update

2026-08-29 11:00:27 +08:00
parent c0df80154b
commit 9e1b5e251a
11 changed files with 55 additions and 33 deletions
--- a/README.md
+++ b/README.md
@@ -11,8 +11,8 @@
 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：

 ```text
-/home/ctyun/ban/banbot
-/home/ctyun/ban/banbot/biz/config.yml
+/data/ban/banbot
+/data/ban/banbot/biz/config.yml
 ```

 安装项目及依赖：
@@ -31,8 +31,8 @@ python3 -m venv .venv
 结果默认写入：

 ```text
-predictions/latest_v1/predictions.csv
-predictions/latest_v1/report.json
+predictions/latest_v1_8h/predictions.csv
+predictions/latest_v1_8h/report.json
 ```

 查看脚本参数：
@@ -54,7 +54,7 @@ predictions/latest_v1/report.json
 ```bash
 # 下载 1H K 线，导出并整理为 8H CSV
 .venv/bin/python -m cbpred prepare \
-  --banbot-config /home/ctyun/ban/banbot/biz/config.yml \
+  --banbot-config /data/ban/banbot/biz/config.yml \
  --out-dir data

 # 使用 data/ 训练并覆盖 artifacts/v1 下的正式模型和报告
@@ -85,7 +85,7 @@ predictions/latest_v1/report.json
 .venv/bin/python -m cbpred prepare \
  --timeframe 1d \
  --out-dir data_1d \
-  --banbot-config /home/ctyun/ban/banbot/biz/config.yml
+  --banbot-config /data/ban/banbot/biz/config.yml
 .venv/bin/python -m cbpred.experiments \
  --data-dir data_1d \
  --output-dir artifacts_1d \
--- a/cbpred/main.py
+++ b/cbpred/main.py
@@ -19,8 +19,8 @@ def build_parser() -> argparse.ArgumentParser:

    prepare = sub.add_parser("prepare", help="filter symbols, call banbot, export complete timeframe CSVs")
    prepare.add_argument("--out-dir", type=Path, default=Path("data"))
-    prepare.add_argument("--banbot-dir", type=Path, default=Path("/home/ctyun/ban/banbot"))
-    prepare.add_argument("--banbot-config", type=Path, default=Path("/home/ctyun/ban/banbot/biz/config.yml"))
+    prepare.add_argument("--banbot-dir", type=Path, default=Path("/data/ban/banbot"))
+    prepare.add_argument("--banbot-config", type=Path, default=Path("/data/ban/banbot/biz/config.yml"))
    prepare.add_argument("--dsn", default=None)
    prepare.add_argument("--db-type", choices=["auto", "questdb", "timescale"], default="auto")
    prepare.add_argument("--exchange", default="binance")
--- a/cbpred/latest_predict.py
+++ b/cbpred/latest_predict.py
@@ -48,6 +48,11 @@ def output_columns_for_timeframe(timeframe: str) -> tuple[str, ...]:
    return (*OUTPUT_COLUMNS[:4], volume_column, *OUTPUT_COLUMNS[5:])


+def default_output_dir(timeframe: str) -> Path:
+    timeframe_step_ms(timeframe)
+    return REPO_ROOT / f"predictions/latest_v1_{timeframe}"
+
+
 def ensure_database(
    banbot_config: Path,
    dsn: str | None,
@@ -169,15 +174,20 @@ def build_predictions(data_dir: Path, artifact: Path, output_dir: Path) -> dict[

 def build_parser() -> argparse.ArgumentParser:
    parser = argparse.ArgumentParser(description="Update banbot K-lines and predict with the current model")
-    parser.add_argument("--banbot-dir", type=Path, default=Path("/home/ctyun/ban/banbot"))
+    parser.add_argument("--banbot-dir", type=Path, default=Path("/data/ban/banbot"))
    parser.add_argument(
        "--banbot-config",
        type=Path,
-        default=Path("/home/ctyun/ban/banbot/biz/config.yml"),
+        default=Path("/data/ban/banbot/biz/config.yml"),
    )
    parser.add_argument("--data-dir", type=Path, default=REPO_ROOT / "data")
    parser.add_argument("--artifact", type=Path, default=REPO_ROOT / "artifacts/v1/model.joblib")
-    parser.add_argument("--output-dir", type=Path, default=REPO_ROOT / "predictions/latest_v1")
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        default=None,
+        help="prediction output directory (default: predictions/latest_v1_<timeframe>)",
+    )
    parser.add_argument("--history-months", type=int, default=36)
    parser.add_argument("--holdout-months", type=int, default=10)
    parser.add_argument("--min-age-days", type=int, default=730)
@@ -194,7 +204,9 @@ def main() -> None:
    args = build_parser().parse_args()
    data_dir = args.data_dir.resolve()
    artifact = args.artifact.resolve()
-    output_dir = args.output_dir.resolve()
+    output_dir = (
+        args.output_dir if args.output_dir is not None else default_output_dir(args.timeframe)
+    ).resolve()
    ensure_database(args.banbot_config, args.dsn)
    manifest = prepare_data(
        out_dir=data_dir,
--- a/cbpred/prediction_service.py
+++ b/cbpred/prediction_service.py
@@ -143,7 +143,7 @@ def run_prediction(config: dict[str, Any], end_ms: int) -> tuple[dict[str, Any],
    print(f"[prediction-service] running completed candle ending {_utc_label(end_ms)}", flush=True)
    subprocess.run(command, cwd=working_dir, check=True)
    output_dir = _config_path(
-        config, config["prediction"].get("output_dir", "predictions/latest_v1")
+        config, config["prediction"].get("output_dir", "predictions/latest_v1_8h")
    ).resolve()
    report_path = output_dir / "report.json"
    if not report_path.exists():
--- a/config/prediction-service.user.yml.example
+++ b/config/prediction-service.user.yml.example
@@ -7,11 +7,11 @@ scheduler:

 prediction:
  working_dir: /data/quant/cbpred
-  banbot_dir: /home/ctyun/ban/banbot
-  banbot_config: /home/ctyun/ban/banbot/biz/config.yml
+  banbot_dir: /data/ban/banbot
+  banbot_config: /data/ban/banbot/biz/config.yml
  data_dir: /data/quant/cbpred/data
  artifact: /data/quant/cbpred/artifacts/v1/model.joblib
-  output_dir: /data/quant/cbpred/predictions/latest_v1
+  output_dir: /data/quant/cbpred/predictions/latest_v1_8h
  history_months: 36
  holdout_months: 10
  min_age_days: 730
--- a/config/prediction-service.yml.example
+++ b/config/prediction-service.yml.example
@@ -9,11 +9,11 @@ scheduler:

 prediction:
  working_dir: /data/quant/cbpred
-  banbot_dir: /home/ctyun/ban/banbot
-  banbot_config: /home/ctyun/ban/banbot/biz/config.yml
+  banbot_dir: /data/ban/banbot
+  banbot_config: /data/ban/banbot/biz/config.yml
  data_dir: /data/quant/cbpred/data
  artifact: /data/quant/cbpred/artifacts/v1/model.joblib
-  output_dir: /data/quant/cbpred/predictions/latest_v1
+  output_dir: /data/quant/cbpred/predictions/latest_v1_8h
  history_months: 36
  holdout_months: 10
  min_age_days: 730
--- a/docs/abstract.md
+++ b/docs/abstract.md
@@ -26,7 +26,7 @@

 测试数据按品种随机划分为两部分，一部分作为验证集，一部分作为测试集。

-我们的K线数据是通过 /home/ctyun/ban/banbot 项目下载维护到postgresql中的
+我们的K线数据是通过 /data/ban/banbot 项目下载维护到postgresql中的

 应该只关注U本位合约中的USDT的品种，且上市至少2年；

--- a/docs/usage.md
+++ b/docs/usage.md
@@ -8,10 +8,10 @@

 - Python 3 和本项目的虚拟环境；
 - `pandas`、`numpy`、`scikit-learn`、`joblib` 等项目依赖；
- Go 和 `/home/ctyun/ban/banbot` 源码；
+- Go 和 `/data/ban/banbot` 源码；
 - banbot 配置中的 QuestDB 数据库，以及对 Binance 数据的访问。

-默认配置文件是 `/home/ctyun/ban/banbot/biz/config.yml`。如果路径不同，可通过 `--banbot-config` 和 `--banbot-dir` 覆盖。也可以直接传入 `--dsn`。
+默认配置文件是 `/data/ban/banbot/biz/config.yml`。如果路径不同，可通过 `--banbot-config` 和 `--banbot-dir` 覆盖。也可以直接传入 `--dsn`。

 安装：

@@ -34,7 +34,7 @@ python3 -m venv .venv
 4. 调用 banbot 导出请求周期的完整 K 线；默认是 8H，也可以通过 `--timeframe 1d` 导出日线。
 5. 写入 `data/manifest.json` 和 `data/raw/*.csv`。
 6. 加载 `artifacts/v1/model.joblib`，对清单中的每个品种使用最新完整 8H K 线预测。
-7. 按最新 8H USDT 成交额降序写入 `predictions/latest_v1/predictions.csv`，并写入 `report.json`。
+7. 按最新 8H USDT 成交额降序写入 `predictions/latest_v1_8h/predictions.csv`，并写入 `report.json`。

 脚本的默认参数可以覆盖：

@@ -44,7 +44,7 @@ python3 -m venv .venv
  --banbot-config /path/to/config.yml \
  --data-dir data \
  --artifact artifacts/v1/model.joblib \
-  --output-dir predictions/latest_v1 \
+  --output-dir predictions/latest_v1_8h \
  --end 2026-08-23T00:00:00Z
 ```

@@ -56,7 +56,7 @@ python3 -m venv .venv

 ```bash
 .venv/bin/python -m cbpred prepare \
-  --banbot-config /home/ctyun/ban/banbot/biz/config.yml \
+  --banbot-config /data/ban/banbot/biz/config.yml \
  --out-dir data
 ```

@@ -64,7 +64,7 @@ python3 -m venv .venv

 ```bash
 .venv/bin/python -m cbpred prepare \
-  --banbot-config /home/ctyun/ban/banbot/biz/config.yml \
+  --banbot-config /data/ban/banbot/biz/config.yml \
  --out-dir data \
  --skip-download
 ```
@@ -77,7 +77,7 @@ python3 -m venv .venv
 .venv/bin/python -m cbpred prepare \
  --timeframe 1d \
  --out-dir data_1d \
-  --banbot-config /home/ctyun/ban/banbot/biz/config.yml
+  --banbot-config /data/ban/banbot/biz/config.yml
 ```

 ### 训练模型
@@ -121,7 +121,7 @@ cbpred/
 ├── artifacts/
 │   └── v1/                         # 唯一正式模型版本
 └── predictions/
-    └── latest_v1/                  # 最近一次批量预测
+    └── latest_v1_8h/               # 最近一次 8H 批量预测
 ```

 模型版本目录使用 `v1` 形式维护。历史实验可以保留在文档或实验输出目录中，但不应作为默认预测模型或在项目根目录新增多个 `artifacts_*` 入口。
--- a/go.mod
+++ b/go.mod
@@ -6,7 +6,7 @@ require github.com/banbox/banbot v0.0.0

 require (
 	github.com/bahlo/generic-list-go v0.2.0 // indirect
-	github.com/banbox/banexg v0.2.60 // indirect
+	github.com/banbox/banexg v0.2.63 // indirect
 	github.com/banbox/banta v0.3.7 // indirect
 	github.com/banbox/bntp v0.1.0 // indirect
 	github.com/banbox/cron/v3 v3.1.2 // indirect
@@ -109,4 +109,4 @@ require (
 	modernc.org/sqlite v1.39.1 // indirect
 )

-replace github.com/banbox/banbot => /home/ctyun/ban/banbot
+replace github.com/banbox/banbot => /data/ban/banbot
--- a/go.sum
+++ b/go.sum
@@ -1,8 +1,8 @@
 github.com/airbrake/gobrake v3.6.1+incompatible/go.mod h1:wM4gu3Cn0W0K7GUuVWnlXZU11AGBXMILnrdOU8Kn00o=
 github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=
 github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=
-github.com/banbox/banexg v0.2.60 h1:0IQaSATKwf6SNLnehGmjdAidnYJsRqhJqruUfh9U8LM=
-github.com/banbox/banexg v0.2.60/go.mod h1:T9JWRGblxAibQjwKK6VABG+r87y1LRnyYe7sz5aBnR4=
+github.com/banbox/banexg v0.2.63 h1:G93/8s+/uddzie+ckMQ0T+AQq+9ULoCs1tp9CsBl4KM=
+github.com/banbox/banexg v0.2.63/go.mod h1:T9JWRGblxAibQjwKK6VABG+r87y1LRnyYe7sz5aBnR4=
 github.com/banbox/banta v0.3.7 h1:R1xVVtds0Temlc1fATX08uG7rR0pbukr3L6FikyKscE=
 github.com/banbox/banta v0.3.7/go.mod h1:43XoXngLPip/pX1OvohnNUScScqb1/jtKxVqgltwZUU=
 github.com/banbox/bntp v0.1.0 h1:kZROpbb3OME8XM8QeM+2SeQWQrHRDFN05okr8OITKAU=
--- a/tests/test_latest_predict.py
+++ b/tests/test_latest_predict.py
@@ -6,7 +6,13 @@ from unittest.mock import patch

 import pandas as pd

-from cbpred.latest_predict import OUTPUT_COLUMNS, build_predictions, output_columns_for_timeframe
+from cbpred.latest_predict import (
+    OUTPUT_COLUMNS,
+    REPO_ROOT,
+    build_predictions,
+    default_output_dir,
+    output_columns_for_timeframe,
+)


 class LatestPredictTests(unittest.TestCase):
@@ -30,6 +36,10 @@ class LatestPredictTests(unittest.TestCase):
    def test_output_columns_follow_timeframe(self):
        self.assertEqual(output_columns_for_timeframe("1d")[4], "quote_volume_usdt_1d")

+    def test_default_output_dir_follows_timeframe(self):
+        self.assertEqual(default_output_dir("8h"), REPO_ROOT / "predictions/latest_v1_8h")
+        self.assertEqual(default_output_dir("1d"), REPO_ROOT / "predictions/latest_v1_1d")
+
    def test_batch_skips_symbols_without_training_profiles(self):
        with tempfile.TemporaryDirectory() as directory:
            root = Path(directory)