Chan/ChanZone.py

"""
结构价值区 (Structure Zone) 系统

将多时间周期的 Chan 中枢边界 (ZD/ZG/GG/DD) 和 EMA52 统一表示为带强度评分的价值区对象。
"""

from dataclasses import dataclass, field
from typing import List, Dict, Optional, Any
from datetime import datetime


# ============================================================
# Dataclasses
# ============================================================

@dataclass
class RawZonePoint:
    """内部中间结构：从 Chan 中枢提取的单个价格点"""
    price: float
    timeframe: str            # '5m', '1h', '4h' 等
    structure_type: str       # 'bi_zhongshu' | 'xd_zhongshu' | 'ema52'
    boundary_type: str        # 'ZD' | 'ZG' | 'GG' | 'DD' | 'EMA52'
    source_zs_id: int         # 来源 ZS 在列表中的 index（调试用）
    is_sure: bool             # 来源 ZS 是否已完成
    candle_time: Optional[str] = None  # 来源 ZS 的 end_time（用于 recency 计算）


@dataclass
class StructureZone:
    """统一的价值区对象"""
    id: int
    lower: float
    upper: float
    center: float                        # (lower + upper) / 2
    width_pct: float                     # (upper - lower) / center * 100
    zone_type: str                       # 'support' | 'resistance' | 'neutral'
    timeframes: List[str]                # 参与形成此区间的时间周期
    structure_types: List[str]           # 参与形成的结构类型
    boundary_types: List[str]            # 参与形成的边界类型
    overlap_count: int                   # 聚类中的原始点数
    touch_count: int                     # MVP: 等于 overlap_count
    recency_score: float                 # 0.0 - 1.0, 1.0 = 最近
    ema52_distance_pct: float            # 到最近 EMA52 的距离百分比
    ema52_aligned: bool                  # 是否有 EMA52 落在区间内
    strength_score: float                # 0-100 综合评分
    confidence: float                    # 0.0 - 1.0
    first_seen: Optional[str]            # 最早的 candle_time
    last_seen: Optional[str]             # 最晚的 candle_time
    metadata: Dict[str, Any] = field(default_factory=dict)


@dataclass
class StructureZoneConfig:
    """StructureZone 提取与评分配置"""
    cluster_radius_pct: float = 0.5         # 价格聚类半径（百分比）
    min_overlap_for_zone: int = 2           # 最少重叠点数才能形成区间
    max_zones: int = 20                     # 返回的最大区间数
    recency_halflife_bars: int = 50         # recency 衰减半衰期（K线数）
    zone_timeframes: List[str] = field(default_factory=lambda: ['4h', '1h', '30m', '15m', '5m'])
    kl_lines_per_tf: int = 500              # 每个时间周期使用最近多少根K线
    structure_weights: Dict[str, float] = field(default_factory=lambda: {
        'bi_zhongshu':   1.0,   # 笔中枢 — 最直接的价格行为
        'xd_zhongshu':   0.8,   # 线段中枢 — 较高级别但粒度较粗
        'ema52':         0.4,   # EMA — 趋势参考，弱于结构
    })


# ============================================================
# Extraction
# ============================================================

def extract_raw_points_from_tf_df(
    tf_df_dict: Dict[str, Any],
    ema_symbols: List[str],
    config: StructureZoneConfig,
) -> List[RawZonePoint]:
    """
    从 ChanLun.tf_df_dict 中提取所有原始价格点。
    仅处理 config.zone_timeframes 中存在的时间周期。
    """
    points: List[RawZonePoint] = []

    for tf_name in config.zone_timeframes:
        if tf_name not in tf_df_dict:
            continue

        tf_df = tf_df_dict[tf_name]

        # 1. 笔中枢 (ChanBIZS)
        try:
            if hasattr(tf_df, 'seg_list') and tf_df.seg_list:
                bi_zs_result = tf_df.cal_bi_zs(tf_df.seg_list)
                if bi_zs_result:
                    _extract_from_zs_objects(
                        points, tf_name, 'bi_zhongshu', bi_zs_result, config.kl_lines_per_tf
                    )
        except Exception:
            pass

        # 2. 线段中枢 (ChanZS)
        try:
            zs_list = getattr(tf_df, 'zs_list', None)
            if zs_list:
                _extract_from_zs_objects(
                    points, tf_name, 'xd_zhongshu', zs_list, config.kl_lines_per_tf
                )
        except Exception:
            pass

    # 3. EMA52 值
    for tf_name in config.zone_timeframes:
        if tf_name in tf_df_dict:
            try:
                ema_val = tf_df_dict[tf_name].get_ema52()
                if ema_val is not None and ema_val > 0:
                    points.append(RawZonePoint(
                        price=float(ema_val),
                        timeframe=tf_name,
                        structure_type='ema52',
                        boundary_type='EMA52',
                        source_zs_id=-1,
                        is_sure=True,
                        candle_time=None,
                    ))
            except Exception:
                pass

    return points


def _extract_from_zs_objects(
    points: List[RawZonePoint],
    tf_name: str,
    structure_type: str,
    zs_list,
    kl_limit: int,
):
    """从 ZS 链表中提取 ZD/ZG/GG/DD 点"""
    count = 0
    node = zs_list
    while hasattr(node, 'next'):
        node = node.next
    # 从链表头开始遍历
    head = zs_list
    # 收集所有节点
    all_nodes = []
    cur = head
    while cur is not None and hasattr(cur, 'next'):
        all_nodes.append(cur)
        cur = cur.next
    # 只取最近 kl_limit 根K线内的 ZS
    all_nodes = all_nodes[-kl_limit:] if len(all_nodes) > kl_limit else all_nodes

    for idx, zs in enumerate(all_nodes):
        if not getattr(zs, 'is_sure', False):
            continue
        try:
            zg = float(zs.zg)
            zd = float(zs.zd)
            gg = float(zs.gg) if getattr(zs, 'gg', 0) else zg
            dd = float(zs.dd) if getattr(zs, 'dd', 0) else zd
            end_time = str(zs.end_time) if hasattr(zs, 'end_time') and zs.end_time else None
        except (ValueError, TypeError, AttributeError):
            continue

        if zg <= 0 or zd <= 0:
            continue

        zs_id = getattr(zs, 'index', idx)
        points.append(RawZonePoint(price=zg, timeframe=tf_name, structure_type=structure_type,
                                   boundary_type='ZG', source_zs_id=zs_id, is_sure=True,
                                   candle_time=end_time))
        points.append(RawZonePoint(price=zd, timeframe=tf_name, structure_type=structure_type,
                                   boundary_type='ZD', source_zs_id=zs_id, is_sure=True,
                                   candle_time=end_time))
        points.append(RawZonePoint(price=gg, timeframe=tf_name, structure_type=structure_type,
                                   boundary_type='GG', source_zs_id=zs_id, is_sure=True,
                                   candle_time=end_time))
        points.append(RawZonePoint(price=dd, timeframe=tf_name, structure_type=structure_type,
                                   boundary_type='DD', source_zs_id=zs_id, is_sure=True,
                                   candle_time=end_time))


def extract_raw_points_from_serialized(
    analyses: Dict[str, Dict],
    ema52_dict: Dict[str, Optional[float]],
    config: StructureZoneConfig,
) -> List[RawZonePoint]:
    """
    从已序列化的分析结果中提取价格点（用于 web API，避免重复计算）。
    analyses: {'5m': {'zs_list': [...], 'bi_zs_list': [...]}, '15m': {...}, ...}
    ema52_dict: {'5m': 123.45, '15m': None, ...}
    """
    points: List[RawZonePoint] = []

    for tf_name in config.zone_timeframes:
        if tf_name not in analyses:
            continue

        analysis = analyses[tf_name]

        # 笔中枢
        bi_zs_items = analysis.get('bi_zs_list', [])
        for idx, zs in enumerate(bi_zs_items):
            if not zs.get('is_sure', False):
                continue
            try:
                zg = float(zs['zg']); zd = float(zs['zd'])
                gg = float(zs.get('gg', zg)); dd = float(zs.get('dd', zd))
                end_time = zs.get('end_time')
            except (ValueError, KeyError):
                continue
            if zg <= 0 or zd <= 0:
                continue
            points.append(RawZonePoint(price=zg, timeframe=tf_name, structure_type='bi_zhongshu',
                                       boundary_type='ZG', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=zd, timeframe=tf_name, structure_type='bi_zhongshu',
                                       boundary_type='ZD', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=gg, timeframe=tf_name, structure_type='bi_zhongshu',
                                       boundary_type='GG', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=dd, timeframe=tf_name, structure_type='bi_zhongshu',
                                       boundary_type='DD', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))

        # 线段中枢
        zs_items = analysis.get('zs_list', [])
        for idx, zs in enumerate(zs_items):
            if not zs.get('is_sure', False):
                continue
            try:
                zg = float(zs['zg']); zd = float(zs['zd'])
                gg = float(zs.get('gg', zg)); dd = float(zs.get('dd', zd))
                end_time = zs.get('end_time')
            except (ValueError, KeyError):
                continue
            if zg <= 0 or zd <= 0:
                continue
            points.append(RawZonePoint(price=zg, timeframe=tf_name, structure_type='xd_zhongshu',
                                       boundary_type='ZG', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=zd, timeframe=tf_name, structure_type='xd_zhongshu',
                                       boundary_type='ZD', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=gg, timeframe=tf_name, structure_type='xd_zhongshu',
                                       boundary_type='GG', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))
            points.append(RawZonePoint(price=dd, timeframe=tf_name, structure_type='xd_zhongshu',
                                       boundary_type='DD', source_zs_id=idx, is_sure=True,
                                       candle_time=str(end_time) if end_time else None))

    # EMA52
    for tf_name in config.zone_timeframes:
        ema_val = ema52_dict.get(tf_name)
        if ema_val is not None and ema_val > 0:
            points.append(RawZonePoint(
                price=float(ema_val),
                timeframe=tf_name,
                structure_type='ema52',
                boundary_type='EMA52',
                source_zs_id=-1,
                is_sure=True,
                candle_time=None,
            ))

    return points


# ============================================================
# Clustering
# ============================================================

def cluster_raw_points(
    points: List[RawZonePoint],
    config: StructureZoneConfig,
) -> List[List[RawZonePoint]]:
    """
    贪心单通聚类：将价格相近的 RawZonePoint 归为一组。
    仅在 1D 价格轴上操作，O(n log n)。
    """
    if not points:
        return []

    sorted_points = sorted(points, key=lambda p: p.price)
    clusters: List[List[RawZonePoint]] = []

    for p in sorted_points:
        placed = False
        for cluster in reversed(clusters):
            # 检查是否可以放入当前聚类（与聚类均价比较）
            avg_price = sum(pt.price for pt in cluster) / len(cluster)
            if abs(p.price - avg_price) / avg_price * 100 <= config.cluster_radius_pct:
                cluster.append(p)
                placed = True
                break
        if not placed:
            clusters.append([p])

    # 过滤点数不足的聚类
    return [c for c in clusters if len(c) >= config.min_overlap_for_zone]


# ============================================================
# Scoring & Building
# ============================================================

def build_structure_zones(
    clusters: List[List[RawZonePoint]],
    current_price: float,
    ema52_values: Dict[str, Optional[float]],
    latest_candle_time: Optional[str],
    config: StructureZoneConfig,
) -> List[StructureZone]:
    """
    从聚类构建 StructureZone 列表，计算所有字段和评分。
    """
    zones: List[StructureZone] = []

    # 收集所有 EMA52 值
    ema_prices = [v for v in ema52_values.values() if v is not None and v > 0]

    for zone_id, cluster in enumerate(clusters):
        prices = [p.price for p in cluster]
        lower = min(prices)
        upper = max(prices)
        center = (lower + upper) / 2
        width_pct = (upper - lower) / center * 100 if center > 0 else 0.0

        # 区间类型
        if upper < current_price:
            zone_type = 'support'      # 区间在当前价格下方 → 支撑
        elif lower > current_price:
            zone_type = 'resistance'   # 区间在当前价格上方 → 阻力
        else:
            zone_type = 'neutral'      # 区间跨越当前价格

        timeframes = sorted(set(p.timeframe for p in cluster))
        structure_types = sorted(set(p.structure_type for p in cluster))
        boundary_types = sorted(set(p.boundary_type for p in cluster))
        overlap_count = len(cluster)

        # Recency
        times = [p.candle_time for p in cluster if p.candle_time]
        first_seen = min(times) if times else None
        last_seen = max(times) if times else None
        recency_score = _calc_recency(last_seen, latest_candle_time, config.recency_halflife_bars)

        # EMA52 alignment
        ema52_distance_pct = 999.0
        ema52_aligned = False
        if ema_prices:
            distances = [abs(center - ep) / ep * 100 for ep in ema_prices]
            ema52_distance_pct = round(min(distances), 2)
        ema52_aligned = any(lower <= ep <= upper for ep in ema_prices)

        # Strength score
        strength_score = _calc_strength(cluster, config, recency_score, ema52_aligned, ema52_distance_pct, width_pct)

        # Confidence
        confidence = _calc_confidence(overlap_count, len(timeframes), cluster)

        zones.append(StructureZone(
            id=zone_id + 1,
            lower=round(lower, 2),
            upper=round(upper, 2),
            center=round(center, 2),
            width_pct=round(width_pct, 2),
            zone_type=zone_type,
            timeframes=timeframes,
            structure_types=structure_types,
            boundary_types=boundary_types,
            overlap_count=overlap_count,
            touch_count=overlap_count,  # MVP: 等于 overlap_count
            recency_score=round(recency_score, 3),
            ema52_distance_pct=ema52_distance_pct,
            ema52_aligned=ema52_aligned,
            strength_score=round(strength_score, 1),
            confidence=round(confidence, 2),
            first_seen=first_seen,
            last_seen=last_seen,
        ))

    # 按强度降序排列
    zones.sort(key=lambda z: z.strength_score, reverse=True)

    # 截断
    if config.max_zones > 0 and len(zones) > config.max_zones:
        zones = zones[:config.max_zones]

    return zones


def _calc_recency(
    last_seen: Optional[str],
    latest_time: Optional[str],
    halflife_bars: int,
) -> float:
    """计算 recency 分数：越近越高"""
    if not last_seen or not latest_time:
        return 0.5

    try:
        # 尝试解析 ISO 格式时间
        from dateutil import parser
        t_last = parser.parse(last_seen)
        t_latest = parser.parse(latest_time)
        offset_seconds = (t_latest - t_last).total_seconds()
        if offset_seconds < 0:
            return 1.0
        # 假设每根K线平均 5 分钟
        bar_seconds = 300
        offset_bars = offset_seconds / bar_seconds
        # 指数衰减: 2 ^ (-offset / halflife)
        score = 2.0 ** (-offset_bars / halflife_bars)
        return float(score)
    except Exception:
        return 0.5


def _calc_strength(
    cluster: List[RawZonePoint],
    config: StructureZoneConfig,
    recency_score: float,
    ema52_aligned: bool,
    ema52_distance_pct: float,
    width_pct: float,
) -> float:
    """计算综合强度评分 (0-100)"""

    # 组件 1: 结构类型多样性 (0-40)
    structure_type_counts: Dict[str, int] = {}
    for p in cluster:
        structure_type_counts[p.structure_type] = structure_type_counts.get(p.structure_type, 0) + 1
    total = sum(structure_type_counts.values())
    structure_score = 0.0
    for st, count in structure_type_counts.items():
        weight = config.structure_weights.get(st, 0.5)
        structure_score += weight * count
    structure_score = min(structure_score / max(1, total), 1.0)
    c1 = structure_score * 40

    # 组件 2: 多周期确认 (0-25)
    tf_set = set(p.timeframe for p in cluster)
    tf_diversity = len(tf_set)
    c2 = min(tf_diversity / 5, 1.0) * 25

    # 组件 3: 区间紧密度 (0-15) — 越窄越强
    tightness = max(0.0, 1.0 - (width_pct / 3.0))
    c3 = tightness * 15

    # 组件 4: Recency (0-10)
    c4 = recency_score * 10

    # 组件 5: EMA52 共振 (0-10)
    if ema52_aligned:
        ema_proximity = max(0.0, 1.0 - (ema52_distance_pct / 2.0))
        c5 = ema_proximity * 10
    else:
        c5 = 0.0

    return c1 + c2 + c3 + c4 + c5


def _calc_confidence(
    overlap_count: int,
    tf_count: int,
    cluster: List[RawZonePoint],
) -> float:
    """计算置信度 (0-1)"""
    base = min(overlap_count / 6.0, 0.85)
    # 多周期加分
    tf_bonus = min(tf_count / 5.0, 0.1)
    # 是否所有点都来自 sure 的 ZS
    all_sure = all(p.is_sure for p in cluster)
    sure_bonus = 0.05 if all_sure else 0.0
    return min(base + tf_bonus + sure_bonus, 1.0)


# ============================================================
# Top-level pipeline
# ============================================================

def analyze_structure_zones(
    tf_df_dict: Dict[str, Any],
    ema_symbols: List[str],
    current_price: Optional[float] = None,
    config: Optional[StructureZoneConfig] = None,
) -> List[StructureZone]:
    """
    一站式分析：提取 → 聚类 → 评分 → 返回排序后的 StructureZone 列表。
    """
    if config is None:
        config = StructureZoneConfig()

    # 提取
    raw_points = extract_raw_points_from_tf_df(tf_df_dict, ema_symbols, config)

    if not raw_points:
        return []

    # 获取当前价格
    if current_price is None:
        for tf_name in config.zone_timeframes:
            if tf_name in tf_df_dict:
                try:
                    ema_val = tf_df_dict[tf_name].get_ema52()
                    if ema_val and ema_val > 0:
                        current_price = float(ema_val)
                        break
                except Exception:
                    pass
        if current_price is None:
            current_price = 0.0

    # EMA52 值
    ema52_values = {}
    for tf_name in config.zone_timeframes:
        if tf_name in tf_df_dict:
            try:
                ema52_values[tf_name] = tf_df_dict[tf_name].get_ema52()
            except Exception:
                ema52_values[tf_name] = None

    # 最晚时间
    latest_time = None
    times = [p.candle_time for p in raw_points if p.candle_time]
    if times:
        latest_time = max(times)

    # 聚类
    clusters = cluster_raw_points(raw_points, config)

    # 构建 & 评分
    return build_structure_zones(clusters, current_price, ema52_values, latest_time, config)


def analyze_structure_zones_from_serialized(
    analyses: Dict[str, Dict],
    ema52_dict: Dict[str, Optional[float]],
    current_price: float,
    config: Optional[StructureZoneConfig] = None,
) -> List[StructureZone]:
    """
    从已序列化的分析结果构建 StructureZone（用于 web API）。
    """
    if config is None:
        config = StructureZoneConfig()

    raw_points = extract_raw_points_from_serialized(analyses, ema52_dict, config)

    if not raw_points:
        return []

    # 最晚时间
    latest_time = None
    times = [p.candle_time for p in raw_points if p.candle_time]
    if times:
        latest_time = max(times)

    # EMA52 值（用于 alignment 检测）
    ema_values = {tf: v for tf, v in ema52_dict.items() if v is not None and v > 0}

    clusters = cluster_raw_points(raw_points, config)
    return build_structure_zones(clusters, current_price, ema_values, latest_time, config)