添加本地数据源，以后就可以直接用本地数据了

.gitignore

@@ -28,3 +28,4 @@ feature_meta
 *.sqlite-wal
 .DS_Store
 交易记录/~$交易规则.docx
+/datasvc/data

ChanHeng.py

@@ -0,0 +1,414 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+"""
+使用 ccxt 获取币安交易所所有 `*/USDT` 交易对最新 100 根 1 小时 K 线数据，并筛选出长期横盘的币种。
+
+横盘判定基于以下三项指标（均可通过命令行参数调整）：
+1. 价格振幅占均价的比例（默认 ≤ 5%）
+2. 收盘价线性回归斜率占均价的比例（默认 ≤ 0.05%）
+3. 收盘价标准差占均价的比例（默认 ≤ 1.5%）
+
+满足以上全部条件的交易对会被视为长期横盘。
+"""
+
+import argparse
+import csv
+import logging
+import math
+import statistics
+import sys
+import time
+from dataclasses import dataclass
+from typing import Iterable, List, Optional, Sequence
+
+import ccxt
+
+# python ChanHeng.py --range-threshold 5 --slope-threshold 5 --std-threshold 0.015
+
+DEFAULT_LIMIT = 100
+DEFAULT_TIMEFRAME = "1h"
+STABLECOINS = {
+    "USDT",
+    "USDC",
+    "BUSD",
+    "TUSD",
+    "USDP",
+    "DAI",
+    "FDUSD",
+    "SUSD",
+    "UST",
+    "USTC",
+    "EUR",
+    "TRY",
+    "BFUSD",
+    "USDE",
+    "XUSD",
+    "USD1",
+    "XUSD"
+}
+
+
+@dataclass
+class SidewaysMetrics:
+    symbol: str
+    price_range_pct: float
+    slope_pct: float
+    std_pct: float
+    mean_close: float
+    last_close: float
+    data_points: int
+
+
+def parse_args(argv: Optional[Sequence[str]] = None) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="筛选币安长期横盘币种（默认 500 根 1 小时 K 线）"
+    )
+    parser.add_argument(
+        "--timeframe",
+        default=DEFAULT_TIMEFRAME,
+        help="K 线周期（默认：1h）",
+    )
+    parser.add_argument(
+        "--limit",
+        type=int,
+        default=DEFAULT_LIMIT,
+        help="每个交易对获取的 K 线数量（默认：500）",
+    )
+    parser.add_argument(
+        "--range-threshold",
+        type=float,
+        default=0.05,
+        help="最大价格振幅占均价比例阈值（默认：0.05，表示 5%%）",
+    )
+    parser.add_argument(
+        "--slope-threshold",
+        type=float,
+        default=0.0005,
+        help="线性回归斜率占均价比例阈值（默认：0.0005，约 0.05%%）",
+    )
+    parser.add_argument(
+        "--std-threshold",
+        type=float,
+        default=0.015,
+        help="标准差占均价比例阈值（默认：0.015，表示 1.5%%）",
+    )
+    parser.add_argument(
+        "--quote",
+        action="append",
+        default=[],
+        help="只保留指定计价货币的交易对，可重复指定（示例：--quote USDT --quote FDUSD）",
+    )
+    parser.add_argument(
+        "--symbol",
+        action="append",
+        default=[],
+        help="仅检测指定交易对，可重复（不指定则遍历所有符合条件的现货交易对）",
+    )
+    parser.add_argument(
+        "--max-symbols",
+        type=int,
+        default=None,
+        help="限制最多检测的交易对数量（用于调试）",
+    )
+    parser.add_argument(
+        "--sleep",
+        type=float,
+        default=0.35,
+        help="请求失败后的基础重试等待秒数（默认：0.35）",
+    )
+    parser.add_argument(
+        "--retries",
+        type=int,
+        default=3,
+        help="单个交易对请求失败后的最大重试次数（默认：3）",
+    )
+    parser.add_argument(
+        "--include-inactive",
+        action="store_true",
+        help="包含已下架/不可交易的交易对（默认不包含）",
+    )
+    parser.add_argument(
+        "--export",
+        type=str,
+        default=None,
+        help="将筛选结果导出为 CSV 文件的路径",
+    )
+    parser.add_argument(
+        "--verbose",
+        action="store_true",
+        help="输出更详细的日志信息",
+    )
+    return parser.parse_args(argv)
+
+
+def setup_logging(verbose: bool) -> None:
+    level = logging.DEBUG if verbose else logging.INFO
+    logging.basicConfig(
+        level=level,
+        format="%(asctime)s [%(levelname)s] %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+
+
+def create_exchange() -> ccxt.binance:
+    exchange = ccxt.binance({"enableRateLimit": True})
+    exchange.options["defaultType"] = "spot"
+    return exchange
+
+
+def iter_target_symbols(
+    exchange: ccxt.binance,
+    quotes: Sequence[str],
+    includes: Sequence[str],
+    include_inactive: bool,
+) -> List[str]:
+    markets = exchange.load_markets()
+    filtered = []
+
+    quote_set = {quote.upper() for quote in quotes}
+    include_set = {sym.upper() for sym in includes}
+
+    for symbol, meta in markets.items():
+        if not meta.get("spot", False):
+            continue
+        if not include_inactive and meta.get("active") is False:
+            continue
+
+        normalized_symbol = symbol.upper()
+
+        if include_set and normalized_symbol not in include_set:
+            continue
+
+        parts = symbol.split("/")
+        if len(parts) != 2:
+            continue
+
+        base_asset, quote_asset = parts[0].upper(), parts[1].upper()
+
+        target_quote = quote_set or {"USDT"}
+        if quote_asset not in target_quote:
+            continue
+
+        if base_asset in STABLECOINS:
+            continue
+
+        filtered.append(symbol)
+
+    filtered.sort()
+    logging.info(
+        "已筛选 %s 个目标交易对（quote 过滤：%s，专门列表：%s）",
+        len(filtered),
+        ",".join(sorted(quote_set or {"USDT"})),
+        ",".join(sorted(include_set)) or "无",
+    )
+    return filtered
+
+
+def fetch_ohlcv_with_retry(
+    exchange: ccxt.binance,
+    symbol: str,
+    timeframe: str,
+    limit: int,
+    retries: int,
+    base_sleep: float,
+) -> List[List[float]]:
+    attempt = 0
+    while True:
+        try:
+            return exchange.fetch_ohlcv(symbol, timeframe=timeframe, limit=limit)
+        except ccxt.RateLimitExceeded as exc:
+            wait_time = max(exchange.rateLimit / 1000.0 if exchange.rateLimit else 0, base_sleep)
+            logging.debug("触发限频，等待 %.2f 秒后重试 %s：%s", wait_time, symbol, exc)
+            time.sleep(wait_time)
+        except (ccxt.NetworkError, ccxt.ExchangeError) as exc:
+            attempt += 1
+            if attempt > retries:
+                logging.warning("多次获取失败，跳过 %s：%s", symbol, exc)
+                return []
+            wait_time = base_sleep * attempt
+            logging.debug("请求失败，等待 %.2f 秒后重试 %s（第 %d 次）：%s", wait_time, symbol, attempt, exc)
+            time.sleep(wait_time)
+
+
+def linear_regression_slope(values: Sequence[float]) -> float:
+    n = len(values)
+    if n < 2:
+        return 0.0
+    mean_x = (n - 1) / 2.0
+    mean_y = sum(values) / n
+    numerator = 0.0
+    denominator = 0.0
+    for idx, value in enumerate(values):
+        dx = idx - mean_x
+        numerator += dx * (value - mean_y)
+        denominator += dx * dx
+
+    if denominator == 0:
+        return 0.0
+    return numerator / denominator
+
+
+def compute_sideways_metrics(closes: Sequence[float], symbol: str) -> Optional[SidewaysMetrics]:
+    if not closes:
+        return None
+
+    mean_close = sum(closes) / len(closes)
+    if math.isclose(mean_close, 0.0):
+        return None
+
+    max_close = max(closes)
+    min_close = min(closes)
+    price_range_pct = (max_close - min_close) / mean_close
+
+    slope = linear_regression_slope(closes)
+    slope_pct = slope / mean_close
+
+    std_dev = statistics.pstdev(closes) if len(closes) > 1 else 0.0
+    std_pct = std_dev / mean_close
+
+    return SidewaysMetrics(
+        symbol=symbol,
+        price_range_pct=price_range_pct,
+        slope_pct=slope_pct,
+        std_pct=std_pct,
+        mean_close=mean_close,
+        last_close=closes[-1],
+        data_points=len(closes),
+    )
+
+
+def is_sideways(metrics: SidewaysMetrics, range_threshold: float, slope_threshold: float, std_threshold: float) -> bool:
+    return (
+        metrics.price_range_pct <= range_threshold
+        and abs(metrics.slope_pct) <= slope_threshold
+        and metrics.std_pct <= std_threshold
+    )
+
+
+def export_results(path: str, results: Sequence[SidewaysMetrics]) -> None:
+    fieldnames = [
+        "symbol",
+        "price_range_pct",
+        "slope_pct",
+        "std_pct",
+        "mean_close",
+        "last_close",
+        "data_points",
+    ]
+    with open(path, "w", newline="", encoding="utf-8") as fp:
+        writer = csv.DictWriter(fp, fieldnames=fieldnames)
+        writer.writeheader()
+        for item in results:
+            writer.writerow(
+                {
+                    "symbol": item.symbol,
+                    "price_range_pct": f"{item.price_range_pct:.6f}",
+                    "slope_pct": f"{item.slope_pct:.6f}",
+                    "std_pct": f"{item.std_pct:.6f}",
+                    "mean_close": f"{item.mean_close:.8f}",
+                    "last_close": f"{item.last_close:.8f}",
+                    "data_points": item.data_points,
+                }
+            )
+    logging.info("结果已导出至 %s", path)
+
+
+def run(argv: Optional[Sequence[str]] = None) -> int:
+    args = parse_args(argv)
+    if not args.quote:
+        args.quote = ["USDT"]
+    setup_logging(args.verbose)
+
+    exchange = create_exchange()
+    symbols = iter_target_symbols(
+        exchange=exchange,
+        quotes=args.quote,
+        includes=args.symbol,
+        include_inactive=args.include_inactive,
+    )
+
+    if args.max_symbols is not None:
+        symbols = symbols[: args.max_symbols]
+        logging.info("出于调试目的，仅检测前 %d 个交易对。", len(symbols))
+
+    if not symbols:
+        logging.error("未找到任何满足条件的交易对，请检查过滤条件。")
+        return 1
+
+    sideways_results: List[SidewaysMetrics] = []
+    total = len(symbols)
+
+    for idx, symbol in enumerate(symbols, start=1):
+        logging.info("(%d/%d) 正在获取 %s 的 %s K 线（limit=%d）", idx, total, symbol, args.timeframe, args.limit)
+        ohlcv = fetch_ohlcv_with_retry(
+            exchange=exchange,
+            symbol=symbol,
+            timeframe=args.timeframe,
+            limit=args.limit,
+            retries=args.retries,
+            base_sleep=args.sleep,
+        )
+
+        if len(ohlcv) < max(100, args.limit // 2):
+            logging.debug("交易对 %s 返回数据不足（%d 根），跳过。", symbol, len(ohlcv))
+            continue
+
+        closes = [entry[4] for entry in ohlcv if entry[4] is not None]
+        metrics = compute_sideways_metrics(closes, symbol)
+        if not metrics:
+            continue
+
+        if is_sideways(metrics, args.range_threshold, args.slope_threshold, args.std_threshold):
+            sideways_results.append(metrics)
+            logging.info(
+                "识别为横盘：%s | 振幅 %.2f%% | 斜率 %.4f%% | 标准差 %.2f%%",
+                symbol,
+                metrics.price_range_pct * 100,
+                metrics.slope_pct * 100,
+                metrics.std_pct * 100,
+            )
+        else:
+            logging.debug(
+                "未满足条件：%s | 振幅 %.2f%% | 斜率 %.4f%% | 标准差 %.2f%%",
+                symbol,
+                metrics.price_range_pct * 100,
+                metrics.slope_pct * 100,
+                metrics.std_pct * 100,
+            )
+
+    if not sideways_results:
+        logging.warning("未检测到满足定义的长期横盘交易对。")
+        return 0
+
+    sideways_results.sort(key=lambda item: (item.price_range_pct, abs(item.slope_pct), item.std_pct))
+    print("=" * 88)
+    print(
+        f"共识别 {len(sideways_results)} 个长期横盘交易对（阈值：振幅≤{args.range_threshold:.2%}，"
+        f"斜率≤{args.slope_threshold:.2%}，标准差≤{args.std_threshold:.2%}）"
+    )
+    print("=" * 88)
+    header = f"{'Symbol':15s} {'Range%':>10s} {'Slope%':>10s} {'STD%':>10s} {'Mean':>14s} {'Last':>14s} {'Count':>6s}"
+    print(header)
+    print("-" * len(header))
+    for item in sideways_results:
+        print(
+            f"{item.symbol:15s}"
+            f" {item.price_range_pct * 100:10.4f}"
+            f" {item.slope_pct * 100:10.4f}"
+            f" {item.std_pct * 100:10.4f}"
+            f" {item.mean_close:14.8f}"
+            f" {item.last_close:14.8f}"
+            f" {item.data_points:6d}"
+        )
+
+    if args.export:
+        export_results(args.export, sideways_results)
+
+    logging.info("任务完成。")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(run())
+

ChanKLC.py

@@ -145,9 +145,9 @@ class ChanKLC():
 	def set_state(self, state):
 		self.state = state
 	def check_klu_included(self, klu):
-		if self.high >= klu.high:
+		if self.high >= klu.high-10:
 			# high大于，low小于，左包含
-			if self.low <= klu.low:
+			if self.low <= klu.low+10:
 				self.add_klu(klu=klu)
 				# gn>gn-1
 				if self.dir == Chan_KLINE_DIR.UP:

ChanMACD.py

@@ -5,246 +5,270 @@ from ChanMACDUnitTF import ChanMACDUnitTF
 from ChanMACDHistSet import ChanMACDHistSet
 
 class ChanMACD():
-    def __init__(self, klu_list: list[ChanKLU]):
-        self.klu_list = klu_list
-        self.seg_list = []
-        self.unittf_list = []
-        self.histset_list = []
-        # 状态标记列表
-        self.high_position_list = []      # 高位列表
-        self.high_empty_list = []         # 高位空列表
-        self.return_zero_list = []        # 归零轴列表
-        self.cross0_up_list = []          # 向上穿越零轴列表
-        self.cross0_down_list = []        # 向下穿越零轴列表
-        # 计算段 / UnitTF / HistSet 及状态标记
-        self.cal_macd_state()
-    def cal_macd_state(self):
-        last_seg = None
-        last_unittf = None
-        last_histset = None
-        last_klu = None
-        for klu in self.klu_list:
-            # initialise first histset
-            if klu.macd == 0 and klu.signal == 0 and klu.macdhist == 0:
-                continue
-            if last_histset is None:
-                if klu.macdhist > 0:
-                    last_histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.ABOVE)
-                    self.histset_list.append(last_histset)
-                else:
-                    last_histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.UNDER)
-                    self.histset_list.append(last_histset)
-            else:
-                # initialise first seg and unittf
-                if last_seg is None:
-                    # create histset afterwards
-                    if last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
-                        if klu.macdhist > 0:
-                            last_histset.add_klu(klu)
-                        else:
-                            histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.UNDER)
-                            self.histset_list.append(histset)
-                            last_histset.set_next(histset)
-                            histset.set_pre(last_histset)
-                            last_histset.set_end_klu(last_klu)
-                            last_histset = histset
-                    else:
-                        if klu.macdhist < 0:
-                            last_histset.add_klu(klu)
-                        else:
-                            histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE)
-                            self.histset_list.append(histset)
-                            last_histset.set_next(histset)
-                            histset.set_pre(last_histset)
-                            last_histset.set_end_klu(last_klu)
-                            last_histset = histset
-                    if last_klu.signal >= 0 and klu.signal < 0:
-                        last_unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, Chan_MACDUNITTF_DIR.UNDER, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
-                        self.unittf_list.append(last_unittf)
-                        last_seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, Chan_MACDSEG_DIR.UNDER, last_unittf)
-                        self.seg_list.append(last_seg)
-                    elif last_klu.signal <= 0 and klu.signal > 0:
-                        last_unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
-                        self.unittf_list.append(last_unittf)
-                        last_seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, Chan_MACDSEG_DIR.ABOVE, last_unittf)
-                        self.seg_list.append(last_seg)
-                # after the first seg and unittf
-                else:
-                    # create histset afterwards
-                    if last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
-                        if klu.macdhist > 0:
-                            last_histset.add_klu(klu)
-                        else:
-                            histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.UNDER)
-                            self.histset_list.append(histset)
-                            last_histset.set_next(histset)
-                            histset.set_pre(last_histset)
-                            last_histset.set_end_klu(last_klu)
-                            last_histset = histset
-                            if last_unittf:
-                                last_unittf.add_histset(last_histset)
-                    else:
-                        if klu.macdhist < 0:
-                            last_histset.add_klu(klu)
-                        else:
-                            histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE)
-                            self.histset_list.append(histset)
-                            last_histset.set_next(histset)
-                            histset.set_pre(last_histset)
-                            last_histset.set_end_klu(last_klu)
-                            last_histset = histset
-                            if last_unittf:
-                                last_unittf.add_histset(last_histset)
-                    if last_klu.signal >= 0 and klu.signal < 0:
-                        last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
-                        unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.UNDER, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
-                        self.unittf_list.append(unittf)
-                        last_unittf.set_next(unittf)
-                        last_seg.set_end_klu(last_klu)
-                        seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, Chan_MACDSEG_DIR.UNDER, unittf)
-                        self.seg_list.append(seg)
-                        last_seg.set_next(seg)
-                        last_seg = seg
-                        last_unittf = unittf
-                    elif last_klu.signal <= 0 and klu.signal > 0:
-                        last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
-                        unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
-                        self.unittf_list.append(unittf)
-                        last_unittf.set_next(unittf)
-                        last_seg.set_end_klu(last_klu)
-                        seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, Chan_MACDSEG_DIR.ABOVE, unittf)
-                        self.seg_list.append(seg)
-                        last_seg.set_next(seg)
-                        last_seg = seg
-                        last_unittf = unittf
-                    elif last_unittf.is_end and last_klu.macd < klu.macd and klu.macd > klu.signal:
-                        unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.NEAR0, last_histset)
-                        self.unittf_list.append(unittf)
-                        last_unittf.set_next(unittf)
-                        last_seg.add_unittf(unittf)
-                        last_unittf = unittf
-                        last_seg.add_klu(klu)
-                    else:
-                        if not last_unittf.is_end:
-                            last_unittf.add_klu(klu)
-                        last_seg.add_klu(klu)
-            last_klu = klu
-            klu.cal_macd_state()
-            #print(klu.time, klu.macd_state, klu.continue_div, klu.separate_div, klu.macd, klu.signal, klu.macdhist, klu.ema24, klu.ema52, klu.close)  
-        return self.klu_list         
-    def cal_macd(self):
-        last_seg = None
-        last_unittf = None
-        last_histset = None
-        histset = None
-        last_klu = None
-        for klu in self.klu_list:          
-            klu.cal_macd_state()
-            print(klu.time, klu.macd_state)
-            # 1) 只有当 MACD 已可用(非 UNKNOWN)时，才开始初始化段/单元
-            if last_seg is None:
-                if klu.macd_state != Chan_MACD_STATE.UNKNOWN:
-                    # 初始化首个直方图集合（根据当前柱体正负）
-                    if klu.macdhist >= 0:
-                        histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.ABOVE)
-                    else:
-                        histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.UNDER)
-                    self.histset_list.append(histset)
-                    last_histset = histset
-                    
-                    # 初始化首段
-                    seg_dir = Chan_MACDSEG_DIR.ABOVE if klu.signal >= 0 else Chan_MACDSEG_DIR.UNDER
-                    seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, seg_dir, last_unittf)
-                    self.seg_list.append(seg)
-                    last_seg = seg
+	def __init__(self, klu_list: list[ChanKLU]):
+		self.klu_list = klu_list
+		self.seg_list = []
+		self.unittf_list = []
+		self.histset_list = []
+		# 状态标记列表
+		self.high_position_list = []      # 高位列表
+		self.high_empty_list = []         # 高位空列表
+		self.return_zero_list = []        # 归零轴列表
+		self.cross0_up_list = []          # 向上穿越零轴列表
+		self.cross0_down_list = []        # 向下穿越零轴列表
+		# 计算段 / UnitTF / HistSet 及状态标记
+		self.cal_macd_state()
+		self.get_klu_sd_list()
+	def get_klu_sd(self):
+		if self.klu_list:
+			sd = self.klu_list[-1].separate_div
+			if sd > 1:
+				print(self.klu_list[-1].time, sd)
+				return True
+		return False
+	def get_klu_sd_list(self):
+		sd_list = []
+		if self.klu_list:
+			for klu in self.klu_list:
+				hist = klu.macdhist
+				singal = False
+				if klu.pre and klu.next:
+					if klu.signal > 0:
+						signal = klu.pre.signal > klu.signal and klu.next.signal < klu.signal
+					else:
+						signal = klu.pre.signal < klu.signal and klu.next.signal > klu.signal
+				sd = klu.separate_div
+				if sd > 1 and ((hist > 0 and hist < 20) or (hist < 0 and hist > -20)):
+					sd_list.append(klu.time)
+					print(klu.time, sd)
+		return sd_list
+	def cal_macd_state(self):
+		last_seg = None
+		last_unittf = None
+		last_histset = None
+		last_klu = None
+		for klu in self.klu_list:
+			# initialise first histset
+			if klu.macd == 0 and klu.signal == 0 and klu.macdhist == 0:
+				continue
+			if last_histset is None:
+				if klu.macdhist > 0:
+					last_histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.ABOVE)
+					self.histset_list.append(last_histset)
+				else:
+					last_histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.UNDER)
+					self.histset_list.append(last_histset)
+			else:
+				# initialise first seg and unittf
+				if last_seg is None:
+					# create histset afterwards
+					if last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
+						if klu.macdhist > 0:
+							last_histset.add_klu(klu)
+						else:
+							histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.UNDER)
+							self.histset_list.append(histset)
+							last_histset.set_next(histset)
+							histset.set_pre(last_histset)
+							last_histset.set_end_klu(last_klu)
+							last_histset = histset
+					else:
+						if klu.macdhist < 0:
+							last_histset.add_klu(klu)
+						else:
+							histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE)
+							self.histset_list.append(histset)
+							last_histset.set_next(histset)
+							histset.set_pre(last_histset)
+							last_histset.set_end_klu(last_klu)
+							last_histset = histset
+					if last_klu.signal >= 0 and klu.signal < 0:
+						last_unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, Chan_MACDUNITTF_DIR.UNDER, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
+						self.unittf_list.append(last_unittf)
+						last_seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, Chan_MACDSEG_DIR.UNDER, last_unittf)
+						self.seg_list.append(last_seg)
+					elif last_klu.signal <= 0 and klu.signal > 0:
+						last_unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
+						self.unittf_list.append(last_unittf)
+						last_seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, Chan_MACDSEG_DIR.ABOVE, last_unittf)
+						self.seg_list.append(last_seg)
+				# after the first seg and unittf
+				else:
+					# create histset afterwards
+					if last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
+						if klu.macdhist > 0:
+							last_histset.add_klu(klu)
+						else:
+							histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.UNDER)
+							self.histset_list.append(histset)
+							last_histset.set_next(histset)
+							histset.set_pre(last_histset)
+							last_histset.set_end_klu(last_klu)
+							last_histset = histset
+							if last_unittf:
+								last_unittf.add_histset(last_histset)
+					else:
+						if klu.macdhist < 0:
+							last_histset.add_klu(klu)
+						else:
+							histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE)
+							self.histset_list.append(histset)
+							last_histset.set_next(histset)
+							histset.set_pre(last_histset)
+							last_histset.set_end_klu(last_klu)
+							last_histset = histset
+							if last_unittf:
+								last_unittf.add_histset(last_histset)
+					if last_klu.signal >= 0 and klu.signal < 0:
+						last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
+						unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.UNDER, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
+						self.unittf_list.append(unittf)
+						last_unittf.set_next(unittf)
+						last_seg.set_end_klu(last_klu)
+						seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, Chan_MACDSEG_DIR.UNDER, unittf)
+						self.seg_list.append(seg)
+						last_seg.set_next(seg)
+						last_seg = seg
+						last_unittf = unittf
+					elif last_klu.signal <= 0 and klu.signal > 0:
+						last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
+						unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.CROSS0, last_histset)
+						self.unittf_list.append(unittf)
+						last_unittf.set_next(unittf)
+						last_seg.set_end_klu(last_klu)
+						seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, Chan_MACDSEG_DIR.ABOVE, unittf)
+						self.seg_list.append(seg)
+						last_seg.set_next(seg)
+						last_seg = seg
+						last_unittf = unittf
+					elif last_unittf.is_end and last_klu.macd < klu.macd and klu.macd > klu.signal:
+						unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, Chan_MACDUNITTF_DIR.ABOVE, Chan_MACDUNITTF_TYPE.NEAR0, last_histset)
+						self.unittf_list.append(unittf)
+						last_unittf.set_next(unittf)
+						last_seg.add_unittf(unittf)
+						last_unittf = unittf
+						last_seg.add_klu(klu)
+					else:
+						if not last_unittf.is_end:
+							last_unittf.add_klu(klu)
+						last_seg.add_klu(klu)
+			last_klu = klu
+			klu.cal_macd_state()
+			#print(klu.time, klu.macd_state, klu.continue_div, klu.separate_div, klu.macd, klu.signal, klu.macdhist, klu.ema24, klu.ema52, klu.close)  
+		return self.klu_list         
+	def cal_macd(self):
+		last_seg = None
+		last_unittf = None
+		last_histset = None
+		histset = None
+		last_klu = None
+		for klu in self.klu_list:          
+			klu.cal_macd_state()
+			print(klu.time, klu.macd_state)
+			# 1) 只有当 MACD 已可用(非 UNKNOWN)时，才开始初始化段/单元
+			if last_seg is None:
+				if klu.macd_state != Chan_MACD_STATE.UNKNOWN:
+					# 初始化首个直方图集合（根据当前柱体正负）
+					if klu.macdhist >= 0:
+						histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.ABOVE)
+					else:
+						histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, None, Chan_MACDHISTSET_DIR.UNDER)
+					self.histset_list.append(histset)
+					last_histset = histset
+					
+					# 初始化首段
+					seg_dir = Chan_MACDSEG_DIR.ABOVE if klu.signal >= 0 else Chan_MACDSEG_DIR.UNDER
+					seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, None, seg_dir, last_unittf)
+					self.seg_list.append(seg)
+					last_seg = seg
 
-                    # 初始化首个UnitTF
-                    unittf_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
-                    unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, unittf_dir, Chan_MACDUNITTF_TYPE.START, histset)
-                    self.unittf_list.append(unittf)
-                    last_unittf = unittf
-                    last_seg.add_unittf(unittf)
-                # 未就绪则继续等下一根；已就绪亦已完成首个结构初始化，继续下一根
-                last_klu = klu
-                continue
-             # 3) 直方图集合（基于当前 unittf）
-            if klu.macdhist >= 0:
-                if last_histset and last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
-                    last_histset.add_klu(klu)
-                else:
-                    # 结束旧 histset（以前一根结束更合理）
-                    if last_histset and last_klu:
-                        last_histset.set_end_klu(last_klu)
-                    histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE if klu.macdhist >= 0 else Chan_MACDHISTSET_DIR.UNDER)
-                    self.histset_list.append(histset)
-                    if last_histset:
-                        last_histset.set_next(histset)
-                    last_histset = histset
-                    if last_unittf:
-                        last_unittf.add_histset(histset)
-            else:
-                if last_histset and last_histset.histset_dir == Chan_MACDHISTSET_DIR.UNDER:
-                    last_histset.add_klu(klu)
-                else:
-                    # 结束旧 histset（以前一根结束更合理）
-                    if last_histset and last_klu:
-                        last_histset.set_end_klu(last_klu)
-                    histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE if klu.macdhist >= 0 else Chan_MACDHISTSET_DIR.UNDER)
-                    self.histset_list.append(histset)
-                    if last_histset:
-                        last_histset.set_next(histset)
-                    last_histset = histset
-                    if last_unittf:
-                        last_unittf.add_histset(histset)
-            # 2) 过零切段（使用KLU中的穿越状态）
-            if (klu.macd_state == Chan_MACD_STATE.CROSS0_UP or 
-                klu.macd_state == Chan_MACD_STATE.CROSS0_DOWN):
-                # 结束旧 unittf
-                last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
-                # 新的单位时间周期
-                new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
-                unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.CROSS0, histset)
-                self.unittf_list.append(unittf)
-                last_unittf.set_next(unittf)
-                last_unittf = unittf
-                # 收尾旧段
-                last_seg.set_end_klu(last_klu)
-                # 新段方向取反
-                new_dir = Chan_MACDSEG_DIR.UNDER if last_seg.seg_dir == Chan_MACDSEG_DIR.ABOVE else Chan_MACDSEG_DIR.ABOVE
-                seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, new_dir, last_unittf)
-                self.seg_list.append(seg)
-                last_seg.set_next(seg)
-                last_seg = seg
-                last_seg.add_unittf(unittf)
-            else:
-                # 4) UnitTF 状态机：用黄线Signal的归零轴
-                if last_klu.macd_state == Chan_MACD_STATE.NEAR0 and last_unittf.div_count > 1:
-                    #print(klu.time, klu.macd_state)
-                    if klu.macd_state == Chan_MACD_STATE.RZ_UP:
-                        last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.NEAR0)
-                        new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
-                        unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.NEAR0, histset)
-                        self.unittf_list.append(unittf)
-                        last_unittf.set_next(unittf)
-                        last_unittf = unittf
-                        last_seg.add_unittf(unittf)
-                    elif klu.macd_state == Chan_MACD_STATE.RZ_DOWN:
-                        last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.NEAR0)
-                        new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
-                        unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.NEAR0, histset)
-                        self.unittf_list.append(unittf)
-                        last_unittf.set_next(unittf)
-                        last_unittf = unittf
-                        last_seg.add_unittf(unittf)
-                    else:
-                        last_unittf.add_klu(klu)
-                        last_seg.add_klu(klu)
-                else:
-                    last_unittf.add_klu(klu)
-                    last_seg.add_klu(klu)
+					# 初始化首个UnitTF
+					unittf_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
+					unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, None, unittf_dir, Chan_MACDUNITTF_TYPE.START, histset)
+					self.unittf_list.append(unittf)
+					last_unittf = unittf
+					last_seg.add_unittf(unittf)
+				# 未就绪则继续等下一根；已就绪亦已完成首个结构初始化，继续下一根
+				last_klu = klu
+				continue
+			 # 3) 直方图集合（基于当前 unittf）
+			if klu.macdhist >= 0:
+				if last_histset and last_histset.histset_dir == Chan_MACDHISTSET_DIR.ABOVE:
+					last_histset.add_klu(klu)
+				else:
+					# 结束旧 histset（以前一根结束更合理）
+					if last_histset and last_klu:
+						last_histset.set_end_klu(last_klu)
+					histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE if klu.macdhist >= 0 else Chan_MACDHISTSET_DIR.UNDER)
+					self.histset_list.append(histset)
+					if last_histset:
+						last_histset.set_next(histset)
+					last_histset = histset
+					if last_unittf:
+						last_unittf.add_histset(histset)
+			else:
+				if last_histset and last_histset.histset_dir == Chan_MACDHISTSET_DIR.UNDER:
+					last_histset.add_klu(klu)
+				else:
+					# 结束旧 histset（以前一根结束更合理）
+					if last_histset and last_klu:
+						last_histset.set_end_klu(last_klu)
+					histset = ChanMACDHistSet(len(self.histset_list), klu.time, klu, last_histset, Chan_MACDHISTSET_DIR.ABOVE if klu.macdhist >= 0 else Chan_MACDHISTSET_DIR.UNDER)
+					self.histset_list.append(histset)
+					if last_histset:
+						last_histset.set_next(histset)
+					last_histset = histset
+					if last_unittf:
+						last_unittf.add_histset(histset)
+			# 2) 过零切段（使用KLU中的穿越状态）
+			if (klu.macd_state == Chan_MACD_STATE.CROSS0_UP or 
+				klu.macd_state == Chan_MACD_STATE.CROSS0_DOWN):
+				# 结束旧 unittf
+				last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.CROSS0)
+				# 新的单位时间周期
+				new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
+				unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.CROSS0, histset)
+				self.unittf_list.append(unittf)
+				last_unittf.set_next(unittf)
+				last_unittf = unittf
+				# 收尾旧段
+				last_seg.set_end_klu(last_klu)
+				# 新段方向取反
+				new_dir = Chan_MACDSEG_DIR.UNDER if last_seg.seg_dir == Chan_MACDSEG_DIR.ABOVE else Chan_MACDSEG_DIR.ABOVE
+				seg = ChanMACDSeg(len(self.seg_list), klu.time, klu, last_seg, new_dir, last_unittf)
+				self.seg_list.append(seg)
+				last_seg.set_next(seg)
+				last_seg = seg
+				last_seg.add_unittf(unittf)
+			else:
+				# 4) UnitTF 状态机：用黄线Signal的归零轴
+				if last_klu.macd_state == Chan_MACD_STATE.NEAR0 and last_unittf.div_count > 1:
+					#print(klu.time, klu.macd_state)
+					if klu.macd_state == Chan_MACD_STATE.RZ_UP:
+						last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.NEAR0)
+						new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
+						unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.NEAR0, histset)
+						self.unittf_list.append(unittf)
+						last_unittf.set_next(unittf)
+						last_unittf = unittf
+						last_seg.add_unittf(unittf)
+					elif klu.macd_state == Chan_MACD_STATE.RZ_DOWN:
+						last_unittf.set_end_klu(last_klu, Chan_MACDUNITTF_TYPE.NEAR0)
+						new_dir = Chan_MACDUNITTF_DIR.ABOVE if klu.signal >= 0 else Chan_MACDUNITTF_DIR.UNDER
+						unittf = ChanMACDUnitTF(len(self.unittf_list), klu.time, klu, last_unittf, new_dir, Chan_MACDUNITTF_TYPE.NEAR0, histset)
+						self.unittf_list.append(unittf)
+						last_unittf.set_next(unittf)
+						last_unittf = unittf
+						last_seg.add_unittf(unittf)
+					else:
+						last_unittf.add_klu(klu)
+						last_seg.add_klu(klu)
+				else:
+					last_unittf.add_klu(klu)
+					last_seg.add_klu(klu)
 
-            last_klu = klu
-        last_histset.set_end_klu(last_klu)
-        last_unittf.set_end_klu(last_klu, None)
-        last_seg.set_end_klu(last_klu)
-        return self.klu_list
+			last_klu = klu
+		last_histset.set_end_klu(last_klu)
+		last_unittf.set_end_klu(last_klu, None)
+		last_seg.set_end_klu(last_klu)
+		return self.klu_list

TF_DF.py

@@ -123,12 +123,12 @@ class TF_DF():
 		return klu_state_list
 	def check_fx(self, klc):
 		if klc.pre and klc.next:
-			if klc.high > klc.pre.high and klc.high > klc.next.high and klc.low > klc.pre.low and klc.low > klc.next.low and klc.next.klc_dir == Chan_KLINE_DIR.DOWN:
+			if klc.high > klc.pre.high and klc.high > klc.next.high and klc.low > klc.pre.low and klc.low > klc.next.low and klc.close > klc.next.close:
 				#if (klc.close > klc.ema52 or klc.next.close > klc.next.ema52) and klc.macd > 0 and klc.macd > klc.macdhist:
 				klc.set_fx(Chan_FX_TYPE.TOP)
 				#print(klc.start_time, klc.end_time,klc.next.start_time, klc.next.end_time, klc.macd, klc.state, klc.fx, "TOP")
 				return Chan_FX_TYPE.TOP
-			elif klc.low < klc.pre.low and klc.low < klc.next.low and klc.high < klc.pre.high and klc.high < klc.next.high and klc.next.klc_dir == Chan_KLINE_DIR.UP:
+			elif klc.low < klc.pre.low and klc.low < klc.next.low and klc.high < klc.pre.high and klc.high < klc.next.high and klc.close < klc.next.close:
 				#if (klc.close < klc.ema52 or klc.next.close < klc.next.ema52) and klc.macd < 0 and klc.macd < klc.macdhist:
 				klc.set_fx(Chan_FX_TYPE.BOTTOM)
 				#print(klc.start_time, klc.end_time,klc.next.start_time, klc.next.end_time, klc.macd, klc.state, klc.fx, "BOTTOM")
@@ -1387,8 +1387,8 @@ class TF_DF():
 			if i >= 2:
 				self._detect_triple_pattern(klu_list[i-2], klu_list[i-1], klu)
 			
-			if klu.pattern != Chan_KLU_PATTERN.UNKNOWN:
-				print(klu.time, klu.pattern, klu.lower_shadow_ratio, klu.upper_shadow_ratio, klu.body_ratio, klu.lower_shadow_ratio/klu.body_ratio, klu.upper_shadow_ratio/klu.body_ratio)
+			#if klu.pattern != Chan_KLU_PATTERN.UNKNOWN:
+				#print(klu.time, klu.pattern, klu.lower_shadow_ratio, klu.upper_shadow_ratio, klu.body_ratio, klu.lower_shadow_ratio/klu.body_ratio, klu.upper_shadow_ratio/klu.body_ratio)
 		return klu_list
 	
 	def _detect_single_reversal_pattern(self, klu):

datasvc/Dockerfile

@@ -10,6 +10,15 @@ RUN pip install -r /app/requirements.txt
 
 COPY app /app/app
 
+ENV DATA_DIR=/data \
+    EXCHANGE=binance \
+    SYMBOLS=BTC/USDT:USDT,ETH/USDT:USDT \
+    TIMEFRAMES=1m,1h,1d,1w,1M \
+    START_FROM=2022-01-01 \
+    POLL_FACTOR=0.5
+
+VOLUME ["/data"]
+
 EXPOSE 9000
 
 CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "9000"]

datasvc/README.md

@@ -1,48 +1,141 @@
-# Local Data Service (REST + WebSocket)
+# Local Data Service（REST + WebSocket）
 
-一键部署、跨平台的本地行情数据服务。默认抓取 Binance 永续合约 `BTC/USDT:USDT, ETH/USDT:USDT` 的 `1m/5m/15m/1h` K 线，增量写入本地 Parquet 并通过 WebSocket 推送。
+本服务基于 FastAPI + ccxt，自动拉取交易所行情、写入本地 Parquet，同时提供 REST 和 WebSocket 数据访问。  
+自带时间周期聚合能力：只需抓取 `1m / 1h / 1d / 1w / 1M` 等基础周期，即可自动生成 `2m/3m/.../30m`、`2h/3h/.../16h` 等衍生周期。
 
-## 快速开始（方式B：已安装 Docker）
+---
 
+## 1. 环境准备
+
+### 1.1 依赖
+- Python ≥ 3.10（本地运行方式需要）
+- `pip install -r requirements.txt`（包含 `fastapi`, `uvicorn`, `ccxt`, `pandas`, `pyarrow`, `technical` 等）
+- 或者直接使用仓库内的 `docker-compose.yml`
+
+### 1.2 关键环境变量
+| 变量 | 说明 | 默认 |
+| --- | --- | --- |
+| `DATA_DIR` | 本地 Parquet 存储目录 | `/data` |
+| `EXCHANGE` | 交易所标识（目前支持 binance） | `binance` |
+| `SYMBOLS` | 逗号分隔的交易对列表 | `BTC/USDT:USDT,ETH/USDT:USDT` |
+| `TIMEFRAMES` | 基础抓取周期，逗号分隔 | `1m,1h,1d,1w,1M` |
+| `START_FROM` | 首次启动回补的起始 UTC 时间（ISO 字符串或毫秒时间戳） | `2022-01-01` |
+| `POLL_FACTOR` | 拉取间隔因子，实际间隔 = 周期毫秒 × factor | `0.5` |
+| `BACKOFF_BASE / BACKOFF_MAX` | 异常重试的指数退避参数 | `2.0 / 30.0` |
+
+> 衍生周期列表由程序自动推导，无需手动写入 `TIMEFRAMES`。
+
+---
+
+## 2. 启动与关闭
+
+### 2.1 Docker 方式
 ```bash
 cd user_data/Chan/datasvc
-docker compose up -d
+docker compose up -d          # 启动
+docker compose logs -f        # 查看日志
+docker compose down           # 关闭
 ```
 
-- REST: http://localhost:9000/api/candles?symbol=BTC/USDT:USDT&tf=1m
-- WS:   ws://localhost:9000/ws?symbol=BTC/USDT:USDT&tf=1m&since=1690000000000
-- Swagger: http://localhost:9000/docs
-
-## 环境变量（docker-compose.yml）
-- EXCHANGE: 交易所，默认 binance
-- SYMBOLS: 逗号分隔交易对
-- TIMEFRAMES: 逗号分隔周期
-- START_DAYS: 首次启动回补最近 N 天
-- POLL_FACTOR: 轮询因子，间隔=周期毫秒*factor
-- DATA_DIR: 容器内数据目录（已映射到 `./data`）
-
-## 数据位置
-- 本地缓存：`user_data/Chan/datasvc/data/{timeframe}/{symbol}.parquet`
-
-## 常用命令
+### 2.2 本地运行（无 Docker）
 ```bash
-docker compose logs -f
+export DATA_DIR=./data
+export SYMBOLS="BTC/USDT:USDT"
+export TIMEFRAMES="1m,1h,1d"
 
-docker compose down
+cd /Users/jack/Project/freqtrade
+uvicorn user_data.Chan.datasvc.app.main:app --reload
 ```
 
-## 接口说明
-- GET /api/candles
-  - 参数：symbol, tf, start(ms), end(ms)
-  - 返回：[{timestamp, open, high, low, close, volume}]
-- WS /ws
-  - 参数：symbol, tf, since(ms)
-  - 消息：
-    - snapshot: 初始快照数组
-    - upsert: 单根K线增量（尾部修正）
+关闭时 Ctrl+C 即可，服务会自动取消后台抓取任务并释放资源。
 
-## 注意
-- 默认未带交易所 API Key，仅公共行情。
-- 如需更多交易对/周期，修改 `docker-compose.yml` 后重启。
+---
 
+## 3. 数据存储与聚合
 
+### 3.1 基础周期
+只会为 `TIMEFRAMES` 声明的基础周期创建抓取任务（例如 `1m / 1h / 1d`）。
+
+### 3.2 衍生周期
+启动后自动维护以下聚合：
+
+| 基础周期 | 自动生成 |
+| --- | --- |
+| `1m` | `2m, 3m, 4m, 5m, 10m, 15m, 20m, 25m, 30m` |
+| `1h` | `2h, 3h, 4h, 6h, 8h, 12h, 16h` |
+| `1d` | `2d, 3d, 4d, 5d, 6d` |
+| `1w` | `2w` |
+| `1M` | `2M, 3M, 6M` |
+
+聚合过程通过 `technical.util.resample_to_interval` 完成，写入同一 Parquet 数据目录。  
+所有周期都可以被 REST/WS 访问。
+
+### 3.3 数据目录
+```
+{DATA_DIR}/{timeframe}/{symbol}.parquet
+```
+
+---
+
+## 4. 接口调用
+
+### 4.1 健康检查
+```
+GET /health
+```
+返回运行状态、基础/衍生周期列表、各抓取任务的最新进度与错误计数，便于监控。
+
+### 4.2 REST API
+```
+GET /api/candles?symbol=BTC/USDT:USDT&tf=2h&start=1700000000000&end=1700003600000
+```
+参数说明：
+- `symbol`：交易对（必须在 `SYMBOLS` 列表中）
+- `tf`：时间周期（支持基础或衍生）
+- `start` / `end`：毫秒时间戳，可选
+
+返回示例：
+```json
+[
+  {"timestamp": 1700000000000, "open": 36000.0, "high": 36120.0, "low": 35980.0, "close": 36050.0, "volume": 125.4},
+  ...
+]
+```
+
+### 4.3 WebSocket
+```
+ws://localhost:8000/ws?symbol=ETH/USDT:USDT&tf=15m&since=1700000000000
+```
+- 首次连接：收到 `snapshot` 消息（快照数组）
+- 后续增量：收到 `upsert` 消息（最新几根K线），以及周期性 `ping`
+
+消息示例：
+```json
+{"topic":"candles.ETH/USDT:USDT.15m","type":"snapshot","data":[{"t":1700000000000,"o":2000.0,"h":2005.0,"l":1995.0,"c":2002.5,"v":312.7}, ...]}
+{"topic":"candles.ETH/USDT:USDT.15m","type":"upsert","data":{"t":1700000900000,"o":2002.5,"h":2006.0,"l":2000.0,"c":2004.0,"v":120.8}}
+```
+
+---
+
+## 5. 停机与维护
+
+- **正常关闭**：`docker compose down` 或 Ctrl+C。服务会等待所有抓取任务结束并关闭 `ccxt` 客户端。
+- **异常恢复**：若网络异常，服务会自动指数退避重试；可通过 `/health` 的 `consecutive_errors` 与 `last_error` 排查。
+- **数据清理**：直接删除 `DATA_DIR` 下对应的 Parquet 文件即可，下次启动会重新回补。
+
+---
+
+## 6. 常见问题
+
+1. **缺少 `technical` 模块**  
+   聚合周期会跳过，并在日志中提示；先执行 `pip install technical` 再重启。
+
+2. **接收不到某个周期的数据**  
+   确认该周期在 `TIMEFRAMES` 或自动聚合列表中；若是衍生周期，需要确保对应基础周期已在运行。
+
+3. **如何新增交易对/周期**  
+   修改环境变量或 docker-compose 配置后，重启服务即可；Parquet 文件会按需生成。
+
+---
+
+欢迎结合自身策略或可视化前端直接消费本地数据服务。若要集成到其他项目，可直接引用 `/api/candles` 的 JSON 响应或订阅 `/ws` 的实时推送。

datasvc/app/main.py

@@ -1,15 +1,24 @@
 import os
 import asyncio
 import json
+import logging
+from contextlib import suppress
+from dataclasses import dataclass, field
 from datetime import datetime, timedelta
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Tuple, Union
 
 import ccxt
+import ccxt.async_support as ccxt_async
 import pandas as pd
-from fastapi import FastAPI, WebSocket, WebSocketDisconnect, Query
+from fastapi import FastAPI, WebSocket, WebSocketDisconnect, Query, HTTPException, status
 from fastapi.responses import JSONResponse
 from fastapi.middleware.cors import CORSMiddleware
 
+try:
+    from technical.util import resample_to_interval  # type: ignore
+except ImportError:  # pragma: no cover - 环境缺失依赖时自动降级
+    resample_to_interval = None  # type: ignore
+
 from .storage import (
     ensure_storage,
     read_candles,
@@ -18,12 +27,86 @@ from .storage import (
 )
 
 
+LOG_LEVEL = os.environ.get("LOG_LEVEL", "INFO").upper()
+logging.basicConfig(
+    level=LOG_LEVEL,
+    format="%(asctime)s %(levelname)s [%(name)s] %(message)s",
+)
+logger = logging.getLogger("datasvc")
+RESAMPLE_AVAILABLE = resample_to_interval is not None
+RESAMPLE_WARNING_EMITTED = False
+
+AGGREGATION_PLAN: Dict[str, List[str]] = {
+    "1m": ["2m", "3m", "4m", "5m", "10m", "15m", "20m", "25m", "30m"],
+    "1h": ["2h", "3h", "4h", "6h", "8h", "12h", "16h"],
+    "1d": ["2d", "3d", "4d", "5d", "6d"],
+    "1w": ["2w"],
+    "1M": ["2M", "3M", "6M"],
+}
+
+CandleRow = List[Union[int, float]]
+
+
+def _split_env_list(value: str) -> List[str]:
+    return [item.strip() for item in value.split(",") if item.strip()]
+
+
+def _unique_preserve(values: List[str]) -> List[str]:
+    seen = set()
+    ordered: List[str] = []
+    for item in values:
+        if item not in seen:
+            ordered.append(item)
+            seen.add(item)
+    return ordered
+
+
+def timeframe_to_minutes(tf: str) -> Optional[int]:
+    if not tf:
+        return None
+    unit = tf[-1]
+    try:
+        value = int(tf[:-1])
+    except ValueError:
+        return None
+    multiplier = {
+        "m": 1,
+        "h": 60,
+        "d": 1440,
+        "w": 10080,
+        "M": 43200,  # 30 天近似
+    }.get(unit)
+    if multiplier is None:
+        return None
+    return value * multiplier
+
 DATA_DIR = os.environ.get("DATA_DIR", "/data")
 EXCHANGE = os.environ.get("EXCHANGE", "binance")
-SYMBOLS = [s.strip() for s in os.environ.get("SYMBOLS", "BTC/USDT:USDT,ETH/USDT:USDT").split(",") if s.strip()]
-TIMEFRAMES = [t.strip() for t in os.environ.get("TIMEFRAMES", "1m,5m,15m,1h").split(",") if t.strip()]
-START_FROM = os.environ.get("START_FROM", "2025-01-01")  # 首次启动拉取起始日期（UTC）
+SYMBOLS = _split_env_list(os.environ.get("SYMBOLS", "BTC/USDT:USDT,ETH/USDT:USDT"))
+if not SYMBOLS:
+    SYMBOLS = ["BTC/USDT:USDT"]
+
+_default_timeframes = ["1m", "1h", "1d", "1w", "1M"]
+requested_timeframes = _split_env_list(os.environ.get("TIMEFRAMES", ",".join(_default_timeframes)))
+if not requested_timeframes:
+    requested_timeframes = _default_timeframes
+
+FETCH_TIMEFRAMES = _unique_preserve(requested_timeframes)
+AVAILABLE_TIMEFRAMES = list(FETCH_TIMEFRAMES)
+for base_tf in FETCH_TIMEFRAMES:
+    for derived_tf in AGGREGATION_PLAN.get(base_tf, []):
+        if derived_tf not in AVAILABLE_TIMEFRAMES:
+            AVAILABLE_TIMEFRAMES.append(derived_tf)
+DERIVED_TIMEFRAMES = [tf for tf in AVAILABLE_TIMEFRAMES if tf not in FETCH_TIMEFRAMES]
+AGGREGATION_TARGETS = {tf: AGGREGATION_PLAN.get(tf, []) for tf in FETCH_TIMEFRAMES}
+
+START_FROM = os.environ.get("START_FROM", "2022-01-01")  # 首次启动拉取起始日期（UTC）
 POLL_FACTOR = float(os.environ.get("POLL_FACTOR", "0.5"))  # 轮询间隔 = tf_ms * factor
+BACKOFF_BASE = float(os.environ.get("BACKOFF_BASE", "2.0"))
+BACKOFF_MAX = float(os.environ.get("BACKOFF_MAX", "30.0"))
+
+VALID_SYMBOLS = set(SYMBOLS)
+VALID_TIMEFRAMES = set(AVAILABLE_TIMEFRAMES)
 
 ensure_storage(DATA_DIR)
 
@@ -38,18 +121,24 @@ app.add_middleware(
 
 
 def tf_to_ms(tf: str) -> int:
-    table = {
-        "1m": 60_000,
-        "3m": 3 * 60_000,
-        "5m": 5 * 60_000,
-        "15m": 15 * 60_000,
-        "30m": 30 * 60_000,
-        "1h": 60 * 60_000,
-        "2h": 2 * 60 * 60_000,
-        "4h": 4 * 60 * 60_000,
-        "1d": 24 * 60 * 60_000,
-    }
-    return table.get(tf, 60_000)
+    minutes = timeframe_to_minutes(tf)
+    if minutes is None:
+        logger.warning("无法解析时间周期，默认使用 60 秒", extra={"timeframe": tf})
+        return 60_000
+    return minutes * 60_000
+
+
+def ensure_symbol_timeframe(symbol: str, timeframe: str) -> None:
+    if symbol not in VALID_SYMBOLS:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=f"symbol 必须为 {sorted(VALID_SYMBOLS)} 之一。",
+        )
+    if timeframe not in VALID_TIMEFRAMES:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=f"tf 必须为 {sorted(VALID_TIMEFRAMES)} 之一。",
+        )
 
 
 def parse_start_from_ms(val: str) -> int:
@@ -63,10 +152,10 @@ def parse_start_from_ms(val: str) -> int:
     except Exception:
         pass
     try:
-        dt = datetime.fromisoformat(val)  # 允许 '2025-01-01' 或 '2025-01-01T00:00:00'
+        dt = datetime.fromisoformat(val)  # 允许 '2022-01-01' 或 '2022-01-01T00:00:00'
     except Exception:
         # 回退到固定日期
-        dt = datetime(2025, 1, 1)
+        dt = datetime(2022, 1, 1)
     return int(dt.timestamp() * 1000)
 
 
@@ -104,52 +193,272 @@ class Hub:
 
 hub = Hub()
 
+fetch_tasks: List[asyncio.Task] = []
+
+
+def resample_and_store(symbol: str, base_timeframe: str, derived_timeframes: List[str]) -> List[Tuple[str, List[CandleRow]]]:
+    if not RESAMPLE_AVAILABLE or not derived_timeframes:
+        return []
+    base_df = read_candles(DATA_DIR, symbol, base_timeframe, None, None)
+    if base_df.empty:
+        return []
+    base_df = base_df.copy()
+    if "date" not in base_df.columns:
+        base_df["date"] = pd.to_datetime(base_df["timestamp"], unit="ms", utc=True)
+    base_df = base_df.sort_values("timestamp")
+
+    updates: List[Tuple[str, List[List[float]]]] = []
+    for target_tf in derived_timeframes:
+        minutes = timeframe_to_minutes(target_tf)
+        if minutes is None:
+            logger.warning("无法解析聚合周期", extra={"target_timeframe": target_tf})
+            continue
+        try:
+            derived_df = resample_to_interval(base_df, minutes)  # type: ignore[misc]
+        except Exception:
+            logger.exception(
+                "聚合周期计算失败",
+                extra={"symbol": symbol, "base_timeframe": base_timeframe, "target_timeframe": target_tf},
+            )
+            continue
+        if derived_df is None or derived_df.empty:
+            continue
+        derived_df = derived_df.copy()
+        if "timestamp" not in derived_df.columns:
+            if "date" in derived_df.columns:
+                dates = pd.to_datetime(derived_df["date"], utc=True, errors="coerce")
+                derived_df["timestamp"] = (dates.view("int64") // 1_000_000)
+            elif isinstance(derived_df.index, pd.DatetimeIndex):
+                idx = derived_df.index
+                if idx.tz is None:
+                    idx = idx.tz_localize("UTC")
+                else:
+                    idx = idx.tz_convert("UTC")
+                derived_df["timestamp"] = (idx.view("int64") // 1_000_000)
+        if "timestamp" not in derived_df.columns:
+            logger.warning(
+                "聚合结果缺少 timestamp 列，已跳过",
+                extra={"target_timeframe": target_tf},
+            )
+            continue
+        derived_df = derived_df.dropna(subset=["timestamp", "open", "high", "low", "close", "volume"])
+        if derived_df.empty:
+            continue
+        derived_df["timestamp"] = derived_df["timestamp"].astype("int64")
+        derived_df = derived_df.sort_values("timestamp")
+        last_ts = get_last_timestamp(DATA_DIR, symbol, target_tf)
+        if last_ts is not None:
+            derived_df = derived_df[derived_df["timestamp"] > last_ts]
+        if derived_df.empty:
+            continue
+        numpy_rows = derived_df[["timestamp", "open", "high", "low", "close", "volume"]].to_numpy()
+        records: List[CandleRow] = []
+        for ts, o, h, l, c, v in numpy_rows:
+            records.append(
+                [
+                    int(ts),
+                    float(o),
+                    float(h),
+                    float(l),
+                    float(c),
+                    float(v),
+                ]
+            )
+        if not records:
+            continue
+        upsert_candles(DATA_DIR, symbol, target_tf, records)
+        updates.append((target_tf, records[-3:] if len(records) > 3 else records))
+    return updates
+
+
+@dataclass
+class FetchState:
+    symbol: str
+    timeframe: str
+    started_at: datetime = field(default_factory=datetime.utcnow)
+    last_fetch_at: Optional[datetime] = None
+    last_candle_ts: Optional[int] = None
+    consecutive_errors: int = 0
+    last_error: Optional[str] = None
+
+    def to_payload(self) -> dict:
+        def serialize_dt(dt: Optional[datetime]) -> Optional[str]:
+            if not dt:
+                return None
+            return dt.replace(microsecond=0).isoformat() + "Z"
+
+        return {
+            "symbol": self.symbol,
+            "timeframe": self.timeframe,
+            "started_at": serialize_dt(self.started_at),
+            "last_fetch_at": serialize_dt(self.last_fetch_at),
+            "last_candle_ts": self.last_candle_ts,
+            "consecutive_errors": self.consecutive_errors,
+            "last_error": self.last_error,
+        }
+
+
+fetch_states: Dict[Tuple[str, str], FetchState] = {}
+
 
 def build_exchange():
     if EXCHANGE.lower() == "binance":
-        return ccxt.binance({"enableRateLimit": True})
+        return ccxt_async.binance({"enableRateLimit": True})
     raise RuntimeError(f"Unsupported EXCHANGE: {EXCHANGE}")
 
 
 async def fetch_loop(symbol: str, timeframe: str):
     """持续增量抓取并广播。"""
+    derived_timeframes = AGGREGATION_TARGETS.get(timeframe, [])
+    global RESAMPLE_WARNING_EMITTED
+    if derived_timeframes and not RESAMPLE_AVAILABLE and not RESAMPLE_WARNING_EMITTED:
+        logger.warning(
+            "缺少 technical.util.resample_to_interval 模块，聚合时间周期生成已跳过",
+            extra={"timeframe": timeframe},
+        )
+        RESAMPLE_WARNING_EMITTED = True
+
     exchange = build_exchange()
     tf_ms = tf_to_ms(timeframe)
     start_since = parse_start_from_ms(START_FROM)
     last_ts = get_last_timestamp(DATA_DIR, symbol, timeframe)
     since = max(start_since, (last_ts + tf_ms) if last_ts else start_since)
+    backoff = 1.0
+    state_key = (symbol, timeframe)
+    fetch_states[state_key] = FetchState(symbol=symbol, timeframe=timeframe, last_candle_ts=last_ts)
 
-    while True:
-        try:
-            candles = exchange.fetch_ohlcv(symbol, timeframe, since=since, limit=1000)
-            if candles:
-                upsert_candles(DATA_DIR, symbol, timeframe, candles)
-                for row in candles[-3:]:
-                    payload = {
-                        "topic": f"candles.{symbol}.{timeframe}",
-                        "type": "upsert",
-                        "data": {
-                            "t": row[0],
-                            "o": row[1],
-                            "h": row[2],
-                            "l": row[3],
-                            "c": row[4],
-                            "v": row[5],
-                        },
-                    }
-                    await hub.publish(symbol, timeframe, payload)
-                since = candles[-1][0] + tf_ms
-            await asyncio.sleep(max(1.0, tf_ms * POLL_FACTOR / 1000.0))
-        except Exception:
-            await asyncio.sleep(3.0)
+    logger.info("启动拉取任务", extra={"symbol": symbol, "timeframe": timeframe})
+
+    try:
+        while True:
+            try:
+                candles = await exchange.fetch_ohlcv(symbol, timeframe, since=since, limit=1000)
+                if candles:
+                    upsert_candles(DATA_DIR, symbol, timeframe, candles)
+                    derived_updates: List[Tuple[str, List[CandleRow]]] = []
+                    if derived_timeframes and RESAMPLE_AVAILABLE:
+                        derived_updates = await asyncio.to_thread(
+                            resample_and_store,
+                            symbol,
+                            timeframe,
+                            derived_timeframes,
+                        )
+                    for row in candles[-3:]:
+                        payload = {
+                            "topic": f"candles.{symbol}.{timeframe}",
+                            "type": "upsert",
+                            "data": {
+                                "t": row[0],
+                                "o": row[1],
+                                "h": row[2],
+                                "l": row[3],
+                                "c": row[4],
+                                "v": row[5],
+                            },
+                        }
+                        await hub.publish(symbol, timeframe, payload)
+                    for target_tf, rows in derived_updates:
+                        if not rows:
+                            continue
+                        for row in rows:
+                            ts = int(row[0])
+                            o, h, l, c, v = map(float, row[1:])
+                            payload = {
+                                "topic": f"candles.{symbol}.{target_tf}",
+                                "type": "upsert",
+                                "data": {
+                                    "t": ts,
+                                    "o": o,
+                                    "h": h,
+                                    "l": l,
+                                    "c": c,
+                                    "v": v,
+                                },
+                            }
+                            await hub.publish(symbol, target_tf, payload)
+                    since = candles[-1][0] + tf_ms
+                    backoff = 1.0
+                    state = fetch_states[state_key]
+                    state.last_fetch_at = datetime.utcnow()
+                    state.last_candle_ts = candles[-1][0]
+                    state.consecutive_errors = 0
+                    state.last_error = None
+                await asyncio.sleep(max(1.0, tf_ms * POLL_FACTOR / 1000.0))
+            except asyncio.CancelledError:
+                raise
+            except (ccxt.NetworkError, ccxt.ExchangeNotAvailable, ccxt.RequestTimeout) as exc:
+                logger.warning(
+                    "网络异常，准备重试",
+                    extra={"symbol": symbol, "timeframe": timeframe, "error": str(exc)},
+                )
+                state = fetch_states[state_key]
+                state.last_error = str(exc)
+                state.consecutive_errors += 1
+                backoff = min(backoff * BACKOFF_BASE, BACKOFF_MAX)
+                await asyncio.sleep(backoff)
+            except Exception as exc:
+                logger.exception(
+                    "抓取循环发生异常，重建客户端后重试",
+                    extra={"symbol": symbol, "timeframe": timeframe},
+                )
+                state = fetch_states[state_key]
+                state.last_error = str(exc)
+                state.consecutive_errors += 1
+                await asyncio.sleep(backoff)
+                with suppress(Exception):
+                    await exchange.close()
+                exchange = build_exchange()
+                backoff = min(backoff * BACKOFF_BASE, BACKOFF_MAX)
+    except asyncio.CancelledError:
+        logger.info("取消拉取任务", extra={"symbol": symbol, "timeframe": timeframe})
+        state = fetch_states.get(state_key)
+        if state:
+            state.last_error = "cancelled"
+        raise
+    finally:
+        with suppress(Exception):
+            await exchange.close()
+        logger.info("拉取任务退出", extra={"symbol": symbol, "timeframe": timeframe})
 
 
 @app.on_event("startup")
 async def on_start():
     ensure_storage(DATA_DIR)
+    fetch_tasks.clear()
     for s in SYMBOLS:
-        for tf in TIMEFRAMES:
-            asyncio.create_task(fetch_loop(s, tf))
+        for tf in FETCH_TIMEFRAMES:
+            task = asyncio.create_task(fetch_loop(s, tf), name=f"fetch::{s}::{tf}")
+            fetch_tasks.append(task)
+
+
+@app.on_event("shutdown")
+async def on_shutdown():
+    if not fetch_tasks:
+        return
+    logger.info("正在停止拉取任务")
+    tasks = list(fetch_tasks)
+    for task in tasks:
+        task.cancel()
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+    for result in results:
+        if isinstance(result, Exception) and not isinstance(result, asyncio.CancelledError):
+            logger.warning("任务停止时出现异常：%s", result)
+    fetch_tasks.clear()
+
+
+@app.get("/health")
+async def health():
+    now = datetime.utcnow().replace(microsecond=0).isoformat() + "Z"
+    return {
+        "status": "ok",
+        "time": now,
+        "exchange": EXCHANGE,
+        "symbols": SYMBOLS,
+        "base_timeframes": FETCH_TIMEFRAMES,
+        "derived_timeframes": DERIVED_TIMEFRAMES,
+        "timeframes": AVAILABLE_TIMEFRAMES,
+        "tasks": [state.to_payload() for state in fetch_states.values()],
+    }
 
 
 @app.get("/api/candles")
@@ -160,6 +469,7 @@ def api_candles(
     end: Optional[int] = Query(None, description="结束时间戳(ms)"),
 ):
     try:
+        ensure_symbol_timeframe(symbol, tf)
         df = read_candles(DATA_DIR, symbol, tf, start, end)
         records = df.to_dict("records") if not df.empty else []
         return JSONResponse(records)
@@ -169,6 +479,9 @@ def api_candles(
 
 @app.websocket("/ws")
 async def ws_endpoint(websocket: WebSocket, symbol: str, tf: str, since: Optional[int] = None):
+    if symbol not in VALID_SYMBOLS or tf not in VALID_TIMEFRAMES:
+        await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="invalid symbol/timeframe")
+        return
     await hub.subscribe(websocket, symbol, tf)
     try:
         snap = read_candles(DATA_DIR, symbol, tf, since, None)
@@ -201,7 +514,9 @@ def root():
         "service": "Local Data Service",
         "exchange": EXCHANGE,
         "symbols": SYMBOLS,
-        "timeframes": TIMEFRAMES,
+        "base_timeframes": FETCH_TIMEFRAMES,
+        "derived_timeframes": DERIVED_TIMEFRAMES,
+        "timeframes": AVAILABLE_TIMEFRAMES,
     }
 
 

datasvc/docker-compose.yml

@@ -7,8 +7,8 @@ services:
     environment:
       - EXCHANGE=binance
       - SYMBOLS=BTC/USDT:USDT,ETH/USDT:USDT
-      - TIMEFRAMES=1m,5m,15m,1h
-      - START_FROM=2025-01-01
+      - TIMEFRAMES=1m,1h,1d,1w,1M
+      - START_FROM=2022-01-01
       - POLL_FACTOR=0.5
       - DATA_DIR=/data
       - TZ=Asia/Shanghai

datasvc/requirements.txt

@@ -4,4 +4,5 @@ ccxt==4.4.27
 pandas==2.2.2
 pyarrow==16.1.0
 orjson==3.10.3
+technical==1.5.0
 

web/app.py

@@ -1,6 +1,10 @@
 from flask import Flask, render_template, jsonify, request
+from collections import OrderedDict
+import json
+import logging
 import ccxt
 import pandas as pd
+import requests
 from datetime import datetime, timedelta
 import sys
 import os
@@ -41,31 +45,170 @@ exchange = ccxt.binance({
 # 初始化A股数据获取器
 china_stock = ChinaStockData()
 
-# 时间周期映射
-TIMEFRAMES = {
-    '1m': '1分钟',
-    '3m': '3分钟',
-    '5m': '5分钟',
-    '15m': '15分钟',
-    '30m': '30分钟',
-    '1h': '1小时',
-    '2h': '2小时',
-    '4h': '4小时',
-    '6h': '6小时',
-    '8h': '8小时',
-    '12h': '12小时',
-    '1d': '日线',
-    '3d': '3日线',
-    '1w': '周线',
-    '1M': '月线',
-}
+logger = logging.getLogger(__name__)
 
-# 常见交易对
-SYMBOLS = [
+DATA_SERVICE_URL = os.environ.get("DATA_SERVICE_URL", os.environ.get("DATASVC_URL", "http://127.0.0.1:9000"))
+
+DEFAULT_TIMEFRAME_LABELS = OrderedDict([
+    ("1m", "1分钟"),
+    ("3m", "3分钟"),
+    ("5m", "5分钟"),
+    ("15m", "15分钟"),
+    ("30m", "30分钟"),
+    ("1h", "1小时"),
+    ("2h", "2小时"),
+    ("4h", "4小时"),
+    ("6h", "6小时"),
+    ("8h", "8小时"),
+    ("12h", "12小时"),
+    ("1d", "日线"),
+    ("3d", "3日线"),
+    ("1w", "周线"),
+    ("1M", "月线"),
+])
+
+DEFAULT_SYMBOLS = [
     'SOL/USDT:USDT', 'BTC/USDT:USDT', 'ETH/USDT:USDT', 'BNB/USDT:USDT', 'XRP/USDT:USDT',
     'ADA/USDT:USDT', 'DOGE/USDT:USDT', 'AVAX/USDT:USDT', 'DOT/USDT:USDT', 'MATIC/USDT:USDT'
 ]
 
+TIMEFRAMES = DEFAULT_TIMEFRAME_LABELS.copy()
+SYMBOLS = DEFAULT_SYMBOLS.copy()
+DATA_SERVICE_AVAILABLE = False
+SERVICE_METADATA_LAST_REFRESH = 0
+
+
+def timeframe_to_minutes(tf: str):
+    """将时间周期转换为分钟数，用于排序。"""
+    if not tf:
+        return None
+    unit = tf[-1]
+    try:
+        value = int(tf[:-1])
+    except (ValueError, TypeError):
+        return None
+    multiplier = {
+        'm': 1,
+        'h': 60,
+        'd': 1440,
+        'w': 10080,
+        'M': 43200,  # 30天近似
+    }.get(unit)
+    if multiplier is None:
+        return None
+    return value * multiplier
+
+
+def format_timeframe_label(tf: str) -> str:
+    """将时间周期转换为可读标签。"""
+    if not tf:
+        return tf
+    unit = tf[-1]
+    try:
+        value = int(tf[:-1])
+    except (ValueError, TypeError):
+        return tf
+    if unit == 'm':
+        return f"{value}分钟"
+    if unit == 'h':
+        return f"{value}小时"
+    if unit == 'd':
+        return "日线" if value == 1 else f"{value}日线"
+    if unit == 'w':
+        return "周线" if value == 1 else f"{value}周线"
+    if unit == 'M':
+        return "月线" if value == 1 else f"{value}月线"
+    return tf
+
+
+def build_timeframe_labels(timeframes):
+    ordered = sorted(
+        timeframes,
+        key=lambda tf: timeframe_to_minutes(tf) if timeframe_to_minutes(tf) is not None else float('inf'),
+    )
+    labels = OrderedDict()
+    for tf in ordered:
+        labels[tf] = format_timeframe_label(tf)
+    return labels
+
+
+def _parse_time_input(value):
+    if value in (None, '', 0):
+        return None
+    try:
+        return int(float(value))
+    except (ValueError, TypeError):
+        return None
+
+
+def refresh_data_service_metadata(force=False):
+    """刷新数据服务提供的交易对与周期元信息。"""
+    global DATA_SERVICE_AVAILABLE, TIMEFRAMES, SYMBOLS, SERVICE_METADATA_LAST_REFRESH
+    now = time.time()
+    if not force and DATA_SERVICE_AVAILABLE and now - SERVICE_METADATA_LAST_REFRESH < 60:
+        return True
+    try:
+        resp = requests.get(f"{DATA_SERVICE_URL}/health", timeout=5)
+        resp.raise_for_status()
+        payload = resp.json()
+        service_symbols = payload.get("symbols") or payload.get("symbol_list") or []
+        base_timeframes = payload.get("timeframes") or payload.get("base_timeframes") or []
+        derived = payload.get("derived_timeframes") or []
+        service_timeframes = list(base_timeframes)
+        for tf in derived:
+            if tf not in service_timeframes:
+                service_timeframes.append(tf)
+        if service_symbols:
+            SYMBOLS[:] = service_symbols
+        if service_timeframes:
+            TIMEFRAMES.clear()
+            TIMEFRAMES.update(build_timeframe_labels(service_timeframes))
+        DATA_SERVICE_AVAILABLE = True
+        SERVICE_METADATA_LAST_REFRESH = now
+        return True
+    except Exception as exc:
+        logger.warning("无法加载数据服务元信息: %s", exc)
+        if not DATA_SERVICE_AVAILABLE:
+            TIMEFRAMES.clear()
+            TIMEFRAMES.update(DEFAULT_TIMEFRAME_LABELS)
+            SYMBOLS[:] = DEFAULT_SYMBOLS
+        DATA_SERVICE_AVAILABLE = False
+        return False
+
+
+def _fetch_kl_from_datasvc(symbol, timeframe, start_ms=None, end_ms=None, limit=None):
+    params = {"symbol": symbol, "tf": timeframe}
+    if start_ms is not None:
+        params["start"] = int(start_ms)
+    if end_ms is not None:
+        params["end"] = int(end_ms)
+    resp = requests.get(f"{DATA_SERVICE_URL}/api/candles", params=params, timeout=10)
+    resp.raise_for_status()
+    data = resp.json()
+    if not data:
+        return None
+    df = pd.DataFrame(data)
+    if df.empty or "timestamp" not in df.columns:
+        return None
+    numeric_cols = ["open", "high", "low", "close", "volume"]
+    df["timestamp"] = pd.to_numeric(df["timestamp"], errors="coerce")
+    df = df.dropna(subset=["timestamp"])
+    df["timestamp"] = df["timestamp"].astype("int64")
+    for col in numeric_cols:
+        if col in df.columns:
+            df[col] = pd.to_numeric(df[col], errors="coerce")
+    df = df.dropna(subset=numeric_cols)
+    df = df.sort_values("timestamp")
+    if limit and len(df) > limit:
+        df = df.tail(limit)
+    df = df.reset_index(drop=True)
+    df["date"] = pd.to_datetime(df["timestamp"], unit='ms', utc=True).dt.tz_convert('Asia/Shanghai')
+    return df
+
+
+# 模块加载时尝试预取一次元信息，但失败不阻塞后续流程
+refresh_data_service_metadata(force=True)
+
 # A股热门股票
 A_STOCK_SYMBOLS = china_stock.get_popular_stocks()
 
@@ -89,7 +232,7 @@ def get_kl_data(symbol, timeframe, limit=1000, start_time=None, end_time=None):
     else:
         return None
 
-def get_crypto_kl_data(symbol, timeframe, limit=1000, start_time=None, end_time=None):
+def _get_crypto_kl_data_via_ccxt(symbol, timeframe, limit=1000, start_time=None, end_time=None):
     """获取加密货币K线数据，支持分页加载确保获取指定时间范围内的所有数据"""
     try:
         # 初始化参数
@@ -202,6 +345,30 @@ def get_crypto_kl_data(symbol, timeframe, limit=1000, start_time=None, end_time=
     except Exception as e:
         return None
 
+
+def get_crypto_kl_data(symbol, timeframe, limit=1000, start_time=None, end_time=None):
+    """优先通过本地数据服务获取加密货币K线，失败时回退至交易所API。"""
+    start_ms = _parse_time_input(start_time)
+    end_ms = _parse_time_input(end_time)
+
+    refresh_data_service_metadata()
+    if DATA_SERVICE_AVAILABLE:
+        try:
+            df = _fetch_kl_from_datasvc(
+                symbol=symbol,
+                timeframe=timeframe,
+                start_ms=start_ms,
+                end_ms=end_ms,
+                limit=limit,
+            )
+            if df is not None and not df.empty:
+                return df
+        except Exception as exc:
+            logger.warning("数据服务请求失败，准备回退至交易所 API：%s", exc)
+
+    return _get_crypto_kl_data_via_ccxt(symbol, timeframe, limit, start_time, end_time)
+
+
 def get_a_stock_kl_data(symbol, timeframe, limit=1000, start_time=None, end_time=None):
     """获取A股K线数据"""
     try:
@@ -733,66 +900,18 @@ def serialize_chan_macd_data(chan_macd_data, client_tz):
 
 def is_smaller_timeframe(tf1, tf2):
     """判断时间周期tf1是否小于tf2"""
-    # 定义时间周期的分钟数映射
-    tf_values = {
-        '1m': 1,
-        '3m': 3,
-        '5m': 5,
-        '15m': 15,
-        '30m': 30,
-        '1h': 60,
-        '2h': 120,
-        '4h': 240,
-        '6h': 360,
-        '8h': 480,
-        '12h': 720,
-        '1d': 1440,
-        '3d': 4320,
-        '1w': 10080,
-        '1M': 43200
-    }
-    
-    # 获取时间周期对应的分钟数
-    tf1_value = tf_values.get(tf1)
-    tf2_value = tf_values.get(tf2)
-    
-    # 如果某个时间周期不在映射中，返回False
+    tf1_value = timeframe_to_minutes(tf1)
+    tf2_value = timeframe_to_minutes(tf2)
     if tf1_value is None or tf2_value is None:
         return False
-    
-    # 返回tf1是否小于tf2
     return tf1_value < tf2_value
 
 def is_smaller_or_equal_timeframe(tf1, tf2):
     """判断时间周期tf1是否小于等于tf2"""
-    # 定义时间周期的分钟数映射
-    tf_values = {
-        '1m': 1,
-        '3m': 3,
-        '5m': 5,
-        '15m': 15,
-        '30m': 30,
-        '1h': 60,
-        '2h': 120,
-        '4h': 240,
-        '6h': 360,
-        '8h': 480,
-        '12h': 720,
-        '1d': 1440,
-        '3d': 4320,
-        '1w': 10080,
-        '1M': 43200
-    }
-    
-    # 获取时间周期对应的分钟数
-    tf1_value = tf_values.get(tf1)
-    tf2_value = tf_values.get(tf2)
-    
-    # 如果某个时间周期不在映射中，返回False
+    tf1_value = timeframe_to_minutes(tf1)
+    tf2_value = timeframe_to_minutes(tf2)
     if tf1_value is None or tf2_value is None:
         return False
-    
-    # 返回tf1是否小于等于tf2
     return tf1_value <= tf2_value
 
 def clean_dataframe_for_json(df):
@@ -900,12 +1019,15 @@ def classify_trend_stage(df):
 
 def load_crypto_symbols(limit=200):
     """加载常见USDT永续合约交易对，返回列表"""
+    refresh_data_service_metadata()
+    if SYMBOLS:
+        return SYMBOLS[:limit]
     try:
         markets = exchange.load_markets()
         symbols = [s for s in markets.keys() if '/USDT' in s and ':USDT' in s]
         return symbols[:limit]
     except Exception:
-        return SYMBOLS
+        return DEFAULT_SYMBOLS[:limit]
 
 
 @app.route('/api/trend_filter', methods=['GET'])
@@ -1030,10 +1152,38 @@ def trend_detail():
 @app.route('/')
 def index():
     """主页"""
-    return render_template('index.html', 
-                         timeframes=TIMEFRAMES, 
-                         symbols=SYMBOLS,
-                         a_stock_symbols=A_STOCK_SYMBOLS)
+    refresh_data_service_metadata()
+    timeframe_items = list(TIMEFRAMES.items())
+    timeframe_keys = [item[0] for item in timeframe_items]
+    symbols = SYMBOLS if SYMBOLS else DEFAULT_SYMBOLS
+
+    preferred_main = next((tf for tf in ['5m', '15m', '1h'] if tf in TIMEFRAMES), None)
+    default_main = preferred_main or (timeframe_keys[0] if timeframe_keys else '1m')
+    if default_main not in TIMEFRAMES and timeframe_keys:
+        default_main = timeframe_keys[0]
+
+    if timeframe_keys:
+        try:
+            idx = timeframe_keys.index(default_main)
+            default_element = timeframe_keys[idx - 1] if idx > 0 else timeframe_keys[0]
+        except ValueError:
+            default_element = timeframe_keys[0]
+    else:
+        default_element = default_main
+
+    default_symbol = 'BTC/USDT:USDT' if 'BTC/USDT:USDT' in symbols else (symbols[0] if symbols else '')
+
+    return render_template(
+        'index.html',
+        timeframes=TIMEFRAMES,
+        symbols=symbols,
+        a_stock_symbols=A_STOCK_SYMBOLS,
+        default_main_timeframe=default_main,
+        default_element_timeframe=default_element,
+        default_symbol=default_symbol,
+        timeframe_keys_json=json.dumps(timeframe_keys),
+        data_service_available=DATA_SERVICE_AVAILABLE,
+    )
 
 @app.route('/api/analyze')
 def analyze():
@@ -1417,13 +1567,16 @@ def analyze():
 @app.route('/api/symbols')
 def get_symbols():
     """获取可用交易对"""
+    refresh_data_service_metadata()
+    if SYMBOLS:
+        return jsonify(SYMBOLS)
     try:
         markets = exchange.load_markets()
         # 合约交易对通常是以USDT结尾的永续合约
         symbols = [symbol for symbol in markets.keys() if '/USDT' in symbol and ':USDT' in symbol]
         return jsonify(symbols)
     except Exception as e:
-        return jsonify({'error': str(e)})
+        return jsonify(DEFAULT_SYMBOLS)
 
 @app.route('/api/a_stocks')
 def get_a_stocks():

web/requirements.txt

@@ -2,6 +2,7 @@ flask>=2.0.1
 ccxt>=4.4.70
 pandas>=1.3.3
 numpy>=1.21.2
+requests>=2.31.0
 plotly>=5.3.1
 matplotlib>=3.4.3
 pytz>=2021.1

web/templates/index.html

@@ -16,6 +16,25 @@
     <script defer src="{{ url_for('static', filename='js/indicators.js') }}"></script>
     <script defer src="{{ url_for('static', filename='js/charts.js') }}"></script>
     <!-- TradingView Widget END -->
+    <script>
+        window.AVAILABLE_TIMEFRAMES = {{ timeframe_keys_json | safe }};
+        window.DEFAULT_MAIN_TIMEFRAME = "{{ default_main_timeframe }}";
+        window.DEFAULT_ELEMENT_TIMEFRAME = "{{ default_element_timeframe }}";
+        window.timeframeToMs = function(tf) {
+            if (!tf) return null;
+            var unit = tf.slice(-1);
+            var value = parseInt(tf.slice(0, -1), 10);
+            if (isNaN(value)) return null;
+            var unitMap = {
+                m: 60 * 1000,
+                h: 60 * 60 * 1000,
+                d: 24 * 60 * 60 * 1000,
+                w: 7 * 24 * 60 * 60 * 1000,
+                M: 30 * 24 * 60 * 60 * 1000
+            };
+            return unitMap[unit] ? value * unitMap[unit] : null;
+        };
+    </script>
     <style>
         body {
             font-family: "Helvetica Neue", Arial, "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", sans-serif;
@@ -765,7 +784,7 @@
                     <label for="symbol" class="form-label">交易对:</label>
                     <select id="symbol" class="form-select">
                         {% for symbol in symbols %}
-                        <option value="{{ symbol }}" {% if symbol == 'BTC/USDT:USDT' %}selected{% endif %}>{{ symbol }}</option>
+                        <option value="{{ symbol }}" {% if symbol == default_symbol %}selected{% endif %}>{{ symbol }}</option>
                         {% endfor %}
                     </select>
                 </div>
@@ -861,7 +880,7 @@
                         <div class="form-check form-check-inline">
                             <select id="timeframe" class="form-select form-select-sm me-2"  style="width: 100px;">
                                 {% for value, label in timeframes.items() %}
-                                <option value="{{ value }}" {% if value == '5m' %}selected{% endif %}>{{ label }}</option>
+                                <option value="{{ value }}" {% if value == default_main_timeframe %}selected{% endif %}>{{ label }}</option>
                                 {% endfor %}
                             </select>
                         </div>
@@ -899,7 +918,7 @@
                         <div class="form-check form-check-inline">
                             <select id="elementTimeframe" class="form-select form-select-sm me-2" style="width: 100px;">
                                 {% for value, label in timeframes.items() %}
-                                <option value="{{ value }}" {% if value == '1m' %}selected{% endif %}>{{ label }}</option>
+                                <option value="{{ value }}" {% if value == default_element_timeframe %}selected{% endif %}>{{ label }}</option>
                                 {% endfor %}
                             </select>
                         </div>
@@ -1144,11 +1163,7 @@
             // 周期变化时，自动填充当前时间回溯300根K线的时间范围
             $('#trendTimeframe').on('change', function(){
                 const tf = $(this).val();
-                const tfToMs = {
-                    '1m': 60*1000, '5m': 5*60*1000, '15m': 15*60*1000, '30m': 30*60*1000,
-                    '1h': 60*60*1000, '4h': 4*60*60*1000, '1d': 24*60*60*1000
-                };
-                const step = tfToMs[tf] || (60*60*1000);
+                const step = window.timeframeToMs(tf) || (60*60*1000);
                 const now = new Date();
                 const endMs = now.getTime();
                 const startMs = endMs - 300 * step;
@@ -1177,11 +1192,7 @@
 
             // 前端必须提供时间范围：若为空，自动以当前时间回溯300根
             if (!start || !end) {
-                const tfToMs = {
-                    '1m': 60*1000, '5m': 5*60*1000, '15m': 15*60*1000, '30m': 30*60*1000,
-                    '1h': 60*60*1000, '4h': 4*60*60*1000, '1d': 24*60*60*1000
-                };
-                const step = tfToMs[timeframe] || (60*60*1000);
+                const step = window.timeframeToMs(timeframe) || (60*60*1000);
                 const now = Date.now();
                 const startMsAuto = now - 300 * step;
                 const toLocal = (ms) => new Date(ms - new Date(ms).getTimezoneOffset()*60000).toISOString().slice(0,16);
@@ -1777,30 +1788,17 @@
         
         // 比较两个时间周期的大小
         function compareTimeframes(tf1, tf2) {
-            const tfValues = {
-                '1m': 1,
-                '3m': 3,
-                '5m': 5,
-                '15m': 15,
-                '30m': 30,
-                '1h': 60,
-                '2h': 120,
-                '4h': 240,
-                '6h': 360,
-                '8h': 480,
-                '12h': 720,
-                '1d': 1440,
-                '3d': 4320,
-                '1w': 10080,
-                '1M': 43200
-            };
-            
-            return tfValues[tf1] - tfValues[tf2];
+            const v1 = window.timeframeToMs(tf1);
+            const v2 = window.timeframeToMs(tf2);
+            if (v1 === null || v2 === null) {
+                return 0;
+            }
+            return v1 - v2;
         }
         
         // 设置比主周期小的最大周期
         function setSmallestLargerTimeframe(mainTimeframe) {
-            const timeframes = ['1m', '3m', '5m', '15m', '30m', '1h', '2h', '4h', '6h', '8h', '12h', '1d', '3d', '1w', '1M'];
+            const timeframes = window.AVAILABLE_TIMEFRAMES || [];
             const mainIndex = timeframes.indexOf(mainTimeframe);
             
             if (mainIndex > 0) {
@@ -1812,7 +1810,7 @@
         
         // 设置小于或等于主周期的时间周期
         function setSmallerOrEqualTimeframe(mainTimeframe) {
-            const timeframes = ['1m', '3m', '5m', '15m', '30m', '1h', '2h', '4h', '6h', '8h', '12h', '1d', '3d', '1w', '1M'];
+            const timeframes = window.AVAILABLE_TIMEFRAMES || [];
             const mainIndex = timeframes.indexOf(mainTimeframe);
             
             // 默认选择相同的时间周期
@@ -1973,9 +1971,9 @@
                 symbol = $('#astockSymbol').val() || '000001';
             }
             
-            const timeframe = $('#timeframe').val() || '5m';
+            const timeframe = $('#timeframe').val() || window.DEFAULT_MAIN_TIMEFRAME || '5m';
             const timezone = $('#timezone').val() || 'Asia/Shanghai';
-            const elementTimeframe = $('#elementTimeframe').val() || '1m';
+            const elementTimeframe = $('#elementTimeframe').val() || window.DEFAULT_ELEMENT_TIMEFRAME || '1m';
             
             // 确保时区参数有效
             console.log('更新图表使用时区:', timezone);
@@ -7166,8 +7164,14 @@
             // 初始化交易对下拉菜单
             $('#symbol').val('BTC/USDT:USDT');
             $('#astockSymbol').val('000001');
-            $('#timeframe').val('5m');
-            $('#elementTimeframe').val('1m');
+            const mainDefault = window.DEFAULT_MAIN_TIMEFRAME || $('#timeframe option:first').val();
+            const elementDefault = window.DEFAULT_ELEMENT_TIMEFRAME || $('#elementTimeframe option:first').val();
+            if (mainDefault) {
+                $('#timeframe').val(mainDefault);
+            }
+            if (elementDefault) {
+                $('#elementTimeframe').val(elementDefault);
+            }
             
             // 测试打印时区偏移量
             console.log('当前时区偏移量 (UTC+8):', getTimezoneOffset('Asia/Shanghai'));