code_public/ja4-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(bot-detector): make scoring functions public (remove underscore prefix)

Browse Source 
compute_shap_top_features, build_reason, cluster_anomalies renamed from
private (_prefixed) to public to match pipeline.py imports.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
toto
2026-04-09 22:49:48 +02:00
parent 629f7b334d
commit 00e99e5464
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
services/bot-detector/bot_detector/scoring.py
View File

@ -186,7 +186,7 @@ def normalize_scores(scores: np.ndarray) -> np.ndarray:
# A4 — EXPLAINABILITÉ SHAP # A4 — EXPLAINABILITÉ SHAP
# ═══════════════════════════════════════════════════════════════════════════════ # ═══════════════════════════════════════════════════════════════════════════════
def _compute_shap_top_features(model, X: pd.DataFrame, features: list, def compute_shap_top_features(model, X: pd.DataFrame, features: list,
n_top: int = 5) -> list: n_top: int = 5) -> list:
""" """
Calcule les valeurs SHAP pour chaque ligne de X et retourne les n_top features Calcule les valeurs SHAP pour chaque ligne de X et retourne les n_top features
@ -216,7 +216,7 @@ def _compute_shap_top_features(model, X: pd.DataFrame, features: list,
return [{}] * len(X) return [{}] * len(X)
def _build_reason(name: str, row: pd.Series, shap_top: dict) -> str: def build_reason(name: str, row: pd.Series, shap_top: dict) -> str:
"""Construit le champ reason enrichi avec le top SHAP ou les métriques clés.""" """Construit le champ reason enrichi avec le top SHAP ou les métriques clés."""
# Utilise le score brut pour l'affichage (plus interprétable que le score normalisé) # Utilise le score brut pour l'affichage (plus interprétable que le score normalisé)
score = round(float(row.get('raw_anomaly_score', row.get('anomaly_score', 0))), 3) score = round(float(row.get('raw_anomaly_score', row.get('anomaly_score', 0))), 3)
@ -233,7 +233,7 @@ def _build_reason(name: str, row: pd.Series, shap_top: dict) -> str:
# A8 — CLUSTERING COMPORTEMENTAL DES ANOMALIES # A8 — CLUSTERING COMPORTEMENTAL DES ANOMALIES
# ═══════════════════════════════════════════════════════════════════════════════ # ═══════════════════════════════════════════════════════════════════════════════
def _cluster_anomalies(anomalies: pd.DataFrame, features: list, def cluster_anomalies(anomalies: pd.DataFrame, features: list,
ae_model=None) -> pd.DataFrame: ae_model=None) -> pd.DataFrame:
"""A8 : Applique HDBSCAN (ou DBSCAN en fallback) sur les features normalisées des anomalies. """A8 : Applique HDBSCAN (ou DBSCAN en fallback) sur les features normalisées des anomalies.