staran 0.6.0__py3-none-any.whl → 0.6.1__py3-none-any.whl

{staran-0.6.0.dist-info → staran-0.6.1.dist-info}/METADATA

@@ -1,42 +1,64 @@
 Metadata-Version: 2.4
 Name: staran
-Version: 0.6.0
+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## ✨ v0.6.0 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-0.6.0.dist-info → staran-0.6.1.dist-info}/RECORD

@@ -6,28 +6,23 @@ 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=VbfrRjmnp8KlFSEZOa-buECAaERptzAnvUUZK9dpgtY,2390
-staran/models/bank_configs.py,sha256=wN3GA_8cb5wevDC-sWRcJ3lMuaHahZVjC85K_t2aQt0,8177
 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=ztrBlQ3irbgM7gHB_dhiLEX1ZpDX2AAWOeiPnZTe-sk,779
-staran/schemas/document_generator.py,sha256=Mr7TjmKwspqxXnp9DhzZxsRx0l2Bo7MOI8mOxRtgwxU,13600
 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/tools/document_generator.py,sha256=Mr7TjmKwspqxXnp9DhzZxsRx0l2Bo7MOI8mOxRtgwxU,13600
-staran-0.6.0.dist-info/licenses/LICENSE,sha256=2EmsBIyDCono4iVXNpv5_px9qt2b7hfPq1WuyGVMNP4,1361
-staran-0.6.0.dist-info/METADATA,sha256=KTBVO9J_Z20Nya-Mj48lXDTUNjWRfbU9wwo81__y7fk,18809
-staran-0.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-staran-0.6.0.dist-info/top_level.txt,sha256=NOUZtXSh5oSIEjHrC0lQ9WmoKtD010Q00dghWyag-Zs,7
-staran-0.6.0.dist-info/RECORD,,
+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']

staran/examples/aum_longtail.py

@@ -1,250 +0,0 @@
-"""
-AUM代发长尾模型示例
-基于Staran v0.3.0架构，使用schemas模块的预定义表结构
-"""
-
-from typing import Dict, Optional
-from ..engines import create_turing_engine
-from ..features import FeatureManager, FeatureConfig, FeatureType
-from ..tools import Date
-from ..schemas.aum import get_aum_schemas
-
-
-class AUMLongtailExample:
-    """AUM代发长尾模型示例类"""
-    
-    def __init__(self, database: str = "dwegdata03000"):
-        """
-        初始化AUM长尾模型示例
-        
-        Args:
-            database: 数据库名称，默认为dwegdata03000
-        """
-        self.database = database
-        self.engine = create_turing_engine(database)
-        self.schemas = get_aum_schemas()  # 从schemas模块获取预定义的表结构
-        
-    def run(self, feature_date: Optional[str] = None, output_path: str = "file:///nfsHome/aum_longtail") -> Dict:
-        """
-        运行完整的AUM长尾模型特征工程
-        
-        Args:
-            feature_date: 特征日期，格式为YYYYMM，默认为当前月
-            output_path: 输出路径，默认为file:///nfsHome/aum_longtail
-            
-        Returns:
-            包含所有结果的字典
-        """
-        if feature_date is None:
-            feature_date = Date.today().format_compact()[:6]
-        
-        print(f"🚀 开始AUM长尾模型特征工程 - {feature_date}")
-        print("="*60)
-        
-        results = {}
-        
-        # 步骤1: 生成A表特征（行为特征表）- 只生成原始拷贝和聚合特征
-        print("📊 步骤1: 生成客户行为特征...")
-        results['behavior'] = self._generate_behavior_features('behavior', feature_date)
-        
-        # 步骤2: 生成B表特征（资产平均值表）- 完整特征
-        print("💰 步骤2: 生成资产平均值特征...")
-        results['asset_avg'] = self._generate_full_features('asset_avg', feature_date)
-        
-        # 步骤3: 生成C表特征（资产配置表）- 完整特征  
-        print("📈 步骤3: 生成资产配置特征...")
-        results['asset_config'] = self._generate_full_features('asset_config', feature_date)
-        
-        # 步骤4: 生成D表特征（月度统计表）- 完整特征
-        print("📋 步骤4: 生成月度统计特征...")
-        results['monthly_stat'] = self._generate_full_features('monthly_stat', feature_date)
-        
-        # 步骤5: 导出特征表
-        print("💾 步骤5: 导出特征表...")
-        results['exports'] = self._export_features(feature_date, output_path)
-        
-        print("="*60)
-        print("✅ AUM长尾模型特征工程完成！")
-        return results
-    
-    def _generate_behavior_features(self, table_type: str, feature_date: str) -> Dict:
-        """生成行为特征（A表）- 只生成原始拷贝和聚合特征"""
-        schema = self.schemas[table_type]
-        manager = FeatureManager(self.engine, self.database)
-        
-        # A表特征配置：只启用原始拷贝和聚合
-        config = FeatureConfig()
-        config.enable_feature(FeatureType.RAW_COPY)
-        config.enable_feature(FeatureType.AGGREGATION)
-        config.disable_feature(FeatureType.MOM)  # 不生成环比
-        config.disable_feature(FeatureType.YOY)  # 不生成同比
-        
-        print(f"   🔧 生成{schema.table_name}的特征...")
-        result = manager.generate_features(
-            schema=schema,
-            config=config,
-            feature_date=feature_date
-        )
-        
-        feature_count = manager.count_features(schema, config)
-        print(f"   ✅ A表特征生成完成: {feature_count}个特征")
-        return result
-    
-    def _generate_full_features(self, table_type: str, feature_date: str) -> Dict:
-        """生成完整特征（B、C、D表）- 聚合+5个月环比+1年同比"""
-        schema = self.schemas[table_type]
-        manager = FeatureManager(self.engine, self.database)
-        
-        # B、C、D表特征配置：完整特征集
-        config = FeatureConfig()
-        config.enable_feature(FeatureType.AGGREGATION)
-        config.enable_feature(FeatureType.MOM, mom_windows=[5])    # 5个月环比
-        config.enable_feature(FeatureType.YOY, yoy_windows=[12])  # 1年同比
-        
-        print(f"   🔧 生成{schema.table_name}的特征...")
-        result = manager.generate_features(
-            schema=schema,
-            config=config,
-            feature_date=feature_date
-        )
-        
-        feature_count = manager.count_features(schema, config)
-        print(f"   ✅ {table_type}表特征生成完成: {feature_count}个特征")
-        return result
-    
-    def _export_features(self, feature_date: str, output_path: str) -> Dict:
-        """导出所有特征表到指定路径"""
-        file_prefixes = {
-            'behavior': 'aum_behavior_features',
-            'asset_avg': 'aum_asset_avg_features',
-            'asset_config': 'aum_asset_config_features',
-            'monthly_stat': 'monthly_stat_features'
-        }
-        
-        results = {}
-        for table_type, file_prefix in file_prefixes.items():
-            print(f"   💾 导出{table_type}表...")
-            
-            # 构建特征表名
-            table_name = f"{self.schemas[table_type].table_name}_{feature_date}_f001"
-            
-            result = self.engine.download_table_data(
-                table_name=f"{self.database}.{table_name}",
-                output_path=f"{output_path}/{file_prefix}_{feature_date}.parquet",
-                mode="cluster"
-            )
-            
-            results[table_type] = result
-            print(f"   ✅ 导出 {table_type}: {result.get('status', 'unknown')}")
-        
-        return results
-    
-    def get_summary(self) -> Dict:
-        """获取示例摘要信息"""
-        summary = {
-            'database': self.database,
-            'tables': {},
-            'total_features': 0
-        }
-        
-        for table_type, schema in self.schemas.items():
-            try:
-                manager = FeatureManager(self.engine, self.database)
-                
-                if table_type == 'behavior':
-                    # A表只有原始拷贝和聚合特征
-                    config = FeatureConfig()
-                    config.enable_feature(FeatureType.RAW_COPY)
-                    config.enable_feature(FeatureType.AGGREGATION)
-                    config.disable_feature(FeatureType.MOM)
-                    config.disable_feature(FeatureType.YOY)
-                else:
-                    # B、C、D表包含完整特征：聚合+5个月MoM+1年YoY
-                    config = FeatureConfig()
-                    config.enable_feature(FeatureType.AGGREGATION, mom_windows=[5], yoy_windows=[12])
-                
-                feature_count = manager.count_features(schema, config)
-                summary['tables'][table_type] = {
-                    'table_name': schema.table_name,
-                    'field_count': len(schema.fields),
-                    'feature_count': feature_count,
-                    'features': {
-                        'total': feature_count,
-                        'aggregation': len(schema.fields),  # 估算
-                        'mom': len(schema.fields) * 5 if table_type != 'behavior' else 0,
-                        'yoy': len(schema.fields) * 1 if table_type != 'behavior' else 0
-                    }
-                }
-                summary['total_features'] += feature_count
-            except Exception as e:
-                # 在模拟模式下返回预估数量
-                base_fields = len(schema.fields)
-                if table_type == 'behavior':
-                    estimated_features = base_fields * 2  # 原始拷贝 + 聚合
-                    agg_count = base_fields
-                    mom_count = 0
-                    yoy_count = 0
-                else:
-                    estimated_features = base_fields * 8  # 聚合 + MoM + YoY 组合
-                    agg_count = base_fields
-                    mom_count = base_fields * 5
-                    yoy_count = base_fields * 1
-                
-                summary['tables'][table_type] = {
-                    'table_name': schema.table_name,
-                    'field_count': base_fields,
-                    'feature_count': estimated_features,
-                    'mode': 'estimated',
-                    'features': {
-                        'total': estimated_features,
-                        'aggregation': agg_count,
-                        'mom': mom_count,
-                        'yoy': yoy_count
-                    }
-                }
-                summary['total_features'] += estimated_features
-        
-        return summary
-
-
-# 简化的API函数
-def create_aum_example(database: str = "dwegdata03000") -> AUMLongtailExample:
-    """
-    一键创建AUM长尾模型示例
-    
-    Args:
-        database: 数据库名称，默认为dwegdata03000
-        
-    Returns:
-        AUMLongtailExample实例
-    """
-    return AUMLongtailExample(database)
-
-
-def run_aum_example(feature_date: Optional[str] = None, 
-                   database: str = "dwegdata03000",
-                   output_path: str = "file:///nfsHome/aum_longtail") -> Dict:
-    """
-    一键运行AUM长尾模型特征工程
-    
-    Args:
-        feature_date: 特征日期，格式为YYYYMM，默认为当前月
-        database: 数据库名称，默认为dwegdata03000
-        output_path: 输出路径，默认为file:///nfsHome/aum_longtail
-        
-    Returns:
-        包含所有结果的字典
-        
-    Example:
-        >>> results = run_aum_example('202507')
-        >>> print(f"生成特征数: {len(results)}")
-    """
-    example = create_aum_example(database)
-    return example.run(feature_date, output_path)
-
-
-__all__ = [
-    'AUMLongtailExample',
-    'create_aum_example', 
-    'run_aum_example'
-]