From 0b797098470764d234e2490c3d83ef6e00fb3b21 Mon Sep 17 00:00:00 2001
From: Sven Geboers <geboers.sven@gmail.com>
Date: Wed, 1 Apr 2026 01:43:39 +0200
Subject: [PATCH] fix(trajectory): normalize MP names to improve party_map
 matching

---
 explorer.py | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/explorer.py b/explorer.py
index d770950..8aa6359 100644
--- a/explorer.py
+++ b/explorer.py
@@ -1648,6 +1648,45 @@ def build_trajectories_tab(db_path: str, window_size: str) -> None:
         f"[TRAJ DEBUG] load_party_map → {len(party_map)} entries, "
         f"sample={list(party_map.items())[:3]}"
     )
+
+    # Add name normalization to improve matching
+    def normalize_mp_name(name):
+        """Normalize MP name for better matching between data sources."""
+        if not name:
+            return name
+        # Remove extra whitespace
+        name = name.strip()
+        # Ensure consistent spacing after comma
+        if "," in name and ", " not in name:
+            name = name.replace(",", ", ")
+        return name
+
+    # Normalize party_map keys
+    party_map = {normalize_mp_name(k): v for k, v in party_map.items()}
+
+    # Also normalize MP names in positions_by_window
+    normalized_positions = {}
+    for window, positions in positions_by_window.items():
+        normalized_positions[window] = {
+            normalize_mp_name(k): v for k, v in positions.items()
+        }
+    positions_by_window = normalized_positions
+
+    # After normalization, log the match rate
+    all_mp_names = set()
+    for positions in positions_by_window.values():
+        all_mp_names.update(positions.keys())
+
+    matched_names = sum(1 for mp in all_mp_names if mp in party_map)
+    logger.info(
+        f"MP name matching: {matched_names}/{len(all_mp_names)} matched ({100 * matched_names / len(all_mp_names):.1f}%)"
+    )
+
+    if matched_names == 0 and len(all_mp_names) > 0:
+        logger.warning("No MP names matched between positions and party_map!")
+        logger.warning(f"Sample positions names: {list(all_mp_names)[:5]}")
+        logger.warning(f"Sample party_map names: {list(party_map.keys())[:5]}")
+
     windows = sorted(positions_by_window.keys())
 
     # Compute party centroids per window