添加 ChanPivotClassifier: 中枢结构特征提取 + 标签化

Phase 1 训练数据集构建工具，从笔中枢提取 3 特征 (duration_norm, contraction, shift_norm) + 1 标签 (break_direction)。 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-25 18:33:56 +08:00
parent 9eae12f07d
commit 5ad761fad4
2 changed files with 530 additions and 0 deletions
@@ -0,0 +1,258 @@
+"""
+中枢结构特征提取 + 标签化
+Market Structure Dataset Builder — Phase 1
+
+定位: 训练数据集构建工具，不是交易信号生成器。
+Feature 描述中枢内部结构，Label 记录中枢后实际演化。
+"""
+
+import math
+import json
+from ChanEnum import Chan_BI_DIR
+
+
+class ChanPivotClassifier:
+    """
+    中枢结构特征提取 + 标签化
+    输入: bi_zs_list (list[ChanBIZS])
+    输出: 结构化数据集 (list[dict])
+    """
+
+    DATASET_VERSION = "pivot_v1"
+    FEATURE_SCHEMA = ["duration_norm", "contraction", "shift_norm"]
+    LABEL_SCHEMA = {"name": "break_direction", "values": ["up", "down", "none"]}
+
+    def __init__(self, bi_zs_list: list, symbol: str = "", timeframe: str = ""):
+        self.bi_zs_list = bi_zs_list
+        self.symbol = symbol
+        self.timeframe = timeframe
+
+    # ------------------------------------------------------------------
+    # Feature extraction
+    # ------------------------------------------------------------------
+
+    def _calc_duration(self, zs) -> int:
+        """持续时间: 第一笔首K → 最后一笔末K 的 index 差"""
+        bi_list = zs.bi_list
+        start_idx = bi_list[0].start_klc.index
+        end_idx = bi_list[-1].end_klc.index
+        return end_idx - start_idx
+
+    def _calc_contraction(self, zs) -> float:
+        """收敛率: 后窗口振幅均值 / 前窗口振幅均值"""
+        bi_list = zs.bi_list
+        if len(bi_list) < 4:
+            return 1.0
+
+        n = min(3, len(bi_list) // 2)
+        first_ranges = [bi.high - bi.low for bi in bi_list[:n]]
+        last_ranges = [bi.high - bi.low for bi in bi_list[-n:]]
+
+        first_mean = sum(first_ranges) / len(first_ranges)
+        last_mean = sum(last_ranges) / len(last_ranges)
+
+        if first_mean == 0:
+            return 1.0
+        return last_mean / first_mean
+
+    def _calc_shift(self, zs) -> tuple[float, float]:
+        """重心漂移: 前后半段重心均值差 (原始值, 归一化值)"""
+        bi_list = zs.bi_list
+        mid = len(bi_list) // 2
+
+        first_centers = [(bi.high + bi.low) / 2 for bi in bi_list[:mid]]
+        last_centers = [(bi.high + bi.low) / 2 for bi in bi_list[mid:]]
+
+        shift_raw = (
+            sum(last_centers) / len(last_centers)
+            - sum(first_centers) / len(first_centers)
+        )
+
+        zs_height = zs.zg - zs.zd
+        if zs_height == 0:
+            shift_norm = 0.0
+        else:
+            shift_norm = shift_raw / zs_height
+
+        return shift_raw, shift_norm
+
+    # ------------------------------------------------------------------
+    # Label computation
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _clamp(x: float, lo: float = 0.0, hi: float = 1.0) -> float:
+        return max(lo, min(hi, x))
+
+    def _compute_label(self, zs, contraction: float, shift_norm: float) -> dict:
+        """计算标签: up / down / none + 连续置信度"""
+        bi_out = zs.bi_out
+
+        if bi_out is None:
+            return {
+                "label": "none",
+                "label_confidence": 0.0,
+                "label_detail": {
+                    "bi_out_dir": "none",
+                    "score_breakout": 0.0,
+                    "score_shift": 0.0,
+                    "score_contraction": 0.0,
+                },
+            }
+
+        zs_height = zs.zg - zs.zd
+        if zs_height == 0:
+            zs_height = 1e-8
+
+        # ---- 向上突破分数 ----
+        if bi_out.dir == Chan_BI_DIR.UP:
+            raw_breakout = (bi_out.high - zs.gg) / zs_height
+            score_breakout_up = self._clamp(raw_breakout)
+            score_shift_up = math.tanh(self._clamp(shift_norm, -3.0, 3.0))
+            score_contraction_up = max(0.0, 1.0 - contraction)
+        else:
+            score_breakout_up = 0.0
+            score_shift_up = 0.0
+            score_contraction_up = 0.0
+
+        up_score = (
+            score_breakout_up * 0.5
+            + score_shift_up * 0.3
+            + score_contraction_up * 0.2
+        )
+
+        # ---- 向下突破分数 ----
+        if bi_out.dir == Chan_BI_DIR.DOWN:
+            raw_breakout = (zs.dd - bi_out.low) / zs_height
+            score_breakout_down = self._clamp(raw_breakout)
+            score_shift_down = math.tanh(self._clamp(-shift_norm, -3.0, 3.0))
+            score_contraction_down = max(0.0, 1.0 - contraction)
+        else:
+            score_breakout_down = 0.0
+            score_shift_down = 0.0
+            score_contraction_down = 0.0
+
+        down_score = (
+            score_breakout_down * 0.5
+            + score_shift_down * 0.3
+            + score_contraction_down * 0.2
+        )
+
+        # ---- 判定 ----
+        threshold = 0.15
+
+        if up_score > down_score and up_score > threshold:
+            label = "up"
+            confidence = up_score
+            detail = {
+                "bi_out_dir": "up",
+                "score_breakout": round(score_breakout_up, 4),
+                "score_shift": round(score_shift_up, 4),
+                "score_contraction": round(score_contraction_up, 4),
+            }
+        elif down_score > up_score and down_score > threshold:
+            label = "down"
+            confidence = down_score
+            detail = {
+                "bi_out_dir": "down",
+                "score_breakout": round(score_breakout_down, 4),
+                "score_shift": round(score_shift_down, 4),
+                "score_contraction": round(score_contraction_down, 4),
+            }
+        else:
+            label = "none"
+            confidence = max(up_score, down_score)
+            bi_dir = "up" if bi_out.dir == Chan_BI_DIR.UP else "down"
+            detail = {
+                "bi_out_dir": bi_dir,
+                "score_breakout": round(max(score_breakout_up, score_breakout_down), 4),
+                "score_shift": round(max(score_shift_up, score_shift_down), 4),
+                "score_contraction": round(max(score_contraction_up, score_contraction_down), 4),
+            }
+
+        return {
+            "label": label,
+            "label_confidence": round(confidence, 4),
+            "label_detail": detail,
+        }
+
+    # ------------------------------------------------------------------
+    # Public API
+    # ------------------------------------------------------------------
+
+    def extract(self) -> list[dict]:
+        """主入口：对每个中枢提取 3 特征 + 1 标签"""
+
+        # 第一遍：计算原始值
+        raw = []
+        for i, zs in enumerate(self.bi_zs_list):
+            if not zs.is_sure or len(zs.bi_list) < 3:
+                continue
+
+            duration_raw = self._calc_duration(zs)
+            contraction = self._calc_contraction(zs)
+            shift_raw, shift_norm = self._calc_shift(zs)
+
+            raw.append({
+                "zs": zs,
+                "zs_index": i,
+                "duration_raw": duration_raw,
+                "contraction": contraction,
+                "shift_raw": shift_raw,
+                "shift_norm": shift_norm,
+                "zs_height": zs.zg - zs.zd,
+            })
+
+        # 归一化 duration: 除以均值
+        if raw:
+            avg_duration = sum(r["duration_raw"] for r in raw) / len(raw)
+        else:
+            avg_duration = 1
+
+        # 第二遍：组装输出 + 计算 label
+        result = []
+        for r in raw:
+            zs = r["zs"]
+            duration_norm = r["duration_raw"] / avg_duration if avg_duration > 0 else 1.0
+            label_info = self._compute_label(zs, r["contraction"], r["shift_norm"])
+
+            # 时间处理
+            start_time = None
+            end_time = None
+            if hasattr(zs, "start_time") and zs.start_time is not None:
+                start_time = str(zs.start_time)
+            if hasattr(zs, "end_time") and zs.end_time is not None:
+                end_time = str(zs.end_time)
+
+            result.append({
+                "dataset_version": self.DATASET_VERSION,
+                "feature_schema": self.FEATURE_SCHEMA,
+                "label_schema": self.LABEL_SCHEMA,
+
+                "symbol": self.symbol,
+                "timeframe": self.timeframe,
+                "zs_index": r["zs_index"],
+                "zs_start_time": start_time,
+                "zs_end_time": end_time,
+
+                "duration_norm": round(duration_norm, 4),
+                "contraction": round(r["contraction"], 4),
+                "shift_norm": round(r["shift_norm"], 4),
+
+                "label": label_info["label"],
+                "label_confidence": label_info["label_confidence"],
+                "label_detail": label_info["label_detail"],
+
+                "duration_raw": r["duration_raw"],
+                "shift_raw": round(r["shift_raw"], 6),
+                "zs_height": round(r["zs_height"], 6),
+            })
+
+        return result
+
+    def export_json(self, path: str):
+        """导出为 JSON 文件"""
+        data = self.extract()
+        with open(path, "w", encoding="utf-8") as f:
+            json.dump(data, f, indent=2, ensure_ascii=False, default=str)
+        return len(data)