数据库支持只需实现BaseEngine接口
+- 📁 **独立引擎存储** - engines/文件夹专门存放所有数据库引擎
+- 🔄 **向后兼容** - 保持对原有API的完全兼容
 
 ## � 专为机器学习设计的Python工具包
 
 Staran是一个强大的特征工程和数据处理工具包，提供从数据到模型的完整解决方案。特别针对工银图灵平台优化，让特征工程和模型训练变得前所未有的简单。
 
-## ✨ v0.4.2 新特性
+## ✨ v0.6.0 新特性
 
 - �️ **模块化引擎架构** - 独立的引擎模块，支持Spark、Hive、图灵平台
 - 🔧 **统一接口设计** - 所有引擎提供一致的SQL生成、执行和下载接口
@@ -361,7 +383,7 @@ tomorrow = date.add_days(1)         # 202504 (智能处理)
 
 ```
 staran/
-├── __init__.py                    # 主包入口，v0.4.2功能导出
+├── __init__.py                    # 主包入口，v0.6.0功能导出
 ├── schemas/                       # 🆕 表结构定义与文档生成模块
 │   ├── __init__.py               # Schema模块入口
 │   ├── document_generator.py     # 文档生成器 (MD/PDF/HTML)
@@ -385,7 +407,7 @@ staran/
 │   ├── __init__.py               # 工具模块
 │   └── date.py                   # Date类实现
 ├── setup.py                      # 安装配置  
-├── README.md                     # 本文档 v0.4.2
+├── README.md                     # 本文档 v0.6.0
 └── quick-upload.sh               # 快速部署脚本
 ```
 
@@ -561,4 +583,4 @@ MIT License
 
 ---
 
-**Staran v0.4.2** - 模块化引擎架构，让机器学习特征工程变得前所未有的简单 🌟
+**Staran v0.6.0** - 模块化引擎架构，让机器学习特征工程变得前所未有的简单 🌟

{staran-0.5.0.dist-info → staran-0.6.1.dist-info}/RECORD

@@ -1,29 +1,28 @@
-staran/__init__.py,sha256=cBUxN-qmS_Bf8r-8k94VdA-OLvjdRZyxTNfgd-X_AE8,7234
+staran/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+staran/banks/__init__.py,sha256=m4IUdFLXvNtgpmxDhKptCtALyaGkF1-T9hbNqdXczLI,544
+staran/banks/xinjiang_icbc/__init__.py,sha256=Ql3gQFh1h4EwUdU3fePW1chV5iAegxjLWiPxbYa_J80,3131
 staran/engines/__init__.py,sha256=aQCpDxY_JcKlApEsEp2wg_P3IwNDTCFb7OYcLHiPPmk,1627
 staran/engines/base.py,sha256=IIN-QxPsO-q3KmQ3Lz0cB9bs6Oac0Wy5MIF605HrHVw,7969
 staran/engines/hive.py,sha256=-KwZiAvK5cxwnoyYQlqGWrcZkeKhbd8QCX3chpbezd0,5894
 staran/engines/spark.py,sha256=XPxzefD9UF8oigeQISBW892RINJ9dGLbl994FWpIKBc,9361
 staran/engines/turing.py,sha256=XEKkEMMWedvaGxKQ2vEHmB3TWLNLxOu1upgiBylwqjA,15516
-staran/examples/__init__.py,sha256=rXjHvD_EA1sl04WAcOMGnktOwZstjUxaei6bo7pPMII,229
-staran/examples/aum_longtail.py,sha256=UFeLzhslS0Qw1defD9M8mI6Jq4G2BHoyqdjNfX0cgH0,9915
-staran/examples/aum_longtail_old.py,sha256=wZW_3NsU8lOjohtzI1ewzFIqTDAt8lnUberQJVYePfs,21723
 staran/features/__init__.py,sha256=uMloEuevUjUPfro8Yv4STwvxpSVL0J1xsQTzN_EkLpo,1828
 staran/features/engines.py,sha256=kqdS2xjmCVi0Xz1Oc3WaTMIavgAriX8F7VvUgVcpfqo,10039
 staran/features/generator.py,sha256=CI1F_PshOvokQJelsqSaVp-SNQpMc-WVmjMQKzgdeLw,23114
 staran/features/manager.py,sha256=2-3Hc3qthtyzwiuQy5QTz6RfhKK3szoylconzI3moc4,5201
 staran/features/schema.py,sha256=FwOfpTcxq4K8zkO3MFNqKPQBp_e8qY-N6gazqm9_lAQ,6067
-staran/models/__init__.py,sha256=NH4r6GTAz9MeUfq1jAyVkx-nC4bM78XvbWA9TuwMLik,2141
-staran/models/bank_configs.py,sha256=wN3GA_8cb5wevDC-sWRcJ3lMuaHahZVjC85K_t2aQt0,8177
+staran/models/__init__.py,sha256=VbfrRjmnp8KlFSEZOa-buECAaERptzAnvUUZK9dpgtY,2390
 staran/models/config.py,sha256=fTbZtJq4-ZuCSSd1eW7TkIbEdDyZv2agHJCYnwOCJ_s,8886
+staran/models/daifa_models.py,sha256=J7aqK41NDMDjacsjmxqwyuJfgf1kJx-Kaxj5CGQLISE,13166
 staran/models/registry.py,sha256=Zeey4TtbHtJ40odyZQzOLijyZCmlMBRuniPk_znS2Q8,10223
 staran/models/target.py,sha256=gKTTatxvOJjmE50qD6G6mhlYLuZL3Cvn3FLNbXl1eeU,10531
-staran/schemas/__init__.py,sha256=2RkcWCaIkrOHd37zzRCla0-jNg4cPnc6BGmmW5Vha0Y,652
-staran/schemas/document_generator.py,sha256=Mr7TjmKwspqxXnp9DhzZxsRx0l2Bo7MOI8mOxRtgwxU,13600
-staran/schemas/aum/__init__.py,sha256=jVkmJdhHGHdGE4rJ605zsRU2zIQMEHWnlgW2ZQk8AdU,13082
+staran/schemas/__init__.py,sha256=ztrBlQ3irbgM7gHB_dhiLEX1ZpDX2AAWOeiPnZTe-sk,779
+staran/schemas/aum/__init__.py,sha256=z0cuC6A3z-1cPKMDYrn0wCumjKkpk_0kfqGfW1JNEbc,9815
 staran/tools/__init__.py,sha256=KtudrYnxKD9HZEL4H-mrWlKrmsI3rYjJrLeC9YDTpG4,1054
 staran/tools/date.py,sha256=-QyEMWVx6czMuOIwcV7kR3gBMRVOwb5qevo7GEFSJKE,10488
-staran-0.5.0.dist-info/licenses/LICENSE,sha256=2EmsBIyDCono4iVXNpv5_px9qt2b7hfPq1WuyGVMNP4,1361
-staran-0.5.0.dist-info/METADATA,sha256=1c6403YfhOFEsZV7Ng1pe4B_wlRdp8SZypmhIH_AaVo,18809
-staran-0.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-staran-0.5.0.dist-info/top_level.txt,sha256=NOUZtXSh5oSIEjHrC0lQ9WmoKtD010Q00dghWyag-Zs,7
-staran-0.5.0.dist-info/RECORD,,
+staran/tools/document_generator.py,sha256=Mr7TjmKwspqxXnp9DhzZxsRx0l2Bo7MOI8mOxRtgwxU,13600
+staran-0.6.1.dist-info/licenses/LICENSE,sha256=2EmsBIyDCono4iVXNpv5_px9qt2b7hfPq1WuyGVMNP4,1361
+staran-0.6.1.dist-info/METADATA,sha256=_lLAAbTSVcGJ4hSj8DVXig4fGhgGVoYlu_YjR14IJ0M,20444
+staran-0.6.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+staran-0.6.1.dist-info/top_level.txt,sha256=NOUZtXSh5oSIEjHrC0lQ9WmoKtD010Q00dghWyag-Zs,7
+staran-0.6.1.dist-info/RECORD,,

staran/examples/__init__.py

@@ -1,8 +0,0 @@
-"""
-Staran Examples Module
-包含各种完整的特征工程示例
-"""
-
-from .aum_longtail import AUMLongtailExample, create_aum_example, run_aum_example
-
-__all__ = ['AUMLongtailExample', 'create_aum_example', 'run_aum_example']