refactor: establish standalone application boundary

2026-08-03 21:42:25 +08:00
parent cc5fb8d73e
commit e1e76cd51e
324 changed files with 63090 additions and 44743 deletions
@@ -0,0 +1,238 @@
+from __future__ import annotations
+
+import math
+import statistics
+from datetime import datetime
+from typing import Any
+
+from backend.data.numbers import finite_number as _number
+
+
+def _optional_number(value: Any) -> float | None:
+    if value in (None, ""):
+        return None
+    try:
+        result = float(value)
+    except (TypeError, ValueError):
+        return None
+    return result if math.isfinite(result) else None
+
+
+def _rounded_optional(value: Any, digits: int = 2) -> float | None:
+    parsed = _optional_number(value)
+    return round(parsed, digits) if parsed is not None else None
+
+
+def _limit_threshold(code: str, name: str) -> float:
+    if code.startswith(("4", "8")):
+        return 29.0
+    if code.startswith(("30", "68")):
+        return 19.0
+    return 9.5
+
+
+def _ending_streak(flags: list[bool], end_index: int | None = None) -> int:
+    if not flags:
+        return 0
+    index = len(flags) - 1 if end_index is None else min(end_index, len(flags) - 1)
+    streak = 0
+    while index >= 0 and flags[index]:
+        streak += 1
+        index -= 1
+    return streak
+
+
+def _max_streak(flags: list[bool]) -> int:
+    best = current = 0
+    for value in flags:
+        current = current + 1 if value else 0
+        best = max(best, current)
+    return best
+
+
+def _rsi(values: list[float], period: int = 6) -> float:
+    if len(values) <= period:
+        return 50.0
+    changes = [values[index] - values[index - 1] for index in range(len(values) - period, len(values))]
+    gains = sum(max(change, 0.0) for change in changes) / period
+    losses = sum(max(-change, 0.0) for change in changes) / period
+    if losses == 0:
+        return 100.0 if gains > 0 else 50.0
+    return 100 - 100 / (1 + gains / losses)
+
+
+def _ema(values: list[float], period: int) -> list[float]:
+    if not values:
+        return []
+    alpha = 2 / (period + 1)
+    result = [values[0]]
+    for value in values[1:]:
+        result.append(value * alpha + result[-1] * (1 - alpha))
+    return result
+
+
+def _macd_series(values: list[float]) -> tuple[list[float], list[float]]:
+    fast = _ema(values, 12)
+    slow = _ema(values, 26)
+    dif = [left - right for left, right in zip(fast, slow)]
+    return dif, _ema(dif, 9)
+
+
+def _macd_last(values: list[float]) -> tuple[float, float]:
+    dif, dea = _macd_series(values)
+    return (dif[-1], dea[-1]) if dif and dea else (0.0, 0.0)
+
+
+def _weekly_series(rows: list[dict[str, Any]]) -> tuple[list[float], list[float]]:
+    weeks: dict[str, tuple[float, float]] = {}
+    for row in rows:
+        trade_date = str(row.get("trade_date") or "")
+        try:
+            key = datetime.strptime(trade_date, "%Y%m%d").strftime("%G-%V")
+        except ValueError:
+            continue
+        close = _number(row.get("close"))
+        amount = _number(row.get("amount"))
+        previous = weeks.get(key, (close, 0.0))
+        weeks[key] = (close, previous[1] + amount)
+    ordered = list(weeks.values())
+    return [item[0] for item in ordered], [item[1] for item in ordered]
+
+
+def _broken_reversal_metrics(
+    rows: list[dict[str, Any]], flags: list[bool], code: str, name: str,
+) -> dict[str, Any]:
+    result = {"signal": 0, "days": 0, "recovered": 0, "volume_ratio": 0.0}
+    if not rows or not flags[-1]:
+        return result
+    current_close = _number(rows[-1].get("close"))
+    current_volume = _number(rows[-1].get("vol"))
+    for days in range(1, 4):
+        index = len(rows) - 1 - days
+        if index <= 0 or flags[index] or _ending_streak(flags, index - 1) < 2:
+            continue
+        broken_high = _number(rows[index].get("high"))
+        broken_volume = _number(rows[index].get("vol"))
+        recovered = int(current_close >= broken_high > 0)
+        volume_ratio = current_volume / broken_volume if broken_volume else 0.0
+        return {
+            "signal": int(recovered and volume_ratio >= 1),
+            "days": days,
+            "recovered": recovered,
+            "volume_ratio": round(volume_ratio, 3),
+        }
+    return result
+
+
+def _is_limit_bar(rows: list[dict[str, Any]], index: int, code: str, name: str) -> bool:
+    if index < 0 or index >= len(rows):
+        return False
+    return _number(rows[index].get("pct_chg")) >= _limit_threshold(code, name)
+
+
+def _touched_limit_bar(rows: list[dict[str, Any]], index: int, code: str, name: str) -> bool:
+    if index <= 0 or index >= len(rows):
+        return False
+    previous_close = _number(rows[index - 1].get("close"))
+    high = _number(rows[index].get("high"))
+    if previous_close <= 0 or high <= 0:
+        return False
+    touched_change = (high / previous_close - 1) * 100
+    return touched_change >= _limit_threshold(code, name)
+
+
+def _matches(actual: Any, operator: str, expected: Any) -> bool:
+    if actual is None:
+        return False
+    try:
+        if operator == "between":
+            return float(expected[0]) <= float(actual) <= float(expected[1])
+        if operator == "in":
+            return actual in expected
+        if operator == ">":
+            return float(actual) > float(expected)
+        if operator == ">=":
+            return float(actual) >= float(expected)
+        if operator == "<":
+            return float(actual) < float(expected)
+        if operator == "<=":
+            return float(actual) <= float(expected)
+        if operator == "==":
+            return actual == expected or float(actual) == float(expected)
+        if operator == "!=":
+            return actual != expected
+    except (TypeError, ValueError, IndexError):
+        return False
+    return False
+
+
+def _percentile_map(rows: list[dict[str, Any]], field: str, direction: str) -> dict[str, float]:
+    ordered = sorted(rows, key=lambda item: _number(item.get(field)))
+    denominator = max(1, len(ordered) - 1)
+    result = {}
+    for index, row in enumerate(ordered):
+        percentile = index / denominator
+        result[row["ts_code"]] = 1 - percentile if direction == "asc" else percentile
+    return result
+
+
+def _available_percentile_map(
+    rows: list[dict[str, Any]], field: str, direction: str,
+) -> dict[str, float | None]:
+    available = [row for row in rows if row.get(field) is not None]
+    result: dict[str, float | None] = {
+        str(row.get("ts_code") or ""): None for row in rows
+    }
+    if not available:
+        return result
+    ordered = sorted(available, key=lambda item: _number(item.get(field)))
+    denominator = max(1, len(ordered) - 1)
+    for index, row in enumerate(ordered):
+        percentile = 0.5 if len(ordered) == 1 else index / denominator
+        result[str(row.get("ts_code") or "")] = (
+            1 - percentile if direction == "asc" else percentile
+        )
+    return result
+
+
+def _pearson(first: list[float], second: list[float]) -> float:
+    if len(first) != len(second) or len(first) < 20:
+        return 0.0
+    first_mean = statistics.fmean(first)
+    second_mean = statistics.fmean(second)
+    numerator = sum(
+        (left - first_mean) * (right - second_mean)
+        for left, right in zip(first, second)
+    )
+    left_sum = sum((value - first_mean) ** 2 for value in first)
+    right_sum = sum((value - second_mean) ** 2 for value in second)
+    denominator = math.sqrt(left_sum * right_sum)
+    return numerator / denominator if denominator else 0.0
+
+
+def _risk_flags(
+    row: dict[str, Any], regime: str, include_regime_risk: bool = True
+) -> list[str]:
+    flags = []
+    if row.get("pct_chg", 0) >= 9.5:
+        flags.append("当日接近涨停，次日存在高开与无法成交风险")
+    if row.get("return_10d", 0) >= 25:
+        flags.append("短期累计涨幅较高")
+    if row.get("volatility_10d", 0) >= 7:
+        flags.append("波动率偏高")
+    if row.get("amount_billion", 0) < 1:
+        flags.append("成交承载力偏弱")
+    if include_regime_risk and regime == "retreat":
+        flags.append("市场处于退潮阶段，策略可能选择空仓")
+    return flags
+
+
+def _regime_reason(regime: str) -> str:
+    return {
+        "ice": "情绪和赚钱效应处于低位，重点观察率先抗跌与转折信号。",
+        "repair": "核心指标从低位改善，适合观察率先修复且有板块共振的方向。",
+        "fermentation": "赚钱效应扩散，主线和梯队持续增强。",
+        "climax": "情绪处于高位，后排跟风与兑现风险同时上升。",
+        "divergence": "指数或核心仍强，但广度、封板质量开始分化。",
+        "retreat": "情绪指标继续走弱，应提高筛选门槛并接受无候选结果。",
+    }.get(regime, "市场阶段待确认。")