checkpoint: working 10-artist batch with log-normalized ranking

core/confidence_scorer.py

@@ -0,0 +1,77 @@
+from typing import Dict, Any
+
+class ConfidenceScorer:
+    """
+    Computes a weighted authenticity and quality score across multiple data sources:
+    - YouTube footprint: 40%
+    - MusicBrainz catalog: 35%
+    - Wikidata entity: 25%
+    """
+    def __init__(self, yt_weight: float = 0.40, mb_weight: float = 0.35, wd_weight: float = 0.25):
+        self.w_yt = yt_weight
+        self.w_mb = mb_weight
+        self.w_wd = wd_weight
+
+    def calculate_score(
+        self,
+        yt_metrics: Dict[str, Any],
+        mb_result: Dict[str, Any],
+        wd_result: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        # 1. YouTube sub-score (0.0 to 1.0)
+        yt_score = 0.0
+        if yt_metrics.get("status") in ["live_api", "cached"]:
+            subs = yt_metrics.get("subscribers", 0)
+            views = yt_metrics.get("lifetime_views", 0)
+            vids = yt_metrics.get("video_count", 0)
+
+            # Baseline 0.5 for a verified channel existence
+            yt_score = 0.5
+            if subs >= 1000:
+                yt_score += 0.2
+            elif subs > 0:
+                yt_score += 0.1
+
+            if views >= 50000:
+                yt_score += 0.2
+            elif views > 0:
+                yt_score += 0.1
+
+            if vids >= 5:
+                yt_score += 0.1
+
+        # 2. MusicBrainz sub-score
+        mb_score = mb_result.get("confidence", 0.0) if mb_result.get("verified") else 0.0
+
+        # 3. Wikidata sub-score
+        wd_score = wd_result.get("confidence", 0.0) if wd_result.get("verified") else 0.0
+
+        # Aggregated composite score
+        composite = (yt_score * self.w_yt) + (mb_score * self.w_mb) + (wd_score * self.w_wd)
+        composite = round(min(1.0, max(0.0, composite)), 2)
+
+        # Confidence category
+        if composite >= 0.75:
+            tier = "High"
+        elif composite >= 0.45:
+            tier = "Medium"
+        else:
+            tier = "Low / Emerging"
+
+        return {
+            "composite_confidence": composite,
+            "confidence_tier": tier,
+            "sub_scores": {
+                "youtube": round(yt_score, 2),
+                "musicbrainz": round(mb_score, 2),
+                "wikidata": round(wd_score, 2)
+            }
+        }
+
+if __name__ == "__main__":
+    scorer = ConfidenceScorer()
+    dummy_yt = {"status": "live_api", "subscribers": 5000, "lifetime_views": 250000, "video_count": 18}
+    dummy_mb = {"verified": True, "confidence": 1.0}
+    dummy_wd = {"verified": True, "confidence": 1.0}
+    print("Test Scorer Output:")
+    print(scorer.calculate_score(dummy_yt, dummy_mb, dummy_wd))