feat: add visualize + e2e orchestrator + run_e2e.sh

2026-06-11 15:45:57 +08:00
parent 29e1c00287
commit dd53205921
3 changed files with 321 additions and 2 deletions
@@ -1,3 +1,119 @@
-"""E2E 编排器（占位 stub）"""
+"""E2E 编排器：inject → 6 算法 → FORECAST → 可视化 → JSON 日志。"""
+
+import json
+import logging
+import time
+from pathlib import Path
+from datetime import datetime
+
+from ts_anomaly_td.connector import TDConnection
+from ts_anomaly_td.schema import setup_schema
+from ts_anomaly_td.io_csv import read_csv
+from ts_anomaly_td.detection import detect_all_algos, ALL_ALGOS
+from ts_anomaly_td.forecast import forecast_anomaly
+from ts_anomaly_td.visualize import render_contrast
+
+logger = logging.getLogger(__name__)
+
+
 def run_e2e(args):
-    raise NotImplementedError("e2e 将在 Task 7 实现")
+    """执行 E2E 全流程。
+
+    Args:
+        args: argparse namespace（含 data_dir, output_dir, log_dir, url）
+    """
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s [%(levelname)s] %(message)s",
+    )
+
+    data_dir = Path(args.data_dir)
+    output_dir = Path(args.output_dir)
+    log_dir = Path(args.log_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    log_dir.mkdir(parents=True, exist_ok=True)
+
+    csv_files = sorted(data_dir.glob("*.csv"))
+    if not csv_files:
+        logger.error("no CSV files found in %s", data_dir)
+        return 1
+
+    conn = TDConnection(args.url)
+    summary = {"run_at": datetime.now().isoformat(), "datasets": {}, "exit_code": 0}
+    last_log_path = None
+
+    try:
+        for csv_path in csv_files:
+            stable = csv_path.stem
+            logger.info("=== E2E %s ===", stable)
+
+            ts, vals, labels = read_csv(str(csv_path))
+            rows = list(zip(ts, vals, labels))
+
+            t0 = time.monotonic()
+            setup_schema(conn, stable)
+            conn.batch_insert(stable, rows)
+            inject_time = time.monotonic() - t0
+            logger.info("inject: %d rows in %.1fs", len(rows), inject_time)
+
+            t0 = time.monotonic()
+            det_results = detect_all_algos(conn, stable)
+            detect_time = time.monotonic() - t0
+            for algo, r in det_results.items():
+                if r["error"]:
+                    logger.info("  %s: ERROR %s", algo, r["error"])
+                else:
+                    logger.info("  %s: %d windows", algo, len(r["windows"]))
+
+            t0 = time.monotonic()
+            try:
+                fc_points = forecast_anomaly(conn, stable)
+                fc_time = time.monotonic() - t0
+                fc_anom_count = sum(1 for p in fc_points if p["is_anomaly"])
+                logger.info("FORECAST: %d points, %d anomalies in %.1fs", len(fc_points), fc_anom_count, fc_time)
+            except Exception as e:
+                logger.warning("FORECAST failed (non-fatal): %s", e)
+                fc_points = []
+                fc_time = time.monotonic() - t0
+                fc_anom_count = 0
+
+            t0 = time.monotonic()
+            png_path = output_dir / f"{stable}_gt_vs_tdengine.png"
+            render_contrast(ts, vals, labels, det_results, str(png_path), title=stable)
+            viz_time = time.monotonic() - t0
+
+            ds_summary = {
+                "rows": len(rows),
+                "inject_time_s": round(inject_time, 1),
+                "detect_time_s": round(detect_time, 1),
+                "forecast_time_s": round(fc_time, 1),
+                "viz_time_s": round(viz_time, 1),
+                "algorithms": {},
+                "forecast": {
+                    "point_count": len(fc_points),
+                    "anomaly_count": fc_anom_count,
+                },
+                "png": str(png_path),
+            }
+            for algo, r in det_results.items():
+                ds_summary["algorithms"][algo] = {
+                    "window_count": len(r["windows"]),
+                    "error": r["error"],
+                }
+
+            summary["datasets"][stable] = ds_summary
+
+        last_log_path = log_dir / f"e2e_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
+        last_log_path.write_text(json.dumps(summary, indent=2, ensure_ascii=False))
+        logger.info("log saved: %s", last_log_path)
+
+    except Exception as e:
+        logger.exception("E2E failed: %s", e)
+        summary["exit_code"] = 1
+        summary["error"] = str(e)
+        last_log_path = log_dir / f"e2e_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
+        last_log_path.write_text(json.dumps(summary, indent=2, ensure_ascii=False))
+    finally:
+        conn.close()
+
+    return summary["exit_code"]