chanmacro: Signal Expectancy Engine V1 — Market Memory System

Phase A-C complete: 4 core factors, regime detection, signal tracking, Bayesian expectancy. chanmacro/ (32 files, ~4000 lines): - models: 12 enums + 15 Pydantic v2 models (DateAwareModel, MarketStateVector, etc.) - fetchers: OHLCV + Breadth (from data_provider) + Derivatives (new endpoint) - scoring: Price Structure / Breadth (quantile buckets) / OI Matrix (5 discrete states) / Volatility Regime - regime_detector: 3-state (TREND/RANGE/PANIC), factor-locked (Price+Breadth+Vol), versioned, 2-day confirmation - expectancy: SignalTracker (record+outcomes), TimeDecay (half-life=180d), BayesianExpectancyEngine (Empirical Bayes, Leveled, SufficiencyGuard) - validation: FactorValidator (IC/ICIR/Hit Ratio), RegimeValidator (MI/KL/ANOVA), TransitionValidator (stability) - CLI: fetch|score|regime|track|backfill|expectancy|validate|serve - tests: 52 passing (models, scoring, regime, expectancy) data_provider: - /api/derivatives endpoint: funding rate, OI, OI change, basis - _derivatives storage: same persist pattern as K-line (merge→lock→snapshot→atomic write) - background refresh every 60s Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-24 17:44:55 +08:00
parent 34040575c1
commit 71951019fb
43 changed files with 5036 additions and 2 deletions
@@ -0,0 +1,248 @@
+"""
+scoring/price_structure.py — Price Structure Score (OHLCV-only).
+
+Three sub-dimensions:
+  1. Trend Strength (40%): EMA alignment + ADX
+  2. Volatility Compression (30%): ATR + BB width
+  3. Momentum (30%): ROC + consecutive candles
+
+This module works with zero external dependencies — just OHLCV data.
+"""
+
+from datetime import date as Date
+import sqlite3
+import math
+import numpy as np
+import pandas as pd
+
+from .base import BaseScorer
+from .constants import (
+    ADX_TREND_THRESHOLD, ADX_STRONG_THRESHOLD,
+    BB_COMPRESSION_LOW, BB_COMPRESSION_HIGH,
+    ROC_STRONG_BULLISH, ROC_STRONG_BEARISH,
+    CONSECUTIVE_CANDLES_SIGNAL,
+)
+from models import FactorScore, PriceStructureScore, MacroDirection
+from config import config
+
+
+class PriceStructureScorer(BaseScorer):
+    """Scores market structure from OHLCV data alone."""
+
+    def compute(self, target_date: Date) -> PriceStructureScore:
+        conn = self.get_connection()
+        try:
+            df = self._load_ohlcv(conn, str(target_date), lookback=120)
+            if df.empty:
+                return PriceStructureScore(
+                    name="Price Structure",
+                    score=50.0,
+                    label="No Data",
+                )
+
+            trend = self._score_trend_strength(df)
+            vol_comp = self._score_volatility_compression(df)
+            momentum = self._score_momentum(df)
+
+            # Weighted aggregate
+            score = trend * 0.40 + vol_comp * 0.30 + momentum * 0.30
+
+            # Determine direction
+            if trend > 60:
+                direction = MacroDirection.BULLISH
+            elif trend < 40:
+                direction = MacroDirection.BEARISH
+            else:
+                direction = MacroDirection.NEUTRAL
+
+            # Build narrative
+            latest = df.iloc[-1]
+            narrative = self._build_narrative(trend, vol_comp, momentum, latest)
+
+            return PriceStructureScore(
+                name="Price Structure",
+                score=round(score, 1),
+                label=self._label(score),
+                direction=direction,
+                trend_strength=round(trend, 1),
+                volatility_compression=round(vol_comp, 1),
+                momentum=round(momentum, 1),
+                sub_scores={
+                    "trend_strength": round(trend, 1),
+                    "volatility_compression": round(vol_comp, 1),
+                    "momentum": round(momentum, 1),
+                },
+                narrative=narrative,
+            )
+        finally:
+            conn.close()
+
+    def _load_ohlcv(self, conn: sqlite3.Connection, date_str: str,
+                    lookback: int = 120) -> pd.DataFrame:
+        """Load OHLCV data up to target_date."""
+        df = pd.read_sql_query(
+            "SELECT * FROM ohlcv_daily WHERE date <= ? ORDER BY date DESC LIMIT ?",
+            conn, params=(date_str, lookback)
+        )
+        if df.empty:
+            return df
+        return df.sort_values("date").reset_index(drop=True)
+
+    def _score_trend_strength(self, df: pd.DataFrame) -> float:
+        """Score trend based on EMA alignment and ADX."""
+        latest = df.iloc[-1]
+
+        # EMA alignment
+        ema20 = latest.get("ema20")
+        ema60 = latest.get("ema60")
+        ema120 = latest.get("ema120")
+
+        ema_score = 50.0
+        if ema20 and ema60 and ema120 and not pd.isna(ema20) and not pd.isna(ema60) and not pd.isna(ema120):
+            alignments = 0
+            if ema20 > ema60: alignments += 1
+            if ema60 > ema120: alignments += 1
+            if ema20 > ema120: alignments += 1
+
+            # Distance from EMAs
+            close = float(latest["close"])
+            ema20_dist = abs(close - ema20) / ema20 * 100 if ema20 else 0
+
+            if alignments == 3:
+                ema_score = 80 + min(ema20_dist, 15)  # strong bullish alignment
+            elif alignments == 0:
+                ema_score = 20 - min(ema20_dist, 15)  # strong bearish alignment
+            elif alignments == 2:
+                ema_score = 65
+            else:
+                ema_score = 35
+
+        # ADX
+        adx = latest.get("adx_14")
+        adx_score = 50.0
+        if adx and not pd.isna(adx):
+            if adx > ADX_STRONG_THRESHOLD:
+                adx_score = 85
+            elif adx > ADX_TREND_THRESHOLD:
+                adx_score = 65 + (adx - ADX_TREND_THRESHOLD) / (ADX_STRONG_THRESHOLD - ADX_TREND_THRESHOLD) * 20
+            else:
+                adx_score = 50 - (ADX_TREND_THRESHOLD - adx) / ADX_TREND_THRESHOLD * 30
+
+        return ema_score * 0.55 + adx_score * 0.45
+
+    def _score_volatility_compression(self, df: pd.DataFrame) -> float:
+        """Score volatility compression — expansion = high, compression = low-mid."""
+        latest = df.iloc[-1]
+
+        bb_width = latest.get("bb_width")
+        if not bb_width or pd.isna(bb_width) or len(df) < 20:
+            return 50.0
+
+        # BB width relative to 20d average
+        recent_bb = df["bb_width"].dropna().tail(20)
+        if len(recent_bb) < 10:
+            return 50.0
+
+        bb_avg = recent_bb.mean()
+        bb_ratio = bb_width / bb_avg if bb_avg > 0 else 1.0
+
+        if bb_ratio < BB_COMPRESSION_LOW:
+            # Compression → potential breakout, neutral-bullish
+            return 45 + (BB_COMPRESSION_LOW - bb_ratio) * 30
+        elif bb_ratio > BB_COMPRESSION_HIGH:
+            # Expansion → trending or chaotic
+            return 75 + min((bb_ratio - BB_COMPRESSION_HIGH) * 20, 20)
+        else:
+            # Normal
+            return 55
+
+    def _score_momentum(self, df: pd.DataFrame) -> float:
+        """Score momentum using ROC and consecutive candles."""
+        if len(df) < 10:
+            return 50.0
+
+        closes = df["close"].astype(float)
+        latest = float(closes.iloc[-1])
+
+        # ROC (5-bar)
+        if len(closes) >= 6:
+            roc5 = (closes.iloc[-1] - closes.iloc[-6]) / closes.iloc[-6] * 100
+        else:
+            roc5 = 0
+
+        # ROC (10-bar)
+        if len(closes) >= 11:
+            roc10 = (closes.iloc[-1] - closes.iloc[-11]) / closes.iloc[-11] * 100
+        else:
+            roc10 = 0
+
+        # ROC (20-bar)
+        if len(closes) >= 21:
+            roc20 = (closes.iloc[-1] - closes.iloc[-21]) / closes.iloc[-21] * 100
+        else:
+            roc20 = 0
+
+        # Score ROC: map to 0-100
+        def roc_to_score(roc, scale=15):
+            return 50 + np.clip(roc / scale * 50, -50, 50)
+
+        roc_score = roc_to_score(roc5, 10) * 0.4 + roc_to_score(roc10, 15) * 0.35 + roc_to_score(roc20, 20) * 0.25
+
+        # Consecutive candle direction
+        consec_score = 50.0
+        consec_up = 0
+        consec_down = 0
+        for i in range(len(closes) - 1, max(0, len(closes) - 10), -1):
+            if closes.iloc[i] > closes.iloc[i - 1]:
+                consec_up += 1
+                consec_down = 0
+            elif closes.iloc[i] < closes.iloc[i - 1]:
+                consec_down += 1
+                consec_up = 0
+            else:
+                break
+
+        if consec_up >= CONSECUTIVE_CANDLES_SIGNAL:
+            consec_score = 70 + min(consec_up * 5, 25)
+        elif consec_down >= CONSECUTIVE_CANDLES_SIGNAL:
+            consec_score = 30 - min(consec_down * 5, 25)
+
+        return roc_score * 0.70 + consec_score * 0.30
+
+    def _build_narrative(self, trend: float, vol: float, momentum: float,
+                         latest: pd.Series) -> str:
+        parts = []
+        if trend > 65:
+            parts.append("EMA多头排列+ADX趋势明确")
+        elif trend > 50:
+            parts.append("趋势温和偏多")
+        elif trend < 35:
+            parts.append("EMA空头排列+ADX趋势明确")
+        elif trend < 50:
+            parts.append("趋势温和偏空")
+        else:
+            parts.append("趋势中性")
+
+        if vol > 70:
+            parts.append("波动率扩张")
+        elif vol < 45:
+            parts.append("波动率压缩(突破前兆)")
+
+        if momentum > 65:
+            parts.append("动量强劲")
+        elif momentum < 35:
+            parts.append("动量疲弱")
+
+        return ", ".join(parts) if parts else "中性"
+
+    @staticmethod
+    def _label(score: float) -> str:
+        if score >= 75:
+            return "Strong Bullish Structure"
+        elif score >= 60:
+            return "Bullish Structure"
+        elif score >= 40:
+            return "Neutral Structure"
+        elif score >= 25:
+            return "Bearish Structure"
+        return "Weak Bearish Structure"