1、策略更新

2、新增qmt
2025-11-29 00:23:12 +08:00
parent 0a942f92d1
commit c9b61db5b7
47 changed files with 97116 additions and 8867 deletions
--- a/main/factor/money_flow_factors.py
+++ b/main/factor/money_flow_factors.py
@@ -0,0 +1,348 @@
+"""
+资金流因子模块
+包含基于股票截面的资金流因子实现
+"""
+
+import numpy as np
+import polars as pl
+from main.factor.operator_framework import StockWiseFactor
+
+
+class LGFlowFactor(StockWiseFactor):
+    """大单净买量因子"""
+    
+    def __init__(self):
+        super().__init__(
+            name="lg_flow",
+            parameters={},
+            required_factor_ids=["buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol"]
+        )
+
+    def calc_factor(self, group_df: pl.DataFrame) -> pl.Series:
+        # 计算大单净买量
+        buy_lg = group_df["buy_lg_vol"]
+        buy_elg = group_df["buy_elg_vol"]
+        sell_lg = group_df["sell_lg_vol"]
+        sell_elg = group_df["sell_elg_vol"]
+        
+        lg_net_flow = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        return lg_net_flow.alias(self.factor_id)
+
+
+class FlowIntensityFactor(StockWiseFactor):
+    """资金流强度因子"""
+    
+    def __init__(self):
+        super().__init__(
+            name="flow_intensity",
+            parameters={},
+            required_factor_ids=["buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol", "vol"]
+        )
+
+    def calc_factor(self, group_df: pl.DataFrame) -> pl.Series:
+        # 计算资金流强度
+        buy_lg = group_df["buy_lg_vol"]
+        buy_elg = group_df["buy_elg_vol"]
+        sell_lg = group_df["sell_lg_vol"]
+        sell_elg = group_df["sell_elg_vol"]
+        vol = group_df["vol"]
+        
+        lg_net_flow = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        flow_intensity = lg_net_flow / (vol + 1e-8)  # 避免除零
+        
+        return flow_intensity.alias(self.factor_id)
+
+
+class FlowDivergenceFactor(StockWiseFactor):
+    """资金流背离因子"""
+    
+    def __init__(self):
+        super().__init__(
+            name="flow_divergence",
+            parameters={},
+            required_factor_ids=["buy_sm_vol", "sell_sm_vol", "buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol"]
+        )
+
+    def calc_factor(self, group_df: pl.DataFrame) -> pl.Series:
+        # 计算资金流背离度
+        buy_sm = group_df["buy_sm_vol"]
+        sell_sm = group_df["sell_sm_vol"]
+        buy_lg = group_df["buy_lg_vol"]
+        buy_elg = group_df["buy_elg_vol"]
+        sell_lg = group_df["sell_lg_vol"]
+        sell_elg = group_df["sell_elg_vol"]
+        
+        sm_net_flow = buy_sm - sell_sm
+        lg_net_flow = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        
+        flow_divergence = sm_net_flow - lg_net_flow
+        return flow_divergence.alias(self.factor_id)
+
+
+class FlowStructureFactor(StockWiseFactor):
+    """资金流结构因子"""
+    
+    def __init__(self):
+        super().__init__(
+            name="flow_structure",
+            parameters={},
+            required_factor_ids=["buy_sm_vol", "buy_lg_vol", "buy_elg_vol", "vol"]
+        )
+
+    def calc_factor(self, group_df: pl.DataFrame) -> pl.Series:
+        # 计算资金流结构
+        buy_sm = group_df["buy_sm_vol"]
+        buy_lg = group_df["buy_lg_vol"]
+        buy_elg = group_df["buy_elg_vol"]
+        vol = group_df["vol"]
+        
+        total_buy = buy_sm + buy_lg + buy_elg
+        lg_elg_buy_prop = (buy_lg + buy_elg) / (total_buy + 1e-8)  # 避免除零
+        
+        flow_structure = lg_elg_buy_prop.diff().alias(self.factor_id)
+        return flow_structure
+
+
+class FlowAccelerationFactor(StockWiseFactor):
+    """资金流加速度因子"""
+    
+    def __init__(self):
+        super().__init__(
+            name="flow_acceleration",
+            parameters={},
+            required_factor_ids=["buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol"]
+        )
+
+    def calc_factor(self, group_df: pl.DataFrame) -> pl.Series:
+        # 计算资金流加速度
+        buy_lg = group_df["buy_lg_vol"]
+        buy_elg = group_df["buy_elg_vol"]
+        sell_lg = group_df["sell_lg_vol"]
+        sell_elg = group_df["sell_elg_vol"]
+        
+        lg_net_flow = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        lg_net_flow_change = lg_net_flow.diff()
+        flow_acceleration = lg_net_flow_change.diff()
+        
+        return flow_acceleration.alias(self.factor_id)
+
+
+class CostSqueeze(StockWiseFactor):
+    factor_id = "factor_cost_squeeze"
+    required_factor_ids = ["close", "cost_15pct", "cost_50pct", "cost_85pct", "vol"]
+
+    def __init__(self):
+        super().__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        close = g["close"]
+        cost15 = g["cost_15pct"]
+        cost50 = g["cost_50pct"]
+        cost85 = g["cost_85pct"]
+        vol = g["vol"]
+
+        cost_range = cost85 - cost15
+        median_cost = cost50
+        price_pos = (close - median_cost) / (cost_range + 1e-6)
+
+        vol_5d = vol.rolling_mean(window_size=5, min_periods=1)
+        vol_ratio = vol / (vol_5d + 1e-6)
+
+        # 核心逻辑：成本区间窄 + 价格居中 + 量能萎缩 → 高挤压度
+        squeeze_score = (
+            (1.0 / (cost_range / (close + 1e-6) + 1e-6))
+            * (1.0 - price_pos.abs())
+            * (1.0 / (vol_ratio + 1e-6))
+        )
+
+        # 稳态化：对数变换
+        factor = (squeeze_score + 1.0).log()
+        return factor.alias(self.factor_id)
+    
+
+class HighCostSelling(StockWiseFactor):
+    factor_id = "factor_high_cost_selling"
+    required_factor_ids = ["close", "cost_85pct", "buy_sm_vol", "sell_lg_vol", "vol"]
+
+    def __init__(self):
+        super().__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        close = g["close"]
+        cost85 = g["cost_85pct"]
+        buy_sm_vol = g["buy_sm_vol"]
+        sell_lg_vol = g["sell_lg_vol"]
+        vol = g["vol"]
+
+        is_above_85 = (close > cost85).cast(pl.Float64)
+        small_buy_ratio = buy_sm_vol / (vol + 1e-6)
+        large_sell_ratio = sell_lg_vol / (vol + 1e-6)
+
+        hcsp = is_above_85 * small_buy_ratio * large_sell_ratio
+
+        # 稳态化：取对数（避免极端值）
+        factor = (hcsp + 1e-6).log()
+        return factor.alias(self.factor_id)
+    
+
+class LowCostAccumulation(StockWiseFactor):
+    factor_id = "factor_low_cost_accumulation"
+    required_factor_ids = ["close", "his_low", "cost_15pct", "buy_lg_vol", "buy_elg_vol", "vol"]
+
+    def __init__(self):
+        super().__init__(
+            name=self.factor_id,
+            parameters={},  # 无参数，可扩展
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        close = g["close"]
+        his_low = g["his_low"]
+        cost15 = g["cost_15pct"]
+        buy_lg_vol = g["buy_lg_vol"]
+        buy_elg_vol = g["buy_elg_vol"]
+        vol = g["vol"]
+
+        is_below_15 = (close < cost15).cast(pl.Float64)
+
+        # 近5日最低价（含当日）
+        rolling_min_5 = his_low.rolling_min(window_size=5, min_periods=1)
+        # 注意：his_low 通常是历史最低，但这里我们用 close 的滚动最小更合理
+        # 修正：应使用 close 的滚动最小判断是否新低
+        close_rolling_min_5 = close.rolling_min(window_size=5, min_periods=1)
+        not_new_low = (close >= close_rolling_min_5).cast(pl.Float64)
+
+        big_buy_vol = buy_lg_vol + buy_elg_vol
+        big_buy_ratio = big_buy_vol / (vol + 1e-6)
+
+        lc_am = is_below_15 * not_new_low * big_buy_ratio
+
+        # 稳态化
+        factor = (lc_am + 1e-6).log()
+        return factor.alias(self.factor_id)
+    
+
+
+class InstNetAccum(StockWiseFactor):
+    factor_id = "inst_net_accum"
+    required_factor_ids = ["close", "buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol", "circ_mv"]
+
+    def __init__(self):
+        super(InstNetAccum, self).__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        close = g["close"]
+        buy_lg = g["buy_lg_vol"]
+        buy_elg = g["buy_elg_vol"]
+        sell_lg = g["sell_lg_vol"]
+        sell_elg = g["sell_elg_vol"]
+        circ_mv = g["circ_mv"]
+
+        big_net_vol = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        circ_shares = circ_mv / (close + 1e-6)
+        ina = big_net_vol / (circ_shares + 1e-6)
+
+        # 3日收益率（抑制大涨）
+        ret3 = close / close.shift(3) - 1
+        ret3 = ret3.fill_null(strategy="forward").fill_null(0.0)
+        ina = pl.when(ret3.abs() < 0.05).then(ina).otherwise(0.0)
+
+        return ina.log1p().alias(self.factor_id)
+    
+class ChipLockin(StockWiseFactor):
+    factor_id = "chip_lockin"
+    required_factor_ids = ["cost_5pct", "cost_95pct", "winner_rate"]
+
+    def __init__(self):
+        super(ChipLockin, self).__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        cost5 = g["cost_5pct"]
+        cost95 = g["cost_95pct"]
+        winner_rate = g["winner_rate"]
+
+        cost_width = cost95 - cost5
+        width_5d = cost_width.rolling_mean(window_size=5, min_periods=1)
+        width_10d = cost_width.rolling_mean(window_size=10, min_periods=1)
+
+        # 避免除零
+        width_contraction = (width_10d - width_5d) / (width_10d + 1e-6)
+        winner_std_5 = winner_rate.rolling_std(window_size=5, min_periods=1).fill_null(1e-6)
+
+        clm = width_contraction * (1.0 / (winner_std_5 + 1e-6))
+        return clm.log1p().alias(self.factor_id)
+    
+
+class RetailOutInstIn(StockWiseFactor):
+    factor_id = "retail_out_inst_in"
+    required_factor_ids = ["close", "buy_sm_vol", "sell_sm_vol", "buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol"]
+
+    def __init__(self):
+        super(RetailOutInstIn, self).__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        close = g["close"]
+        buy_sm = g["buy_sm_vol"]
+        sell_sm = g["sell_sm_vol"]
+        buy_lg = g["buy_lg_vol"]
+        buy_elg = g["buy_elg_vol"]
+        sell_lg = g["sell_lg_vol"]
+        sell_elg = g["sell_elg_vol"]
+
+        small_net_out = sell_sm - buy_sm
+        big_net_in = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+
+        # 价格抗跌：近5日未破位（用 close 自身滚动最小）
+        close_min_5 = close.rolling_min(window_size=5, min_periods=1)
+
+        roii = small_net_out * big_net_in
+        return roii.log1p().alias(self.factor_id)
+    
+
+class AccumAccel(StockWiseFactor):
+    factor_id = "accum_accel"
+    required_factor_ids = ["buy_lg_vol", "buy_elg_vol", "sell_lg_vol", "sell_elg_vol", "vol"]
+
+    def __init__(self):
+        super(AccumAccel, self).__init__(
+            name=self.factor_id,
+            parameters={},
+            required_factor_ids=self.required_factor_ids
+        )
+
+    def calc_factor(self, g: pl.DataFrame) -> pl.Series:
+        buy_lg = g["buy_lg_vol"]
+        buy_elg = g["buy_elg_vol"]
+        sell_lg = g["sell_lg_vol"]
+        sell_elg = g["sell_elg_vol"]
+        vol = g["vol"]
+
+        big_net_vol = (buy_lg + buy_elg) - (sell_lg + sell_elg)
+        big_net_ratio = big_net_vol / (vol + 1e-6)
+
+        net_5d = big_net_ratio.rolling_mean(window_size=5, min_periods=1)
+        net_5d_lag = net_5d.shift(5).fill_null(strategy="forward").fill_null(0.0)
+        acceleration = net_5d - net_5d_lag
+
+        return acceleration.log1p().alias(self.factor_id)