fix predict

README.md

@@ -4,6 +4,12 @@
 
 当前正式模型只有一个：[`artifacts/v1/model.joblib`](artifacts/v1/model.joblib)。它由最近 18 根 8H K 线预测未来 6 根 8H K 线的稳健低点收益，并输出点预测以及用于区间参考的 q20/q80 结果。根目录不放置历史实验模型；历史实验说明保留在 [`docs/v0_0823.md`](docs/v0_0823.md) 和 [`docs/v1_0823.md`](docs/v1_0823.md)。
 
+
+
+## TODO
+
+增加1D级别的模型训练和预测
+
 ## 快速开始
 
 运行环境需要 Python 3、Go、可访问的 banbot 源码和 banbot 配置中的 QuestDB。默认路径是：
@@ -75,18 +81,20 @@ predictions/latest_v1/report.json
 
 一键脚本生成的 CSV 固定只包含以下 10 列：
 
-| 列 | 含义 |
+
-| --- | --- |
+| 列                           | 含义                                    |
-| `rank` | 按 8H USDT 成交额从高到低的排名 |
+| --------------------------- | ------------------------------------- |
-| `symbol` | 合约符号 |
+| `rank`                      | 按 8H USDT 成交额从高到低的排名                  |
-| `latest_bar_start_utc` | 最新完整 8H K 线的 UTC 起始时间 |
+| `symbol`                    | 合约符号                                  |
-| `close` | 最新完整 8H K 线收盘价 |
+| `latest_bar_start_utc`      | 最新完整 8H K 线的 UTC 起始时间                 |
-| `quote_volume_usdt_8h` | 最新 8H 的 USDT 成交额 |
+| `close`                     | 最新完整 8H K 线收盘价                        |
-| `atr_rank_200_pct` | 当前 ATR 在过去 200 根 8H ATR 中的百分位，单位为 `%` |
+| `quote_volume_usdt_8h`      | 最新 8H 的 USDT 成交额                      |
-| `drawdown_point_pct` | 点预测对应的回撤百分比 |
+| `atr_rank_200_pct`          | 当前 ATR 在过去 200 根 8H ATR 中的百分位，单位为 `%` |
-| `drawdown_cap_80pct_pct` | q80 对应的回撤百分比上界参考 |
+| `drawdown_point_pct`        | 点预测对应的回撤百分比                           |
-| `price_level_reached_80pct` | q20 对应的价格水平参考 |
+| `drawdown_cap_80pct_pct`    | q80 对应的回撤百分比上界参考                      |
-| `price_level_cap_80pct` | q80 对应的价格水平参考 |
+| `price_level_reached_80pct` | q20 对应的价格水平参考                         |
+| `price_level_cap_80pct`     | q80 对应的价格水平参考                         |
+
 
 回撤列是收益的相反数：预测收益为负时表示价格可能低于当前收盘；预测收益为正时，回撤列可能为负，表示未来稳健低点仍高于当前收盘。模型不满足资格条件时，预测字段为空，不应把空值当作零回撤。
 
@@ -107,3 +115,4 @@ predictions/latest_v1/report.json
 - [`docs/usage.md`](docs/usage.md)：安装、数据流、命令、目录和故障排查。
 - [`docs/model.md`](docs/model.md)：目标定义、特征、训练协议、指标和限制。
 - [`docs/v0_0823.md`](docs/v0_0823.md)、[`docs/v1_0823.md`](docs/v1_0823.md)：历史实验记录，不是当前运行入口。
+

cbpred/latest_predict.py

@@ -10,6 +10,7 @@ from datetime import datetime, timezone
 from pathlib import Path
 from urllib.parse import urlparse
 
+import joblib
 import pandas as pd
 
 from .pipeline import load_database_url, parse_time_ms, predict_from_csv, prepare_data
@@ -84,9 +85,28 @@ def ensure_database(
 
 def build_predictions(data_dir: Path, artifact: Path, output_dir: Path) -> dict[str, object]:
     manifest = json.loads((data_dir / "manifest.json").read_text())
+    artifact_data = joblib.load(artifact)
+    trained_symbols = set(artifact_data.get("asset_profiles", {}))
+    if trained_symbols:
+        skipped_symbols = [
+            item["symbol"]
+            for item in manifest["symbols"]
+            if item["symbol"] not in trained_symbols
+        ]
+        prediction_items = [
+            item for item in manifest["symbols"] if item["symbol"] in trained_symbols
+        ]
+    else:
+        skipped_symbols = []
+        prediction_items = manifest["symbols"]
+    if skipped_symbols:
+        print(
+            f"[latest-predict] skipped {len(skipped_symbols)} symbols without stored training profiles",
+            flush=True,
+        )
     rows: list[dict[str, object]] = []
-    total = len(manifest["symbols"])
+    total = len(prediction_items)
-    for index, item in enumerate(manifest["symbols"], 1):
+    for index, item in enumerate(prediction_items, 1):
         csv_path = data_dir / item["path"]
         frame = pd.read_csv(csv_path).sort_values("timestamp").drop_duplicates("timestamp")
         latest = frame.iloc[-1]
@@ -128,6 +148,7 @@ def build_predictions(data_dir: Path, artifact: Path, output_dir: Path) -> dict[
     summary = {
         "model": str(artifact.resolve()),
         "symbols": len(rows),
+        "skipped_symbols": skipped_symbols,
         "eligible_predictions": sum(row["drawdown_point_pct"] is not None for row in rows),
         "latest_bar_start_utc": rows[0]["latest_bar_start_utc"] if rows else None,
         "csv": str(output_csv.resolve()),

tests/test_latest_predict.py

@@ -1,6 +1,12 @@
+import json
+import tempfile
 import unittest
+from pathlib import Path
+from unittest.mock import patch
 
-from cbpred.latest_predict import OUTPUT_COLUMNS
+import pandas as pd
+
+from cbpred.latest_predict import OUTPUT_COLUMNS, build_predictions
 
 
 class LatestPredictTests(unittest.TestCase):
@@ -21,6 +27,51 @@ class LatestPredictTests(unittest.TestCase):
             ),
         )
 
+    def test_batch_skips_symbols_without_training_profiles(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            data_dir = root / "data"
+            output_dir = root / "output"
+            data_dir.mkdir()
+            for symbol, filename in (
+                ("TRAIN/USDT:USDT", "train.csv"),
+                ("STALE/USDT:USDT", "stale.csv"),
+            ):
+                pd.DataFrame(
+                    [{"timestamp": 1, "quote": 10.0, "close": 100.0}]
+                ).to_csv(data_dir / filename, index=False)
+            (data_dir / "manifest.json").write_text(
+                json.dumps(
+                    {
+                        "symbols": [
+                            {"symbol": "TRAIN/USDT:USDT", "path": "train.csv"},
+                            {"symbol": "STALE/USDT:USDT", "path": "stale.csv"},
+                        ]
+                    }
+                )
+            )
+
+            result = {
+                "symbol": "TRAIN/USDT:USDT",
+                "timestamp": 1,
+                "close": 100.0,
+                "volatility_rank_200": 0.5,
+                "eligible_for_model": False,
+            }
+            with patch(
+                "cbpred.latest_predict.joblib.load",
+                return_value={"asset_profiles": {"TRAIN/USDT:USDT": {}}},
+            ), patch(
+                "cbpred.latest_predict.predict_from_csv", return_value=result
+            ) as predict:
+                summary = build_predictions(data_dir, root / "model.joblib", output_dir)
+
+            predict.assert_called_once_with(
+                root / "model.joblib", data_dir / "train.csv", symbol="TRAIN/USDT:USDT"
+            )
+            self.assertEqual(summary["symbols"], 1)
+            self.assertEqual(summary["skipped_symbols"], ["STALE/USDT:USDT"])
+
 
 if __name__ == "__main__":
     unittest.main()