kcg-monitoring/prediction/models/result.py
htlee a68dfb21b2 feat: Python 어선 분류기 + 배포 설정 + 백엔드 모니터링 프록시
- prediction/: FastAPI 7단계 분류 파이프라인 + 6개 탐지 알고리즘
  - snpdb 궤적 조회 → 인메모리 캐시(13K척) → 분류 → kcgdb 저장
  - APScheduler 5분 주기, Python 3.9 호환
  - 버그 수정: @property last_bucket, SQL INTERVAL 바인딩, rollback, None 가드
  - 보안: DB 비밀번호 하드코딩 제거 → env 환경변수 필수
- deploy/kcg-prediction.service: systemd 서비스 (redis-211, 포트 8001)
- deploy.yml: prediction CI/CD 배포 단계 추가 (192.168.1.18:32023)
- backend: PredictionProxyController (health/status/trigger 프록시)
- backend: AppProperties predictionBaseUrl + AuthFilter 인증 예외

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 12:10:21 +09:00

85 lines
2.0 KiB
Python

from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Optional
@dataclass
class AnalysisResult:
"""vessel_analysis_results 테이블 28컬럼 매핑."""
mmsi: str
timestamp: datetime
# 분류 결과
vessel_type: str = 'UNKNOWN'
confidence: float = 0.0
fishing_pct: float = 0.0
cluster_id: int = -1
season: str = 'UNKNOWN'
# ALGO 01: 위치
zone: str = 'EEZ_OR_BEYOND'
dist_to_baseline_nm: float = 999.0
# ALGO 02: 활동 상태
activity_state: str = 'UNKNOWN'
ucaf_score: float = 0.0
ucft_score: float = 0.0
# ALGO 03: 다크 베셀
is_dark: bool = False
gap_duration_min: int = 0
# ALGO 04: GPS 스푸핑
spoofing_score: float = 0.0
bd09_offset_m: float = 0.0
speed_jump_count: int = 0
# ALGO 05+06: 선단
cluster_size: int = 0
is_leader: bool = False
fleet_role: str = 'NOISE'
# ALGO 07: 위험도
risk_score: int = 0
risk_level: str = 'LOW'
# 특징 벡터
features: dict = field(default_factory=dict)
# 메타
analyzed_at: Optional[datetime] = None
def __post_init__(self):
if self.analyzed_at is None:
self.analyzed_at = datetime.now(timezone.utc)
def to_db_tuple(self) -> tuple:
import json
return (
self.mmsi,
self.timestamp,
self.vessel_type,
self.confidence,
self.fishing_pct,
self.cluster_id,
self.season,
self.zone,
self.dist_to_baseline_nm,
self.activity_state,
self.ucaf_score,
self.ucft_score,
self.is_dark,
self.gap_duration_min,
self.spoofing_score,
self.bd09_offset_m,
self.speed_jump_count,
self.cluster_size,
self.is_leader,
self.fleet_role,
self.risk_score,
self.risk_level,
json.dumps(self.features),
self.analyzed_at,
)