factor minner

factor_mining/validator.py

@@ -0,0 +1,237 @@
+"""
+因子有效性检验模块：整合所有检验方案
+"""
+import numpy as np
+import pandas as pd
+from typing import Dict, List, Optional
+from dataclasses import dataclass
+from statsmodels.regression.linear_model import OLS
+
+from validation import (
+    compute_ic,
+    compute_rolling_ic,
+    group_backtest,
+    factor_span_regression
+)
+
+
+@dataclass
+class ValidationConfig:
+    """验证配置"""
+    ic_window: int = 30
+    ic_method: str = "spearman"  # "spearman" or "pearson"
+    n_groups: int = 3
+    group_period: int = 180
+    min_ic: float = 0.01
+    min_tstat: float = 1.5
+    min_r2_change: float = 0.05
+
+
+class FactorValidator:
+    """因子有效性检验器"""
+    
+    def __init__(self, config: ValidationConfig):
+        self.config = config
+    
+    def validate_ic(
+        self,
+        factor: pd.Series,
+        forward_return: pd.Series
+    ) -> Dict:
+        """
+        IC检验
+        
+        Returns:
+        --------
+        dict: 包含mean_ic, ic_ir, ic_series等
+        """
+        rolling_ic = compute_rolling_ic(
+            factor,
+            forward_return,
+            window=self.config.ic_window,
+            method=self.config.ic_method
+        )
+        
+        mean_ic = rolling_ic.mean()
+        ic_std = rolling_ic.std()
+        ic_ir = mean_ic / (ic_std + 1e-8)  # IC信息比率
+        
+        return {
+            "mean_ic": mean_ic,
+            "ic_std": ic_std,
+            "ic_ir": ic_ir,
+            "ic_series": rolling_ic,
+            "is_valid": abs(mean_ic) >= self.config.min_ic
+        }
+    
+    def validate_group_backtest(
+        self,
+        factor: pd.Series,
+        forward_return: pd.Series
+    ) -> Dict:
+        """
+        分组回测检验
+        
+        Returns:
+        --------
+        dict: 包含mean_h_l_return, mean_h_l_tstat等
+        """
+        result = group_backtest(
+            factor,
+            forward_return,
+            n_groups=self.config.n_groups,
+            group_period=self.config.group_period
+        )
+        
+        is_valid = abs(result.get('mean_h_l_tstat', 0)) >= self.config.min_tstat
+        
+        return {
+            **result,
+            "is_valid": is_valid
+        }
+    
+    def validate_regression(
+        self,
+        factor: pd.Series,
+        forward_return: pd.Series,
+        other_factors: Optional[pd.DataFrame] = None
+    ) -> Dict:
+        """
+        因子跨度回归检验
+        
+        Parameters:
+        -----------
+        factor : Series
+            待检验因子
+        forward_return : Series
+            未来收益率
+        other_factors : DataFrame, optional
+            其他因子（用于控制变量）
+        
+        Returns:
+        --------
+        dict: 包含beta, tstat, r2_change等
+        """
+        if other_factors is None:
+            other_factors = pd.DataFrame()
+        
+        # 合并因子
+        factors_df = pd.concat([other_factors, factor.to_frame(name='target')], axis=1)
+        
+        result = factor_span_regression(
+            factors_df,
+            forward_return,
+            target_factor='target'
+        )
+        
+        is_valid = (
+            abs(result.get('tstat', 0)) >= self.config.min_tstat and
+            result.get('r2_change', 0) >= self.config.min_r2_change
+        )
+        
+        return {
+            **result,
+            "is_valid": is_valid
+        }
+    
+    def validate_all(
+        self,
+        factor: pd.Series,
+        forward_return: pd.Series,
+        other_factors: Optional[pd.DataFrame] = None
+    ) -> Dict:
+        """
+        综合检验：执行所有检验方法
+        
+        Returns:
+        --------
+        dict: 包含所有检验结果和综合判断
+        """
+        results = {}
+        
+        # IC检验
+        ic_result = self.validate_ic(factor, forward_return)
+        results['ic'] = ic_result
+        
+        # 分组回测
+        group_result = self.validate_group_backtest(factor, forward_return)
+        results['group_backtest'] = group_result
+        
+        # 回归检验
+        reg_result = self.validate_regression(factor, forward_return, other_factors)
+        results['regression'] = reg_result
+        
+        # 综合判断
+        is_valid = (
+            ic_result['is_valid'] and
+            group_result['is_valid'] and
+            reg_result['is_valid']
+        )
+        
+        results['is_valid'] = is_valid
+        results['score'] = self._calculate_score(ic_result, group_result, reg_result)
+        
+        return results
+    
+    def _calculate_score(
+        self,
+        ic_result: Dict,
+        group_result: Dict,
+        reg_result: Dict
+    ) -> float:
+        """计算综合得分"""
+        score = 0.0
+        
+        # IC得分（权重0.3）
+        ic_score = abs(ic_result.get('mean_ic', 0)) * 10
+        score += ic_score * 0.3
+        
+        # 分组回测得分（权重0.4）
+        tstat = abs(group_result.get('mean_h_l_tstat', 0))
+        tstat_score = min(tstat / 3.0, 1.0)  # 归一化到[0, 1]
+        score += tstat_score * 0.4
+        
+        # 回归得分（权重0.3）
+        r2_change = reg_result.get('r2_change', 0)
+        r2_score = min(r2_change / 0.1, 1.0)  # 归一化到[0, 1]
+        score += r2_score * 0.3
+        
+        return score
+    
+    def filter_factors(
+        self,
+        factors: pd.DataFrame,
+        forward_return: pd.Series
+    ) -> pd.DataFrame:
+        """
+        批量过滤因子：只保留有效因子
+        
+        Returns:
+        --------
+        DataFrame: 有效因子
+        """
+        valid_factors = []
+        
+        for col in factors.columns:
+            factor = factors[col]
+            result = self.validate_all(factor, forward_return, factors.drop(columns=[col]))
+            
+            if result['is_valid']:
+                valid_factors.append(col)
+        
+        return factors[valid_factors] if valid_factors else pd.DataFrame()
+
+
+def create_validator(
+    ic_window: int = 30,
+    min_ic: float = 0.01,
+    min_tstat: float = 1.5
+) -> FactorValidator:
+    """创建验证器（便捷函数）"""
+    config = ValidationConfig(
+        ic_window=ic_window,
+        min_ic=min_ic,
+        min_tstat=min_tstat
+    )
+    return FactorValidator(config)
+