feat(factors): 新增筹码集中度相关因子并优化训练框架

- 添加 19 个筹码分布和胜率相关因子(包括chip_dispersion、winner_rate等系列)
- LightGBM模型添加早停和训练指标记录功能
- 统一Label配置到common.py模块
- 新增list_factors.py因子列表脚本

src/scripts/list_factors.py

@@ -0,0 +1,81 @@
+"""列出所有已入库的因子。
+
+以 Python 列表格式输出所有已注册因子的名称，方便复制使用。
+保持 factors.jsonl 中的原始顺序（按 factor_id）。
+
+使用方法:
+    uv run python -m src.scripts.list_factors
+"""
+
+import json
+import re
+from pathlib import Path
+
+from src.config.settings import get_settings
+
+
+def extract_factor_id_number(factor_id: str) -> int:
+    """从 factor_id 中提取数字部分用于排序。
+
+    Args:
+        factor_id: 如 "F_001"
+
+    Returns:
+        数字部分，如 1
+    """
+    match = re.match(r"F_(\d+)", factor_id)
+    if match:
+        return int(match.group(1))
+    return 0
+
+
+def list_factors():
+    """读取 factors.jsonl 并按 factor_id 顺序打印因子名称列表。"""
+    settings = get_settings()
+    factors_path = settings.data_path_resolved / "factors.jsonl"
+
+    if not factors_path.exists():
+        print(f"[错误] 因子文件不存在: {factors_path}")
+        return
+
+    # 读取所有因子并按 factor_id 排序
+    factors = []
+    try:
+        with open(factors_path, "r", encoding="utf-8") as f:
+            for line in f:
+                line = line.strip()
+                if not line:
+                    continue
+                try:
+                    data = json.loads(line)
+                    factor_id = data.get("factor_id", "")
+                    name = data.get("name")
+                    if name and factor_id:
+                        factors.append((factor_id, name))
+                except json.JSONDecodeError:
+                    continue
+    except Exception as e:
+        print(f"[错误] 读取因子文件失败: {e}")
+        return
+
+    if not factors:
+        print("[信息] 没有找到任何因子")
+        return
+
+    # 按 factor_id 数字排序（保持入库顺序）
+    factors.sort(key=lambda x: extract_factor_id_number(x[0]))
+
+    # 以 Python 列表格式输出
+    print("[")
+    for i, (factor_id, name) in enumerate(factors):
+        if i == len(factors) - 1:
+            print(f'    "{name}"')
+        else:
+            print(f'    "{name}",')
+    print("]")
+
+    print(f"\n[统计] 共计 {len(factors)} 个因子")
+
+
+if __name__ == "__main__":
+    list_factors()

src/scripts/register_factors.py

@@ -26,24 +26,126 @@ from typing import Any, Dict, List, Optional
 
 from src.factors.metadata import FactorManager
 from src.factors.metadata.exceptions import DuplicateFactorError, ValidationError
+from src.config.settings import get_settings
 
 
 # ============================================================================
 # 用户配置区域 - 在这里添加要注册的因子
 # ============================================================================
 
-FACTORS: List[Dict[str, Any]] = [
-    # 示例因子，请根据实际需要修改或添加
+FACTORS: List[Dict[str, Any]] =[
+    # ==================== 第一类：筹码集中度与离散度因子 ====================
     {
-        "name": "turnover_volatility_ratio",
-        "desc": "5日价格动量，收盘价相对于5日前收盘价的涨跌幅进行截面排名",
-        "dsl": "cs_rank(close / ts_delay(close, 5) - 1)",
-        "category": "momentum",
+        "name": "chip_dispersion_90",
+        "desc": "90%筹码离散度：衡量市场90%持仓筹码的宽度，值越小表示筹码越高度集中（单峰密集），往往是洗盘结束的前兆",
+        "dsl": "(cost_95pct - cost_5pct) / (cost_95pct + cost_5pct)",
+    },
+    {
+        "name": "chip_dispersion_70",
+        "desc": "70%核心筹码离散度：剔除极端的底部死筹和高位套牢盘，反映中间70%主流资金的成本集中度",
+        "dsl": "(cost_85pct - cost_15pct) / (cost_85pct + cost_15pct)",
+    },
+    {
+        "name": "cost_skewness",
+        "desc": "筹码偏度：反映筹码分布的不对称性。大于1说明上方套牢盘拖尾严重，小于1说明下方获利盘雄厚",
+        "dsl": "(cost_95pct - cost_50pct) / (cost_50pct - cost_5pct)",
+    },
+    {
+        "name": "dispersion_change_20",
+        "desc": "筹码集中度近期变化率：过去20天筹码宽度的变化比例，持续下降说明主力正在暗中吸筹",
+        "dsl": "ts_pct_change((cost_95pct - cost_5pct) / cost_50pct, 20)",
+    },
+
+    # ==================== 第二类：筹码相对位置与压力/支撑因子 ====================
+    {
+        "name": "price_to_avg_cost",
+        "desc": "整体浮盈比例：当前价格相对加权平均成本的溢价率。高溢价有均值回归压力，负溢价代表超跌",
+        "dsl": "(close - weight_avg) / weight_avg",
+    },
+    {
+        "name": "price_to_median_cost",
+        "desc": "中位数成本偏离度：价格相对于50%分位点（绝对半数人持仓价）的偏离，向上突破通常是右侧买点",
+        "dsl": "(close - cost_50pct) / cost_50pct",
+    },
+    {
+        "name": "mean_median_dev",
+        "desc": "均值中位数背离：均值显著大于中位数说明高位筹码堆积，上涨阻力大",
+        "dsl": "(weight_avg - cost_50pct) / cost_50pct",
+    },
+    {
+        "name": "trap_pressure",
+        "desc": "高位套牢盘压力指数：当前价格距离上方95%高位套牢成本的距离。距离越大，反弹的真空期阻力越小",
+        "dsl": "(cost_95pct - close) / close",
+    },
+    {
+        "name": "bottom_profit",
+        "desc": "底部支撑底仓利润率：当前价格距离底部5%筹码的利润空间。暴跌时大于0说明底仓极度稳定",
+        "dsl": "(close - cost_5pct) / cost_5pct",
+    },
+    {
+        "name": "history_position",
+        "desc": "历史区间分位点：当前价格在个股上市以来历史最高点和最低点之间的相对位置",
+        "dsl": "(close - his_low) / (his_high - his_low)",
+    },
+
+    # ==================== 第三类：胜率相关的动量与反转因子 ====================
+    {
+        "name": "winner_rate_surge_5",
+        "desc": "获利盘短期爆发力：胜率在过去5天内的变化值，急剧上升是极强的动量做多信号",
+        "dsl": "ts_delta(winner_rate, 5)",
+    },
+    {
+        "name": "winner_rate_cs_rank",
+        "desc": "获利盘高位反转信号：全市场胜率截面排名，极端高胜率往往面临多头踩踏的获利了结压力（反转因子）",
+        "dsl": "cs_rank(winner_rate)",
+    },
+    {
+        "name": "winner_rate_dev_20",
+        "desc": "获利盘均线偏离：当前胜率相对过去20天平均胜率的偏离程度，捕捉筹码情绪的边际超买/超卖",
+        "dsl": "winner_rate - ts_mean(winner_rate, 20)",
+    },
+    {
+        "name": "winner_rate_volatility",
+        "desc": "获利盘波动率：过去20天胜率的波动率。波动率低且胜率高说明单边上涨极度稳健",
+        "dsl": "ts_std(winner_rate, 20)",
+    },
+    {
+        "name": "smart_money_accumulation",
+        "desc": "潜在主力吸筹隐蔽指标：胜率的60日时序分位数减去价格的时序分位数。值越大说明‘价平而获利盘增’，底部吸筹明显",
+        "dsl": "ts_rank(winner_rate, 60) - ts_rank(close, 60)",
+    },
+
+    # ==================== 第四类：量价与筹码交乘因子 ====================
+    {
+        "name": "winner_vol_corr_20",
+        "desc": "放量突破筹码密集区：胜率与成交量的20日时序相关性，正相关说明增量资金在主动解套上方筹码",
+        "dsl": "ts_corr(winner_rate, vol, 20)",
+    },
+    {
+        "name": "cost_base_momentum",
+        "desc": "成本重心上移换手率：过去20天加权平均成本的变化幅度，快速上移说明高位换手极其充分",
+        "dsl": "ts_pct_change(weight_avg, 20)",
+    },
+    {
+        "name": "bottom_cost_stability",
+        "desc": "底部坚如磐石因子：底部5%成本的60天波动率相对于中位数的比值，波动越小说明死筹越稳固",
+        "dsl": "ts_std(cost_5pct, 60) / cost_50pct",
+    },
+    {
+        "name": "pivot_reversion",
+        "desc": "盈亏分界线乖离修复：价格偏离50%分位点除以近20日价格标准差，用于寻找超跌后的均值回归买点",
+        "dsl": "(close - cost_50pct) / ts_std(close, 20)",
+    },
+    {
+        "name": "chip_transition",
+        "desc": "强弱筹码切换度：上方厚度与下方厚度差值的20日变化量。由正变负说明筹码彻底完成了自上而下的转移（洗盘结束）",
+        "dsl": "ts_delta((cost_85pct - cost_50pct) - (cost_50pct - cost_15pct), 20)",
     },
 ]
 
-# 因子存储路径（默认使用实验目录）
-OUTPUT_PATH = Path(__file__).parent.parent / "experiment" / "data" / "factors.jsonl"
+# 因子存储路径（使用项目根路径下的 data 目录）
+settings = get_settings()
+OUTPUT_PATH = settings.data_path_resolved / "factors.jsonl"
 
 
 # ============================================================================