e1e3bba296
Some checks failed
E2E Health Check / e2e-health (push) Has been cancelled
P2.3: LearningService.get_learning_summary() 業務邏輯移至 Service 層 - Repository 只提供原始統計數據 - Service 計算 best_action 和 learning_status P2.6: Playbook similarity 計算邏輯抽取 - 新增 src/utils/similarity.py - Repository 從 utils 導入，不再定義演算法 2026-03-31 Claude Code (首席架構師技術債修復) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
88 lines
2.1 KiB
Python
88 lines
2.1 KiB
Python
"""
|
||
Similarity Calculation Utils
|
||
=============================
|
||
Phase 22 P2: 將相似度計算邏輯從 Repository 移出
|
||
|
||
設計原則:
|
||
- 演算法邏輯應獨立於資料存取層
|
||
- Repository 只負責 CRUD，不負責演算法
|
||
- Service 層可以使用這些工具函數
|
||
|
||
版本: v1.0
|
||
建立: 2026-03-31 (台北時區)
|
||
建立者: Claude Code (首席架構師技術債修復)
|
||
"""
|
||
|
||
from src.models.playbook import SymptomPattern
|
||
|
||
|
||
def calculate_jaccard_similarity(set_a: set, set_b: set) -> float:
|
||
"""
|
||
計算 Jaccard 相似度
|
||
|
||
Jaccard = |A ∩ B| / |A ∪ B|
|
||
|
||
Args:
|
||
set_a: 集合 A
|
||
set_b: 集合 B
|
||
|
||
Returns:
|
||
float: 0.0 ~ 1.0
|
||
"""
|
||
if not set_a and not set_b:
|
||
return 1.0 # 兩個空集合視為完全相同
|
||
if not set_a or not set_b:
|
||
return 0.0
|
||
|
||
intersection = len(set_a & set_b)
|
||
union = len(set_a | set_b)
|
||
return intersection / union if union > 0 else 0.0
|
||
|
||
|
||
def calculate_symptom_similarity(
|
||
pattern_a: SymptomPattern,
|
||
pattern_b: SymptomPattern,
|
||
) -> float:
|
||
"""
|
||
計算症狀相似度
|
||
|
||
算法: 加權 Jaccard 相似度
|
||
|
||
維度權重:
|
||
- alert_names: 0.35 (最重要)
|
||
- affected_services: 0.30
|
||
- severity: 0.15
|
||
- keywords: 0.20
|
||
|
||
Returns:
|
||
float: 0.0 ~ 1.0 相似度分數
|
||
"""
|
||
weights = {
|
||
"alert_names": 0.35,
|
||
"affected_services": 0.30,
|
||
"severity": 0.15,
|
||
"keywords": 0.20,
|
||
}
|
||
|
||
scores = {
|
||
"alert_names": calculate_jaccard_similarity(
|
||
set(pattern_a.alert_names),
|
||
set(pattern_b.alert_names),
|
||
),
|
||
"affected_services": calculate_jaccard_similarity(
|
||
set(pattern_a.affected_services),
|
||
set(pattern_b.affected_services),
|
||
),
|
||
"severity": (
|
||
1.0
|
||
if set(pattern_a.severity_range) & set(pattern_b.severity_range)
|
||
else 0.0
|
||
),
|
||
"keywords": calculate_jaccard_similarity(
|
||
set(pattern_a.keywords),
|
||
set(pattern_b.keywords),
|
||
),
|
||
}
|
||
|
||
return sum(weights[k] * scores[k] for k in weights)
|